Planning a Community Approach to Diabetes Care in Low- and Middle-Income Countries Using Optimization

• DOI: 10.48550/arxiv.2305.06426
• Publication Date: 2023-01-01
• Authors: Katherine B. Adams; Justin J. Boutilier; Sarang Deo; Yonatan Mintz
• Keywords: Community Health; Diabetes management

Diabetes is a global health priority, especially in low- and-middle-income countries, where over 50% of premature deaths are attributed to high blood glucose. Several studies have demonstrated the feasibility using Community Health Worker (CHW) programs provide affordable and culturally tailored solutions for early detection management diabetes. Yet, scalable models design implement CHW while accounting screening, management, patient enrollment decisions not been proposed. We introduce an optimization framework determine personalized visits that maximize glycemic control at community-level. Our explicitly trade-off between screening new patients providing individuals who already enrolled treatment. account patients' motivational states, which affect their enroll or drop out treatment and, therefore, effectiveness intervention. incorporate these by modeling as utility-maximizing agents within bi-level provider problem we solve approximate dynamic programming. By estimating our model builds visit plans tradeoffs when deciding treatment, leading reduced dropout rates improved resource allocation. apply approach generate operational data from social enterprise serving low-income neighborhoods urban areas India. Through extensive simulation experiments, find requires up 73.4% less capacity than best naive policy achieve same performance terms control. experiments also show solution algorithm can improve upon policies 124.5% capacity.