Awards
Grand Challenges is a family of initiatives fostering innovation to solve key global health and development problems. Each initiative is an experiment in the use of challenges to focus innovation on making an impact. Individual challenges address some of the same problems, but from differing perspectives.
Showing page 1 out of 26 with 100 results per page.
Climate-Focused Analytics and Modeling for Mosquito-Borne Infections in Southern Africa (CAMMISA)
Sheetal Silal of the University of Cape Town in South Africa will establish a research consortium to analyze how climate change affects the transmission and control of mosquito-borne diseases, focusing on how to optimize interventions for malaria, chikungunya and dengue in Southern Africa. The consortium will integrate research projects led by local data scientists working closely with local decision-makers. Through mathematical and statistical modeling together with climate science, these projects will determine climate scenarios across time scales relevant for management of mosquito-borne diseases. These time scales will encompass short-term windows (6-12 months) as well as longer windows (5-10 years) relevant for policy planning and that incorporate the predicted impact and costs of new interventions. The consortium will also explore even longer windows (over 30 years) to provide predictions useful to initiate policy discussions and bring attention to the long-term implications of climate change on disease control strategies.
This grant is funded by The Wellcome Trust.
Leptospirosis in Changing Climates: Soil Health, Sociocultural Behaviors, and Public Health Policy
Roman Thibeaux of the Institut Pasteur de Nouvelle Calédonie in New Caledonia will examine how climate-driven soil changes and societal and behavioral factors can affect the incidence of leptospirosis to develop community-centered prevention strategies. The causal agent of the disease is the bacterium Leptospira, which can be found in water or soil contaminated with the urine of infected animals and thus can spread following heavy rainfall. Leptospirosis is endemic in the New Caledonia archipelago in the South Pacific, with potential climate-driven increases in incidence. Using soil microcosms in the laboratory, they will explore the effects of temperature, rainfall, and soil structure on Leptospira survival and dispersion. Through interviews and focus groups with New Caledonia community members together with ethnographic fieldwork, they will record local perceptions and knowledge relevant to leptospirosis and its transmission. In partnership with local community members and health authorities, they will then identify sustainable strategies to reduce leptospirosis incidence.
This grant is funded by the Pasteur Network.
Machine-Learning Ultrasound Tools to Monitor Women's Nutrition in Ethiopia
Bryan Ranger of Boston College in the U.S. will develop a cost-effective, portable, and automated ultrasound tool to monitor nutritional health of young pregnant women in Ethiopia. The tool will incorporate AI models that guide users in collecting high quality data, so the tool can be used by frontline and community healthcare workers without extensive ultrasound training, and the models will use this data to predict metrics of nutritional status. In a pilot study conducted at the Jimma Medical center, they will create a database of ultrasound scans, anthropometry, body composition measured by gold standard techniques, and the associated clinical data from a group of young pregnant women. Ultrasound measurements will incorporate data on user position to identify the most informative positions via machine learning. They will survey clinical users to guide the ultimate design of the ultrasound system.
Modeling for Decisions in a Dynamic Africa
Susan Rumisha of Ifakara Health Institute in Tanzania will support the establishment of data modeling hubs in the Democratic Republic of Congo, Nigeria, and Tanzania, linking them into a collaborative network to guide the control of mosquito-borne diseases in the face of climate change. The focus will be on the direct and indirect effects of environmental change on malaria, modeling the interplay of these effects with public health systems and mosquito vector and disease patterns. This will encompass modeling mosquito vector distribution, abundance, and seasonality using historical climate data together with new microclimate information. The models will be designed to support national programs in prioritizing vector surveillance activities, targeting interventions, and developing early warning systems for emerging health threats. The network will strengthen model-building expertise and could be adapted to address mosquito-borne arboviral diseases.
This grant is funded by The Wellcome Trust.
Modelling Aedes-borne Diseases for Improved Public Health Decision-Making in the Horn of Africa
Bernard Bett of the International Livestock Research Institute in Kenya will develop disease transmission models for two Aedes mosquito-borne arboviral diseases, dengue and chikungunya, and use the models to design decision support tools to guide surveillance and control of these diseases in Kenya, Somalia and Ethiopia. The models will be validated with longitudinal field data, including mosquito population density, infection patterns, blood meal sources, and the incidence of Aedes-borne diseases in humans. The models will be used to estimate important metrics for disease management, such as time-to-disease outbreak, cost effectiveness of control, and spatial distribution of risk. They will also help identify how the ecological tipping points for outbreaks of dengue and chikungunya compare to each other and how existing control measures for the two diseases could be integrated for better health outcomes. The project will link institutions including the Ethiopia Public Health Institute, Kenya’s Department of Disease Surveillance and Epidemic Response, Somalia’s Federal Ministry of Health, Jomo Kenyatta University of Agriculture and Technology, Abrar University, the Kenya Medical Research Institute, Ohio State University, Global One Health Initiative, and the International Livestock Research Institute.
This grant is funded by The Wellcome Trust.
Uncovering Targets of Protective Immunity for Next-Generation Malaria Vaccines
James Beeson of Burnet Institute in Australia, Melissa Kapulu of Health Research Operations Kenya Limited in Kenya, Isaac Ssewanyana of Infectious Diseases Research Collaboration in Uganda, Faith Osier of Imperial College London in the U.K. and Pras Jagannathan of Stanford University in the U.S., will analyze clinical samples using an antibody functional assay platform with malaria antigen arrays to identify antigens targeted by protective antibodies for next-generation malaria vaccines. They will identify antigen-specific functional antibodies that strongly correlate with protective immunity to malaria observed in clinical studies with two populations: Kenyan adults after controlled experimental challenge infection with Plasmodium falciparum and children followed longitudinally who were naturally exposed in Uganda and in Papua New Guinea. They will then use biostatistical modeling approaches to identify antigen and functional antibody types that most frequently occur in protective combinations, identifying additive and synergistic combinations of responses and responses most predictive of protective immunity across age groups and populations. This will enable prioritization of antigens and their combinations for malaria vaccine candidates.
Syndemic Disease Modeling to Optimize Health Service Integration in Africa
Mary Mwanyika-Sando of Africa Academy for Public Health in Tanzania will develop a mathematical model that accounts for multiple co-occurring diseases and their interactions as well as resource constraints to design integrated healthcare services for people living with HIV in Burkina Faso, Tanzania, and South Africa. The team will use high-quality longitudinal data from four health and demographic surveillance sites. They will characterize co-morbidities and the syndemic clustering of HIV with other diseases (synergistic epidemics), including hypertension, diabetes, and depression, that is due to interrelated biological, environmental, and behavioral factors. They will use the model to predict current and future chronic disease burdens of HIV and other diseases, and then determine optimal health service delivery. The results will be used to co-design intervention implementation strategies with local implementers and policy makers.
Anti-TB Drug Discovery: Design, Synthesis, Evaluation, and Mechanistic Studies
Rajshekhar Karpoormath of the University of KwaZulu-Natal in South Africa will test a set of potential anti-TB hit compounds against clinically relevant TB strains, using the results to generate optimized hit compounds for development of new anti-TB drugs. They will screen the potential hits against susceptible, monodrug-resistant, multidrug-resistant, and extensively drug-resistant TB strains as well as other Mycobacterium strains. The screening results will inform structure-based drug design to generate optimized hit compounds. Potential lead hits will be screened again, with the most promising evaluated against intracellular bacteria in macrophages, tested for in vitro cytotoxicity, and evaluated for mechanism of action in bioassays including carbon-isotope tracing metabolomics and an in vitro granuloma assay.
Remodeling Maternal Health Care: Evaluating the Impact of Midwife-Led Birthing Centers on Maternal and Neonatal Health Outcomes in Ethiopia
Solomon Hailemeskel of Debre Berhan University in Ethiopia will pilot test midwife-led birthing centers for pregnant women and newborns at low risk of complications to increase access to safe, high-quality childbirth experiences for Ethiopian women. They will implement a multicenter randomized controlled trial, recruiting a cohort of pregnant women from antenatal care clinics across diverse healthcare facilities to ensure a representative sample. After training midwives to provide continuity of care before, during, and after pregnancy, they will establish midwife-led birthing centers in dedicated spaces, either within or separate from a higher-level health facility. A subset of trial participants will be randomly assigned to the birthing centers. They will compare outcomes for the two groups, including data on maternal and neonatal health outcomes, as well as qualitative data from interviews of mothers, midwives, and healthcare providers.
Revolutionizing Decentralized Diagnosis of Bacterial Sexually Transmitted Infections for Women Worldwide
Rapidemic in the Netherlands will collaborate with Mohammed Majam of Ezintsha in South Africa to develop a prototype for a molecular test for rapid multiplex diagnosis of chlamydia and gonorrhea, while determining the requirements for its deployment in South African primary care settings to serve hard-to-reach populations. The test system will be designed to diagnose symptomatic and asymptomatic patients accurately and inexpensively using a rapid and disposable test. To guide prototyping, they will research user preferences and assess the usability of the developed device. They will also conduct research to ensure that the development meets regulatory requirements for the South African market and addresses the needs of pharmacies and primary healthcare settings in South Africa.
Integrating ChatGPT-4 with a Wearable Vital Signs Monitor to Improve User Proficiency and Clinical Decision Making for Neonatal Care in Kenya
Sona Shah of Neopenda, PBC in Kenya will integrate ChatGPT-4 as a virtual assistant for the wearable, vital sign monitor neoGuard, supporting healthcare providers in effectively monitoring and managing neonatal health. They will train ChatGPT-4 to help providers identify and address challenges with the neoGuard monitor, such as poor sensor placement on the patient, and to give providers appropriate recommendations based on vital sign data together with the clinical information they gathered. This real-time clinical decision support would be particularly beneficial in remote and understaffed healthcare facilities. For model training, they will use a dataset of newborns admitted to a hospital in Kenya, including vital signs, clinical histories, and treatment outcomes, as well as insights from unstructured clinical notes extracted using natural language processing. They will evaluate use of neoGuard with ChatGPT-4 for reliability, accuracy, and user-friendliness, and compare neonatal patient outcomes before and after ChatGPT-4 integration with the monitor.
Molecular Epidemiology of HPV Infections in Kenyan Women with Cervical Cytological Abnormalities
Moses Obimbo Madadi of the University of Nairobi in Kenya and Aida Sivro of the University of Manitoba in Canada will determine the molecular epidemiology of human papillomavirus (HPV) in cervical cancer cases in Kenya to enable monitoring of changes in the prevalence of HPV types targeted by current vaccines and detect possible replacement with other types. They will perform a cross-sectional study on Kenyan women being followed-up for cervical cell abnormalities at hospitals in Nairobi and in rural Kenya. Outcome measures will include prevalence of HPV genotypes by age, geographic location, and HIV status. HPV genotypes will be stratified by cervical diagnosis to determine the top genotypes associated with cervical cancer. This research will provide robust and standardized statistics on the burden and genetics of oncogenic HPV infection in Kenyan women.
Strengthening Childcare Models that Advance Women’s Economic Empowerment in Machakos County in Kenya
Mary Mbithi of the University of Nairobi in Kenya will test a childcare model in Kenya's Machakos County to increase women's economic participation, reduce and redistribute the burden of unpaid care, and shift gender norms related to childcare. This test will build on results from one tested by the University of Nairobi Women's Economic Empowerment Hub in a different Kenyan county and will inform the model's deployment more broadly across the country. In collaboration with the county government and the local community, they will establish childcare facilities in three sub-counties, including recruiting staff and participating children aged 0-4 years. They will measure impact on child growth, development, and school readiness, as well as measuring impact on women's economic empowerment, including video interviews as qualitative assessment of women's experiences. The county government will take over the running of the childcare centers at the end of the project.
Market and Usability Feasibility for Fetal Lite in Kenya
Wambui Nyabero of Medevice Kenya in Kenya and Vibhav Joshi of InnAccel Technologies Pvt Ltd in India will pilot test Fetal Lite, a fetal monitor for early detection of fetal distress to reduce intrapartum mortality. The monitor is designed for ease of use and patient comfort. It measures fetal and maternal heart rate and uterine activity, has automated data analysis with audio and visual alerts, and has a built-in electronic partogram and AI-based pregnancy risk scoring. It is cloud-enabled with a central web dashboard for report sharing and trend monitoring. They will deploy devices in medical facilities associated with the University of Nairobi, measuring the quality of the auto-generated analysis compared to blinded expert annotation and the ease of use by nursing staff. They will also capture the associated birth outcomes, the guidance provided through remote monitoring, and the number of detected fetal distress cases and referrals.
Meeting Them Where They Are At: Using Large Language Models to Lower Barriers to Measuring the Impact of Gender-Based Violence on Mental Health and HIV Outcomes in Girls and Women in Kenya
Mike Baiocchi of Stanford University in the U.S. will use LLMs to analyze conversational interviews with adolescent girls and young women in Kenya to identify causal mechanisms impairing their health within the potential interplay between living with HIV, mental health conditions, and gender-based violence. Working with the Kenyan Medical Research Institute, they will re-identify and enroll a previously studied cohort living with HIV. The new longitudinal dimension of the study will contribute to untangling causes and effects in parallel to the new LLM-based analysis. They will use LLMs to create statistical measures of participants' descriptions of their experiences to help identify the underlying causes, for instance detecting differences between the responses of those experiencing violence or depression compared to those who have not. Such improved understanding will help to design and target appropriate health interventions.
Acceptability and Marketing of Innovative, Quick-Drying, Reusable, Menstrual SunPad in Kenya
Elizabeth Nyothach of Kenya Medical Research Institute in Kenya will explore introduction of SunPad, a prototype reusable menstrual pad, determining its acceptability, marketability, and regulatory requirements in Kenya. The SunPad product is made of fabric with a built-in cleaning and disinfecting process that is activated by sunlight. They will conduct focus group discussions with women in Kenya to understand their needs in terms of washing, drying, and reusing the pad, and to gauge their willingness to pay for the product. They will also research the potential for local manufacturing of the pad and determine the regulatory requirements and associated documentation.
Queen Bees: Transforming Agriculture and Livelihoods Through Scientific Beekeeping
Monika Shukla of Buzzworthy Ventures Private Limited in India will establish a women-led beekeeping network in India to enhance crop yields through bee pollination and improve women's livelihoods. The network will be established initially in one climate zone with a known array of crops. They will educate women about bee pollination for agriculture and provide hands-on training in scientific methods of beekeeping. They will provide multiple types of support for the network, including guidance on integrating weather information to determine optimal times for harvesting honey and deploying bees for pollination, advice on running a beekeeping business, and access to an AI-based app for advice on beehive management. They will also create a community center serving the network with educational programs and as a central site for warehousing honey and processing hive products.
Identifying Correlates of Anti-Parasite Immunity to Malaria in Infants and Adults: A Systems-Based Approach
Isaac Sseswanyana of the Infectious Diseases Research Collaboration in Uganda will investigate natural anti-parasite immunity to malaria to guide the development of improved malaria vaccines and therapeutics. Natural anti-parasite immunity is observed in malaria endemic regions in adults and infants who control parasitemia at low levels without developing symptoms, in the latter group likely due at least in part to the transfer of effective maternal antibodies. They will use existing samples from two longitudinal studies in Uganda to test the hypothesis that the repertoires, biophysical properties, and functional features of Plasmodium falciparum-specific antibodies are determinants of this natural immunity. They will also identify and characterize malaria-specific T cells that correlate with anti-parasite immunity and focus on evaluating cellular or proteomic predictors of durable anti-parasite antibodies.
Empowering Women-Led Agricultural Microenterprises in Rural Bangladesh with Climate-Smart Technology
Provat Saha of the Bangladesh University of Engineering and Technology in Bangladesh will support women-led, rural agricultural microenterprises in Bangladesh in deploying a set of climate-smart technologies to enhance their productivity and resilience to climate change. They will engage microenterprises distributed across three sectors: vegetable cultivation, fish farming, and poultry production. They will provide each with a system for user-friendly access to weather forecasts based on international weather models. Each will also receive a cost-effective system for real-time weather monitoring, consisting of a micro-weather station along with relevant sensors, such as soil moisture meters for crops, dissolved oxygen sensors for fisheries, and ammonia and light-intensity sensors for poultry farms. They will provide technical training and guidelines on using the technologies to improve farming decisions, and they will monitor outcomes, including reductions in time, labor, and costs.
CARE for Women (Climate Adaptation and Resilience Empowerment)
Rashima Kazal of the Association of Voluntary Actions for Society in Bangladesh will support women smallholder farmers in the southern and southwestern coastal areas of Bangladesh to improve their livelihoods and enhance their resilience to climate change. They will form and strengthen self-help groups of women farmers, providing seed money to scale-up new ideas they generate on topics such as labor-saving technologies, climate-smart tools, and digital marketing. They will provide training for the groups, including on managing livestock, preventing crop failure, and ensuring family nutrition through low-cost, short-term agricultural production and through food processing techniques that enable year-round nutrition. They will also facilitate communication between rural women's groups and relevant government ministries, committees, and policymakers, so that the perspectives of rural women farmers can be integrated into climate adaptation policies and decisions.
Integrating Traditional Birth Attendants to Strengthen Regulation and Improve Quality Maternal Care
Geraldine Mbagwu of Corona Management Systems in Nigeria will implement a pilot project in Bayelsa state in Nigeria that provides training to traditional birth attendants and links them with primary healthcare centers to improve maternal health outcomes. They will engage birth attendants and provide training on topics including using a mobile application to get the latest evidence and health guidelines, as well as training for identifying women with high-risk pregnancies and referring them to the appropriate level of care. They will also ensure access by the birth attendants to key maternal health products and services, including immunization and postpartum family planning. Better integration of traditional birth attendants into the healthcare system will embrace women's agency while improving health outcomes.
Empowering Women in Integrated Avocado Production and Market Enhancement
David Chiawo of Strathmore University in Kenya will develop an integrated approach that empowers women smallholder farmers in the Mount Kenya region to improve their livelihoods and adapt to climate change. The approach combines avocado cultivation, beekeeping for honey production, and bean farming. This integration will help women farmers optimize their limited land resources and diversify their income sources, with nitrogen fixation by beans improving soil fertility and increased pollination of avocado trees enhancing yield. The approach includes technology for digital tracking of avocados from farm to market, supporting product traceability and consumer trust to increase attractiveness for the export market. They will also establish a women-led aggregator system for farmers to pool their produce, negotiate better prices, and access larger markets more efficiently.
Engaging Women and Youth as Catalysts for Sustainable Aedes Control: A Community Participatory Model in Kinshasa, Democratic Republic of the Congo
Emery Metelo of the Institut National pour la Recherche Biomedicale in the Democratic Republic of the Congo will test implementation by women and youth community members of a mosquito vector control program to reduce the burden of disease caused by Aedes-borne arboviruses. The program will be guided by local health authorities and the network of community health workers. It will be implemented over 15 months in two areas of the city of Kinshasa, and it will consist of community education and training of participants, followed by mosquito trapping and clearing of potential habitats for mosquito larvae. They will assess the program's effectiveness by comparing data before and after the intervention, including an arbovirus serosurvey covering dengue, chikungunya, Zika, and yellow fever, and an entomological survey of mosquitos and their larvae. They will also assess changes in relevant behaviors, knowledge, and perceptions due to community participation in the program.
Pharmacokinetics of Primaquine in Lactating Women - Towards Equitable Radical Cure of Vivax Malaria
Brioni Moore of Curtin University in Australia will perform a trial in Papua New Guinea to validate minimal transfer through breastmilk of the antimalarials primaquine and tafenoquine to enable access by postpartum women to radical malaria cure. Verifying minimal drug transfer in the first two weeks post-birth would enable maternal treatment before hospital discharge, preventing postpartum relapses and improving maternal health outcomes and malaria control. They will recruit a cohort of mother-child pairs in which the mother has confirmed vivax malaria or a recent history of it. They will then quantify the excretion of primaquine and tafenoquine in colostrum and transitional breast milk and determine relative infant exposure, while assessing indices of neonatal physiology.
Rapid Detection of Neisseria gonorrhoeae and Relevant Antimicrobial Resistance Targets
Nicole Ertl of the University of Queensland in Australia will develop a molecular test prototype for diagnosis of gonorrhea and antimicrobial resistance of the causative agent Neisseria gonorrhoeae. To increase access to testing, they will design the nucleic acid-based test to be rapid, inexpensive, and to work at ambient temperature without the need for electricity. The prototype platform will combine a sample preparation reagent requiring only short incubation at room temperature, chemically heated isothermal amplification, and lateral flow detection. It will incorporate detection of a relevant genetic signature to distinguish sensitivity versus resistance to the relevant drugs ceftriaxone and ciprofloxacin. They will evaluate the sensitivity and specificity of this sample-to-results platform and its usability in settings with minimal laboratory and testing infrastructure.
Know Your Water: Citizen Science and Community Participation in Three African Countries
Bastien Linol of Nelson Mandela University in South Africa will develop a platform for crowd-sourced monitoring of surface water and groundwater by local communities in rural areas of South Africa, Ghana, and Kenya. Through collaboration across the three countries, the platform will enable geoscientists to work together with local communities to characterize the availability and quality of water sources. The research teams will train local community members as citizen scientists to collect information on water sources and take weekly samples, with data entered into a mobile application. Together with geochemical analysis of the samples, the data will be entered into a database with an interactive website for user-friendly geographic analysis and reporting back to communities. This platform for participatory science will empower local communities to make recommendations to governmental water and sanitation agencies, helping solve the water-related challenges posed by climate change.
Democratizing Access to Health Information and Services for Marginalized Youth in Ivory Coast
Rory Assandey of La Ruche Health in Côte d'Ivoire will expand an AI-based platform to provide youth with information on mental health and wellbeing, while increasing awareness about and access to relevant services. The platform will build on their voice-compatible chatbot KIKO, which is currently available through WhatsApp and used by marginalized youth for automated anonymous access to health guidance and to make appointments with clinicians. They will further develop their tool to make it usable through additional apps such as the Ministry of Health's DHIS2 and interoperable with additional sources of public health data. They will also improve its capabilities for data analysis and report generation to inform public health decision making. To better understand user needs, they will organize discussion groups with university students and youth in remote villages as well as meetings bringing together youth, mental health clinicians, and health ministry representatives.
Incorporating a Sex and Gender Lens into Medical Education in Pakistan
Zainab Samad of Aga Khan University in Pakistan will incorporate sex and gender as a cross-cutting theme embedded in medical education in Pakistan at Aga Khan University and Khyber Medical University. They will perform a curriculum review across the two universities, engaging students, faculty, university leadership, and patients to understand the current teaching gaps related to sex and gender. This will guide development of a tool kit for incorporating the sex and gender theme across all years of training, with customizable strategies based on sociocultural context. They will implement a year-long pilot test of the program at the universities, integrating the theme into core subjects, including how different diseases are recognized and treated and how treatment decisions are made. Feedback from participants in the program will be incorporated into a road map to guide other medical schools in Pakistan in revising their curriculum.
Piloting Extended Integrated Child Development Services for Informally Working Women in India
Gautam Bhan of the Indian Institute for Human Settlements in India will provide technical support to Indian state governments to design, pilot, and test models for expanding the Integrated Child Development Services program to offer community-based childcare suitable for working women, particularly those in the informal economy. This will build on services already provided in the well-established community childcare centers known as Aganwadis. They will make the hours of operation suitable for informal women workers and extend services to include the needs of children from ages 0-6 years, including increased support for health checkups for mothers and their children, as well as additional support for supplementary nutrition and pre-school education. They will also develop processes to empower women's active participation in the program and increase the demand for the new services. The piloted models will be assessed for their impact on women and children's health and on women's economic participation and productivity.
Seaweed Biofertilizers for Climate Change Adaptation and Women Empowerment in Rural Cape Verde
Edita Magileviciute of the Caboverdean Ecotourism Association in Cape Verde will explore the potential of locally harvested seaweed as a biofertilizer to support rural women's livelihoods and agricultural development in Cape Verde. After women-led hand-harvesting, Sargassum and Ulva seaweed will be processed and tested for use as a safe and effective compost for vegetable crops. Testing will be in collaboration with local stakeholders and the University of York in the United Kingdom, who have assessed seaweed products in Jamaica. They will also explore dried Sargassum seaweed combined with recycled glass and plastic for production of building bricks, as well as Ulva seaweed as a food or additive to cosmetics. These seaweed-based products would provide new business opportunities for rural women, while contributing to rural agricultural development.
Dharma Life Community Learning Centre Through "Better Skills Better Care"
Gaurav Mehta of the Dharma life Foundation gGmbH in Germany will establish Dharma Life Community Learning Centers in India that combine vocational training for mothers with early childhood care and education for their children to improve women's workforce participation, children's educational outcomes, and social acceptance of professional childcare. Training will include vocational courses based on demand in the local job market, and entrepreneurial opportunities will be provided, including linking to women who are starting businesses. They will compare outcomes for women and children in low-income populations in rural and semi-urban India in randomly selected villages with and without the Learning Centers. This comparison will be informed by three centers already operating as a pilot trial. Integrating vocational training with childcare in the Learning Center will accustom women to effective childcare while working, increasing their economic empowerment while broadening social norms around division of labor.
Enhancing Data Systems of African National Regulatory Agencies - Burkina Faso
Issiaka Soulama of the Agence Nationale de Régulation Pharmaceutique (ANRP) in Burkina Faso will support national regulatory processes by enhancing the data systems with a package of improvements. The project is a collaboration with the Food and Drugs Authority in Ghana. They will implement training programs for staff to enhance the technical evaluation of marketing authorization applications and clinical trial protocols. For all pharmaceutical regulatory functions, they will define a framework for developing key performance indicators as well as develop and implement standard operating procedures for the production, collection, analysis, and dissemination of key statistics. They will also implement a digital and integrated information management system to support standardizing the regulatory data and connecting the relevant databases.
Enhancing Data Systems of African National Regulatory Agencies - Uganda
The National Drug Authority in Uganda will support national regulatory processes by enhancing the data systems with components that monitor key performance indicators. The project is a collaboration with the Uganda National Council for Science and Technology and with the Tanzania Medicines and Medical Devices Authority, who will help ensure that systems of both partners are interoperable across regulatory functions covering clinical trials, market authorization, and good manufacturing practices. They will design and then incorporate monitoring and evaluation modules into the regulatory information management system. The modules will track key performance indicators of the system, generating real-time reports as well as quarterly and annual reports on performance trends. This monitoring will facilitate evidence-based improvements in the process. It will also facilitate integration with other systems within the National Drug Authority, including a harmonized approach to data standardization.
Enhancing Data Systems of African National Regulatory Agencies - Ghana
The Food and Drugs Authority in Ghana will support national regulatory processes by enhancing the data systems with a package of improvements. The project is a collaboration with the Botswana Medicines Regulatory Authority. They will bolster processes across both agencies by deploying a standardized set of metrics and key performance indicators. This will include finalizing the implementation of integrated regulatory information management systems. These systems will be harmonized so that the two agencies can share reports following data capture and analysis. They will also share analytics tools and methodologies for deriving insights from data, including predictive modeling, trend analysis, as well as real-time monitoring to proactively address challenges that arise for the data systems.
Empowering Women Agripreneurs: Incubating Climate-Smart Potato Venture for Nutrition Market and Livelihood
Richa Verma of Siddhi Vinayak Agri Processing Private Limited in India will support women entrepreneurs and women-led Farmer Producer Organizations in adopting climate-resilient potato varieties through a pilot program in four states in India. They will collaborate with Friends for Women's World Banking to support farmers' access to financial services and guidance on marketing, and they will collaborate with Agrico (Netherlands) to support decisions on potato varieties. The pilot program will be established in the states of Uttar Pradesh, Assam, Bengal, and Gujarat. They will provide training and support that broadly encompasses the business of potato farming, ranging from marketing climate-resilient seed varieties to drone-based spraying of crops to post-harvest processes that add to the agricultural value chain.
SensMyN: Monitor Biological Nitrogen Fixation by Integrative Soil-Vegetation Spectral Data, and RNA-Based Biomarkers
Alexandre ten Caten of the Universidade Federal de Santa Catarina with the Universidade Federal do Rio de Janeiro in Brazil will pilot test an affordable field-based system for measuring biological nitrogen fixation (BNF) to guide BNF-based strategies to improve crop production. They will test their system in a field experiment including crops grown with either of two treatments: nitrogen-capturing microorganisms applied to seeds or nitrogen-fixing legumes grown with the crop. They will then assess BNF, comparing measurement of nitrogen isotopes by mass spectrometry as the benchmark to spectral measurements with more affordable spectrometers. They will use machine learning to integrate data from spectral analysis of soil with that of plant leaves to generate a model, which could be incorporated into a mobile app, for more accurate BNF monitoring. They will also develop an RNA-based diagnostic test to identify plant genotypes more responsive to nitrogen-fixing bacteria. These tools would enable agricultural extension workers and farmers to independently monitor new BNF-based strategies.
Enhancing Data Systems of African National Regulatory Agencies - Botswana
The Botswana Medicines Regulatory Authority in Botswana will support national regulatory processes by enhancing the data systems with a package of improvements. The project is a collaboration with the Ghana Food and Drugs Authority. They will bolster processes across both agencies by deploying a standardized set of metrics and key performance indicators. This will include finalizing the implementation of integrated regulatory information management systems. These systems will be harmonized so that the two agencies can share reports following data capture and analysis. The collaboration will include strengthening multiple regulatory functions in Botswana, including strengthening pharmacovigilance by incorporating procedures for monitoring activities for risk minimization and risk communication. It will also include strengthening clinical trial regulation by enhancing management of the review process from receipt of applications to post-approval compliance to final reporting.
Femtech Innovation Hub
Imran Zia of the Centre for Economic Research in Pakistan (CERP) with the National Incubation Center will establish an innovation hub to support startup companies in creating practical and accessible health solutions for women living in underserved and low-income communities in Pakistan. They will establish a physical hub that is integrated with an existing research network and uses a human-centered design approach with evidence-based decision-making throughout, from product conception to launch and scale-up. They will develop and implement an open-source curriculum tailored to entrepreneurs for women's health and incubate a cohort of startups. Participating startups will be selected through gatherings held at leading medical universities and through collaboration with other incubators. The hub will lead to improved women's health outcomes, while generating insights on the health needs of women in Pakistan that can help inform national health policy.
Nutritional Supplementation in Pregnancy to Neutralize Heat Stress
Junaid Iqbal of Aga Khan University in Pakistan will test the effects of daily supplemental feeding for women in rural Pakistan to mitigate the negative effects of heat stress during pregnancy on maternal and neonatal health outcomes. They will enroll 250 women, comparing pregnancy in the summer and winter and with and without daily supplemental feeding in the first trimester. The supplemental food will be designed for increased nutritional value, based on ingredients from local diets. They will measure a variety of clinical outcomes in mother and child, including maternal ultrasound measurements and newborn anthropometry. To explore potential mechanisms underlying the effects of heat stress and their potential mitigation by supplemental feeding, they will also use maternal samples taken at the time of delivery to assess serum micronutrients, the gut microbiome, and the placental transcriptome.
Improving Women's Health Globally Through On-Line Education and Training
Kimberly Templeton of the University of Kansas Medical Center Research Institute in the U.S. will develop educational materials for healthcare providers and researchers on women's health, focusing on sex and gender influences on health. They will establish a virtual center for women's health education to develop, disseminate, and evaluate online teaching materials. These materials will be developed by experts in the field, with guidance from healthcare professionals in the country in which they would be used, and they will be created by partners in the United States, Nigeria, and Kenya initially as a proof of concept. The materials will provide practical, clinically relevant information encompassing common communicable, non-communicable, and chronic conditions across the life course, and they will be available on-line free of charge for a global audience.
Effects of Heat Stress on Maternal Lactation Performance and Infant Growth and Potential Mitigation
Santu Ghosh of the St John's Research Institute in India will explore the effects of heat stress on lactation and infant growth, including their potential mitigation by a nutritional supplement for breastfeeding mothers in India. They will enroll two cohorts of 65 women in the state of Tamal Nadu, comparing data for breastfeeding in the summer versus the winter. They will measure breast milk quantity and quality, an oxidative stress marker in maternal blood, iron nutritional status in mother and infant, and infant growth. To test the hypothesis that heat stress causes harm via oxidative stress in mothers, they will assess the potential benefit of giving a subset of the breastfeeding mothers an omega 3-fatty acid nutritional supplement as an antioxidant. The results could guide simple strategies based on diet or nutritional supplementation to mitigate the effects of heat stress on the health of pregnant and lactating women.
Innovating Menstrual Health Management: Clinically Informed Absorbency Standards and Digital Diaries
Robert Gorkin of Western Sydney University in Australia will develop a clinically relevant qualitative measure of absorbency for menstrual health and hygiene products together with a digital tool incorporating this measure to help women self-identify when their menstrual bleeding requires clinical attention. They will conduct workshops to gather end-user requirements from consumers and clinicians, while defining target technical specifications. Collaborating with the company Enersol, they will evaluate the latest absorbency testing methods to establish a comprehensive testing methodology useful across pads, tampons, and period underwear. Incorporating this measurement system, they will develop a user-friendly digital diary for women to track their menstrual bleeding, guided by relevant existing web- and application-based tools. They will then perform a pilot trial at a clinic, comparing women with normal versus abnormal uterine bleeding, to assess the feasibility, acceptability, and clinical benefit of their menstrual health management system.
Modeling Infectious Disease Drivers for Gestational Diabetes Outcomes
Nicki Tiffin and Tsaone Tamuhla of the University of the Western Cape in South Africa will model how infectious and non-communicable diseases interact to affect maternal, neonatal, and child health outcomes, using gestational diabetes as a case study. These interactions include those between multiple chronic conditions and multiple medications in individuals and those due to variable access to health care. They will develop risk factor models for gestational diabetes, harnessing Large Language Models for data harmonization and standardization. The models will be applied to mother and child clinical datasets held by collaborators across the Global South through a federated data analysis approach (joint analysis without sharing the data itself). This collaboration will generate new models and evidence for gestational diabetes outcomes. It will also establish guidelines more broadly for health data modeling to inform policy, while helping build a collaborative Global South data modeling community.
Predicting Responsiveness to BG505 SOSIP GT1.1 Immunogen in African Populations
Daniel Muema of the KAVI Institute of Clinical Research, University of Nairobi in Kenya and Marit J. van Gils of the University of Amsterdam in the Netherlands will characterize the B cell immune repertoire in defined African populations to inform the use of an HIV vaccine with a germline-targeted immunogen. This clinically advanced, HIV envelope glycoprotein immunogen, BG505 SOSIP GT1.1, is engineered to guide the development of naïve B cells to produce broadly neutralizing antibodies (bnAbs) against HIV. They will determine the baseline frequencies of bnAb-precursor naïve B cells and bnAb-like memory B cells that recognize this immunogen in uninfected, adult sex workers highly exposed to HIV and in adults living with HIV. This will determine if the immunogen will be effective in these populations for HIV prophylaxis and functional cure, informing the design of vaccine clinical trials.
Advancing Fungal Pathogen Surveillance in African Informal Settlements: Integrating Community Engagement, Environmental Monitoring, and Predictive Modelling
Cleo Conacher of Stellenbosch University in South Africa will develop a surveillance and risk prediction system for the presence of Candida pathogens in river water sources used by informal settlements in South Africa. This system will account for climate change-influenced environmental factors that can affect the prevalence, distribution, and behavior of these fungal pathogens. They will survey community members for data on river water exposure. They will also design a sampling device to collect data on river water properties as well as microbiological samples for data on Candida pathogen prevalence and gene expression. They will combine this data to enhance an existing framework for microbial risk assessment and to develop an AI-based model that predicts fungal infection risk from environmental trends. They will communicate the risk estimates and overall conclusions to community members through meetings and a project website, with materials translated into relevant local languages.
Building Climate Resilience Through Women-Centric Agricultural Innovations
Maria Jones of UN Women (India Country Office) in India with Umang Agarwal of GROW Indigo and Sudarshan Thakur of PRADAN, both in India will develop a sensor to measure biological nitrogen fixation (BNF) and provide it together with access to biofertilizers to women small-scale producers in India as a model of gender-intentional agricultural innovation. They will develop a low-cost sensor for real-time measurement of BNF in the field. They will conduct field trials with the sensor, using the data to generate a model that incorporates satellite imagery data to estimate BNF, and then validate the model with mass spectrometry data from the field trial. They will pilot test the sensor plus access to biofertilizers and training on complementary climate-smart agricultural practices with women small-scale producers in the state of Madhya Pradesh in India. This package of support could lead to improved soil health and crop productivity, increasing income as well as resilience to climate change.
Impact and Genetic Landscape of Endometriosis in Africa
Krina Zondervan of the University of Oxford in the United Kingdom will characterize endometriosis in African populations to close knowledge gaps and inform the development of non-surgical diagnostics and therapeutics with global applicability. Endometriosis is a chronic inflammatory condition due to growth of endometrial-like tissue outside of the uterus, and it can cause pain and infertility. Working with local collaborators, they will collect endometriosis and related phenotypic data for women across South Africa, Ghana, and Kenya, with genetic data collected from a subset of women. They will identify women with confirmed endometriosis and collect phenotypic data through a globally standardized questionnaire. including the condition's impact on quality of life. They will perform genome-wide association analysis, investigate putative causal genetic variants to help uncover biological mechanisms, and hold meetings to inform and strengthen the collaboration network and plan future research.
Assessing Recent and Future Climate Change Impacts on Anopheles gambiae Species Complex Bionomics and Malaria Risk in Senegal
Ousmane Sy of the Universite Cheikh Anta Diop de Dakar in Senegal will develop mathematical and AI-based models to predict the impact of climate change on malaria morbidity, mortality, and transmission by the Anopheles gambiae species complex in Senegal. They will use epidemiological, environmental, and entomological data from the last 20 years in northern and central Senegal to predict the future of the disease in these areas. The models will incorporate the effects of interventions for malaria control being used in Senegal, including long-lasting insecticidal nets, indoor residual spraying with insecticides, and seasonal chemoprevention. The project's interdisciplinary approach will support the National Malaria Control Program, while building and strengthening collaborations for malaria modeling.
Predicting Drug-Resistant Bacterial Dynamics in Maternity Wards of Burkina Faso and Cameroon under Climate Change: A Precision Public Health Study
Blaise Bougnom of the Centre for Research in Infectious Diseases in Cameroon will develop models to predict the impact of climate change on the spread of clinically relevant, drug-resistant bacteria in maternity wards in Cameroon and Burkina Faso to enhance public health preparedness. The models will integrate climate data with data from hospitals across different climate zones in the two countries, enabled by a partnership with the University of Ouagadougou in Burkina Faso. They will collect and sequence bacterial samples from these hospitals, while also performing environmental monitoring in them. They will then collect historical and projected climate data for the relevant areas of the countries, using it to develop models that predict transmission of drug-resistant bacterial strains. Using the models, they will design targeted interventions, such as enhanced hygiene protocols, pilot testing them in hospitals to improve maternal and neonatal health outcomes.
Empowering Women Through Climate-Responsive Community Health Information to Tackle Schistosomiasis
Diana Karanja of COHESU in Kenya will develop a community health information system to reduce the burden of schistosomiasis in Kenya. They will implement the project in persistent hotspot areas of schistosomiasis near Lake Victoria. They will perform surveys to assess women's decision-making power in the household and how this correlates with schistosomiasis health outcomes for them and their families. The results will be used to inform communication strategies that improve these health outcomes. They will also train community healthcare providers to collect information on use of local water sources as a risk factor for water-borne transmission of the schistosomiasis parasite. This information will be integrated into existing predictive models of risk that will be used to develop an app. The app will provide simple messages and alerts, including information tailored based on the household surveys as well as seasonal updates on schistosomiasis risk.
Climate-Smart Labor-Saving Agrotechnologies for Increased Resilience of Women in Dryland Kenya
Kenneth Odhiambo of the University of Eldoret in Kenya will support the design and implementation of scalable, climate-smart, labor-saving agricultural practices and technologies to improve women's livelihoods in drylands of three counties in Kenya. These practices, depending on the county, will focus on beekeeping and production of poultry, fruit, sorghum, groundnuts, and cowpeas, as well as rice paddy fish farming where feasible. The approach will be co-designed by the intended beneficiaries. The set of technologies will include new mechanisms for water harvesting and automated solar-powered irrigation systems. Farming practices will be introduced to increase food and nutrition security as well as for higher and more stable income.
Driving Investment in Equitable and Appropriate Health Products and Services
Yacine Djibo of Speak Up Africa in Senegal will develop a set of indicators to guide increased incorporation of diverse women's perspectives into health research and development to ensure that women's health products are broadly suitable and accessible. Speak Up Africa will work with Gawani Africa and the Africa Center for Health Systems and Gender Justice, building on their recent related project for Kenya and Nigeria and expanding the analysis to Senegal. They will consolidate data across the three countries to identify measurable indicators for health research and development that encompass elements including whether there are policies promoting gender equality and women's access to leadership roles, the gender diversity of project teams, and the proportion of funding for women-led projects and gender-responsive research. They will then work with stakeholders, ranging from medical women's associations to academic institutions to funding agencies, to refine and validate the proposed indicators.
Sustainable Maternal and Newborn Child Health Initiative
Shahid Yusuaf of Fincon Services with the Poverty Eradication Initiative in Pakistan will pilot test use of the AI-based mobile application Umeed Sey by community midwives to enhance maternal and newborn health services in Pakistan. The mobile app will help participating midwives in registering pregnant women and capturing their current health status and medical history. It will also support effective triage, identifying high-risk pregnancies for timely referral to specialists, and support management of emergency cases, directing them to the appropriate medical facilities. They will monitor and evaluate use of Umeed Sey in the pilot trial, with a focus on gauging its ability to optimize the patient referral process.
Promoting Gender Equality Through Sustainable Access to Climate Information
Celestina Innih of Kogi State Fadama Coordination Office in Nigeria with Cynthia Nwobodo of University of Nigeria Nsukka also in Nigeria will develop advisory services for rural women in Nigeria to make informed decisions for climate change adaptation. This includes providing women, youth, and agricultural extension workers with access to information on climate-smart practices. It also includes access to timely weather information to guide planning of farming calendars, which will be done in partnership with the Nigeria Meteorological Agency. A gender perspective on climate-smart practices will be sustainably incorporated through creation of women's groups on the topic in the agricultural zones of two states in Nigeria. The project will implement a variety of relevant training sessions, workshops, and field demonstrations, as well as producing a training manual on soil and crop management practices for climate change adaptation.
Rise to the Challenge: AI-Powered Communities Battling Vector-Borne Diseases in the Face of Climate Change
Devotha Nyambo of the Nelson Mandela African Institute of Science and Technology in Tanzania will develop AI-based predictive models as an early warning system for vector-borne diseases, integrating community-based information gathering and vector control and focusing on malaria and dengue in areas of Tanzania particularly vulnerable to climate change. They will develop the models using topographic data from satellite images, historical climate and weather data, and vector-borne disease data sets. They will train women and youth to identify and eliminate mosquito breeding sites and larvae, and they will create user-friendly interfaces for this observational data to be reported and integrated into the predictive models. The early warning system, enhanced by direct engagement and education of community members, will guide effective strategies to mitigate the impact of vector-borne diseases.
Caring Blocks: Neighborhood Childcare Hubs to Advance Women's Economic Power in Nigeria
Blessing Adesiyan of the MH Institute for WorkLife Care and Policy Research Africa in Nigeria will establish 300 high-quality, cost-efficient childcare hubs across three states in Nigeria to increase women's economic potential. They will pilot three childcare models: direct care to families via a certified care worker, enrolling employees into an employer- or government-sponsored program, and community-based childcare. Partnering with government agencies to ensure meeting local and national care standards, they will identify suitable neighborhoods and workplaces as sites, screen and recruit care workers, and enroll children. They will build a technology platform, named Caring Blocks, where employees can access childcare hubs for on-demand, back-up, or long-term childcare. They will use this platform to get feedback and monitor outcomes, while exploring sustainable funding models for the childcare hubs.
AI-Supported Platform Innovation for Maternal Health
Bernard Olayo of the Center for Public Health and Development in Kenya will develop an AI-based platform to support product innovation for women's health, pilot testing it with Kenyan healthcare providers using heat-stable carbetocin, a drug for preventing postpartum hemorrhage. The platform will broadly serve providers as a resource for new product information, current clinical guidelines, and decision-making support. They will develop the platform through an initial focus on the drug carbetocin as a product with high potential for impact. They will build a library of reference materials for carbetocin, including guidelines contextualized for different healthcare settings; use the library to train a chatbot integrated into WhatsApp; and deploy the platform through relevant professional societies. They will evaluate the platform's impact based on data on providers' use of the chatbot, carbetocin use at Kenyan health facilities, and trends in maternal health outcomes at health facilities using the drug.
Building Resilience: Addressing Climate Change Impacts on Health in Rwanda Through Systematic Approaches
Muhammed Semakula of the Rwanda Ministry of Health in Rwanda will establish an integrated data system with analytical tools to monitor and predict the effects of climate change on public health in Rwanda. The focus will be to understand the impact of temperature, rainfall, and air pollution on the top five causes of mortality: cardiovascular, diarrheal, and respiratory diseases; malnutrition; and accidents and injuries. After establishing a database of historical and current data, they will develop statistical models to assess the short- and long-term effects of climate on health. They will also launch a publicly accessible dashboard for real-time monitoring of these effects and develop educational materials and workshops on the topic. This combination of approaches will inform and engage the public while building and supporting a research community for a sustainable response to climate change.
Climate Change Impacts on Ticks and Tick-Related Pathogens in Lao PDR
Khamsing Vongphayloth of Institut Pasteur du Laos in Lao PDR will develop a surveillance program for ticks and tick-borne pathogens to model and predict the transmission dynamics of tick-borne diseases. They will perform sampling at two sites in the northern region of Lao PDR suitable to monitor the effects of climate change. Over two years, they will collect ticks and other ectoparasites from host animals as well as free-living ticks, sampling across multiple seasons each year. Ticks will be screened by PCR for two viruses (Severe Fever with Thrombocytopenia Syndrome Virus and tick-borne encephalitis virus) and for spotted fever group rickettsiae, which are intracellular bacteria. Corresponding weather data will be collected along with land use data from direct and satellite observation. This monitoring data will help predict climate-driven changes in the risk of human exposure to tick-borne pathogens and support the development of a country-wide and regional surveillance system.
This grant is funded by the Pasteur Network.
Resilience for Women Through Climate-Smart Economic Transformation (RECET)
Manda Kumari Karn of the Janaki Women Awareness Society in Nepal will support women farmers in Nepal to incorporate labor-saving technologies and non-agricultural sources of income and to participate in community-based responses to climate change. For 100 households dependent on subsistence agriculture in the Dhanusha district, they will provide training to establish climate-smart, labor-saving agricultural systems, including solar-powered water systems. Women in these households will receive support in creating micro-enterprises that reduce their dependence on agriculture, including needs-based training and business coaching. They will also bring together women farmers and entrepreneurs to support their participation in developing local action plans for climate change response.
Fostering Resilience in Tanzanian Communities Through Inclusive Climate Information Services
Mahadia Tunga of the Tanzania Data Lab in Tanzania will support women and youth running small and medium enterprises to integrate current information on climate change, enabling them to make data-driven decisions for more sustainable agricultural practices in Tanzania. After assessing the local needs for this information by relevant enterprises, they will design and implement training programs, including through on-line materials and in-person workshops. They will also create an accelerator program to identify and support new enterprises with a focus on climate adaptation strategies. This set of support will engage women and youth, building a community around navigating the challenges of climate change in Tanzania and piloting a model of support that could be replicated more broadly.
Energizing Women Agricultural Cooperatives Via a Smart, Pay-As-You-Go Battery Solution
Martin Tarkpor of the Liberia Institute for Development Assessment and Research in Liberia will pilot test a battery rental system for women agricultural cooperatives to use to power their food processing equipment and sustainably increase their productivity and incomes. Food processing, such as rice threshing and milling and palm kernel pressing, is typically done using equipment operated manually or with a generator. Pay-as-you-go battery rental systems are a rapidly growing alternative to provide affordable, clean power to low-income communities off the power grid. Batteries are charged at solar charging stations and then rented directly there or distributed through agents. They will perform field trials in Liberia and then Sierra Leone, testing the battery rental system at six cooperatives and at different times in the growing season to encompass multiple crops. Based on the trials, they will develop a simple business model to facilitate rolling out the battery system more broadly in sub-Saharan African countries.
Is Diagnostic Sexually Transmitted Infection Screening for Adolescent Girls and Young Women a Worthwhile Investment in Low- and Middle-Income Countries?
Aamirah Mussa of Botswana Harvard AIDS Institute Partnership in Botswana will pilot test a diagnostic screening program for sexually transmitted infections (STIs) in adolescent girls and young women in Botswana to determine the infection burden and the cost effectiveness of the program. Chlamydia, gonorrhea, and trichomoniasis are common, curable STIs, but asymptomatic infections can be unknowingly spread and may not be detected until they cause serious, long-term complications. They will work with a youth advisory board to design the screening protocol, including determining how best to reach the target population and whether to screen at home or in the clinic and by a self-collected or clinician-collected swab. They will then screen a cohort in the capital city Gaborone using a nucleic acid amplification test. The cost of the screening and treatment will be compared to the cost of the currently used protocol of syndromic management with diagnosis by microscopy for persistent infections.
Resilient Women Farmers in Côte d’Ivoire
Daniel Oulai of Grainothèque in Cote d'Ivoire will support women farmers in the Tonkpi region of Cote d'Ivoire to improve their livelihoods through rice-fish farming. Rice-fish farming is a mutually beneficial combination of agriculture with aquaculture simultaneously in the same fields. They will train women farmers in setting up and managing rice-fish farming, including matching farmers to the most suitable land and providing them with a mobile phone-based alert system to get information on the agricultural calendar and weather. They will provide business training, including for marketing their rice product and for setting up village savings and loan associations. They will also hold community meetings to involve the families of the women farmers and raise awareness about how the farming program reduces gender inequalities in a way that benefits the economic empowerment of the entire community.
Co-Creation of Women's Health in Asia and Africa: Improving Menstrual Hygiene Management
Taro Yamauchi of Hokkaido University in Japan will explore a community-based approach for menstrual hygiene management through fieldwork across different socioeconomic and sociocultural contexts in Japan, Bangladesh, Indonesia, Cameroon, and Zambia. This broad exploration will guide solutions that are tailored to each local context while also applicable in other countries and regions to improve the health and wellbeing of girls and women. Field work will encompass living conditions in urban, urban slum, and rural contexts, as well as in indigenous communities. They will incorporate a gender perspective on menstrual hygiene to understand how men's and women's knowledge and attitudes influence each other. They will engage community and religious leaders; healthcare providers, such as nurses and midwives; and girls and women, along with older generations. In Bangladesh, they will perform an intervention to improve menstrual hygiene and evaluate its impact.
Data Science to Advance Women's Health Fellowship
Elaine Nsoesie of Boston University in the U.S. will develop a fellowship program to provide data science and research training to early-career women working to advance women's health. The fellowship will include participation in the annual convening organized by Data Science Africa, an organization focused on building expertise in data science and AI in local communities across Africa. It will also include an online scientific writing retreat, mentorship programs, and community building activities. The fellowship program would contribute to progress in women's health by advancing the careers of researchers working in the area, supporting research publication, and by encouraging trainees to share their knowledge with other women in their networks.
Metabolite-Based Point-of-Care Diagnostics for Vaginal Microbiome Composition
Seth Bloom of Massachusetts General Hospital and Margaret Kasaro of the University of North Carolina Global Projects Zambia in Zambia will validate metabolite biomarkers of clinically-relevant, vaginal microbiota community state types (CSTs) for development of diagnostics for research and clinical care. Different CSTs confer distinct risks for diseases linked to bacterial vaginosis, including risk of preterm birth and HIV infection. They will validate in a Zambian cohort the CST metabolite biomarkers that they previously identified in a South African cohort. They will grow pure cultures of individual bacteria to identify species and candidate enzymes responsible for vaginal CST biomarker production or consumption to inform development of a diagnostic assay. An inexpensive, real-time, point-of-care, diagnostic assay for use in low-resource settings would remove the need for slower, costlier DNA sequencing methods. Such a diagnostic test for vaginal microbiota-associated diseases will improve diagnosis, prediction of clinical risk, and monitoring of responses to therapy.
ClimateWISE: Strengthening Resilience through Women, Youth and Innovation in the Horn of Africa
Patricia Bamanyaki of the African Group of Negotiators Experts Support in Kenya will generate sex-disaggregated data and information together with platforms and tools to increase the resilience of women and youth to the challenges posed by climate change to agriculture and health in Kenya and Ethiopia. They will collect and integrate data from diverse sources to identify geographic hotspots in the two countries where women and youth are particularly vulnerable to climate change due to the overlap of risks associated with gender inequality, vector-borne diseases, and agricultural losses. This data will be made accessible and usable by stakeholders inside and outside government. They will also establish hubs at the regional level in each country that foster collaborative action between policymakers and agricultural and health practitioners to support women, youth, and marginalized groups in the face of climate change.
Climate-Smart Decision Support System for Women- and Youth-Run Micro, Small, and Medium Enterprises (MSMEs) to Enhance Rice Production and Improve Livelihoods in Sub-Saharan Africa
Cecilia Limera of the African Agricultural Technology Foundation in Kenya will develop a platform to convert weather information into practical recommendations that support data-driven, rice crop management in Nigeria, Kenya, Senegal and Ghana. The platform will complement existing weather information systems and serve to boost rice production by women- and youth-run MSMEs, improving the livelihoods of rice farmers. They will co-create the platform with MSMEs in the four countries after identifying their needs and climate change-related challenges. The platform will integrate satellite data with weather data from a network of weather stations and sensors. It will analyze this data, including customizable AI-based modeling, to provide climate-smart guidance to optimize rice production. This guidance will be accessible through user-friendly mobile and web-based formats.
Revolutionizing Research Ethics and Regulatory Systems for Clinical Trials Through the Integration of an Artificial Intelligence Ethics Review Decision-Making Model
Francis Kombe of EthiXPERT NPC in South Africa will develop an AI-based platform to support African research ethics committees and clinical trial decision-making. It will build on their cloud-based, online review system RHInnO Ethics. This system is currently used to manage the entire ethics review cycle, including protocol submission and review, approval, and follow-up, with the goal of shortening the review timeline, enhancing review quality, and speeding the discovery of life-saving public health interventions. They will consult with relevant stakeholders to identify elements of ethics review that could benefit from AI. They will then identify the required structured and unstructured data, use this data to train a model based on GPT-4, and integrate the model into their existing review system. They will evaluate the new platform, comparing it with and without the AI element and assessing results from current users, including decision quality and timeliness.
Climate-Intelligent Delivery of Malaria Chemoprevention in Cameroon
Innocent Mbulli Ali of the University of Dschang in Cameroon will develop an AI-based forecasting system to guide the delivery of seasonal malaria chemoprevention in Northern Cameroon. The system will build on an existing AI-based model and incorporate historical environmental, epidemiological, and mosquito vector surveillance data from relevant regions of Cameroon. They will train the model to predict changes in malaria morbidity and mortality due to extreme weather events, including the timing, peak number, and distribution of malaria cases. They will collaborate with the National Malaria Control Program to test the system as a tool for optimizing the timing of malaria interventions in different health districts, evaluating its prediction accuracy and cost effectiveness.
A Global Measure of Women's Experience of Care that Improves Qualitative Measurement Development
Nirali Chakraborty of Metrics for Management in the U.S. with Population Services International will develop a measure of women's experience of healthcare using an approach that could be deployed more broadly for measurement. They will convene international experts in a workshop to create a conceptual framework that defines the essential domains of women's experience of care. The workshop will identify measurable indicators for each domain of care in the framework and identify a list of attributes that would make a final integrated measure the most useful. They will then design short questionnaires to measure each identified domain and use them to survey a panel of adult women representing multiple low- and middle-income countries and healthcare contexts. Based on the data collected, they will create a prototype integrated metric of a client's experience of care for use by healthcare providers, product developers, and researchers.
An Ex Vivo Lung Model of Mycobacterium tuberculosis (Mtb) Infectivity and the Early Host-Mtb Interaction
Digby Warner of the University of Cape Town in South Africa and Catherine Blish of Stanford University in the U.S. will explore human precision-cut lung slices (hPCLS) as an Mtb bioaerosol detection platform and model system for infection. Such a platform would provide an immediate read-out of Mtb infectivity and give insights into the initial Mtb-host interaction. They will determine the feasibility and reproducibility of using the hPCLS platform with samples containing extremely low numbers of Mtb bacilli, monitoring bacterial infectivity, replication, and dissemination by time-lapse fluorescence microscopy and examining key early events by cytometric and single-cell molecular assays. The platform could be used to answer specific questions, including whether Mtb organisms released during coughing by symptomatic TB patients are more infectious than those aerosolized during normal respiratory activities by asymptomatic individuals. It could also be applied at the site of aerosol sampling to guide and monitor preventative and therapeutic interventions.
Improving Sickle Cell Disease Care in the Democratic Republic of Congo (DRC) with Mobile Lab Screening
Leon Tshilolo of the Institut de Recherche Biomédicale 1-Health in the Democratic Republic of Congo and Johnny Mahlangu of University of the Witwatersrand in South Africa will perform a pilot study using a mobile laboratory to conduct sickle cell disease (SCD) screening and patient follow-up in hard-to-reach and rural areas of the DRC. A mobile laboratory could lead to broader and earlier detection of SCD, enabling treatment sooner, and help ensure continued treatment, together reducing mortality and improving health outcomes. Sickle cell carriers will also be identified, with the study contributing to a more accurate epidemiological map of SCD to guide national healthcare strategy and advocacy efforts.
Characterization of Vaccine-Induced Immune Response in Lung Mucosa in Humans
Erica Andersen-Nissen of Hutchinson Center Research Institute of South Africa and Gerhard Walzl of Stellenbosch University, both in South Africa, will perform bronchoalveolar lavage in volunteers receiving the BCG or MTBVAC vaccine intradermally in the HVTN 605 clinical trial to delineate vaccine-induced lung immune responses and identify correlates of protection. Lavage will be performed pre- and post-vaccination, and cells isolated from the lavage fluid will be analyzed for protein expression and by transcriptional profiling. They will compare the lung immune response they detect with the blood immune response identified in the large datasets available as part of the trial. Correlations between them could identify human blood biomarkers of lung T-cell responses that protect against TB. Such biomarkers will inform ongoing and future studies of immune correlates of efficacious TB vaccines.
A User-Centered Approach to Empowering Healthcare Providers with Up-to-Date Adolescent HIV Information by Leveraging Large Language Models (LLMs)
Paul Macharia of the University of Nairobi in Kenya will develop an LLM-based platform to give healthcare providers real-time access to comprehensive, up-to-date, adolescent HIV information for enhanced decision-making and better patient health outcomes. To guide the project, they will establish a community advisory board, including HIV-positive adolescents, healthcare providers, and community leaders. They will interview providers to identify their current sources of this information and their unmet needs. They will then create a dataset relevant for adolescent HIV care, including medical literature, clinical guidelines, and research findings; use it to train an LLM; and develop a natural language interface for healthcare providers to interact with the LLM. They will pilot test the platform in different healthcare settings, collecting data on its impact on provider knowledge and practice.
Contribution to Improving the Health of the Populations of Saint-Louis Through Modeling and Monitoring of Cardiovascular Risk at Family Level
Philippe Manyacka Ma Nyemb of Gaston Berger University in Senegal will develop AI-based approaches to better monitor and manage cardiovascular diseases and understand their risk factors. They will perform a household-level study in the Saint-Louis Region of Senegal with monthly data collection, including medical examinations, behavioral surveys, and physical environment assessments. The monthly monitoring data will be analyzed by AI-based approaches, yielding cardiovascular disease risk scores for household members. They will use the study data and risk scores to train a Large Language Model with a chatbot interface available to healthcare professionals and the public. The chatbot and data collection process will serve as an integrated platform to reduce the burden of cardiovascular diseases. It will increase awareness of the disease and its risk factors for the public, and it will help increase adoption and effective use of digital tools more broadly to improve health.
Empowering Health Communication in Fulfulde-Speaking Communities Through an Innovative Multilingual Educational Chabot
Jules Brice Tchatchueng Mbougua of Centre Pasteur du Cameroun in Cameroon will develop a chatbot to provide health information in the Fulfulde language, which is commonly spoken in West Africa, to increase equitable access to healthcare. To overcome language barriers as well as variable levels of literacy, the chatbot will interact with users by speech or text and with bidirectional translation between Fulfulde, French, and English. To enable this, they will compile an extensive Fulfulde dataset covering health-related expressions and terminology. They will develop health information content that is culturally relevant by co-creating it with the communities the tool is meant to serve, and it will be focused on primary healthcare. The chatbot will include a way for users to provide feedback to ensure it is delivering information most relevant to the evolving needs of Fulfulde-speaking communities.
Galsen Deep Vision: Study and Proposal of Automatic Diagnosis Methods for Strabismus and Calculation of Angular Deviation Based on Deep Learning Approaches
Mandicou Ba of Université Cheikh Anta Diop in Senegal will develop an AI-based tool for automatic, cost-effective, and accessible early diagnosis of the eye disorder strabismus and for guiding surgical correction. Strabismus is eye misalignment, the two eyes pointing in different directions, and the associated impaired vision can become permanent at a young age if uncorrected. They will collect a clinical dataset of facial images of strabismus patients in Senegal, annotated by experts. After identifying a suitable AI-based method, they will apply it to the dataset to create an AI model for diagnosis and accurate calculation of angular deviation between the two eyes for use during surgical repair. They will use the model to develop an automated system as a web-based tool and also as a smartphone app, making it accessible even in rural areas for early diagnosis in children.
Liver Fibrosis Early Detection Using Ultrasound Images
Mamadou Bousso of Iba Der Thiam University in Senegal will develop methods for AI-based analysis of ultrasound images for cost-effective early detection of liver fibrosis caused by hepatitis B viral infection. They will improve the performance of an existing method by acquiring ultrasound data that more comprehensively encompasses the clinically-recognized stages of liver fibrosis. The expanded dataset will be used to train an AI model well-suited to capture complex patterns in imaging data. They will also establish support for healthcare professionals that facilitates the adoption and effective use of the application, including training courses, web-based and mobile phone-based tools with user-friendly interfaces, and ongoing technical support. The application would enable more screening in underserved areas, with increased early detection and awareness of liver fibrosis decreasing mortality from the disease as well as healthcare costs.
Modeling Multi-Pathogen Serosurveillance Data for Public Health Impact
Nicole Wolter of Wits Health Consortium (Pty) Limited in South Africa will establish an African modeling partnership between South Africa, Malawi, and Kenya to ensure that serosurveillance data for vaccine-preventable diseases are effectively incorporated into epidemiological models to guide immunization programs and policies. Serosurveillance provides the most direct measure of a population's immunity. They will establish a collaborative network across the three countries to use serological data to develop two types of models: epidemiological models to inform vaccine program priorities, predict disease burden, and identify immunity gaps and vulnerable groups at risk of outbreaks, and cost-effectiveness models to assess potential changes to these programs. They will train students in the use of AI to enhance data analysis, improve model outputs, and facilitate effective communication. They will regularly engage policymakers and other stakeholders, sharing results to enable comparisons between different countries and making resources available on open-access platforms.
My Daily Health
Mame Marème Fall of Kajou Senegal in Senegal will develop a platform to increase access to accurate health information, including information on available healthcare services, to improve the quality of life for rural populations in Senegal. They will use a Large Language Model to create a database of health information with a chatbot interface enabling questions and answers by either speech or text, including spoken questions in either French or Wolof. The database will be accessible online via internet technology that accommodates connections of short duration and low bandwidth, and it will be available offline as content stored on mobile phone microSD cards. They will evaluate the quality of answers to health questions through the system by engaging experts and by surveying users through pilot distribution of 1,000 microSD cards with the database.
The Village: Reimagining Global Health Collaboration and Decolonization Through AI-Powered Connections
Yap Boum II of Institute Pasteur of Bangui will develop a digital platform, called The Village, that strengthens the scientific research capacity across the Pasteur Network and beyond through conversational chatbots that forge productive links between those seeking and offering resources, ideas, and collaboration. They will identify suitable Large language Models and create a chatbot that collects unstructured data through conversations with scientists to generate user profiles with higher potential for productive matching across the research community. They will test and continually refine the platform through in-person and virtual meetings across the scientific community. As a platform making connections between scientists regardless of their location, resources, and research capacity, The Village will increase equity in global health research.
WISE-Ethiopia: Workforce, Information Systems, and Supply Chain Optimization to Strengthen Primary Healthcare in Ethiopia
Teferi Gedif of Addis Ababa University in Ethiopia will use health and economic data modeling to improve the efficiency and effectiveness of primary healthcare in Ethiopia through enhancements in the supply chain, health information system, and workforce distribution. Current challenges include inaccurate forecasting leading to shortages and wastage of healthcare commodities, lack of interoperability between patient and healthcare commodity information systems, poor implementation and integration of community-based and social health insurance schemes, and fragmented workflow with poorly matched workforce in terms of number of workers and their training. The models will identify key bottlenecks and inefficiencies. In collaboration with the Ethiopian Ministry of Health, these results will be used to design evidence-based guidelines and protocols for improved primary healthcare service delivery. They will pilot test the proposed strategies in two regions of the country.
Exploiting Metal Dependencies to Support a Low-Risk Vaginal Microbiome
Marguerite Hood-Pishchany of the University of North Carolina in the U.S. will characterize the metal nutrient dependencies of vaginal microbial communities to design interventions that support communities associated with a low risk of diseases linked to bacterial vaginosis. Using vaginal swabs from a longitudinal study of vaginal microbiota, they will measure the total elemental abundance of key metals, the concentration of relevant host metal-binding proteins, and the intracellular metal concentration of prevalent vaginal taxa. This will include comparison of samples across the menstrual cycle and across microbiota community types. They will also culture isolates of three key representatives of these bacterial community types, comparing their nutrient metal requirements and their susceptibility to metal sequestration and metal intoxication. This data will inform the design of interventions that alter metal availability, including identifying when in the menstrual cycle to intervene and guiding the best strategy for either metal supplementation or metal limitation.
AI-Driven Clinical Decision Support: Transforming Non-Communicable Disease Care in Kiambu County, Kenya
David Kamau of Mary Help of the Sick Mission Hospital in Kenya will integrate ChatGPT and a medical Large Language Model with the existing health management information systems in Kiambu County, Kenya, to provide clinical decision support for noncommunicable diseases. This integration will support healthcare providers in diagnosing diseases accurately and quickly, reducing misdiagnoses and improving patient outcomes, and it will support optimizing treatment plans, reducing unnecessary procedures and healthcare costs. They will evaluate the performance of the integrated AI tools, assess the usability of the system through surveys, and capture demographic data for patients receiving AI-assisted care. They will also provide training for healthcare professionals on effectively using AI tools to enhance patient care.
AI-Enabled Modeling of Cervical Cancer Registry Data for Enhanced Surveillance and Prevention Impact
Steven Wanyee of IntelliSOFT Consulting Limited in Kenya will develop an AI-based framework for analysis of cervical cancer registry data to identify epidemiological trends and improve surveillance and prevention efforts. The analysis will incorporate variables such as demographic factors, geographic locations, screening history, HPV vaccination rates, and treatment outcomes. They will use natural language processing to extract and analyze unstructured data. Machine learning algorithms will be used to identify patterns and trends in cervical cancer incidence rates, stage at diagnosis, treatment outcomes, and survival rates. They will develop predictive models to forecast cervical cancer burdens, estimate the potential impact of interventions for prevention, and guide resource allocation and targeted prevention strategies. They will also create user-friendly interfaces and visualizations to enable policymakers, public health professionals, and researchers to easily interpret the modeled data and use it effectively.
AI-Enhanced Clinical Decision Support for Nurse-Led Health Posts in Rwanda: Disrupting Primary Healthcare in Africa - "The AI-Enabled Nurse Project"
David Kamugundu of eFiche Limited in Rwanda will develop an AI-based platform to support nurses in Rwanda in accurate and efficient diagnosis and patient treatment. The platform will be integrated into the already-operational, web-based electronic medical records system eFiche. It will serve as a virtual assistant for nurses, including providing diagnostic support, suggesting treatment plans based on the latest medical guidelines and assessing adherence, and identifying potential adverse events. They will train a Large Language Model with historical health data to help predict diagnostic outcomes, laboratory orders, and subsequent procedures and prescriptions, and they will develop a chatbot to provide information and recommendations to nurses in a conversational manner. They will evaluate the platform based on the accuracy of the model, satisfaction of users, and the impact on healthcare delivery, including diagnostic accuracy, treatment efficacy, and adherence to health guidelines.
AI-Integrated Maternal Preeclampsia Detection and Care Transformation (AIMPact)
Obed Brew of Kwame Nkrumah University of Science and Technology in Ghana will explore applying a combination of AI-based analytical approaches to clinical data for early detection of preeclampsia in pregnancy to reduce maternal and neonatal morbidity and mortality. They will collect a diverse set of data from pregnant women, including physiological data from wearable devices, electronic health records, clinical notes, and fetal nucleic acids from non-invasive prenatal testing. They will apply a variety of AI tools to detect patterns across the data, such as associations between fetal gene signatures and maternal physiological markers. While evaluating the performance of the AI models in detecting preeclampsia, they will develop training programs for healthcare professionals in the use of AI tools in clinical settings.
AI-Powered Screening Tool for the Triage of Patients with Suspicion of Pulmonary Tuberculosis
Mihaja Raberahona of Equipe de Recherche Clinique en Maladies Infectieuses in Madagascar will develop an AI-based triage tool to identify patients likely to have pulmonary TB based on combining physiological data from wearable devices, cough acoustics, and anthropometric data. They will create an AI model that can find patterns in the combined data to help staff with minimal medical training quickly prioritize patients needing confirmatory testing. From a cohort of patients with symptoms suggestive of TB from primary healthcare centers in Madagascar, they will collect physiological and anthropometric data and perform a digital chest X-ray, cough sound analysis, and a GeneXpert molecular assay for the presence of Mycobacterium tuberculosis. They will evaluate performance of the AI-based triage tool primarily as compared to the microbiological assay, but also to other current screening methods, including chest X-rays analyzed by clinicians with or without AI support.
Aifya: Using GPT-4 to Enhance Newborn Care in Bungoma County, Kenya
Jesse Gitaka of Mount Kenya University in Kenya will develop the GPT-4 AI model to support healthcare providers with up-to-date medical information for improved clinical decision-making and neonatal care. They will identify knowledge gaps among providers, using this information to guide training for a cohort on using GPT-4 for clinical support. They will then evaluate their use of GPT-4 for its impact on clinical decisions and neonatal outcomes. A subset of the healthcare provider cohort will be engaged to identify the barriers, risks, and opportunities associated with use of the AI tool. Results from both these evaluations will be used to develop a scalable framework for the deployment of AI in similar healthcare contexts to reduce neonatal morbidity and mortality, especially where there is a shortage of medical personnel.
Design of Community- and Health Worker-Centered Data Collection Systems for the Health National Adaptation Plan
Maria Qambayot of the University of Global Health Equity in Rwanda will develop a set of mechanisms for engaging local health professionals and communities in data collection and real-time assessment of the health impacts of climate change to support data-driven adaptation strategies. They will conduct household surveys to better understand the vulnerabilities of communities most at risk for these impacts. They will interview health professionals to better understand how they track these impacts and what types of data and information they currently lack. They will also collect 10 years of historical environmental and health data to identify potential patterns and trends linking public health to climate change. These efforts will guide the creation of data collection tools for ongoing community-based assessment as well as a framework for measurement and evaluation of strategies for climate change adaptation.
Development of an Integrated Early Warning and Response System (IEWRS) for Health in the Context of Climate Change in Rwanda
Didier Ntwali of the Rwanda Space Agency in Rwanda will develop and implement an integrated early warning and response system for climate-related diseases and other health challenges. They will collect historical data encompassing meteorological data from satellites and ground-based instruments, air pollution data from satellites, and health data from Rwandan organizations and the World Health Organization. Using this data, they will identify key diseases likely to be associated with climate change, including vector-borne, water-borne, and respiratory diseases. They will analyze the spatial and temporal distribution of these diseases and develop predictive models as the basis for an early warning system. The models will guide the design of interventions to minimize the impact of climate change on health as well as the design of mechanisms for real-time communication of risks to those most vulnerable.
Dialogues of Delivery: Fine-Tuning Large Language Models (LLMs) for Prenatal and Perinatal Care in East African Languages
Fred Kaggwa of Mbarara University of Science and Technology in Uganda will develop an LLM for answering questions related to prenatal and postpartum care in Uganda in three languages: Swahili, Runyankore-Rukiga, and Luganda. This will also serve to create a scalable, open-source pipeline for developing AI models incorporating underrepresented languages more broadly. They will identify the most suitable LLM and train it with existing databases and with new, high-quality medical text, including that extracted from textbooks and patient education materials as well as new question-and-answer pairs written by local clinicians. They will iteratively evaluate and improve the LLM, working directly with community health workers and expectant mothers to ensure the model’s responses are safe, accurate, relevant, and accessible.
Early Warning System Developed with AI and Human Centered Design for Tracking the Effects of Climate Change on Maternal and Newborn Health
Mawuli Dzodzomenyo of the University of Ghana School of Public Health in Ghana will use a human-centered design approach to develop an AI-based early warning system to support communities in Ghana prepare for climate change-related risks to maternal and newborn health. They will develop a machine learning model that integrates climate and public health data to identify patterns relevant for maternal and newborn health. They will then use a human-centered design approach to engage community healthcare workers and women's groups in workshops, choosing communities in two distinct ecological zones in Ghana to encompass a range of climate change issues. The initial modeling results will be presented at the workshops, with participants providing feedback to shape the model into a prototype early warning system most suitable to their needs and concerns.
Leveraging AI to Address Disease Management Knowledge Gaps Among Persons Living with Sickle Cell Disease (SCD) in Kenya
Dennis Maorwe of DPE Company Limited in Kenya will develop a Large Language Model (LLM) to support the planning and execution of behavior change interventions to improve health outcomes for Kenyans living with SCD. Guided by insights from SCD patients and medical specialists, they will train an LLM with SCD management practices and additional open data relevant to designing interventions for social behavior change for SCD. The LLM will be used to generate tailored health messages to support SCD patients through the different disease management stages and to empower them to take an active role in their health. This will help reduce the stigma around the disease and improve their quality of life.
MamaOpeAI: Clinical Decision Support to Manage Respiratory Illnesses
Brian Turyabagye of MamaOpe Medicals in Uganda will develop an AI-based platform integrated with the MamaOpe screening tool to enhance the diagnosis and management of respiratory illnesses. MamaOpe is a pneumonia screening tool based on vital signs, including respiratory rate and lung sounds, with results presented via a mobile app into which healthcare workers can enter patient symptoms and store patient histories. They will train a Large Language Model with the MamaOpe database to help guide differential diagnosis by highlighting critical indicators and suggesting supplementary tests for more accurate diagnosis. In settings with limited direct access to specialists, the platform can facilitate remote consultations. They will perform an efficacy study to evaluate how well the platform correctly predicts clinical outcomes.
Multimodal Machine Learning for Cancer Pathogen Detection and Automated Pathology Report Generation
Rose Nakasi of Makerere University in Uganda will develop an AI-based platform to support diagnosis and management of cervical cancer in Uganda. They will collaborate with the Uganda Cancer Institute to develop a set of AI tools for automated diagnosis of cervical cancer based on microscopy of patient samples and for automated generation of the associated pathology reports. This will include categorizing pathologies, enabling identification of trends over time. The AI tools will be integrated into a web-based platform along with the capacity for Visual Question Answering to support interpretation based on medical images and diagnosis in remote areas of the country with limited access to pathologists. They will evaluate the accuracy of the cervical cancer diagnoses and the quality of reports generated through the platform as compared to those generated by expert pathologists.
Optimizing Health Policy Enactment, Implementation, and Monitoring by Application of Large Language Models (LLMs)
Kevin Korir of Visortech Solutions in Kenya in partnership with Yemaya Health Advisory will develop an LLM to map the process of health policy creation and approval, serving as a tool for quicker translation of new evidence into policies. They will pilot test the tool by using it to develop a policy framework for strengthening national HIV prevention management systems. They will develop the LLM as support for policy simulation and scenario planning to inform the policy approval process, for gap analysis to optimize current policies, and for identification of conflicts across related policies and their implementation. The LLM will facilitate generating written documents useful for policymakers, including briefs for new policies and summaries of proposed changes to existing ones.
Responsible AI-Powered Decision Support for the Management of Diabetes in Pregnant Women in Ghana (RAID-MaP-Gh)
Prince Adjei of Kwame Nkrumah University of Science and Technology in Ghana will develop an AI-based tool to support clinicians and patients in managing complications and comorbidities in pregnancies, focusing on pre-gestational and gestational diabetes. They will train a Large Language Model with relevant data and health guidelines from Ghana, including a glossary of medical and nutritional terms in the local language Twi. They will also design a user-friendly interface for interactions in English and Twi, with the patient interface incorporated into WhatsApp. The resulting tool, RAID-MaP-Gh, will provide practical guidance to clinicians, ranging from specialists to midwives and traditional birth attendants, and guidance to patients that takes into consideration the socioeconomic and cultural contexts most relevant to Ghana. The tool will help close health information gaps associated with gestational diabetes, reducing the number of undiagnosed cases and improving maternal and infant health outcomes.