Enabling Cost-Effective Population Health Monitoring By Exploiting Spatiotemporal Correlation

Because of its important role in health policy-shaping, population monitoring (PHM) is considered a fundamental block for public services. However, traditional data collection approaches, such as clinic-visit-based integration or surveys, could be very costly and time-consuming. To address this challenge, article proposes cost-effective approach called Compressive Population Health (CPH), where subset given area selected terms regions within the way, while leveraging inherent spatial correlations neighboring to perform inference rest area. By alternating longitudinally, can validate correct previously assessed correlations. verify whether idea CPH feasible, we conduct an in-depth study based on spatiotemporal morbidity rates chronic diseases more than 500 around London over 10 years. We introduce our present three extensive analytical studies. The first confirms that significant do exist. In second study, by deploying multiple state-of-the-art recovery algorithms, these leveraged accurately using only small number samples. Finally, compare different methods region selection show how further reduce overall cost maintaining high PHM quality.