Reducing the dimension of the service readiness index

Further improvements in population health in low-and-middle-income countries demand high-quality care to address an increasingly complex burden of disease. With colleagues Dr. Margaret Kruk and Hannah Leslie, we have submitted a manuscript to apply unsupervised machine learning methods to assess the performance of the service readiness index (SRI) defined by the World Health Organization. We compared three approaches against the full item set: SRI, a new index based on sequential backward selection, and an enriched SRI that added empirically selected items to the SRI. In the manuscript, we concluded that SRI performed poorly in capturing the totality of readiness information collected during facility surveys. Our proposed machine learning approaches to identify the most informative items dramatically improved performance.