Authors : Dr. Sharad Mathur; Dr. Deepak Mathur

Volume/Issue : Volume 11 - 2026, Issue 5 - May

Google Scholar : https://tinyurl.com/fv5p53xy

Scribd : https://tinyurl.com/y6r8vvpy

DOI : https://doi.org/10.38124/ijisrt/26May116

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : Hospital readmissions, particularly those occurring within 30 days of discharge, represent a pivotal failure in the continuity of healthcare delivery, contributing significantly to patient morbidity, mortality, and escalating operational costs. As healthcare systems globally transition toward value-based care models, the imperative to accurately identify patients at high risk of readmission has catalyzed a surge in computational research. This research provides an exhaustive analysis of machine learning (ML) and deep learning (DL) applications in this domain. We critically examine the persistent performance dichotomy between ensemble tree-based methods (e.g., XGBoost) and deep neural architectures (e.g., LSTM, Transformer) on structured electronic health record (EHR) data. Furthermore, we explore the emerging frontier of multimodal fusion, where unstructured clinical notes are integrated via Large Language Models (LLMs) and Graph Neural Networks (GNNs) to capture semantic nuances missed by tabular data. Through a rigorous benchmarking analysis utilizing the MIMIC-IV and eICU databases, this paper delineates the comparative efficacy of Early, Late, and Joint Fusion strategies. Finally, we address the critical barriers to clinical deployment, including model interpretability (XAI), reproducibility, and the architectural requirements for real-time inference, offering a roadmap for the next generation of clinical decision support systems.

Keywords : Machine Learning, XGBoost, Random Fores, NLP, GNNs, LLMs.

References :

1. Sharma, Y.; Mangoni, A.A.; Horwood, C.; Thompson, C. External validation and comparative analysis of the HOSPITAL score and LACE index for predicting readmissions among patients hospitalised with community-acquired pneumonia in Australia. Aust. Health Rev. 2024, 48, 656-663.
2. Mathur S., Joshi B., Survey on Needs, Applications and Agorithms of Data Mining for Healthcare, International Journal of Advance Research in Science and Engineering”, Vol 6(8), 80-87, August, 2017, ISSN: 2319-8346.
3. Chen C, Scheffler G, Chandra A. Readmission penalties and health insurance expansions: a dispatch from Massachusetts. J Hosp Med. 2014;9(11):681–687. 10.1002/jhm.2213
4. Ponzoni CR, Corrêa TD, Filho RR, Serpa Neto A, Assunção MSC, Pardini A, et al. Readmission to the intensive care unit: incidence, risk factors, resource use, and outcomes. A retrospective cohort study. Ann Am Thorac Soc. 2017;14:1312–9.
5. Lin Y-W, Zhou Y, Faghri F, Shaw MJ, Campbell RH. Analysis and prediction of unplanned intensive care unit readmission using recurrent neural networks with long short-term memory. PLoS One. 2019;14:e0218942.
6. Polo Friz, H.; Esposito, V.; Marano, G.; Primitz, L.; Bovio, A.; Delgrossi, G.; Bombelli, M.; Grignaffini, G.; Monza, G.; Boracchi, P. Machine learning and LACE index for predicting 30-day readmissions after heart failure hospitalization in elderly patients. Intern. Emerg. Med. 2022, 17, 1727-1737.
7. Mathur S., Joshi B., Application of Naïve Bayes Classification for disease Prediction International Journal of Management, IT & Engineering, Vol. 9 Issue 4, April 2019, ISSN: 2249-0558
8. Voulodimos A, Doulamis N, Doulamis A, Protopapadakis E. Deep Learning for Computer Vision: A Brief Review. Comput Intell Neurosci. 2018;2018:7068349 10.1155/2018/7068349
9. Nates JL, Nunnally M, Kleinpell R, Blosser S, Goldner J, Birriel B, et al. Icu admission, discharge, and triage guidelines: a framework to enhance clinical operations, development of institutional policies, and further research. 2016;44:1553–602.
10. Ravi D, Wong C, Deligianni F, Berthelot M, Andreu-Perez J, Lo B, et al. Deep learning for health informatics. IEEE J Biomed Health Inform. 2017;21:4–21.
11. Noraziani, K.; Nurul'Ain, A.; Azhim, M.Z.; Eslami, S.R.; Drak, B.; Sharifa Ezat, W.; Siti Nurul Akma, A. An overview of electronic medical record implementation in healthcare system: Lesson to learn. World Appl. Sci. J. 2013, 25, 323-332.
12. Rajkomar, A.; Dean, J.; Kohane, I. Machine Learning in Medicine. N. Engl. J. Med. 2019, 380, 1347-1358.
13. Chakraborty H, Axon RN, Brittingham J, Lyons GR, Cole L, Turley CB. Differences in Hospital Readmission Risk across All Payer Groups in South Carolina. Health Serv Res. 2017;52(3):1040–1060. 10.1111/1475-6773.12579
14. Tang, S.; Davarmanesh, P., Song, Y.; Koutra, D.; Sjoding, M.W.; Wiens, J. Democratizing EHR analyses with FIDDLE: A flexible data-driven preprocessing pipeline for structured clinical data. J. Am. Med. Inform. Assoc. 2020, 27, 1921-1934.
15. Mathur S., Rai A., "Enhancing Disease Forecasting Through Naïve Bayes Classification Techniques", International Journal of Engineering Research & Technology (IJERT),ISSN: 2278-0181, Vol. 14 Issue 12 , December – 2025
16. Scott, I.A.; Shohag, H.; Ahmed, M. Quality of care factors associated with unplanned readmissions of older medical patients: A case-control study. Intern. Med. J. 2014, 44, 161-170.
17. Krumholz HM, Lin Z, Drye EE, et al. An Administrative Claims Measure Suitable for Profiling Hospital Performance Based on 30-Day All-Cause Readmission Rates Among Patients With Acute Myocardial Infarction. Circulation Cardiovascular Quality and Outcomes. 2011;4(2):243–252. 10.1161/CIRCOUTCOMES.110.957498
18. Le Gall J-R. A new simplified acute physiology score (SAPS II) based on a european/north American multicenter study. JAMA. 1993;270:2957-63.
19. Esther Omolara, A.; Jantan, A.; Abiodun, O.I.; Arshad, H.; Dada, K.V.; Emmanuel, E. HoneyDetails: A prototype for ensuring patient's information privacy and thwarting electronic health record threats based on decoys. Health Inform. J. 2020, 26, 2083-2104.
20. Levy, W.C., Anand, I.S. Heart failure risk prediction models: What have we learned? JACC Heart Fail. 2014, 2, 437-439.
21. Chang I-M, Gelman R, Pagano M. Corrected group prognostic curves and summary statistics. Journal of chronic diseases. 1982;35(8):669–674. 10.1016/0021-9681(82)90019-4
22. Deng Y, Liu S, Wang Z, Wang Y, Jiang Y, Liu B. Explainable time-series deep learning models for the prediction of mortality, prolonged length of stay and 30-day readmission in intensive care patients. Front Med. 2022;9:933037
23. Ramspek CL, Jager KJ, Dekker FW, Zoccali C, Van Diepen M. External validation of prognostic models: what, why, how, when and where? Clin Kidney J. 2021;14:49–58.
24. Kamal, U.; Zunaed, M.; Nizam, N.B.; Hasan, T. Anatomy-xnet: An anatomy aware convolutional neural network for thoracic disease classification in chest X-rays. IEEE J. Biomed. Health Inform. 2022, 26, 5518-5528.
25. Mathur S., Rai A., Mathur D., " Predictive Data Mining for Disease Diagnosis-Decision Tree Approach", International Journal of Engineering Research & Technology (IJERT),ISSN: 2278-0181,Vol. 14 Issue 05, May-2025
26. van Walraven, C. The Utility of Unplanned Early Hospital Readmissions as a Health Care Quality Indicator. JAMA Intern. Med. 2015, 175, 1812-1814.
27. Lee J. Covariance adjustment of rates based on the multiple logistic regression model. Journal of Clinical Epidemiology. 1981;34(8):415–426.
28. Young T, Hazarika D, Poria S, Cambria E. Recent Trends in Deep Learning Based Natural Language Processing. IEEE Computational Intelligence Magazine. 2018; 13 (3) : 55 – 75   10.1109/MCI.2018.2840738
29. Harrell FE. Regression Modeling Strategies: With Applications to Linear Models, Logistic and Ordinal Regression, and Survival Analysis [Internet]. Cham: Springer International Publishing; 2015: https://link.springer.com/10.1007/978-3-319-19425-7.
30. Liang, J., Li, Y.; Zhang, Z.; Shen, D., Xu, J.; Zheng, X., Wang, T.; Tang, B.; Lei, J.; Zhang, J. Adoption of electronic health records (EHRs) in China during the past 10 years: Consecutive survey data analysis and comparison of Sino-American challenges and experiences. J. Med. Internet Res. 2021, 23, e24813.
31. Grant, K.; McParland, A.; Mehta, S.; Ackery, A.D. Artificial Intelligence in Emergency Medicine: Surmountable Barriers With Revolutionary Potential. Ann. Emerg. Med. 2020, 75, 721-726.
32. Zaheer M, Kottur S, Ravanbakhsh S, Poczos B, Salakhutdinov RR, Smola AJ. Deep Sets In: Guyon I, Luxburg UV, Bengio S, et al. , eds. Advances in Neural Information Processing Systems 30. Curran Associates, Inc; 2017:3391–3401.
33. Gajic O, Malinchoc M, Comfere TB, Harris MR, Achouiti A, Yilmaz M, et al. The stability and workload index for transfer score predicts unplanned intensive care unit patient readmission: initial development and validation. 2008;36(3):676–82.
34. Sun M, Yang X, Niu J, Gu Y, Wang C, Zhang W. A cross-modal clinical prediction system for intensive care unit patient outcome. Knowledge-Based Systems. 2024;283:111160.
35. Rockenschaub P, Hilbert A, Kossen T, Elbers P, Von Dincklage F, Madai VI, et al. The impact of multi-institution datasets on the generalizability of machine learning prediction models in the ICU. Crit Care Med. 2024;52:1710–21