Unlocking insights from complex data: Leveraging heat maps for decision-making in LMIC.

<h4>Introduction</h4>In low- and middle-income countries (LMICs), health outcomes are often constrained by inadequate or misdirected resource allocation and limited access to services such as contraception and immunization. We explore the use of spatial heat maps to analyze the stock availability and dispensation/vaccination patterns of contraceptives and vaccines in Pakistan.<h4>Methods</h4>We used data from national contraceptive (cLMIS) and vaccine logistics management information systems (vLMIS). We applied univariate, bivariate, and trivariate spatial heat maps to assess contraceptive and vaccine stock levels, dispensation/vaccination, and wastage across districts. For contraception, we standardized stocks per 100,000 married women of reproductive age (MWRA) and dispensation rates. In immunization, we focused on Pentavalent-3 (Penta3) vaccine outreach, dropout rates, and Bacillus Calmette-Guérin (BCG) vaccine wastage.<h4>Results</h4>Temporal and spatial variations highlighted regional disparities, revealing that developed regions like Punjab had better stock availability, while underserved areas like Balochistan faced higher dispensation rates and stockouts. We also show the effect of inputs (supplies, outreach) on dispensation and utilization of contraceptives and vaccines, respectively. Finally, we depict how these visualizations can help track changes in programming over time.<h4>Conclusions</h4>Our findings show that integrating spatial data visualization with health logistics data identifies critical gaps in health service supply and demand, guiding policymakers in resource allocation, stock management, and service outreach. This scalable approach suits systems with limited analytical resources, as many analyses can be automated and embedded in datasets, providing policymakers with a focused set of visualizations for interpretation, avoiding the need for extensive training or deploying analysis teams at local levels. By leveraging spatial and temporal data, this method supports efficient health system strengthening and resource allocation in LMIC.