Enhanced Prediction of Intensive Care Unit Length of Stay using a Stack Ensemble of Machine Learning Models
Received: 14 September 2024 | Revised: 31 October 2024, 13 November 2024, and 18 November 2024 | Accepted: 20 November 2024 | Online: 2 February 2025
Corresponding author: Ashok Kumar Tella
Abstract
The Length of Stay (LoS) refers to the time between a patient's hospital admission and discharge. LoS is considered to increase as the complexity of the disease increases. A prolonged stay in the Intensive Care Unit (ICU) can consume clinical resources and be labor intensive. Models that correctly predict LoS are needed to help medical experts make better decisions. To define an ideal process system, healthcare models must consider the patient's condition, availability of beds, resources, etc. These predictions can also help insurance companies manage their budgets. Existing models deploy machines and deep learning techniques to predict LoS. However, there is a need for improvement, considering the features associated with the process. This study presents machine learning algorithms, such as SVM and a stack ensemble, with improved accuracy over existing models. Experiments were carried out on a benchmark dataset, MIMIC-III, specific to ICU patients. The SVM model achieved an accuracy of 93.88%, while the stack ensemble model showed an improved accuracy of 94.70%. The results show that combining machine learning models achieves better prediction rates, which helps healthcare professionals make better decisions.
Keywords:
length of stay, intensive care unit, machine learning models, stack ensemble models, healthcare analytics, ICU patient managementDownloads
References
L. Y. Sun, A. Bader Eddeen, M. Ruel, E. MacPhee, and T. G. Mesana, "Derivation and Validation of a Clinical Model to Predict Intensive Care Unit Length of Stay After Cardiac Surgery," Journal of the American Heart Association, vol. 9, no. 21, Nov. 2020, Art. no. e017847.
N. B. Medeiros, F. S. Fogliatto, M. K. Rocha, and G. L. Tortorella, "Forecasting the length-of-stay of pediatric patients in hospitals: a scoping review," BMC Health Services Research, vol. 21, no. 1, Sep. 2021, Art. no. 938.
B. Stocker, H. K. Weiss, N. Weingarten, K. Engelhardt, M. Engoren, and J. Posluszny, "Predicting length of stay for trauma and emergency general surgery patients," The American Journal of Surgery, vol. 220, no. 3, pp. 757–764, Sep. 2020.
S. Bacchi, Y. Tan, L. Oakden-Rayner, J. Jannes, T. Kleinig, and S. Koblar, "Machine learning in the prediction of medical inpatient length of stay," Internal Medicine Journal, vol. 52, no. 2, 2022, Art. no. 176–185.
C. Neto, M. Brito, H. Peixoto, V. Lopes, A. Abelha, and J. Machado, "Prediction of Length of Stay for Stroke Patients Using Artificial Neural Networks," in Trends and Innovations in Information Systems and Technologies, Budva, Montenegro, 2020, pp. 212–221.
L. Hempel, S. Sadeghi, and T. Kirsten, "Prediction of Intensive Care Unit Length of Stay in the MIMIC-IV Dataset," Applied Sciences, vol. 13, no. 12, Jan. 2023, Art. no. 6930.
K. Stone, R. Zwiggelaar, P. Jones, and N. M. Parthaláin, "A systematic review of the prediction of hospital length of stay: Towards a unified framework," PLOS Digital Health, vol. 1, no. 4, 2022, Art. no. e0000017.
S. Iwase et al., "Prediction algorithm for ICU mortality and length of stay using machine learning," Scientific Reports, vol. 12, no. 1, Jul. 2022, Art. no. 12912.
H. Magunia et al., "Machine learning identifies ICU outcome predictors in a multicenter COVID-19 cohort," Critical Care, vol. 25, no. 1, Aug. 2021, Art. no. 295.
S. S. Lorenzen et al., "Using machine learning for predicting intensive care unit resource use during the COVID-19 pandemic in Denmark," Scientific Reports, vol. 11, no. 1, Sep. 2021, Art. no. 18959.
S. K. Andersen, C. L. Montgomery, and S. M. Bagshaw, "Early mortality in critical illness – A descriptive analysis of patients who died within 24 hours of ICU admission," Journal of Critical Care, vol. 60, pp. 279–284, Dec. 2020.
Y. Xue, D. Klabjan, and Y. Luo, "Predicting ICU readmission using grouped physiological and medication trends," Artificial Intelligence in Medicine, vol. 95, pp. 27–37, Apr. 2019.
B. Shickel, T. J. Loftus, L. Adhikari, T. Ozrazgat-Baslanti, A. Bihorac, and P. Rashidi, "DeepSOFA: A Continuous Acuity Score for Critically Ill Patients using Clinically Interpretable Deep Learning," Scientific Reports, vol. 9, no. 1, Feb. 2019, Art. no. 1879.
J. L. Dickson et al., "Generalisability of a Virtual Trials Method for Glycaemic Control in Intensive Care," IEEE Transactions on Biomedical Engineering, vol. 65, no. 7, pp. 1543–1553, Jul. 2018.
Y. Ding, X. Li, and Y. Wang, "Mortality prediction for ICU patients using just-in-time learning and extreme learning machine," in 2016 12th World Congress on Intelligent Control and Automation (WCICA), Guilin, China, Jun. 2016, pp. 939–944.
S. B. Nagaraj et al., "Electroencephalogram Based Detection of Deep Sedation in ICU Patients Using Atomic Decomposition," IEEE Transactions on Biomedical Engineering, vol. 65, no. 12, pp. 2684–2691, Sep. 2018.
R. J. Delahanty, D. Kaufman, and S. S. Jones, "Development and Evaluation of an Automated Machine Learning Algorithm for In-Hospital Mortality Risk Adjustment Among Critical Care Patients*," Critical Care Medicine, vol. 46, no. 6, Jun. 2018, Art. no. e481.
Y. Ding, X. Ma, and Y. Wang, "Health status monitoring for ICU patients based on locally weighted principal component analysis," Computer Methods and Programs in Biomedicine, vol. 156, pp. 61–71, Mar. 2018.
P. F. Tsai et al., "Length of Hospital Stay Prediction at the Admission Stage for Cardiology Patients Using Artificial Neural Network," Journal of Healthcare Engineering, vol. 2016, no. 1, 2016, Art. no. 7035463.
A. Lim and P. Tongkumchum, "Methods for analyzing hospital length of stay with application to inpatients dying in Southern Thailand," Global Journal of Health Science, vol. 1, no. 1, 2009, Art. no. 27.
D. A. Huntley, D. W. Cho, J. Christman, and J. G. Csernansky, "Predicting Length of Stay in an Acute Psychiatric Hospital," Psychiatric Services, vol. 49, no. 8, pp. 1049–1053, Aug. 1998.
P. Manorom, U. Detthamrong, and W. Chansanam, "Comparative Assessment of Fraudulent Financial Transactions using the Machine Learning Algorithms Decision Tree, Logistic Regression, Naïve Bayes, K-Nearest Neighbor, and Random Forest," Engineering, Technology & Applied Science Research, vol. 14, no. 4, pp. 15676–15680, Aug. 2024.
M. Ivanova, V. Tsenev, and V. Mikova, "An Approach for the Evaluation of a Measurement System: A Study on the Use of Machine Learning and Predictions," Engineering, Technology & Applied Science Research, vol. 13, no. 6, pp. 12342–12347, Dec. 2023.
A. Johnson, T. Pollard, and R. Mark, "MIMIC-III Clinical Database." PhysioNet, 2015.
Downloads
How to Cite
License
Copyright (c) 2025 Ashok Kumar Tella, S. R. Balasundaram

This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.