TY  - JOUR
T1  - Predictive Modeling of 30-Day Readmission Risk: A Machine Learning Approach for Health Management
TT  - 30 Günlük Yeniden Yatış Riskinin Öngörülmesi: Sağlık Yönetimi için Bir Makine Öğrenmesi Yaklaşımı
AU  - Doğan, Alican
PY  - 2026
DA  - August
Y2  - 2026
DO  - 10.46413/boneyusbad.1737521
JF  - Bandırma Onyedi Eylül Üniversitesi Sağlık Bilimleri ve Araştırmaları Dergisi
PB  - Bandırma Onyedi Eylül Üniversitesi
WT  - DergiPark
SN  - 2687-2145
SP  - 441
EP  - 455
VL  - 8
IS  - 2
LA  - en
AB  - Aim: This study aims to develop and evaluate predictive models capable of identifying patients at risk of 30-day readmission using structured inpatient data.Material and Method: The analysis was conducted on a fully synthetic dataset designed to reflect the complexity of real-world clinical data while ensuring the protection of personal health information. The dataset includes key features relevant to inpatient care, such as patient demographics, diagnosis codes, laboratory abnormalities, procedural counts, length of stay, and risk scores. A comprehensive preprocessing phase involving label encoding, data balancing, and normalization is completed. In the data preprocessing stage, categorical variables were encoded, class imbalance was corrected using the SMOTE method, and Logistic Regression, Random Forest, and XGBoost models were applied.Results: According to the results, the Random Forest model demonstrated the highest performance, achieving over 92% accuracy and an AUC value of 0.95. Feature significance analysis revealed that risk score, length of stay, and number of procedures were the most effective variables in determining the risk of readmission. The findings indicate that predictive analytics approaches can make significant contributions to early intervention planning and resource optimization in healthcare management.Conclusion: The proposed modeling approach may support early intervention planning and hospital resource optimization while promoting data-driven strategies to reduce preventable readmissions.
KW  - Inpatient readmission
KW  - Predictive modeling
KW  - Risk management implications
KW  - Clinical decision support
KW  - Health management
KW  - Machine learning
N2  - Amaç: Bu çalışma, yapılandırılmış yatan hasta verilerini kullanarak 30 günlük yeniden yatış riski taşıyan hastaları belirleyebilecek öngörüsel modeller geliştirmeyi ve değerlendirmeyi amaçlamaktadır.Gereç ve Yöntem: Analizler, gerçek dünyadaki klinik verilerin karmaşıklığını yansıtırken kişisel sağlık bilgilerinin gizliliğini korumak amacıyla oluşturulmuş tamamen sentetik bir veri kümesi üzerinde gerçekleştirilmiştir. Veri kümesi, hasta demografisi, tanı kodları, laboratuvar anormallikleri, uygulanan işlem sayısı, hastanede kalış süresi ve risk skorları gibi yatan hasta bakımına ilişkin temel özellikleri içermektedir. Etiketleme, veri dengesinin sağlanması ve normalizasyon gibi kapsamlı bir ön işleme yapılmıştır. Veri ön işleme aşamasında kategorik değişkenler kodlanmış, sınıf dengesizliği SMOTE yöntemi ile giderilmiş ve Logistic Regression, Random Forest ve XGBoost modelleri uygulanmıştır.  Bulgular: Sonuçlara göre Random Forest modeli en yüksek performansı göstermiş; %92’nin üzerinde doğruluk ve 0.95 AUC değeri elde edilmiştir. Özellik önem analizi, risk skoru, yatış süresi ve işlem sayısının yeniden yatış riskini belirlemede en etkili değişkenler olduğunu ortaya koymuştur. Bulgular, öngörücü analitik yaklaşımların sağlık yönetiminde erken müdahale planlaması ve kaynak optimizasyonu açısından önemli katkılar sağlayabileceğini göstermektedir.Sonuç: Önerilen modelleme yaklaşımı, erken müdahale planlaması ve hastane kaynaklarının optimize edilmesine katkı sağlayabilirken, önlenebilir yeniden yatışların azaltılmasına yönelik veri odaklı stratejileri de desteklemektedir.
CR  - Brady, N., Liang, Y., Seidl, K. L., Marcozzi, D., Stryckman, B., Gingold, D. B. (2024). Association of timely outpatient follow-up and readmission risk in a mobile integrated health program. Population Health Management, 27 (4), 249–256. doi:10.1089/pop.2024.0020
CR  - Bozorgpanah, A., & Torra, V. (2024). Explainable machine learning models with privacy. Progress in Artificial Intelligence, 13, 31–50. https://doi.org/10.1007/s13748-024-00315-2
CR  - Carroll, A. R., Hall, M., Harris, M., Carroll, M. S., Auger, K. A., Davis, M. M., … Williams, D. J. (2025). Validation of 30-day pediatric hospital readmission risk prediction models. JAMA Network Open, 8 (2), e2459684.  doi:10.1001/jamanetworkopen.2024.59684
CR  - Cui, S., Gao, R., Kuang, J., Yang, L., Qiu, H., Wei, X. (2025). An interpretable imbalance ensemble classification method for readmission risk assessment incorporating multi-view perturbation and SHAP analysis. Decision Support Systems, 190, Article 114404.  doi:10.1016/j.dss.2025.114404
CR  - Durmaz, H., Doğan, M., & Yenilmez, İ. (2024, Aralık). Enhancing explainability in machine learning models: Addressing the Rashomon effect with SHAP and LORE. Sözel bildiri, Selçuk 11th International Conference on Applied Sciences, Konya.
CR  - Gerstmeyer, J., Gorbacheva, A., Avantaggio, A., Pierre, C., Yilmaz, E., Schildhauer, T. A., … Chapman, J. R. (2025). Spine surgery and readmission: Risk factors in lumbar corpectomy patients. North American Spine Society Journal, 21, Article 100587.  doi:10.1016/j.xnsj.2025.100587
CR  - Góngora Alonso, S., Herrera Montano, I., Ayala, J. L. M., Rodrigues, J. J. P. C., Franco-Martín, M., de la Torre Díez, I. (2024). Machine learning models to predict readmission risk of patients with schizophrenia in a Spanish region. International Journal of Mental Health and Addiction, 22(4), 2508–2527. doi:10.1007/s11469-022-01001-x
CR  - González-Santa Cruz, A., Mauro, P. M., Sapag, J. C., Martins, S. S., Ruiz-Tagle, J., Gaete, J., … Castillo-Carniglia, A. (2025). Effect of residential versus ambulatory treatment for substance use disorders on readmission risk in a register-based national retrospective cohort. Social Psychiatry and Psychiatric Epidemiology.  doi:10.1007/s00127-025-02865-9
CR  - Kwon, J., Farquhar, D., Tasoulas, J., Hackman, T. G. (2024). Post-surgical readmission risk factors in otolaryngology/head and neck surgery. Head and Neck, 46(10), 2407–2414. doi:10.1002/hed.27706
CR  - Li, J., Liang, L., Samuel Cai, Y., Zuo, Y., Su, J., Feng, L., … Tong, Z. (2024). Tracking COPD exacerbation patterns and forecasting readmission risks utilizing electronic medical records. International Journal of Medical Informatics, 189, 105505. doi:10.1016/j.ijmedinf.2024.105505
CR  - Liu, Y., Du, L., Li, L., Xiong, L., Luo, H., Kwaku, E., … Yue, R. (2024). Development and validation of a machine learning-based readmission risk prediction model for non-ST elevation myocardial infarction patients after percutaneous coronary intervention. Scientific Reports, 14 (1), Article 13393.  doi:10.1038/s41598-024-64048-x
CR  - Luo, H., Xiang, C., Zeng, L., Li, S., Mei, X., Xiong, L., … Yue, R. (2024). SHAP-based predictive modeling for 1-year all-cause readmission risk in elderly heart failure patients: Feature selection and model interpretation. Scientific Reports, 14 (1), Article 17728.  doi:10.1038/s41598-024-67844-7
CR  - Panchangam, P. V. R., Tejas, A., Thejas, B. U., Maniaci, M. J. (2024). Machine learning-based prediction of readmission risk in cardiovascular and cerebrovascular conditions using patient EMR data. Healthcare (Switzerland), 12 (15), Article 1497. doi:10.3390/healthcare12151497
CR  - Serna, M. K., Sadang, K. G., Vollbrecht, H. B., Yoon, C., Fiskio, J., Lakin, J. R., … Schnipper, J. L. (2024). Identification of hospitalized patients who may benefit from a serious illness conversation using the readmission risk score combined with the Surprise Question. Joint Commission Journal on Quality and Patient Safety, 50 (12), 842–848.  doi:10.1016/j.jcjq.2024.08.003
CR  - Sweeney, L. C., Reddy, U. M., Campbell, K., Xu, X. (2024). Postpartum readmission risk: A comparison between stillbirths and live births. American Journal of Obstetrics and Gynecology, 231 (4), 463.e1–463.e14. doi:10.1016/j.ajog.2024.02.017
CR  - Todd, J., Stern, S. E. (2024). Decomposing the hazard function into interpretable readmission risk components. Decision Support Systems, 183, 114264. doi:10.1016/j.dss.2024.114264
CR  - Tokac, U., Chipps, J., Brysiewicz, P., Bruce, J., Clarke, D. (2025). Using machine learning to improve readmission risk in surgical patients in South Africa. International Journal of Environmental Research and Public Health, 22 (3), Article 345.  doi:10.3390/ijerph22030345
CR  - Tonde, B., Traore, M. M., Landa, P., Côté, A., Laberge, M. (2025). Predictive modelling methods of hospital readmission risks for patients with chronic obstructive pulmonary disease (COPD): A systematic review protocol. BMJ Open, 15 (4), e093771.  doi:10.1136/bmjopen-2024-093771
CR  - Yenilmez, İ. (2025, Şubat). Balancing exploration and exploitation in hyperparameter tuning with hybrid optimization approaches. Sözel bildiri, 4th International Conference on Mathematics and Engineering, Bursa
CR  - You, S. B., Song, J., Hsu, J. Y., Bowles, K. H. (2025). Characteristics and readmission risks following sepsis discharges to home. Medical Care, 63 (2), 89–97.  doi:10.1097/MLR.0000000000002091
CR  - Zhang, J., Liu, M., Gao, J., Tian, X., Song, Y., Zhang, H., Zhao, P. (2025). ApoB/ApoA-Ι is associated with major cardiovascular events and readmission risk of patients after percutaneous coronary intervention in one year. Scientific Reports, 15 (1), Article 996.  doi:doi.org/10.1038/s41598-024-84092-x
CR  - Zhou, Y., Fu, C., Wei, L., Zhou, W., Li, X., & You, Y. (2026). An integrated approach for addressing data imbalance in predicting fatality of helicopter accidents. Reliability Engineering and System Safety, 267, Article 111921. https://doi.org/10.1016/j.ress.2025.111921
UR  - https://doi.org/10.46413/boneyusbad.1737521
L1  - https://dergipark.org.tr/tr/download/article-file/5034775
ER  -