What does this research mean for the field?

While deep learning models show promising performance for predicting ICU readmissions, the current body of evidence is of poor quality due to high heterogeneity, risk of bias, and low reproducibility, hindering their clinical applicability. Novelty: ClaimNovelty.SYNTHESIS. Consensus alignment: ConsensusAlignment.NEUTRAL.

October 17, 2025Critical Care4 citationsOpen Access

Deep learning models for ICU readmission prediction: a systematic review and meta-analysis

EKEmanuele KoumantakisTorino e-district KRKonstantina RemoundouNational Technical University of Athens NCNicoletta ColombiUniversity of Turin

Structured PICO

Do deep learning models accurately predict ICU readmission?

Population

24 studies encompassing 49 deep learning models for ICU readmission prediction

Intervention

Deep learning models for ICU readmission prediction

Outcome

Model performance (AUROC) for predicting ICU readmissionsurrogate

Deep learning models show promising performance for predicting ICU readmissions but are limited by poor reproducibility, high risk of bias, and reliance on US-based datasets, hindering clinical applicability.

Abstract

Intensive Care Unit (ICU) readmissions are associated with increased morbidity, mortality, and healthcare costs. Therefore, determining an appropriate timing of ICU discharge is critical. In this context, deep learning (DL) approaches have attracted significant attention. We conducted a systematic review of studies developing or validating DL models for ICU readmission prediction, published up to March 4th, 2025, and indexed in PubMed, Embase, Scopus, and Web of Science. We summarised them along multiple dimensions, including outcome and population definition, DL architecture, reproducibility, generalizability, and explainability, and provided a meta-analytic estimate of model performance. We included 24 studies encompassing 49 DL models, predominantly trained on US-based datasets, and rarely subjected to external validation. There was considerable variability across study settings, including the definition and timeframe of the ICU readmission outcome, as well as DL architecture used, alongside a substantial risk of bias. Technical reproducibility and model interpretation were rare. A meta-analysis of AUROC values from 11 studies yielded a mean of 0.78 (95% CI = 0.72–0.84), with very high heterogeneity (I2 = 99.9%). Models targeting disease-specific ICU subpopulations achieved significantly higher performance (mean AUROC = 0.92, 95% CI = 0.89–0.95, p = 0.002), and substantially lower heterogeneity (I2 = 17.1%). DL models showed promising performances in predicting ICU readmissions, but exhibited several shortcomings, including low reproducibility, over-reliance on a few US-based datasets, and limited explainability. Additionally, the high heterogeneity and risk of bias limited our ability to assess their pooled performance through meta-analysis. Taken together, our observations suggest that the quality of the evidence regarding the application of DL approaches to ICU readmission prediction is poor, thus hindering their clinical applicability.

问 AI

Bookmark

View Full Paper