FROM MEDICAL RECORDS TO PREDICTIVE CARE: UTILIZING ELECTRONIC HEALTH DATA FOR EARLY IDENTIFICATION OF HIGH-RISK PATIENTS IN PRIMARY HEALTHCARE

Aidi Sopyan; Juita Purnama Sari; Holid Saputra

doi:10.55681/aohj.v3i1.564

Authors

Aidi Sopyan Institut Teknologi dan Kesehatan Aspirasi
Juita Purnama Sari Institut Teknologi dan Kesehatan Aspirasi
Holid Saputra Institut Teknologi dan Kesehatan Aspirasi

DOI:

https://doi.org/10.55681/aohj.v3i1.564

Keywords:

Electronic health records, Predictive care, High-risk patients

Abstract

Electronic health records are increasingly central to primary healthcare, yet their value remains underused when data are treated only as retrospective documentation rather than as a resource for prospective risk identification. This study examines how routinely collected electronic health data can support predictive care and the early identification of patients at elevated risk of adverse clinical outcomes. A quantitative retrospective predictive design was simulated using 1,250 adult primary-care records containing demographic characteristics, diagnoses, medication history, vital signs, laboratory indicators, service utilization, and documented comorbidities. Logistic regression, random forest, and gradient-boosting models were compared using discrimination, calibration, sensitivity, specificity, and positive predictive value. The simulated results showed that the gradient-boosting model achieved the strongest discrimination, with an area under the receiver operating characteristic curve of 0.86, while calibrated logistic regression remained clinically interpretable and produced stable risk estimates. High-risk classification was most strongly associated with multimorbidity, repeated unscheduled visits, abnormal blood pressure, elevated glycated hemoglobin, reduced renal function, polypharmacy, and recent emergency utilization. Incorporating longitudinal utilization patterns improved sensitivity for identifying patients who subsequently required intensified care. The findings demonstrate that electronic health data can transform routine records into actionable population-health intelligence when predictive outputs are integrated with clinical judgment, transparent thresholds, data-quality controls, and equity monitoring. The study contributes a practical primary-care framework linking data preparation, risk modeling, stratified intervention, and continuous model evaluation for earlier, safer, and more personalized preventive care. This interpretation supports transparent clinically supervised equitable implementation.

Downloads

Download data is not yet available.

References

Abdulazeem, H., Whitelaw, S., Schauberger, G., & Klug, S. J. (2023). A systematic review of clinical health conditions predicted by machine learning diagnostic and prognostic models trained or validated using real-world primary health care data. PLOS ONE, 18(9), e0274276. https://doi.org/10.1371/journal.pone.0274276

Agovi, A. M.-A., Serdarevic, M., Gehr, A. W., Thompson, C. T., Li, W., Claassen, J., Cvitanovich, M., & Ojha, R. P. (2025). External validation of an EHR-based model for risk of patient no-show in primary care. JAMA Network Open, 8(7), e2521637. https://doi.org/10.1001/jamanetworkopen.2025.21637

Apenteng, P. N., Prieto-Merino, D., Hee, S. W., et al. (2023). Optimising prediction of mortality, stroke, and major bleeding for patients with atrial fibrillation: Validation of the GARFIELD-AF tool in UK primary care electronic records. British Journal of General Practice, 73(736), e816-e824. https://doi.org/10.3399/BJGP.2023.0082

Beaney, T., Clarke, J., Salman, D., et al. (2023). Identifying potential biases in code sequences in primary care electronic healthcare records: A retrospective cohort study of the determinants of code frequency. BMJ Open, 13(9), e072884. https://doi.org/10.1136/bmjopen-2023-072884

Carrasco-Ribelles, L. A., Llanes-Jurado, J., et al. (2023). Prediction models using artificial intelligence and longitudinal data from electronic health records: A systematic methodological review. Journal of the American Medical Informatics Association, 30(12), 2072-2082. https://doi.org/10.1093/jamia/ocad168

Deimazar, G., & Sheikhtaheri, A. (2023). Machine learning models to detect and predict patient safety events using electronic health records: A systematic review. International Journal of Medical Informatics, 180, 105246. https://doi.org/10.1016/j.ijmedinf.2023.105246

Dormosh, N., Heymans, M. W., van der Velde, N., Hugtenburg, J., Maarsingh, O., Slottje, P., Abu-Hanna, A., & Schut, M. C. (2022). External validation of a prediction model for falls in older people based on electronic health records in primary care. Journal of the American Medical Directors Association, 23(10), 1691-1697.e3. https://doi.org/10.1016/j.jamda.2022.07.002

Fernandes Prabhu, D., Gurupur, V., Stone, A., & Trader, E. (2025). Integrating artificial intelligence, electronic health records, and wearables for predictive, patient-centered decision support in healthcare. Healthcare, 13(21), 2753. https://doi.org/10.3390/healthcare13212753

Grim, S., Kotz, A., Kotz, G., Halliwell, C., Thomas, J. F., & Kessler, R. (2024). Development and validation of electronic health record-based, machine learning algorithms to predict quality of life among family practice patients. Scientific Reports, 14, 30077. https://doi.org/10.1038/s41598-024-80064-3

Hobensack, M., Song, J., Scharp, D., et al. (2023). Machine learning applied to electronic health record data in home healthcare: A scoping review. International Journal of Medical Informatics, 170, 104978. https://doi.org/10.1016/j.ijmedinf.2022.104978

Hunik, L., Chaabouni, A., van Laarhoven, T., Olde Hartman, T. C., Leijenaar, R. T. H., Cals, J. W. L., Uijen, A. A., & Schers, H. J. (2025). Diagnostic prediction models for primary care, based on AI and electronic health records: Systematic review. JMIR Medical Informatics, 13, e62862. https://doi.org/10.2196/62862

Ioakeim-Skoufa, I., et al. (2025). Electronic health records: A gateway to AI-driven multimorbidity solutions-A comprehensive systematic review. Journal of Clinical Medicine, 14(10), 3434. https://doi.org/10.3390/jcm14103434

Jordan, K. P., Rathod-Mistry, T., Bailey, J., Chen, Y., et al. (2022). Long-term cardiovascular risk and management of patients recorded in primary care with unattributed chest pain: An electronic health record study. Journal of the American Heart Association, 11(7), e023146. https://doi.org/10.1161/JAHA.121.023146

Mukherjee, P., Humbert-Droz, M., Chen, J. H., & Gevaert, O. (2023). SCOPE: Predicting future diagnoses in office visits using electronic health records. Scientific Reports, 13, 11005. https://doi.org/10.1038/s41598-023-38257-9

Muñoyerro-Muñiz, D., Villegas, R., de la Oliva, V., et al. (2025). Ethical and secure evidence generation from regionwide clinical data through a collaborative environment for advancing predictive care. Frontiers in Public Health, 13, 1630351. https://doi.org/10.3389/fpubh.2025.1630351

Nadarajah, R., Wu, J., Hogg, D., Raveendra, K., Nakao, Y. M., Nakao, K., et al. (2023). Prediction of short-term atrial fibrillation risk using primary care electronic health records. Heart, 109(14), 1072-1079. https://doi.org/10.1136/heartjnl-2022-322076

Reeves, D., et al. (2024). Identifying individuals at high risk for dementia in primary care: Development and validation of the DemRisk risk prediction model using routinely collected patient data. PLOS ONE, 19(10), e0310712. https://doi.org/10.1371/journal.pone.0310712

Steinberg, M. B., Young, W. J., Miller Lo, E. J., Bover-Manderski, M. T., Jordan, H. M., Hafiz, Z., et al. (2023). Electronic health record prompt to improve lung cancer screening in primary care. American Journal of Preventive Medicine, 65(5), 892-895. https://doi.org/10.1016/j.amepre.2023.05.016

Tsai, M.-L., Chen, K.-F., Chen, P.-C., et al. (2025). Harnessing electronic health records and artificial intelligence for enhanced cardiovascular risk prediction: A comprehensive review. Journal of the American Heart Association, 14(6), e036946. https://doi.org/10.1161/JAHA.124.036946

van Os, H. J. A., Kanning, J. P., Wermer, M. J. H., Chavannes, N. H., Numans, M. E., Ruigrok, Y. M., van Zwet, E. W., Putter, H., Steyerberg, E. W., & Groenwold, R. H. H. (2022). Developing clinical prediction models using primary care electronic health record data: The impact of data preparation choices on model performance. Frontiers in Epidemiology, 2, 871630. https://doi.org/10.3389/fepid.2022.871630

Wang, J., Luo, J., Ye, M., Wang, X., Zhong, Y., et al. (2024). Recent advances in predictive modeling with electronic health records. Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, 8272-8280. https://doi.org/10.24963/ijcai.2024/914

Young, J. A., Chang, C.-W., Scales, C. W., Menon, S. V., Holy, C. E., & Blackie, C. A. (2024). Machine learning methods using artificial intelligence deployed on electronic health record data for identification and referral of at-risk patients from primary care physicians to eye care specialists: Retrospective, case-controlled study. JMIR AI, 3, e48295. https://doi.org/10.2196/48295

Sugiyono. (2022). Metode penelitian kuantitatif, kualitatif, dan R&D. Alfabeta.