Hospitals in the United States are under increasing pressure to manage patient flow and allocate resources effectively to maintain quality of care and operational performance. This study proposes a novel framework that integrates geospatial analytics with hospital workflow data to support proactive and equitable decision making. Electronic health records, geographic information systems, and social determinants of health indicators were combined to create a harmonized dataset representing patient encounters and community context. Spatial representation ratios were used to evaluate geographic coverage, and spatial autocorrelation methods identified clusters of high demand. Temporal patterns were modeled to forecast patient arrivals, and machine learning models predicted daily admissions and bed occupancy. Prescriptive analytics were then applied to recommend optimal bed allocation and staff scheduling. Results demonstrated accurate prediction of demand surges, improved resource distribution, and reductions in simulated emergency department boarding times. Geospatial outputs revealed disparities in utilization that can inform targeted outreach to underserved communities. The findings suggest that integrating spatial and operational data provides a powerful tool for enhancing hospital efficiency, promoting equity, and strengthening preparedness for routine and surge conditions. This framework offers a foundation for data-driven hospital operations and value-based care strategies.

Geospatial analytics, hospital operations, patient flow, resource allocation, predictive modeling

Anselin, L. (1995). Local indicators of spatial association—LISA. Geographical Analysis, 27(2), 93–115. https://doi.org/10.1111/j.1538-4632.1995.tb00338.x

Badmus, A., Adebayo. M, Ehigie, D. E. (2018). Secure And Scalable Model Lifecycle Management in Healthcare AI: A DevOps Approach for Privacy, Compliance, and Traceability. Scholars Journal of Medical Case Reports Abbreviated Key Title: Sch. J. Med. Case Rep. ©Scholars Academic and Scientific Publishers (SAS Publishers), (An International Publisher for Academic and Scientific Resources), DOI: 10.36347/sjmcr, 2018.v06i12.025, Vol 6, Issue 12, pages 1087–1099, (SJMCR) ISSN 2347-6559 (Online) ISSN 2347-9507 (Print)

Flood, D. M., Haneuse, S., & Yoon, J. (2020). Post-stratification methods to address representativeness in electronic health record data. Journal of Biomedical Informatics, 107, 103437. https://doi.org/10.1016/j.jbi.2020.103437

Granell, C., Hagenlocher, M., Muki, H., & Pebesma, E. (2014). Geospatial information science for public health: A framework for integration. International Journal of Health Geographics, 13(1), 7. https://doi.org/10.1186/1476-072X-13-7

Mehta, N., Pandit, A., & Shukla, S. (2019). Transforming healthcare with big data analytics and artificial intelligence: A systematic mapping study. Journal of Biomedical Informatics, 100, 103311. https://doi.org/10.1016/j.jbi.2019.103311

Mooney, S. J., Pejaver, V., & Hulland, E. (2019). Applications of geospatial analytics to electronic health records for public health surveillance. Public Health Reports, 134(5), 472–478. https://doi.org/10.1177/0033354919857453

Peterson, K., Helfand, M., & Humphrey, L. (2015). The role of prediction models in improving hospital operations. Medical Care Research and Review, 72(3), 223–240. https://doi.org/10.1177/1077558714565025

Roth, C., Coles, R., & Duff, M. (2016). Community-level determinants of hospital utilization: A geospatial approach. Preventive Medicine, 85, 39–45. https://doi.org/10.1016/j.ypmed.2016.01.003

Vielot, N. A., & Horney, J. A. (2014). Data governance and privacy protection in health geoinformatics. Journal of Public Health Management and Practice, 20(3), 291–298. https://doi.org/10.1097/PHH.0000000000000043

Xie, S. J., Jung, S. Y., & Mendez, D. D. (2017). Using EHR-derived geospatial data to understand health disparities. BMC Medical Informatics and Decision Making, 17(1), 64. https://doi.org/10.1186/s12911-017-0455-8