Large language models (LLMs) have significantly improved natural language processing, holding the potential to support health workers and their clients directly. Unfortunately, there is a substantial and variable drop in performance for low-resource languages. Here we present results from an exploratory case study in Malawi, aiming to enhance the performance of LLMs in Chichewa throughRead more about Human Review for Post-Training Improvement of Low-Resource Language Performance in Large Language Models[…]

In 2017, WHO and global partners launched ‘The Network for Improving Quality of Care for Maternal, Newborn and Child Health’ (QCN) seeking to reduce in-facility maternal and newborn deaths and stillbirth by 50% in health facilities by 2022. We explored how the QCN theory of change guided what actually happened over 2018–2022 in order toRead more about Evaluating theory of change to improve the functioning of the network for improving quality of care for maternal, newborn and child health[…]

The Quality-of Care Network (QCN), launched by WHO and partners, links global and national actors across several countries to improve maternal and newborn health. We conducted a prospective qualitative study to examine how QCN in Bangladesh, Ethiopia, Malawi and Uganda facilitated learning, sharing, and innovation within and between network countries. We conducted 227 key informantRead more about Do global health networks facilitate innovation, learning and sharing? A qualitative analysis of the Quality-of-Care Network in Bangladesh, Ethiopia, Malawi, and Uganda[…]