UNICEF, together with the Department of Health (DOH) and PhilHealth collaborated to develop a national health insurance benefit package for prematurity and small babies launched in late 2016. The project seeks to catalyze the readiness of government hospitals to be contracted for the special health financing package.

Sailendra Appanah of EnerGaia Bangladesh Ltd in Bangladesh will teach low-income women in rural Bangladesh to farm Spirulina, which is an edible protein- and nutrient-rich microalgae, to provide better nutrition and an income for them and their families. They have developed a low-cost Spirulina production system comprising closed tanks with filtered air and water inputs, and a business model that provides the farmers with a lease-to-own financing solution and guaranteed buyers of excess product. They will recruit 30 interested women from Dhaka, Bangladesh, and pay them a small wage to undergo three months of training at their local Spirulina farm. They will then provide them with tanks through the lease-to-own program, help them with installation and operation, and process the fresh spirulina produce for sale or for local consumption. They will evaluate the effect of their approach on income and malnutrition in the community.

Lorraine Weatherspoon of Michigan State University in the U.S. will develop a blended instant bean sauce in an edible pouch that provides a culturally-acceptable iron and folic acid supplement for low-income pregnant women in Uganda. Iron and folic acid are particularly important during pregnancy as they reduce the risk of low birth weight and neural tube defects amongst many other morbidities and mortalities also for the mothers. Supplements provided as tablets are available, but have not been widely accepted. They are developing a more appealing iron and folic acid supplement by combining it with a commonly used product: a bean and silver fish sauce that can be made with local ingredients. They are using dried namulonge beans as they have high yields and a desirable taste, mixed with roasted, milled silver fish and micronutrients, packaged in an edible film to protect the food during storage and transport. The food is cooked in hot water and eaten with traditional foods such as cooking banana or rice. They will assess the nutritional composite of the product and acceptability by the target group. Their product will then be tested in a randomized controlled trial with teenage women at different stages of pregnancy at an antenatal clinic in Kampala to determine its effect on nutrition during pregnancy and the overall health of the mother and child at birth.

Joachim Loo of Nanyang Technical University in Singapore will develop techniques to encapsulate micronutrients such as iron for food fortification using okara, which is a nutritionally-rich pulp that is made as a wasted by-product during the production of soybean products. Micronutrient malnutrition affects two billion people globally. Providing micronutrients in the diet is difficult because they are unstable by themselves, and so need some form of protection, for example by encapsulating them in a stable, digestible material. Okara is produced in large quantities during the production of soybean products like tofu and soya milk, leading to high environmental and economic costs for disposal. They will determine whether okara can be repurposed as an encapsulation material for micronutrients by developing and testing drying and sterilization methods and designing protocols to encapsulate vitamin A and iron. They will then evaluate the ability of the okara microcapsules to release bioactive micronutrients when exposed to artificial gastric and intestinal fluids.

Owens Wiwa of the Clinton Health Access Initiative in the U.S. will determine whether providing free vouchers for mothers to receive a nutrient-dense food can help infants with moderate acute malnutrition in Nigeria. By linking the vouchers to attendance at immunization clinics, they also hope to boost immunization coverage. Malnutrition is a major public health concern in Nigeria, where almost one third of children are underweight, and ten percent are wasted. However, improving nutrition in poor and rural households is difficult because of a lack of education and limited access to nutritional foods. They will pilot test their approach in a randomized controlled trial at two locations by training healthcare workers at immunization centers to council mothers on feeding practices and to monitor infant growth to identify malnutrition. The mothers of malnourished infants between six and 23 months old will be provided with vouchers to receive three months' worth of an existing fortified food, which will be provided at a local health facility. They will evaluate the effect of their approach on the infants' nutritional status and immunization coverage.

Tsegaye Nega of Carleton College in the U.S. will develop methods to produce and distribute affordable nutritional food supplements made from excess, dried spent grains from the brewery process. Beer production has grown recently in Ethiopia, and a by-product, brewer's spent grain, is rich in fiber and protein and can be easily added to bread to boost its nutritional content. They will perform a pilot study in Addis Ababa and Dukem, Ethiopia, where they will partner with a major brewing company to access the starting materials, and determine the standards needed for this human-grade food and the production and distribution setups required. They will also further develop nutritional product marketing and testing. Their approach is a low-cost, sustainable solution to combat malnutrition in Ethiopia.

Samantha Dolan and Peter Rabinowitz of the University of Washington in the U.S., and Ian Njeru of I-TECH Kenya, will improve digital data collection and monitoring of childhood immunizations at Kenyan health facilities by optimizing workflows. Using electronic tools to track immunizations has the potential to improve the accuracy of data collection and reporting, identify children who have not been vaccinated, and free up time for health care workers. To fully realize this potential, workflow patterns need optimizing for different types of health facilities. They will use an iterative approach with so-called Lean methods to maximise value while reducing waste, and time-motion study techniques to evaluate current workflows and identify bottlenecks that reduce efficiency. These workflows will then be redesigned and tested across different sizes and types of facilities in Kenya. They will also compare the efficiency and performance of electronic registries with paper-based registries.

Matt Berg of Ona in the U.S. will combine high-resolution satellite images, spatial sampling statistics, and mobile data collection to better calculate local immunization coverage in Bangladesh. Current approaches often vastly overestimate coverage because of the difficulty in calculating actual population sizes from nationwide data and birth registries. As a more effective approach, they will use satellite imagery to detect liveable structures within a set area, and software that selects possible households that require verification by community surveillance teams. These teams will be supplied with offline maps and a mobile application to note actual households and record the immunization status of any children under five. These data will then be used to generate maps to visualize actual coverage and identify areas with the greatest immunization needs. They will develop tools for automation, coverage calculations, and map visualizations to supplement their existing mapping and mobile data collection tools and test their approach in a research site in Bangladesh.

Ross Boyce at the University of North Carolina in the U.S. will develop an approach that uses new methods of mapping households together with available health data to better identify places that have limited access to healthcare to improve immunization coverage. Many sub-Saharan African countries have very poor rates of childhood vaccination coverage. Improving coverage requires identifying those households and areas with poor access to healthcare, but this is challenging with the limited data available. To more accurately measure healthcare access and thereby immunization coverage, they will perform a six-month study in a rural sub-county of western Uganda. By providing user-friendly tools to health workers and providers, they will generate more accurate household maps and assess three different metrics of healthcare access using freely available software and a Bayesian statistical framework. They will evaluate the accuracy of their approach for predicting coverage by conducting a cross-sectional survey to determine the vaccination status of all children aged between 12 and 23 months in the sub-county.

Michael Nunan of Beyond Essential Systems in Australia will build on their existing data platform to collect and analyze vaccine data in real-time to provide an early warning of areas or facilities with low immunization coverage. The platform integrates data from various sources, including vaccine supply and healthcare infrastructure such as equipment and staff. They will further develop it to record actual vaccine administrations from health workers entering details on mobile phones, and to produce local estimates of vaccine demand and actual coverage and provide alerts. They will also integrate real-time monitoring of the cold supply chain using sensors. Their system will be evaluated in the Solomon Islands and Vanuatu by comparing it with current methods for estimating vaccine demand and coverage.

Benjamin Fels and Suvrit Sra of Macro-Eyes, Inc. in the U.S. will engage with frontline health workers in immunization centers and combine their knowledge with existing supply chain and immunization data using machine learning to better predict vaccine demand and thereby improve immunization coverage. Vaccine supply levels in Ethiopia are predicted using data that may be inaccurate or outdated. These low-confidence data could be enhanced with the unique insights of frontline health workers by using machine learning, which is a valuable statistical method for increasing the accuracy of predictions. They will test this at three health centers in Ethiopia by exploring approaches such as WhatsApp to engage health workers and collect relevant information on vaccine stocks and demand in the clinics. These data, along with available supply data, will be used to train so-called classifiers, or algorithms, that transform the input data into more accurate predictions of monthly vaccine use. They will test whether their method improves the accuracy of predictions compared to the original methods.

Pierluigi Bonello of Ohio State University in the U.S. will develop a surveillance system for crops using unmanned aerial vehicles (drones) to position sensors to help diagnose plant diseases in low-income countries. Plant diseases are usually identified first by the farmers or human scouts and then confirmed by laboratory testing. This process is inefficient and requires resources often unavailable in low-income countries, calling for alternative approaches. It is known that when a plant becomes infected, it produces specific chemicals. In addition, functional chemical groups in biological samples are known to vibrate in predictable ways after absorbing light. They will test whether this information can be exploited for the rapid and widespread detection of two plant diseases, rice blast and maize dwarf mosaic, by vibrational spectroscopy that could be positioned inside crop canopies by drones. Rice and maize grown in greenhouses and fields in the U.S. will be infected, and they will develop statistical methods to evaluate whether handheld spectrometers can distinguish between infected and uninfected plants. This technology could ultimately allow crop managers to control the spread of a disease even before plants show visual symptoms.

James Bell of Rothamsted Research in the United Kingdom will test an integrated surveillance system for the real-time detection of ground and upper atmospheric levels of the fall armyworm, which is a moth that devastates maize crops. Maize is a vital food source in Kenya but is currently largely imported and has become too expensive for most households. They propose to help local farmers grow maize by developing an early warning system for the African moth pests. Their system will integrate an entomological radar to detect moths flying up to 1,200 metres overhead, with twenty ground traps covering 7,000 km2 that transmit data to a central institute, and a smart-phone application for workers and growers that automatically detects the caterpillars and moths. They will optimize the equipment and software to detect the specific moth species and test it in a region of Western Kenya over one year. Their system will also reveal details of seasonal moth migrations, ground spread, and crop growth to help develop effective pest management strategies.

Bruce Grieve of Manchester University in the United Kingdom will develop a low-cost, stereo-printed sensor that mimics plant leaves and stems and can detect and signal the presence of live pathogens as an early warning system to help protect crops in low-resource settings. They will demonstrate proof-of-concept of their approach in the laboratory by designing three dimensional sensors with specific patterns of cells and chemically-doped polymers to identify an ideal surface on which pathogenic fungal spores can grow and differentiate. Incorporated sensor cells will be designed to detect the live pathogens and produce a detectable response, such as a visible density change, and results can be stored locally or transmitted wirelessly. They will test different sensor designs for the detection of rust pathogens in wheat. Their approach can be adapted to detect multiple pathogens simultaneously, including viruses, as well as for human and livestock pathogens, and when deployed in the field can ultimately be linked to national surveillance systems.

Christopher Gilligan of the University of Cambridge in the United Kingdom will develop a data collection and analysis platform for crop diseases that uses Bayesian modelling frameworks to better integrate data from diverse sources and identifies cost-effective pest and disease control solutions for small-holder farmers. Current crop disease surveillance programs generally collect data from limited sources and lack the capacity to use the data to advise farmers how to manage any disease outbreaks. By integrating a wider variety of data, including meteorological data, and grower and market behaviour such as household nutrition, their approach can predict much broader consequences of crop diseases on individual households and thereby provide more valuable solutions. They will focus on pests and diseases of maize, wheat, and cassava in East Africa and pilot test their SMS and smart phone platform by holding training workshops for participants, testing data analytics and validating the results.

Menale Kassie of the International Centre of Insect Physiology and Ecology in Kenya along with Ram Fishman and Opher Mendelsohn from Tel Aviv University in Israel will take a community-based crowdsourcing approach to crop protection of smallholder farms in low-resource settings by developing a simple software platform for basic feature phones to monitor pest incidence. Human-based monitoring of crops is the most accurate way to identify pests, but there are too few public monitoring agents in low-resource settings, leaving the majority of farms unprotected. Engaging the smallholder farmers to monitor their own crops is a promising solution, but most of them lack sophisticated equipment like smart phones and have low technical knowledge, so simpler solutions are needed. Therefore, they will adapt commercially-available software that collates and analyzes pest incidence data for basic feature phones and, together with smallholder farmers, design simple interfaces for SMS communication. They will test their approach by performing a pilot study to monitor wheat and maize, covering one to two counties in Kenya, and teach smallholder farmers and government agents how to use the monitoring system and compare the data with that collected by expert field agents.

Janos Zempleni of the University of Nebraska-Lincoln in the U.S. will test whether supplementing milk formula with exosomes from milk could have the potential to improve the growth of babies aged between 6 and 12 months and help protect them from infections. Exosomes are membrane-bound vesicles naturally present in all bodily fluids and are thought to transfer small molecules such as RNAs between different cells to regulate various cell functions. However, during the production of milk formula for babies, the exosomes are destroyed. They have preliminary data demonstrating that RNAs and exosomes in milk enhance growth and the immune response in mouse pups. They will expand these studies to confirm their results in mice, with a view to progressing to clinical trials to test the value of exosome-fortified milk formula in humans.

Chinedu Chugbo of Avigo Health L.L.C. in the U.S. will develop an approach to crowdsource reports of infant births and deaths from community members by health workers to better monitor vaccine coverage in low- to middle-income countries. In Nigeria, only 30% of births are registered, making it difficult to estimate numbers of vaccine-eligible children and ensure every child is properly vaccinated. Current methods for estimating population sizes include household surveys, which are costly, or records from health clinics, which suffer from limited coverage. Crowdsourcing is a proven method for efficient data collection, although data quality may be variable. They will develop electronic data-collection and storage tools and pilot test their crowdsourcing approach in a selected region in Nigeria. Health workers will be trained to administer brief interviews to community members visiting clinics and during outreach programs to document local births and deaths. They will evaluate the performance of their approach and particularly data accuracy by comparing it with data collected by household surveys in the same region.

The idea is to develop an artificial intelligence model capable of simultaneously analyzing data from the Laboratory Information System and from the Hospital Information System. This technology aims to enable the delivery to hospital physicians of a ranked list of antimicrobials that are more suitable to treat infection by multi-resistant microorganism with a focus on newborn and young children.

This project proposes the development of the One Health Brazilian Resistance (OneBR), a curated and integrated genomic database. OneBR will use algorithms based on artificial intelligence to conduct surveillance, diagnosis, management and treatment of antimicrobial resistance (AMR) in the human-animal-environment interface. The goal is for this platform to be used by Brazilian health professionals in diverse settings, particularly within the Unified Healthcare System (SUS).

The project proposes to characterize the resistant determinants of microbial communities from key sources in hospitals, environment and farms to model the dynamics of the flow of antibiotic resistant microorganisms. The goal is to understand how the hospital environment and animal farming affect the ecology of antibiotic resistance movement. The project will rely on a methodology that allows the analysis of genes related to antibiotic resistance in a complex microbial community derived from specific samples instead of culture based methods for AMR identification.

The project aims to monitor AMR in microorganisms of the urinary tract and correlate it with the genetic determinants of resistance in animal enterobacteria. The study results will be disseminated in order to inform potential changes to guidelines regarding selection of the appropriate antimicrobials first-line treatment for urinary tract infections (UTI).

The project will develop a cellulose filter containing immobilized DNA aptamers, molecules that bind to a specific target molecule, that act as specific and high affinity probes for the uptake and retention of antibiotic molecules present in effluents. Nowadays, the removal of antibiotic residues from effluents is mainly based on chemical processes and physical methods that require expensive technologies and costly maintenance. The success of this project will represent a wastewater treatment option that is low-cost and environment-friendly.

The main goal of the project is to develop and explore an innovative measure of gestational age - "potential pregnancy days lost" (PPDL) - to produce evidence of its association with maternal and child health, morbidity and mortality in the short, medium and long term. The indicator also aims to convince women and policy makers about the need to promote less interventions and "harm-free care" during pregnancy.