Drew Arenth, Benjamin Fels, and Suvrit Sra of Macro-Eyes in the U.S. are applying a statistical machine learning approach to the immunization supply chains of health facilities in Tanzania that accurately and continuously predicts demand to ensure the right vaccines and levels are being stocked. Currently, vaccine supply is largely fixed or driven by depleted stocks. This leaves children unable to be vaccinated due to stock outs at clinics, as well as often high levels of waste, which could both be overcome by better forecasting vaccination needs for individual clinics. In Phase I, they worked with an NGO and the Ministry of Health to access routinely-collected daily vaccination data from 710 health facilities spread across Tanzania. These data were then used to train algorithms to identify predictive patterns that were tested on independent datasets. This led to a model that could accurately forecast future vaccine consumption. In Phase II, they will work out how best to integrate their approach as an automated component within the existing supply chain infrastructure in Tanzania and develop tools and train advocates to demonstrate its value and encourage implementation and adoption.

Patricia Connolly of the University of Strathclyde and colleagues in the United Kingdom will develop a low-cost, wearable skin patch that can continuously monitor metabolite levels in newborns without the need for blood sampling, and can alert mothers and health workers to potential problems via mobile phone. Changes in metabolites such as those of hemoglobin and bilirubin are used to assess many aspects of newborn health, but current methods require invasive blood sampling and access to laboratory analysis, which is often unavailable in low-resource settings. To address this, in consultation with users in Sierra Leone, Vietnam and India, they will develop a flat patch incorporating their new technology, which painlessly enhances the flow of analytes through the skin for detection, and a Bluetooth connector that can communicate levels to a smartphone. The prototype patch will be laboratory tested to refine the design.

Joanna Bichsel of Kasha in Rwanda will adapt their mobile ecommerce platform to enable women in Kenya to confidentially order health products such as contraceptives and sanitary pads by mobile phone. There are many social barriers preventing women in developing countries from accessing products at health clinics. Their platform, Kasha, requires only a mobile phone to order and pay for products that are then delivered to local pick-up points. They have successfully implemented Kasha in Rwanda and will now perform a pilot study in several counties in Kenya. They will customize the platform to the language and existing technology in Kenya, and develop private and public partnerships to tap into existing distribution networks, thereby minimizing costs. Their pilot study will evaluate how well the platform is received by Kenyan women, and how effective it is at delivering products.

Bulara Mpiti of the Clinton Health Access Initiative (CHAI) in the U.S. will use the clinical sample transportation network in Lesotho to increase the efficiency of delivering viable vaccines to local health facilities. Most health facilities in Lesotho experience stock-outs of essential vaccines, which are caused by weak supply chains from the stores at district offices. The health facilities are also visited at least once per week by motorcyclists from delivery agencies to pick-up clinical samples for rapid transport to diagnostic laboratories, which are located in the same district offices as the vaccine stores. They will engage these delivery agencies to also manage the ordering and transport of vaccines in the other direction, from district stores to health facilities. To test their approach, they will perform a pilot in selected districts and train vaccine supply managers, health workers, and sample transporters.