Vol. 4 No. 4 (2025): October
RESEARCH ARTICLES

Explainable AI for Hospitalization Duration Predictions

DOWNLOAD PDF
  • S Latha,
  • V Hari Sai Praneeth,
  • T Siddhartha,
  • S Syed Moheed Nawaz,
  • P Prasanthi
S Latha
Department of AI and Data Science, Annamacharya Institute of Technology and Sciences, Kadapa, Andhra Pradesh, India
V Hari Sai Praneeth
Department of AI and Data Science, Annamacharya Institute of Technology and Sciences, Kadapa, Andhra Pradesh, India
T Siddhartha
Department of AI and Data Science, Annamacharya Institute of Technology and Sciences, Kadapa, Andhra Pradesh, India
S Syed Moheed Nawaz
Department of AI and Data Science, Annamacharya Institute of Technology and Sciences, Kadapa, Andhra Pradesh, India
P Prasanthi
Department of AI and Data Science, Annamacharya Institute of Technology and Sciences, Kadapa, Andhra Pradesh, India
DOI: https://doi.org/10.5281/zenodo.15260285

Published 2025-04-22

Keywords

  • Healthcare decision support systems,
  • explainable artificial intelligence,
  • machine learning,
  • XGBOOST

How to Cite

S Latha, V Hari Sai Praneeth, T Siddhartha, S Syed Moheed Nawaz, & P Prasanthi. (2025). Explainable AI for Hospitalization Duration Predictions. International Journal of Computational Learning & Intelligence, 4(4), 766–780. https://doi.org/10.5281/zenodo.15260285

Copyright (c) 2025 S Latha, V Hari Sai Praneeth, T Siddhartha, S Syed Moheed Nawaz, P Prasanthi

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Abstract

Effective bed management is essential for reducing hospital expenses, improving operational efficiency, and enhancing patient care. This study introduces a predictive framework for ICU length of stay (LOS) at the time of admission, utilizing electronic health records (EHR). Our research applies supervised machine learning classification models to estimate ICU patients’ LOS within hospital clinical information systems (CIS). Notably, this work represents the first known application of explainable artificial intelligence (xAI) to real-world hospital stay data for interpretable machine learning predictions. We assessed predictive classification models using various performance metrics, including Accuracy, AUC, Sensitivity, Specificity, F1-score, Precision, Recall, and others, to classify ICU stays as short or long upon admission. XGBoost demonstrated a 98% AUC in predicting LOS categories. This study highlights how hospitals and ICUs can integrate machine learning to forecast patient stays at admission. Additionally, our findings enhance clinical information systems by incorporating xAI to ensure robust and interpretable LOS prediction models.
DOWNLOAD PDF

References

  1. Awad, M., Bader-El-Den, M., & McNicholas, J. (2017). Patient length of stay and mortality prediction: A survey. Health Services Management Research, 30(2), 105–120. https://doi.org/10.1177/0951484817706580
  2. OECD. (2020). Length of hospital stay (indicator). https://data.oecd.org/healthcare/length-of-hospital-stay.htm
  3. Australian Institute of Health and Welfare. (2011). Hospital performance: Length of stay in public hospitals in 2011–12. https://www.aihw.gov.au/reports/hospitals/hospital-performance-length-of-stay-in-2011-12
  4. Pecoraro, F., Clemente, F., & Luzi, D. (2020). The efficiency in the ordinary hospital bed management in Italy: An in-depth analysis of intensive care unit in the areas affected by COVID-19 before the outbreak. PLoS ONE, 15(9), e0239249. https://doi.org/10.1371/journal.pone.0239249
  5. Hassan, M., Tuckman, H. P., Patrick, R. H., Kountz, D. S., & Kohn, J. L. (2010). Hospital length of stay and probability of acquiring infection. International Journal of Pharmaceutical and Healthcare Marketing, 4(4), 324–338. https://doi.org/10.1108/17506121011095267
  6. Blom, M. C., Erwander, K., Gustafsson, L., Landin-Olsson, M., Jonsson, F., & Ivarsson, K. (2015). The probability of readmission within 30 days of hospital discharge is positively associated with inpatient bed occupancy at discharge—A retrospective cohort study. BMC Emergency Medicine, 15(1), 1–6. https://doi.org/10.1186/s12873-015-0042-7
  7. Rocheteau, E., Liò, P., & Hyland, S. (2020). Temporal pointwise convolutional networks for length of stay prediction in the intensive care unit. arXiv preprint arXiv:2007.09483. https://arxiv.org/abs/2007.09483
  8. Hanson, C. W., Deutschman, C. S., Anderson, H. L., Reilly, P. M., Behringer, E. C., Schwab, C. W., & Price, J. (1999). Effects of an organized critical care service on outcomes and resource utilization: A cohort study. Critical Care Medicine, 27(2), 270–274. https://doi.org/10.1097/00003246-199902000-00033
  9. Pérez, S., Siddiqui, S., Ahmed, S., & Manasia, R. (2005). Apache II score as a predictor of length of stay and outcome in our ICUs. Journal of the Pakistan Medical Association, 55(6), 253.
  10. Knaus, W. A., Zimmerman, J. E., Wagner, D. P., Draper, E. A., & Lawrence, D. E. (1981). APACHE—Acute physiology and chronic health evaluation: A physiologically based classification system. Critical Care Medicine, 9(8), 591–597. https://doi.org/10.1097/00003246-198108000-00008
  11. Knaus, A., Wagner, D. P., Draper, E. A., Zimmerman, J. E., Bergner, M., Bastos, P. G., Sirio, C. A., Murphy, D. J., Lotring, T., Damiano, A., & Harrell, F. E., Jr. (1991). The APACHE III prognostic system: Risk prediction of hospital mortality for critically ill hospitalized adults. Chest, 100(6), 1619–1636. https://doi.org/10.1378/chest.100.6.1619
  12. Keegan, M. T., Gajic, O., & Afessa, B. (2012). Comparison of APACHE III, APACHE IV, SAPS 3, and MPM0III and influence of resuscitation status on model performance. Chest, 142(4), 851–858. https://doi.org/10.1378/chest.11-2764
  13. Yeh, C.-C., Chen, Y.-A., Hsu, C.-C., Chen, J.-H., Chen, W.-L., Huang, C.-C., & Chung, J.-Y. (2020). Quick-SOFA score ≥ 2 predicts prolonged hospital stay in geriatric patients with influenza infection. American Journal of Emergency Medicine, 38(4), 780–784. https://doi.org/10.1016/j.ajem.2019.07.021
  14. Ahmed, S. T., Basha, S. M., Ramachandran, M., Daneshmand, M., & Gandomi, A. H. (2023). An edge-AI-enabled autonomous connected ambulance-route resource recommendation protocol (ACA-R3) for eHealth in smart cities. IEEE Internet of Things Journal, 10(13), 11497-11506.
  15. Ahmed, S. T., Fathima, A. S., Nishabai, M., & Sophia, S. (2024). Medical ChatBot assistance for primary clinical guidance using machine learning techniques. Procedia Computer Science, 233, 279-287.
  16. Calloway, S., Akilo, H. A., & Bierman, K. (2013). Impact of a clinical decision support system on pharmacy clinical interventions, documentation efforts, and costs. Hospital Pharmacy, 48(9), 744–752. https://doi.org/10.1310/hpj4809-744
  17. Dwaram, J. R., & Madapuri, R. K. (2022). Crop yield forecasting by long short‐term memory network with Adam optimizer and Huber loss function in Andhra Pradesh, India. Concurrency and Computation: Practice and Experience, 34(27), e7310. https://doi.org/10.1002/cpe.7310
  18. Islam, M. M., Poly, T. N., & Li, Y.-C. (2018). Recent advancement of clinical information systems: Opportunities and challenges. Yearbook of Medical Informatics, 27(1), 83–90. https://doi.org/10.1055/s-0038-1667072
  19. Kumar, S. S., Ahmed, S. T., Sandeep, S., Madheswaran, M., & Basha, S. M. (2022). Unstructured Oncological Image Cluster Identification Using Improved Unsupervised Clustering Techniques. Computers, Materials & Continua, 72(1).
  20. Levesque, E., Hoti, E., Azoulay, D., Ichai, P., Samuel, D., & Saliba, F. (2015). The implementation of an intensive care information system allows shortening the ICU length of stay. Journal of Clinical Monitoring and Computing, 29(2), 263–269. https://doi.org/10.1007/s10877-014-9607-0
  21. Li, C., Chen, L., Feng, J., Wu, D., Wang, Z., Liu, J., & Xu, W. (2019). Prediction of length of stay on the intensive care unit based on least absolute shrinkage and selection operator. IEEE Access, 7, 110710–110721. https://doi.org/10.1109/ACCESS.2019.2934063
  22. Madapuri, R. K., & Senthil Mahesh, P. C. (2017). HBS-CRA: Scaling impact of change request towards fault proneness: Defining a heuristic and biases scale (HBS) of change request artifacts (CRA). Cluster Computing, 22(S5), 11591–11599. https://doi.org/10.1007/s10586-017-1424-0
  23. McMullin, S. T., Lonergan, T. P., Rynearson, C. S., Doerr, T. D., Veregge, P. A., & Scanlan, E. S. (2004). Impact of an evidence-based computerized decision support system on primary care prescription costs. Annals of Family Medicine, 2(5), 494–498. https://doi.org/10.1370/afm.113
  24. Pasha, A., Ahmed, S. T., Painam, R. K., Mathivanan, S. K., Mallik, S., & Qin, H. (2024). Leveraging ANFIS with Adam and PSO optimizers for Parkinson's disease. Heliyon, 10(9).
  25. Periasamy, K., Periasamy, S., Velayutham, S., Zhang, Z., Ahmed, S. T., & Jayapalan, A. (2022). A proactive model to predict osteoporosis: An artificial immune system approach. Expert Systems, 39(4), e12708.
  26. Reddy, B. S. H. (2025). Deep learning-based detection of hair and scalp diseases using CNN and image processing. Milestone Transactions on Medical Technometrics, 3(1), 145–155. https://doi.org/10.5281/zenodo.14965660
  27. Reddy, B. S. H., Venkatramana, R., & Jayasree, L. (2025). Enhancing apple fruit quality detection with augmented YOLOv3 deep learning algorithm. International Journal of Human Computations & Intelligence, 4(1), 386–396. https://doi.org/10.5281/zenodo.14998944
  28. Romanow, D., Rai, A., Keil, M., & Luxenberg, S. (2017). Does extended CPOE use reduce patient length of stay? International Journal of Medical Informatics, 97, 128–138. https://doi.org/10.1016/j.ijmedinf.2016.10.020
  29. Sreedhar, K. S., Ahmed, S. T., & Sreejesh, G. (2022, June). An Improved Technique to Identify Fake News on Social Media Network using Supervised Machine Learning Concepts. In 2022 IEEE World Conference on Applied Intelligence and Computing (AIC) (pp. 652-658). IEEE.
  30. Sutton, R. T., Pincock, D., Baumgart, D. C., Sadowski, D. C., Fedorak, R. N., & Kroeker, K. I. (2020). An overview of clinical decision support systems: Benefits, risks, and strategies for success. NPJ Digital Medicine, 3(1), 1–10. https://doi.org/10.1038/s41746-020-0221-y