AI prediction models for ICU readmission exhibited moderate-to-high predictive performance with a pooled AUC of 0.82 (95% CI 0.77-0.87), significantly outperforming traditional models.
Systematic Review
Do artificial intelligence prediction models improve predictive performance for readmission in critically ill patients compared to traditional models?
AI prediction models demonstrate moderate-to-high predictive performance for ICU readmission, outperforming traditional models, though current studies are limited by a high risk of bias.
Effect estimate: Pooled AUC (95% CI 0.77-0.87)
Background: Artificial intelligence (AI) prediction models can accurately identify high-risk populations by integrating multi-dimensional clinical data, providing decision support for doctors in formulating individualized discharge plans and optimizing follow-up intervention strategies, thereby reducing the risk of readmission from the source. Currently, the number of AI prediction models for readmission of critically ill patients is increasing, but the quality and applicability of these models in clinical practice and future research remain uncertain. Objective: To systematically evaluate published studies on AI prediction models for critically ill patients. Methods: This study conducted a computerized search of the CNKI, Wanfang Data, VIP, SinoMed, PubMed, Web of Science, Cochrane, and Embase databases, with the time range from 2020 to June 25, 2025. Information such as study design, data sources, outcome definitions, sample size, predictors, model development, and performance was extracted from the selected studies. The Prediction Model Risk of Bias Assessment Tool (PROBAST) checklist was used to evaluate the risk of bias and applicability. Results: A total of 387 studies were retrieved, and after screening, 31 studies with their 31 prediction models were included in this review. All studies developed risk prediction models for readmission of critically ill patients using artificial intelligence algorithms. The readmission risk of critically ill patients ranged from 1.3% to 13.7%. The most commonly used predictors were structured data. The reported area under the curve (AUC) ranged from 0.66 to 0.98. All studies had a high risk of bias, mainly due to poor reporting quality in the analysis domain and insufficient applicability. The pooled AUC of the 24 validation models was 0.82, with a 95% confidence interval of 0.77–0.87. Conclusion: These study results constitute a comprehensive set of high-quality evidence, demonstrating that AI prediction models exhibit moderate-to-high predictive performance and that their predictive performance is significantly higher than that of traditional prediction models. Patient or public contribution No Patient or Public Contribution. This Meta-analysis is based on the systematic review and statistical combination of the published clinical research data. The processes of research design, data extraction, and result interpretation did not involve the participation of patients or the public. Registration: The protocol for this study has been registered in PROSPERO (registration number: CRD42025637829).
Zheng et al. (Fri,) conducted a systematic review in Critically ill patients at risk of ICU readmission. Artificial intelligence (AI) prediction models vs. Traditional prediction models was evaluated on Predictive performance (Area Under the Curve / AUC) (Pooled AUC, 95% CI 0.77-0.87). AI prediction models for ICU readmission exhibited moderate-to-high predictive performance with a pooled AUC of 0.82 (95% CI 0.77-0.87), significantly outperforming traditional models.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: