Search

Objectives: Government public health expenditure data sets require time- and labor-intensive manipulation to summarize results that public health policy makers can use. Our objective was to compare the performances of machine-learning algorithms with manual classification of public health expenditures to determine if machines could provide a faster, cheaper alternative to manual classification.Methods: We used machine-learning algorithms to replicate the process of manually classifying state public health expenditures, using the standardized public health spending categories from the Foundational Public Health Services model and a large data set from the US Census Bureau. We obtained a data set of 1.9 million individual expenditure items from 2000 to 2013. We collapsed these data into 147 280 summary expenditure records, and we followed a standardized method of manually classifying each expenditure record as public health, maybe public health, or not public health. We then trained 9 machine-learning algorithms to replicate the manual process. We calculated recall, precision, and coverage rates to measure the performance of individual and ensembled algorithms.Results: Compared with manual classification, the machine-learning random forests algorithm produced 84% recall and 91% precision. With algorithm ensembling, we achieved our target criterion of 90% recall by using a consensus ensemble of ≥6 algorithms while still retaining 93% coverage, leaving only 7% of the summary expenditure records unclassified.Conclusions: Machine learning can be a time- and cost-saving tool for estimating public health spending in the United States. It can be used with standardized public health spending categories based on the Foundational Public Health Services model to help parse public health expenditure information from other types of health-related spending, provide data that are more comparable across public health organizations, and evaluate the impact of evidence-based public health resource allocation.

ABSTRACTOn the global health agenda, Universal Health Coverage has been displaced by the COVID-19 pandemic while disparities in COVID-19 outcomes have exposed stark gaps in quality, access, equity, and financial risk protection. These disparities highlight the importance of the core goals of Universal Health Coverage and the need for innovative approaches to working toward them. The newly codified concept of “Networks of Care” offers a promising option for implementation. The articles in this special issue present the Networks of Care lexicon and framework and demonstrate the development of leadership, responsibility, intra- and inter-facility cooperation, and dynamic cycles of quality improvement. These elements are associated with better access to services and better health outcomes, the ultimate goals of Universal Health Coverage. Increases in poverty, food insecurity, and deleterious impact on the status of women secondary to the COVID-19 pandemic add urgency to Universal Health Coverage, while the economic impact of pandemic mitigation may reduce availability of resources for years to come. The need for Universal Health Coverage and efficiency and flexibility in health spending, including the ability to contract directly, has become even more important. Countries where Universal Health Coverage efforts have yet to carry through to provision of good quality, accessible and equitable service delivery could potentially benefit from concurrent Networks of Care implementation. Documentation of Networks of Care in the context of Universal Health Coverage should be prioritized to understand how Networks of Care can be used to help realize the goals of Universal Health Coverage around the world.