Modern approaches for assessing hospitalization risk and predictors based on health information system data. A systematic review

The increase in hospitalizations of patients with noncommunicable diseases remains a key challenge for healthcare systems. A significant portion of these hospitalizations is potentially preventable with timely outpatient monitoring and effective primary care. Predictive models based on data from health information systems (HIS) and electronic health records (EHRs) make it possible to identify patients at increased risk of hospitalization and improve their management strategies. The article systematizes and summarizes international experience in using hospitalization risk prognostic models, developed on the basis of HIS and EHR data. We made a systematic review of publications presented in Russian and foreign databases (Scopus, PubMed, BMC Health Services Research, BMJ Research, Google Scholar, Elibrary, Oxford Academic, Wiley Online Library) for the period 1993-2023. The analysis included studies that used EHR and HIS data to develop and/or validate prognostic models of hospitalization risk. The information is systematized by following predictor categories: diseases and comorbidities, prescriptions, interaction with healthcare organizations, sociodemographic and laboratory parameters. The final analysis included 14 studies describing 28 models for predicting the hospitalization risk. Most studies used logistic regression. Machine learning methods (gradient boosting, random forest, and Bayesian ensemble models) were used in some studies. The categories with the highest prognostic value were "diseases and comorbidities" (42,3%), "medication prescriptions" (23,6%), and "interaction with health organizations" (19,8%). Including temporal characteristics (frequency and recency of hospitalizations, visits to primary care facilities, and laboratory tests) increased the model accuracy. Predictive models based on EHR and HIS data demonstrate high discriminatory power and enable the assessment of hospitalization risk at the primary care level. Machine learning methods in some studies demonstrated the possibility of a more in-depth analysis of the relationships between predictors and improved prediction accuracy. A promising area of research is the further development, external validation, and adaptation of models using expanded EHR and HIS data sets for its use in outpatient monitoring and preventing noncommunicable diseases.

1. Drapkina OM, Kontsevaya AV, Kalinina AM, et al. Comorbidity of patients with noncommunicable diseases in general practice. Eurasian guidelines. Cardiovascular Therapy and Prevention. 2024;23(3):3996. (In Russ.) doi:10.15829/1728-8800-2024-3996. EDN: AVZLPJ.

2. Sundmacher L, Fischbach D, Schuettig W, et al. Which hospi­talisations are ambulatory care-sensitive, to what degree, and how could the rates be reduced? Results of a group consensus study in Germany. Health Policy. 2015;119(11):1415-23. doi:10.1016/j.healthpol.2015.08.007.

3. Malyavin AG, Avksentieva MV, Babak SL, et al. Medical and eco­no­mic consequences of expanding the drug provision program for patients with COPD in Russia. Therapy. 2019;5(5): 36-44. (In Russ.) doi:10.18565/therapy.2019.5.36-44. EDN: VLVVPJ.

4. Klunder JH, Panneman SL, Wallace E, et al. Prediction models for the prediction of unplanned hospital admissions in com­munity-­dwelling older adults: A systematic review. PLoS One. 2022;17(9):e0275116. doi:10.1371/journal.pone.0275116.

5. Shepel RN, Drapkina OM, Kontsevaya AV, et al. Ambulatory care sen­sitive diseases/conditions in adult patients. A systematic review. Cardiovascular Therapy and Prevention. 2024;23(9):4128. (In Russ.) doi:10.15829/1728-8800-2024-4128. EDN: MAIAVK.

6. Castro Vargas S, Bauhoff S. Evaluating health systems through ambulatory care-sensitive conditions. Rev Panam Salud Publica. 2025;49:e75. doi:10.26633/RPSP.2025.75.

7. Saturno-­Hernández P, Moreno-­Zegbe E, Poblano-­Verastegui O, et al. Hospital care direct costs due to ambulatory care sensitive conditions related to diabetes mellitus in the Mexican public healthcare system. BMC Health Serv Res. 2024;24(1):507. doi:10.1186/s12913-024-10937-w.

8. Somé NH, Devlin RA, Mehta N. Primary care payment models and avoidable hospitalizations in Ontario, Canada: A multivalued treatment effects analysis. Health Econ. 2024;33(10):2288-305. doi:10.1002/hec.4872.

9. Loukianov MM, Gomova TA, Savishceva AA, et al. RegiStry Of the multiFaceted medIcal cenTer (SOFIT): the main tasks, de­ve­lopment, and the first results. The Russian Journal of Pre­ven­tive Medicine. 2023;26(6):46-54. (In Russ.) doi:10.17116/profmed20232606146.

10. Martsevich SYu, Kutishenko NP, Lukina Yu, et al. Polypharmacy: definition, impact on outcomes, need for correction. Rational Phar­ma­co­therapy in Cardiology. 2023;19(3):254-63. (In Russ.) doi:10.20996/1819-6446-2023-2924.

11. Dolgusheva YuA, Efremova YuE, Kudrina VG, et al. Risks of po­lypharmacy in elderly patients with cardiovascular diseases. RMJ. Medical Review. 2025;9(1):77-84. (In Russ.) doi:10.32364/2587-6821-2025-9-1-10.

12. Oddy C, Zhang J, Morley J. Promising algorithms to perilous applications: a systematic review of risk stratification tools for predicting healthcare utilisation. BMJ Health Care Inform. 2024;31(1):e101065. doi:10.1136/bmjhci-2024-101065.

13. Shepel RN, Demko VV, Goncharov MV, et al. Analysis of ques­tionnaires from the perspective of hospitalization risk prediction. Sys­tematic review. Cardiovascular Therapy and Prevention. 2024;23(5):4026. (In Russ.) doi:10.15829/1728-8800-2024-4026. EDN: FRKOHO.

14. Raldow AC, Raja N, Villaflores CW, et al. Proactive care mana­gement of AI-identified at-risk patients decreases preventable ad­missions. Am J Manag Care. 2024;30(11):548-54. doi:10.37765/ajmc.2024.89625.

15. Golinelli D, Pecoraro V, Tedesco D, et al. Population risk stra­ti­fication tools and interventions for chronic disease management in primary care: a systematic literature review. BMC Health Serv Res. 2025;25;526. doi:10.1186/s12913-025-12690-0.

16. Andreychenko AE, Ermak AD, Gavrilov DV, et al. Development and validation of machine learning models predicting hospi­ta­lizations of hypertensive patients over 12 months. Cardio­vascular Therapy and Prevention. 2025;24(1):4130. (In Russ.) doi:10.15829/1728-8800-2025-4130. EDN: YXVRIN.

17. Andreychenko AE, Ermak AD, Gavrilov DV, et al. Development and validation of machine learning models predicting hospi­ta­li­zation risk in patients with diabetes mellitus within the next 12 months. Diabetes Mellitus. 2024;27(2):142-57. (In Russ.) doi:10.14341/DM13065.

18. Rukodayny OV, Goloshchapov-­Aksenov RS, Shaburov RI, et al. The experience of the decision-­making algorithm of primary healthcare for the elderly patients with cardiovascular diseases. Complex Issues of Cardiovascular Diseases. 2022;11(2):85-97. (In Russ.) doi:10.17802/2306-1278-2022-11-2-85-97.

19. Page MJ, McKenzie JE, Bossuyt PM, et al. The PRISMA 2020 statement: an updated guideline for reporting systematic reviews. BMJ. 2021;372:n71. doi:10.1136/bmj.n71.

20. Hippisley-­Cox J, Coupland C. Predicting risk of emergency ad­mis­sion to hospital using primary care data: derivation and valida­tion of QAdmissions score. BMJ Open. 2013;3(8):e003482. doi:10.1136/bmjopen-2013-003482.

21. Rahimian F, Salimi-­Khorshidi G, Payberah AH, et al. Predicting the risk of emergency admission with machine learning: development and validation using linked electronic health records. PLoS Me­dicine. 2018;15(11):e1002695. doi:10.1371/journal.pmed.1002695.

22. Riley RD, Ensor J, Snell KI, et al. External validation of clinical prediction models using big datasets from e-health records or IPD meta-analysis: opportunities and challenges. BMJ. 2016; 353:i3140. doi:10.1136/bmj.i3140.

23. Donnan PT, Dorward DW, Mutch B, et al. Development and validation of a model for predicting emergency admissions over the next year (PEONY): a UK historical cohort study. Arch Intern Med. 2008;168(13):1416-22. doi:10.1001/archinte.168.13.1416.

24. Tomlin AM, Lloyd HS, Tilyard MW, et al. Risk stratification of New Zealand general practice patients for emergency admissions in the next year: adapting the PEONY model for use in New Zealand. J Prim Health Care. 2016;8(3):227-37. doi:10.1071/HC15000.

25. Chenore T, Pereira Gray DJ, Forrer J, et al. Emergency hospital admissions for the elderly: insights from the Devon Predictive Model. J Public Health (Oxford). 2013;35(4):616-23. doi:10.1093/pubmed/fdt009.

26. Mesgarpour M, Chaussalet T, Chahed S. Ensemble Risk Model of Emergency Readmissions (ERMER). Int J Med Inform. 2017;103:65-77. doi:10.1016/j.ijmedinf.2017.04.010.

27. Gao J, Moran E, Li YF, et al. Predicting potentially avoidable hospitalizations. Med Care. 2014;52(2):164-71. doi:10.1097/MLR.0000000000000041.

28. Hutchings HA, Evans BA, Fitzsimmons D, et al. Predictive risk stratification model: a progressive cluster-­randomised trial in chronic conditions management (PRISMATIC) research protocol. Trials. 2013;14:301. doi:10.1186/1745-6215-14-301.

29. Lemke KW, Weiner JP, Clark JM. Development and validation of a model for predicting inpatient hospitalization. Med Care. 2012;50(2):131-9. doi:10.1097/MLR.0b013e3182353ceb.

30. Wang L, Porter B, Maynard C, et al. Predicting risk of hos­pi­talization or death among patients receiving primary care in the Veterans Health Administration. Med Care. 2013;51(4):368-73. doi:10.1097/MLR.0b013e31827da95a.

31. Benthien KS, Jacobsen RK, Hjarnaa L, et al. Predicting individual risk of emergency hospital admissions — a retrospective validation study. Risk Manag Healthc Policy. 2021;14:3865-72. doi:10.2147/RMHP.S314588.

32. Crane SJ, Tung EE, Hanson GJ, et al. Use of an electronic ad­ministrative database to identify older community-­dwelling adults at high risk for hospitalization or emergency department visits: the Elders Risk Assessment Index. BMC Health Serv Res. 2010;10:338. doi:10.1186/1472-6963-10-338.

33. Larina VN, Karpenko DG, Mikhailusova MP. Risk factors asso­ciated with cardiovascular hospitalizations in outpatients aged 60 years and older with chronic heart failure. Therapy. 2020;6(8):47-54. (In Russ.) doi:10.18565/therapy.2020.8.47-54. EDN: VAFJEM.

34. Guo Y, Wang Y, Li X, et al. Optimal Thromboprophylaxis in Elderly Chinese Patients with Atrial Fibrillation (ChiOTEAF) registry: protocol for a prospective, observational nationwide cohort study. BMJ Open 2018;8:e020191. doi:10.1136/bmjopen-2017-020191.

35. Mannucci PM, Nobili A. Multimorbidity and polypharmacy in the elderly: lessons from REPOSI. Intern Emerg Med. 2014;9(7):723-34. doi:10.1007/s11739-014-1124-1.

36. Billings J, Georghiou T, Blunt I. Choosing a model to predict hospital admission: an observational study of new variants of predictive models for case finding. BMJ Open. 2013;3(8): e003352. doi:10.1136/bmjopen-2013-003352.

37. Nunes AL, Lisboa T, da Rosa BN. Impact of artificial intelligence on hospital admission prediction and flow optimization in health services: a systematic review. Int J Med Inform. 2025;204:106057. doi:10.1016/j.ijmedinf.2025.106057.

38. Zhang X, Wang H, Yu G. Machine learning-­driven prediction of hospital admissions using gradient boosting and GPT-2. Digit Health. 2025;11:20552076251331319. doi:10.1177/20552076251331319.

39. Sharda M, Sharma S, Raikar S, et al. The Role of Machine Learning in Predicting Hospital Readmissions Among General Internal Medicine Patients: A Systematic Review. Cureus. 2025;17(5):e84761. doi:10.7759/cureus.84761.