Read-ICU: An Ensemble Deep Learning Model for ICU Readmission Prediction
DOI:
https://doi.org/10.54103/2282-0930/29400Abstract
INTRODUCTION
Intensive Care Unit (ICU) readmissions are linked to increased morbidity, mortality, and healthcare costs [1]. The correct timing of ICU discharge is critical to prevent these adverse outcomes. Traditional predictive models have limited accuracy, while deep learning (DL) models offer potential improvements by extracting richer information from multimodal electronic health record data [2].
OBJECTIVES
To enhance ICU readmission prediction task accuracy by developing READ-ICU, an ensemble DL model trained on harmonized multi-institutional data.
METHODS
We identified standardized, publicly available ICU datasets from different institutions and geographical regions. Existing pipelines to merge and pre-process the datasets were searched. A previously conducted systematic review and meta-analysis informed the selection of DL architectures, outcome definitions, and predictors [3]. Bayesian Model Averaging (BMA) was chosen to ensemble the retrieved DL models whose code was publicly available [4]. The area under the receiving operating curve (AUROC) served as the primary performance metric, which guided the training and fine-tuning process. To improve the explainability of the resulting model, we applied an explainable artificial intelligence (XAI) technique able to identify key predictors influencing model output. Analyses were conducted using Python v. 3.10.12.
RESULTS
We gained access to MIMIC-III, MIMIC-IV, the multi-center eICU US datasets, and the European AmsterdamUMCdb [6-9]. We harmonized the four datasets through the BlendedICU pipeline [10]. The 48-hour readmission interval was selected as the outcome measure due to its stronger association with ICU care quality [11]. Recurrent neural networks (RNNs), long short-term memory (LSTM) networks, and convolutional neural networks (CNNs) were retrieved from the selected articles and were integrated into the ensemble READ-ICU model. Key predictors included static variables (e.g., demographics, length of ICU stay, admission source, comorbidities) and time-dependent variables from the last 48 hours of ICU stay (e.g., vital signs, laboratory test results, diagnosis codes, medications), which improved predictive performance in previous models [12].
CONCLUSIONS
DL enables innovative predictive models that may outperform traditional prognostic tools for ICU readmissions. Our systematic review identified promising DL models and challenges, though further efforts are required to optimize performance through multimodal data integration. This study highlights the potential of using ensemble DL techniques, multi-institutional datasets, and XAI techniques to improve the prediction of important outcomes in critical care.
Downloads
References
1. Nates J.L., Nunnally M., Kleinpell R. et al., ICU Admission, Discharge, and Triage Guidelines: A Framework to Enhance Clinical Operations, Development of Institutional Policies, and Further Research. Crit Care Med, 2016 Aug; 44(8):1553–602. DOI: https://doi.org/10.1097/CCM.0000000000001856
2. Hu H., Li J., Ge H. et al. Prognostic models for unplanned intensive care unit readmission risk prediction: A systematic review and meta-analysis based on HSROC model. Nurs Crit Care, 2025 Mar; 30(2):e13306. DOI: https://doi.org/10.1111/nicc.13306
3. Koumantakis E., Visconti A., Berchialla P., Deep learning models for ICU re-admission prediction: a systematic review. PROSPERO 2025 CRD420251000813. Available from https://www.crd.york.ac.uk/PROSPERO/view/CRD420251000813. DOI: https://doi.org/10.1186/s13054-025-05642-x
4. Hoeting J.A., Madigan D., Raftery A.E. et al., Bayesian Model Averaging: A Tutorial. Statistical Science, 1999 Nov; 14(4):382-417. DOI: https://doi.org/10.1214/ss/1009212519
5. Ali S., Abuhmed T., El-Sappagh S. et al., Explainable Artificial Intelligence (XAI): What we know and what is left to attain Trustworthy Artificial Intelligence. Information Fusion, 2023 Nov; 99(3):101805. DOI: https://doi.org/10.1016/j.inffus.2023.101805
6. Johnson A.E., Pollard T.J., Shen L. et al., MIMIC-III, a freely accessible critical care database. Sci Data, 2016 May; 24(3):160035. DOI: https://doi.org/10.1038/sdata.2016.35
7. Johnson A.E., Bulgarelli L., Shen L. et al., MIMIC-IV, a freely accessible electronic health record dataset. Sci Data, 2023 Jan; 10(1):1. DOI: https://doi.org/10.1038/s41597-023-01945-2
8. Pollard T.J., Johnson A.E., Raffa J.D. et al., The eICU Collaborative Research Database, a freely available multi-center database for critical care research. Sci Data, 2018 Sep; 11(5):180178. DOI: https://doi.org/10.1038/sdata.2018.178
9. Thoral P.J., Peppink J.M., Driessen R.H. et al., Sharing ICU Patient Data Responsibly Under the Society of Critical Care Medicine/European Society of Intensive Care Medicine Joint Data Science Collaboration: The Amsterdam University Medical Centers Database (AmsterdamUMCdb) Example. Crit Care Med. 2021 Jun; 49(6):e563-e577. DOI: https://doi.org/10.1097/CCM.0000000000004916
10. Oliver M., Allyn J., Carencotte R. et al., Introducing the BlendedICU dataset, the first harmonized, international intensive care dataset. J Biomed Inform, 2023 Oct; 146:104502. DOI: https://doi.org/10.1016/j.jbi.2023.104502
11. Brown, S.E., Ratcliffe, S.J., Halpern, S.D., An empirical derivation of the optimal time interval for defining ICU readmissions. Med Care, 2013 Aug; 51(8):706–14. DOI: https://doi.org/10.1097/MLR.0b013e318293c2fa
12. Lin Y.W., Zhou Y., Faghri F. et al., Analysis and prediction of unplanned intensive care unit readmission using recurrent neural networks with long short-term memory. PLoS One, 2019 Jul;14(7):e0218942. DOI: https://doi.org/10.1371/journal.pone.0218942
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Emanuele Koumantakis , Konstantina Remoundou , Stavros Xynogalas , Ioanna Roussaki , Alessia Visconti , Paola Berchialla
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
