Awards

Orapan Sripichai of the National Institute of Health of Thailand in Thailand will engage a national network of laboratories for the genomic surveillance of Salmonella, involving sequencing clinical isolates to characterize strains, virulence factors and mechanisms of antimicrobial resistance. Salmonella infection is prevalent in Thailand and can be life-threatening. The emergence of multidrug-resistant Salmonella strains in Southeast Asia is an additional major concern. They will collect approximately 1,500 clinical isolates from 77 provincial hospitals across Thailand over one year, and train local laboratory scientists and bioinformaticians to produce and analyze genomics data. The data will be uploaded to a standard repository in the National Center for Biotechnology Information (NCBI) and will help to guide prevention and control measures.

Rifky Waluyajati Rachman of the West Java Provincial Health Laboratory in Indonesia will employ targeted next-generation sequencing (NGS) to support genomic surveillance of drug-resistant tuberculosis (TB) in Indonesia. Indonesia has the second highest number of TB cases globally and a growing burden of largely undetected multidrug-resistant TB, yet no drug resistance surveillance in place. They will perform targeted NGS on over 5,000 positive sputum samples to more accurately estimate drug-resistant TB prevalence. They will also conduct whole genome sequencing at the community level to understand transmission patterns and help guide public health interventions. To build capacity, they will provide tailored training on the experimental, bioinformatic, public health, and epidemiological aspects of infectious disease surveillance. They will also establish a public center of expertise for pathogen surveillance in West Java, which has a population of 48 million.

Jacqueline Weyer of the National Institute for Communicable Diseases in South Africa and Jinal Bhiman of Wits Health Consortium (Pty) Ltd also in South Africa will leverage a rapid monoclonal antibody (mAb) isolation and screening pipeline to develop diagnostics that differentiate between pathogens to support epidemic responses. Africa’s burden of many zoonoses and vector-borne diseases (VBD), such as Lassa fever and yellow fever, remains largely unknown, mainly due to diagnostic costs and limited access to reagents. They will leverage an existing screening pipeline, with infrastructure established by the Global Immunology and Immune Sequencing for Epidemic Response - South Africa (GIISER-SA) project, using a mouse model as a more readily available source of pathogen-specific B cells to identify mAbs that detect three ebolavirus species. These mAbs will be tested for sensitivity and specificity using patient samples and can be used to develop immunoassays, including rapid lateral flow assays, which are important for rapid, field-based diagnosis.

Anne Lee of Brigham and Women's Hospital in the U.S. and Yasir Shafiq of Aga Khan University in Pakistan will develop geospatial models to predict risks of undernutrition among adolescent girls and pregnant and lactating women in settings affected by conflict, climate and COVID-19 to help target interventions. Globally, around 30–40 million pregnant women and 50 million adolescent girls are underweight. Risks of undernutrition have recently been amplified by numerous armed conflicts, climatic shocks such as flooding and the COVID-19 pandemic. However, real-time data shortages prevent interventions, such as balanced energy-protein supplements, from reaching the highest-risk groups. Using Bayesian Hierarchical Spatial modeling, they will develop geospatial models for countries vulnerable to conflict and climate change, such as Ethiopia and Yemen. By incorporating socio-demographic and economic indicators, and climate-related and conflict-related shocks from national databases, they can estimate risks based on exposure and predict outcomes, such as undernutrition and anemia.

Margaret Kasaro and Soumya Benhabbour of the University of North Carolina at Chapel Hill in the U.S. will evaluate 3D-printed intravaginal ring (IVR) prototypes in Zambia to identify the design most acceptable to women for long-term use against unplanned pregnancy and HIV infection. In Zambia, HIV prevalence remains particularly high among women, and 41% of pregnancies are unplanned. IVRs are an effective, well-tolerated, and women-controlled contraceptive and HIV-preventative; however, their performance has suffered in large-scale clinical trials because of poor adherence. They have exploited a state-of-the-art 3D-printing process to rapidly engineer IVRs in a cost-effective, single-step process enabling the controlled release of multiple drugs for HIV prevention and contraception. They will recruit around 16 women, aged 18–45 from Kampala Health Centre, and use focus groups to evaluate their views on the proposed 90-day timeframe of use for four different IVR prototypes to guide the final design.

Aida Sadikh Badiane of the Universite Cheikh Anta Diop de Dakar in Senegal will use a metabolomics platform to identify cervicovaginal metabolites and inflammatory mediators associated with high-risk human papillomavirus (HPV) infection, which cause the majority of cervical cancer cases, in Senegalese women. Cervical cancer is the leading cause of cancer deaths in women in sub-Saharan Africa. Metabolic and immune markers could enable more effective diagnoses for these diseases than the current methods used in low-resource settings. They will perform a prospective, cross-sectional study on a cohort of 385 women using an untargeted metabolomics platform to identify molecules within the cervicovaginal microenvironment that are predictive of infection and cancer risk. They will also use Luminex assays to evaluate inflammatory molecules and other markers associated with infection, and sequence the L1-HPV gene in the samples to better track the genotypes in Senegal.

Pragya Yadav of the Indian Council of Medical Research - National Institute of Virology in India will strengthen genomic and epidemiological surveillance in different locations across India to enhance preparedness against high-risk viral diseases. With India's extreme geo-climatic diversity, it is under constant threat of emerging and reemerging viral infections. They will enhance surveillance of endemic diseases in India, including Zika and Dengue, by establishing a network of seven laboratories and training staff in molecular diagnostic techniques, including sequencing, data analysis, and biosafety. They will also select surveillance sites for collecting samples and expand next-generation sequencing capacity to identify variants.

Simon Kariuki of the Kenya Medical Research Institute in Kenya will use an antibody platform to characterize children's immune responses to the new malaria vaccine to determine the impact of any accompanying infections. The WHO recently approved a new malaria vaccine that will mainly be deployed in sub-Saharan Africa. During its development, HIV-infected children were found to mount weaker immune responses. Helminth infections, which are prevalent in sub-Saharan Africa, are also suspected to negatively impact vaccine efficacy. To test this, they will use an antibody-dynamics platform to assess the impact of helminths and other current or prior parasitic, bacterial, and viral infections on humoral and cellular immune responses following the 4th dose of the new malaria vaccine in two- to three-year-old children at six hospitals in western Kenya. This will help design more effective deployment strategies such as deworming before vaccination.

Senjuti Saha of the Child Health Research Foundation in Bangladesh will use a single-cell analytics platform to track the immune responses of babies before and after receiving a pneumococcal conjugate vaccine to determine the impact of various factors, including nutritional status and seasonality, on vaccine efficacy. Vaccines have successfully reduced childhood morbidity and mortality; however, their efficacy can be influenced by host factors and extrinsic factors through unknown cellular mechanisms. They will recruit 50 newborns in a rural district north of Dhaka and collect blood and nasopharyngeal swabs before, during and after a routine vaccination series. They will extract peripheral blood mononuclear cells and use them to perform single-cell RNA sequencing to identify cell subtypes and link differential vaccine responses to factors including gestational age, nutritional status and sex.

Yasir Shafiq of Aga Khan University in Pakistan and Anne Lee of Brigham and Women's Hospital in the U.S. will develop geospatial models to predict risks of undernutrition among adolescent girls and pregnant and lactating women in settings affected by conflict, climate and COVID-19 to help target interventions. Globally, around 30–40 million pregnant women and 50 million adolescent girls are underweight. Risks of undernutrition have recently been amplified by numerous armed conflicts, climatic shocks such as flooding and the COVID-19 pandemic. However, real-time data shortages prevent interventions, such as balanced energy-protein supplements, from reaching the highest-risk groups. Using Bayesian Hierarchical Spatial modeling, they will develop geospatial models for countries vulnerable to conflict and climate change, such as Ethiopia and Yemen. By incorporating socio-demographic and economic indicators, and climate-related and conflict-related shocks from national databases, they can estimate risks based on exposure and predict outcomes, such as undernutrition and anemia.

Raghavan Varadarajan in collaboration with Sudha Kumari, both of the Indian Institute of Science in India and Nico Callewaert of the VIB-UGent Center for Medical Biotechnology in Belgium will modify the microorganism, Pichia pastoris, used to produce lower-cost vaccines in low-resource settings, to generate more effective vaccines. Many vaccines are composed of pathogen-derived proteins that require production inside other cells. Although P. pastoris can produce these antigens at a lower cost than mammalian or insect cells, the viral proteins it produced for the SARS-CoV-2 vaccine were hyperglycosylated and poorly immunogenic, unlike those produced in mammalian cells. They will express different antigen forms in mammalian cells, and in different Pichia hosts, to determine whether altering glycosylation and protein size affects immunogenicity. They will also glycoengineer Pichia hosts to determine whether they can produce more effective vaccines. Ultimately, this approach could improve vaccine production for COVID-19 and other viruses.

Jinal Bhiman of Wits Health Consortium (Pty) Ltd in South Africa and Jacqueline Weyer of the National Institute for Communicable Diseases also in South Africa will leverage a rapid monoclonal antibody (mAb) isolation and screening pipeline to develop diagnostics that differentiate between pathogens to support epidemic responses. Africa's burden of many zoonoses and vector-borne diseases (VBD), such as Lassa fever and yellow fever, remains largely unknown, mainly due to diagnostic costs and limited access to reagents. They will leverage an existing screening pipeline, with infrastructure established by the Global Immunology and Immune Sequencing for Epidemic Response - South Africa (GIISER-SA) project, using a mouse model as a more readily available source of pathogen-specific B cells to identify mAbs that detect three ebolavirus species. These mAbs will be tested for sensitivity and specificity using patient samples and can be used to develop immunoassays, including rapid lateral flow assays, which are important for rapid, field-based diagnosis.

Simon Kariuki of the Liverpool School of Tropical Medicine, Kenya in Kenya and Holden Maecker of Stanford University in the U.S. will determine whether probiotics and synbiotics can boost infant immune responses to vaccines. Diarrhea is the second leading cause of death in young children, with rotavirus a leading culprit. Oral rotavirus vaccines are routinely administered in low- and middle-income countries (LMIC) but are only 50% effective compared to 85–98% effectivity in high-income countries. One major cause could be environmental enteric dysfunction (EED), which is pervasive in children in LMIC. Their clinical trial of 600 newborns from western Kenya indicated that administering weekly probiotics and synbiotics (Lactobacilli and Bifidobacteria) up to age six months improved gut health and prevented EED-associated inflammation. They will use stored plasma samples and vaccination records to determine the impact of EED and systemic inflammation, as well as pro- and synbiotic effects on rotavirus vaccine efficacy.

Abdoulaye Djimde of the University of Sciences, Techniques, and Technologies of Bamako in Mali will use a metabolomics platform to identify biomarkers to detect dormant Plasmodia hypnozoites in a previously malaria-infected individual as a diagnostic method and to screen for new therapeutics. Malaria remains one of the deadliest parasitic diseases in the world, with 95% of deaths occurring in sub-Saharan Africa. Most research focuses on the most prevalent causative parasite, Plasmodium falciparum, but other strains, including P. vivax and P. ovale, are likely to become more dominant. These strains uniquely produce hypnozoites, which can lay dormant for years in the liver where they are undetectable and resistant to treatment. They will generate hypnozoite-containing liver cells in vitro and subject them to metabolomics analysis to identify hypnozoite-associated biomarkers. Candidate biomarkers will then be validated in serum samples from thirty infected individuals.

Georgia Tomaras and Nathanial Chapman of Duke University and Girija Goyal and Don Ingber of the Wyss Institute at Harvard University, both in the U.S., will test whether Organ-on-a-Chip technology can inform how antibodies protect humans from pathogen infections to design more effective vaccines. Identifying protective vaccine features and validating them in human clinical trials is time-consuming and costly. An alternative is to use primary human organ chips that reproduce human physiology in vitro. They will stimulate peripheral blood mononuclear cells on the human lymph-node-on-a-chip with existing COVID vaccines and extensively characterize the resultant antibodies, including evaluating epitope specificity, and isotype and glycan profiling. They will also assess the capacity of these antibodies to prevent or reduce SARS-CoV-2 infection using the lung-on-a-chip technology. This approach can ultimately be applied to other pathogens, such as those causing malaria.

Audrey Dubot-Pérès of the Lao-Oxford-Mahosot Hospital-Wellcome Trust Research Unit (LOMWRU) in Lao PDR will establish a pilot respiratory syncytial virus (RSV) genomic surveillance system to determine disease burden and monitor strain circulation in Lao PDR. RSV is the leading cause of viral pneumonia in young children in low-income countries. Accurate data on disease burden, transmission and viral evolution are critical to successfully introduce emerging vaccines and therapies. Leveraging their experience as a national center for SARS-CoV-2 genomic surveillance, they will develop an RSV genomic sequencing protocol using samples collected from children at two central and four provincial hospitals. They will also investigate whether RSV RNA can be purified directly from rapid diagnostic tests to improve surveillance in remote areas. The data will be displayed on a national health dashboard. If successful, their approach could be expanded into a national surveillance system.

This grant is one of three grants that are funded and administered by the Programme for Research in Epidemic Preparedness and Response (PREPARE) in Singapore.

Chhorvann Chhea of the National Institute of Public Health in Cambodia will expand Cambodia’s Severe Acute Respiratory Infections (SARI) surveillance network by integrating metagenomic next-generation sequencing to better diagnose and monitor severe respiratory infections. Pneumonia is the leading cause of death globally in children under five years old, with the majority of severe cases classified as viral. To successfully develop treatments and vaccines, a comprehensive understanding of viral genetic diversity is required; however, this remains largely uncatalogued for common respiratory viruses, such as respiratory syncytial virus (RSV). They will collect oropharyngeal swabs, blood culture isolates, or lower respiratory tract samples from adults and children with SARI at nine sites. They will extract RNA and leverage pandemic sequencing infrastructure for sequencing, taxonomic identification and phylogenetic analyses to guide molecular epidemiology and outbreak investigations. The data will be integrated with a country-wide genomic surveillance strategy, currently under development.

This grant is one of three grants that are funded and administered by the Programme for Research in Epidemic Preparedness and Response (PREPARE) in Singapore.

Mai Le of the National Institute of Hygiene and Epidemiology in Vietnam will expand Vietnam’s systematic surveillance and sequencing capacities to detect potential pandemic pathogens, including influenza and coronaviruses, and incorporate agnostic sequencing of conventionally undiagnosed pathogens. They will build on the existing infrastructure of the influenza-like illnesses sentinel surveillance network, which collects samples from four outpatient clinics, to include testing for both influenza A and B and SARS-CoV-2 viruses, with the possibility to expand. They will also revive the hospital-based Severe Acute Respiratory Infections (SARI) surveillance network, which works with three hospital emergency departments and ICUs, to focus on 12 pathogens and incorporate an agnostic sequencing component. Their activities will include training health workers in sample collection and scientists in directed and agnostic sequencing of respiratory pathogens and bioinformatics analysis. The data produced will be shared in real-time on an online dashboard.

This grant is one of three grants that are funded and administered by the Programme for Research in Epidemic Preparedness and Response (PREPARE) in Singapore.

Olayinka Omigbodun of the University of Ibadan in Nigeria will build a critical mass of female researchers and policymakers to adapt and apply diverse mathematical models to better understand the epidemiology of depression in young women in sub-Saharan Africa and identify more effective preventative measures and treatments. Adolescent girls and young women in sub-Saharan Africa are three times more likely than their male counterparts to have a depressive disorder. Mathematical modeling provides a powerful means of predicting the dynamics of depression. However, there is a paucity of models that inform mental health strategies in this region. They will leverage existing research networks across the region to train new female modelers and, together with them, critique existing mathematical models of mental health and depression. This will enable the development of more suitable models, populated with local data, to identify predictors of depression in this group.

Cameron Myhrvold of Princeton University and Mireille Kamariza of the University of California, Los Angeles, both in the U.S., will develop an assay to rapidly detect multiple drug resistance mutations in Plasmodium falciparum and Mycobacterium tuberculosis for malaria and tuberculosis (TB) surveillance, respectively. Malaria and TB are two of the world's deadliest infectious diseases. Rapid and accurate drug resistance testing can save lives but current assays are slow or difficult to scale. Combinatorial Arrayed Reactions for Multiplexed Evaluation of Nucleic acids (CARMEN) is a CRISPR-based diagnostic test that detects nucleic acid biomarkers, such as those in pathogens, with high specificity and throughput. They have developed microfluidic CARMEN (mCARMEN), which produces results in under five hours, and will use an algorithm to design assays that detect the top ten drug-resistant P. falciparum mutations from blood samples, and M. tuberculosis mutations from saliva samples that confer resistance to two first-line TB drugs.

Alex Ario of Makerere University in Uganda, together with the Uganda National Institute of Public Health, the Ministry of Health of Uganda, and sister organizations in the East Africa region will expand their modeling capacities and establish collaborative research groups to apply modeling and data analytics to study health issues disproportionately affecting women. They will set up a multi-country steering committee to identify teams of modelers in Uganda, Kenya, and Rwanda. This committee will also select the most pressing women’s health issues and assign them to the modeling teams for investigation. They will also train modelers, particularly women, through on-the-job teaching and mentorship. The main findings from the collaborative studies will be disseminated to decision-makers and they will also advocate to influence policy.

Project intends to capture the images of blood samples for diagnosis of Lymphatic Filariasis and applying customized machine learning algorithms for quantification and classification of Lymphatic Filariasis.

Esnat Chirwa of the South African Medical Research Council in South Africa will strengthen modeling and data science capacities by incorporating training and networking approaches, particularly for female researchers in Malawi and South Africa. The rising disease burden in sub-Saharan Africa has resulted in the generation of many large, complex datasets; although these provide rich research resources, local analytical capabilities are limited. They will increase the number of female modelers and statisticians by providing financial support to seven female Biostatistics and Statistics master’s students, who will be mentored by their team, and a series of free, short in-person and online advanced statistics courses to over 90 more female researchers. They will also build networks between female researchers to facilitate collaborations on defined topics, including identifying the mechanisms driving women’s health outcomes in Southern Africa and the long-term impact of rape on mental health.

Project intends to discover high affinity and specific ligands called suprabodies as the biomarkers of Lymphatic Filariasis.

Maurício Barreto and colleagues of Fiocruz in Brazil, together with Alexa Heeks and colleagues of the Health Foundation of South Africa in South Africa, will employ real-world data from two large countries of the Global South to develop a common data model of infectious diseases affecting pregnant women to identify causes and aid intervention development. Centro de Integração de Dados e Conhecimentos para Saúde (CIDACS), together with the Western Cape Provincial Health Data Centre (WCPHDC), have built data systems to utilize routinely collected health data for exploring disease impacts. They will leverage these data systems to explore the impact of gestational syphilis in Bahia, Brazil, and tuberculosis in the Western Cape province of South Africa, and the coverage and effects of screening interventions. Teams will include data curators, analysts and scientists, who will perform data discovery and processing, alongside epidemiologists, clinicians and public health specialists, who will perform epidemiological analyses and community engagements.

Alexa Heeks and colleagues of the Health Foundation of South Africa in South Africa, together with Maurício Barreto and colleagues of Fiocruz in Brazil, will employ real-world data from two large countries of the Global South to develop a common data model of infectious diseases affecting pregnant women to identify causes and aid intervention development. Centro de Integração de Dados e Conhecimentos para Saúde (CIDACS), together with the Western Cape Provincial Health Data Centre (WCPHDC), have built data systems to utilize routinely collected health data for exploring disease impacts. They will leverage these data systems to explore the impact of gestational syphilis in Bahia, Brazil, and tuberculosis in the Western Cape province of South Africa, and the coverage and effects of screening interventions. Teams will include data curators, analysts and scientists, who will perform data discovery and processing, alongside epidemiologists, clinicians and public health specialists, who will perform epidemiological analyses and community engagements.

Seth Adu-Afarwuah of the University of Ghana in Ghana and Julie Croff of Oklahoma State University Center for Health Sciences in the U.S. will assess the effects of nutritional supplementation on adolescent brain development in low-resource settings to support interventions. Nutritional behavior majorly impacts the rapid stage of adolescent neurodevelopment, which in turn impacts future generations through effects on maternal and paternal nutritional status, cognition and parenting. However, little is known about typical adolescent neurodevelopment in low- and middle-income countries, where 90% of the world’s adolescents live. They will recruit 40–60 post-pubertal adolescents in Accra, Ghana, measure their corticolimbic system development over nine months, and assess their problem-solving, planning and cognitive functioning. In another cohort of 40–60 post-pubertal adolescents, they will measure adherence to an eight-month twice-daily micronutrient supplementation program and associated nutritional outcomes.

Julie Croff of Oklahoma State University Center for Health Sciences in the U.S. and Seth Adu-Afarwuah of the University of Ghana in Ghana will assess the effects of nutritional supplementation on adolescent brain development in low-resource settings to support interventions. Nutritional behavior majorly impacts the rapid stage of adolescent neurodevelopment, which in turn impacts future generations through effects on maternal and paternal nutritional status, cognition and parenting. However, little is known about typical adolescent neurodevelopment in low- and middle-income countries, where 90% of the world’s adolescents live. They will recruit 40–60 post-pubertal adolescents in Accra, Ghana, measure their corticolimbic system development over nine months, and assess their problem-solving, planning and cognitive functioning. In another cohort of 40–60 post-pubertal adolescents, they will measure adherence to an eight-month twice-daily micronutrient supplementation program and associated nutritional outcomes.

Brigida Rusconi of Washington University in the U.S. will determine whether female infants develop long-lived antibodies against gut bacteria that subsequently both protect against bacterial infections and promote healthy gut immune and microbiota development in their offspring. Enteric bacterial infections are leading causes of infant morbidity in low- and middle-income countries. Using their mouse model, they found that mothers lacking IgG antibodies, which normally develop before weaning, are unable to provide passive protection against enteric infections to their pups. They will adapt their microbial flow cytometry to test whether maternal serum IgGs react more strongly to infant gut bacteria, suggesting establishment in infancy, and whether they provide passive immunity during pregnancy. They will also analyze plasma from two-year-old infants to identify those with weak IgG reactivity and potential causes. Finally, using a malnutrition cohort in Pakistan, they will train local bioinformaticians and assess whether malnutrition inhibits anti-gut commensal IgG responses.

Sandra Agudelo-Londoño of the Pontificia Universidad Javeriana in Bogota, in collaboration with various partners across Colombia including Yadira Eugenia Borrero Ramirez at the University of Antioquia in Medellín, will apply gender-transformative and feminist-based approaches to data analysis to identify the structural barriers affecting women's health in Colombia. Women's health is a complex issue with biological, historical, sociocultural, economic, and political aspects. The Global South has few female data modelers and no training or mentoring networks for women. They have therefore assembled an interdisciplinary group of female scholars and will deploy five virtual training courses on an open and free educational platform, focusing on gender, feminism, and health data analysis, alongside political advocacy, and data-driven decisions. They will also create a health data feminist network and use an existing gender-specific health and social dataset to conduct a comprehensive analysis focused on health issues disproportionally affecting women.

Laeticia Toe of the Institut de Recherche en Sciences de la Sante in Burkina Faso will use a metabolomics profiling platform to identify new biomarkers that can be used to diagnose environmental enteric dysfunction (EED) in women of reproductive age. EED affects nutrient absorption and immune function and may cause adverse birth outcomes in pregnant women. It is widespread in deprived areas in low- and middle-income settings but is often undiagnosed because the gold-standard diagnostic method requires an invasive procedure by trained personnel. They will determine the prevalence of EED by performing ELISA on existing plasma, serum and stool samples from 80 women of reproductive age living in rural Burkina Faso. They will then apply untargeted metabolomics on the samples to identify biomarkers that can be integrated with inflammatory markers and sequencing data and cross-validated for large-scale diagnoses of EED in women from low-resource settings.

Daniel Kiboi of the Jomo Kenyatta University of Agriculture and Technology in Kenya will assess whether a novel mutation in the human malaria parasite, Plasmodium falciparum, can be used as a marker to identify drug-resistant malaria and protect key antimalarial drugs. Emerging P. falciparum variants resistant to the three frontline drugs kill millions of people annually but are hard to detect. A better understanding of how these variants resist the actions of existing drugs can help to develop more effective drugs. They previously used a mouse malaria model to produce Plasmodium parasites resistant to all three main drugs and identified the candidate mutated protein likely causing this resistance. They will use in silico bioinformatics analysis, CRISPR/Cas9 approaches, and in vitro drug susceptibility assays to evaluate and validate this mutant protein and determine its role in drug resistance in the human malaria parasite.

Yingda Xie of Rutgers New Jersey Medical School in the U.S. and Joaniter Nankabirwa of Makerere University in Uganda will use CRISPR-based technology to monitor respiratory, food-borne and antimicrobial-resistant pathogens in Ugandan wastewater. A recent Ebola outbreak in Uganda highlights the need for routine multi-pathogen surveillance. However, the vast quantities and diversities of microbes in wastewater make it hard to identify those that might cause deadly outbreaks. They will combine CRISPR-based diagnostics with the recently developed multiplex assay, Combinatorial Arrayed Reactions for Multiplexed Evaluation of Nucleic acids (CARMEN), which enables highly sensitive and specific detection of over 150 nucleic acid sequences from dozens of samples in parallel. They will assess the performance of a field-deployable CRISPR assay to monitor specific pathogens in hospital sewage lines of Mulago Hospital. They will also leverage CARMEN to broadly survey for high-priority outbreak pathogens, including Ebola and yellow fever, in Kampala’s regional wastewater sources.

Amira Kebir of the Pasteur Institute of Tunis in Tunisia will create an African-based and -led learning and research network that links Francophone and Anglophone African research institutions to strengthen the capacity and ecosystem for modeling and analyzing women's health in Africa. They will train eight Ph.D. and Postdoctoral researchers in an intra-African collaboration to use modeling approaches on available datasets that can inform public health decisions. They will also establish a summer school and workshops for training up to twenty students. These trainees will be incorporated into modeling groups by partners in northern, western, central, and eastern Africa that will apply mathematical modeling and gender-based data analysis to investigate four infectious disease areas that highly impact women, namely human papillomavirus, hepatitis B virus, COVID-19, and antimicrobial resistance. They will also build a software platform to standardize data collection and manage project information and data security.

Berge Tsanou of the University of Dschang in Cameroon will support trainee mathematical modelers in epidemiology, particularly women, to strengthen capacity and to investigate health problems related to human papillomavirus (HPV) and cervical cancer (CC) in four Central-East African countries. Both HPV and CC are affected by HIV, all of which disproportionately affect women, particularly in sub-Saharan Africa. However, the nature of this interplay is largely unknown. They will synergize efforts across sub-Saharan Africa and use modeling approaches to study the co-evolution, prevention, and diagnosis of these diseases to enable earlier-stage treatments. They will support 30 master’s students, 14 PhD students, and three Postdoc fellows, at least 70% of whom will be female, and hold workshops to engage stakeholders and support evidence-based policymaking. They will also develop a dashboard and interactive software for ongoing disease surveillance in the region.

Praveen Devarsetty of the George Institute for Global Health in India will integrate an LLM into their SMARThealth Pregnancy application to enable two-way communication support for frontline health workers to improve healthcare services for pregnant and postpartum women in India. Reducing maternal and newborn mortality and morbidity is a global priority, particularly in low- and middle-income countries where information about medical conditions and pregnancy symptoms is difficult to access in simple terms and local languages. Together with experts, they will create an "encyclopedia" of pregnancy advice based on Indian and WHO guidelines, integrate ChatGPT-4 into their SMARThealth Pregnancy application, and evaluate the application for providing high-quality and contextually relevant healthcare information and services following prompts from healthcare workers.

Imad Elhajj of the Humanitarian Engineering Initiative of the American University of Beirut in Lebanon will use Large Language Models (LLMs) to develop an interactive community health promotion platform with a chatbot that provides accurate health messages and real-time responses to queries on platforms like WhatsApp to vulnerable populations in Lebanon and Jordan. They will process texts from trusted websites, documents, and other text repositories, such as UNICEF and the WHO, into smaller text segments. These segments will then be converted into fixed-length vectors that capture their semantic meaning and contextual relationships. To generate answers, the GPT-3.5/4 model will retrieve the relevant vectors based on the user's query and use them together with the context taken from the conversation history. They will first evaluate the platform internally to ensure the relevancy, coherence and accuracy of the generated messages, and then conduct a pilot study with a small representative group from the target communities.

Maryam Mustafa of the Lahore University of Management Sciences in Pakistan will build a voice-enabled, mobile phone-based, conversational AI assistant, Awaaz-e-Sehat, for maternal healthcare workers in Pakistan to create and manage detailed electronic medical records. Pakistan has among the poorest pregnancy outcomes worldwide. The lack of documented medical records of pregnant women seeking care makes it challenging for doctors to provide accurate diagnoses and contextualized care based on socio-economic and lifestyle factors, which also play a vital role in maternal health outcomes. They will develop a proof-of-concept system comprising an intuitive user interface speech recognition module and a text recognition module to record audio responses in different languages following specific prompts. The system will then convert responses into text and populate a template electronic medical record in Urdu. Awaaz-e-Sehat will be evaluated by maternal healthcare workers at Shalamar Hospital for its ability to collect records from 500 patients.

Nirmal Ravi of EHA Clinics Ltd. in Nigeria will develop and test scalable and cost-effective ways to use large language models (LLMs) such as ChatGPT-4 to provide “second opinions” for community health workers (CHEWs) in low- and middle-income countries (LMICs). These second opinions would mirror what a reviewing physician might advise the provider in question after seeing or hearing their initial report. If LLMs can enhance the capabilities of CHEWs in this way, it could improve patient outcomes, free high-skill providers for other tasks, and mitigate the serious shortage of qualified health personnel in many LMICs. The specific outcomes of this project will be: a proof of concept that LLMs can be integrated within LMIC healthcare systems to improve quality of care; a proof of concept of a system architecture for LLMs that can be scaled up and deployed progressively in LMIC healthcare systems; and an initial understanding of the capacity of current LLMs to interact with CHEWs in LMIC settings.

Henrique Araujo Lima of the Universidade Federal de Minas Gerais in Brazil will develop a tool to systematically assess the accuracy and clarity of responses generated by Large Language Models (LLMs) to common questions on maternal health to increase their value in settings with limited healthcare access. To improve LLMs, it is essential to ensure the information they provide is both reliable and understandable, and for purposes such as health, LLMs will only be successful if both healthcare providers and users are confident about their benefits. They will collect the most common types of questions about maternal health in English, Portuguese, and Urdu, and submit them to the LLM. The quality of the answers will then be evaluated by medical experts from the U.S., Brazil and Pakistan, and the readability of the answers will be evaluated by individuals and a software model.

Shashi Jain of the Indian Institute of Science in India in collaboration with Uma Urs from Oxford Brookes University in the United Kingdom along with colleagues from Akaike and Kotak Mahindra Bank also in India, will build a GPT-enabled AI bot called SATHI, which stands for Scheme, Access, Training, Help, and Inclusion, to deliver information on the latest government financial schemes that support sectors, like micro-enterprises and farms, to potential customers and providers in rural and suburban India. Together with several partners, they will capture data and provide context to SATHI to enable it to answer queries related to financial schemes. They will also use a translation module so it can understand voice queries and respond with an audio answer in the local language. They will perform a field test at a bank branch to compare the use of SATHI alone with a human financial expert and with semi-experts supported by SATHI. They will collect data on customer satisfaction and their follow-up actions using standard field research methodology, including oral interviews and survey questionnaires.

Theofrida Maginga of the Sokoine University of Agriculture in Tanzania will develop a ChatGPT-powered Swahili chatbot for smallholder farmers with limited literacy and scarce resources in Tanzania to detect crop diseases quickly and easily. Maize is one of the most important crops in Tanzania and generates up to 50% of rural cash income. Several diseases that afflict maize are hard to detect visually, leading to substantial losses in crop productivity and income. They will integrate AI with Internet of Things (IoT) technologies that use non-invasive sensors to monitor the non-visual early indicators of diseases, including volatile organic compounds, ultrasound movements, and soil nutrient uptake. They will also develop and integrate a Swahili chatbot to interact with farmers in their local language in a culturally-sensitive manner and perform model validation and field testing.

Sophie Pascoe of Wits Health Consortium (Pty) Ltd. in South Africa, with support from the organizations, AUDERE in the U.S. and the Centre for HIV and AIDS Prevention Studies (CHAPS) in South Africa, will develop a Large Language Model (LLM)-based application, Your Choice, that interacts with individuals in a human-like way to respectfully obtain their sexual history and improve the accuracy of HIV risk assessments to control the epidemic in South Africa. Gathering accurate sexual history is essential for assessing HIV risk and prescribing preventative drugs but is challenging due to concerns about stigma and discrimination. Your Choice, which stands for Your Own Unique Risk Calculation for HIV-related Outcomes and Infections using a Chat Engine, leverages an LLM to ensure privacy and confidentiality, improve the accuracy of risk assessments, and increase awareness of preventative treatments. This solution would provide 24/7 access to an unbiased and non-judgmental counselor for marginalized and vulnerable populations specifically, greatly reducing the barriers and concerns around seeking advice. They will co-design the app with at-risk populations and evaluate a prototype using 550 public sector healthcare providers and clients.

Tamlyn Roman of Quantium Health in South Africa will use generative AI and Large Language Models (LLMs) to develop an automated analyst that integrates disparate health datasets and automates data analytics to support evidence-based decision-making in public health. Although there is a relative abundance of health-related data in South Africa, it is difficult to use effectively because the datasets are not standardized and analytics capacity to support policy- and decision-making is limited. They will source datasets for the analyst and assess the LLM's ability to automate checks and link multiple datasets. Improving interoperability between datasets will enable unique correlations to be identified between separate social indicators, which are currently recorded in distinct databases. They will also develop a user-friendly platform for output generation and visualization.

João Paulo Souza of the Fundação de Apoio ao Ensino, Pesquisa e Assistência in Brazil will determine whether Large Language Models (LLMs) can be utilized as accurate information sources to guide healthcare provider decision-making. Frontline health workers must make real-life care decisions by distinguishing between relevant and irrelevant information and contextualizing it to their setting. This is particularly challenging in remote areas with limited healthcare specialists. To support them, an information program, the Formative Second Opinion (FSO), was developed to produce curated evidence summaries based on a large repertoire of real-life clinical queries. An updated version of this program is now being developed to combine a mobile messaging platform with LLMs for regions with limited internet connectivity and computer access. Using a mixed-methods study approach, they will evaluate the accuracy of the evidence summaries generated by ChatGPT-4 and those created by humans to 450 randomly selected clinical questions.

Livia Oliveira-Ciabati of the Sociedade Beneficente Israelita Brasileira Albert Einstein Hospital in Brazil will leverage AI to produce guidance and monitoring tools for less-experienced or overworked health professionals providing prenatal care via telemedicine to people from minority groups and people with greater social vulnerabilities. During the COVID-19 pandemic, Brazil's maternal mortality rate jumped to 110 deaths per 100,000 live births, which is far from their target of reaching 30 deaths per 100,000 live births by 2030. To increase the quality of prenatal care, they will integrate LLMs with an API for converting and preparing voice data and develop a simple interface to present suggestions and results to the healthcare professional. The training database will be developed using protocols defined and validated by the scientific community, including from the Global South. They will test their model with health professionals by comparing the professional decisions with the AI's suggestions which they will then follow up with a randomized clinical trial.

Alain Ndayishimiye of the Center for AI Policy and Innovation Ltd. in Rwanda will integrate a translation model with GPT-4 to produce a health service support tool in the national language, bypassing the need to build language-specific LLMs from scratch. LLMs have broad and powerful applications for improving public services such as education and healthcare by bridging information gaps across different cohorts. However, to create an impact in Rwanda, LLMs must be able to converse in Kinyarwanda, and current approaches to train LLMs in relatively minor languages are too expensive for low-resource nations. They will develop a support tool for community health workers focused on malnutrition leveraging GPT-4 as a knowledge base and an Mbaza English-Kinyarwanda translation model. The integrated support tool will be evaluated by assessing the quality of its translations.

Nana Kofi Quakyi of the Aurum Institute in Ghana will develop an AI-powered decision support tool for antibiotic prescribers to improve appropriate antimicrobial usage and combat antimicrobial resistance (AMR) in Ghana. AMR is a major public health concern, with the highest mortality rates occurring in Africa. To address this, Ghana's National Action Plan for Antimicrobial Use and Resistance (2018) identified the need for support tools that provide personalized, adaptable, and context-sensitive recommendations. They will develop an interactive, AI-powered clinical decision support tool that allows prescribers to enter prompts, respond to system queries, and receive personalized, real-time antibiotic prescribing recommendations, such as drug, dosage, and duration of administration. The model will be trained with a comprehensive dataset consisting of clinical guidelines, research data, expert opinions, and surveillance evidence that has been reviewed for its representativeness. The proposal includes field testing, iterative refinement, and engagement with stakeholders to ensure effectiveness and scalability.

Nirat Bhatnagar of the Belongg Community Ventures Private Ltd. in India, in collaboration with colleagues at ARTPARK also in India, will develop a Large Language Model (LLM)-based tool to enable development practitioners, funders, and researchers to adopt more equitable approaches, particularly addressing the intersections of marginalization. They will assemble a comprehensive and trusted corpus of development research papers, reports, and media articles and use it to build a user-friendly website and a backend ChatGPT 4.0 API-based LLM model. Users will be able to upload their draft research or program proposals and receive tailored recommendations on how to increase inclusivity across dimensions such as gender, disability, caste, religion, ethnicity, and sexual orientation. The tool will also connect users with researchers and experts with experience living with marginalized identities.

Yogesh Hooda of the Child Health Research Foundation in Bangladesh will use AI-based tools to teach low- and middle-income scientists to perform modeling and prediction studies in public health, which are dominated by researchers in the Global North. The codes generated during modeling studies are not often shared amongst researchers, making the methods difficult to learn. They found that ChatGPT could produce a code using a published model in just three weeks with only a beginner-level programmer and a biostatistician. Using epidemiological and demographic data and medical records collected from a catchment area, they will adapt published code with the help of ChatGPT to predict the impact of introducing specific vaccines in Bangladesh. They will also develop a curriculum, covering the basics of ChatGPT, data preprocessing and modeling techniques, for a course that they will pilot with public health professionals and students. All materials will be openly available in Bangla and English.