EUVIMEDAtrasti EUVIMED
Systematische ÜbersichtMetaanalyseOpen access

The Predictive Value of Machine Learning for Postoperative Delirium in Cardiac Surgery: Systematic Review and Meta-Analysis

Der Vorhersagewert von Machine Learning für postoperatives Delir nach Herzchirurgie: systematische Übersicht und Metaanalyse

Yi Guo, Hong Xu, Ankui Wang, Mingming Zhang, Shuai Zhang, Peng Xie

Journal of Medical Internet Research · 2026-02-23 · 28 · e72304-e72304

DOI: 10.2196/72304 ↗

Auf einen Blick

28 Studien mit 80.143 Patient:innen untersuchten ML-basierte Vorhersage für postoperatives Delir nach Herzchirurgie. In Validierungsdatensätzen zeigte sich eine gute Vorhersageleistung.

Fragestellung

Wie gut sagen Machine-Learning-Modelle ein postoperatives Delir nach Herzchirurgie vorher?

Methode

Systematische Übersicht und Metaanalyse; Suche in PubMed, Cochrane Library, Embase und Web of Science bis 30. August 2024; Biasbewertung mit Prediction Model Bias Risk Assessment Tool.

Ergebnisse

28 Originalstudien mit 80.143 Patient:innen, davon 6.326 mit POD. In Validierungsdatensätzen: c-index 0,805 (95 %-KI 0,759–0,852), Sensitivität 0,72 (95 %-KI 0,65–0,79), Spezifität 0,78 (95 %-KI 0,71–0,83).

Einschränkungen

Begrenzte Zahl an Studien und Validierungsansätzen; Ergebnisse sollten vorsichtig interpretiert werden.

Schlussfolgerung der Autor:innen

ML-basierte Vorhersageinstrumente für POD nach Herzchirurgie zeigen eine vielversprechende Leistung, die Befunde sollten aber vorsichtig interpretiert werden.

Kernaussagen

  • 28 Studien mit 80.143 Patient:innen wurden eingeschlossen
  • Validierungsdatensätze: c-index 0,805
  • Die Autor:innen sehen die Evidenz wegen begrenzter Studienzahl als vorsichtig zu bewerten an

Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.

At a glance

Systematische Übersicht in Journal of Medical Internet Research, published online on 2026-02-23. Written by Yi Guo and 5 co-authors. Institution: Department of Anesthesiology, Norinco General Hospital, Xi'an, China. Major MEDLINE topics: Machine Learning, Delirium, Cardiac Surgical Procedures, Postoperative Complications. Cited 3 times so far (Crossref); 41 references. The full text is freely available in PubMed Central.

Auf einen BlickSantraukaSubjectsBibliografiniai duomenysCiteRelated studies

Abstract (original language)

Background

Postoperative delirium (POD) following cardiac surgery is a severe complication, and early identification of delirium risk remains a challenge in clinical practice. While machine learning (ML) has garnered increasing attention in health care applications, effective early prediction tools remain limited in current clinical practice. Recent investigations have explored the effectiveness of ML-based methods for identifying the risk of POD in patients undergoing cardiac surgery. However, more evidence is required to validate the feasibility of these methods.

Objectives

This study aims to ascertain the performance of ML in identifying the risk of POD following cardiac surgery, providing evidence for the development or updating of future ML-based assessment tools.

Methods

A comprehensive literature search was conducted across 4 databases—PubMed, the Cochrane Library, Embase, and Web of Science—through August 30, 2024, to identify studies investigating individual POD risk prediction using ML approaches and nomograms. The risk of bias of the models in the included studies was assessed leveraging the Prediction Model Bias Risk Assessment Tool. Subgroup analyses were performed based on datasets, validation methods, study types, risk of bias, and model types.

Results

The analysis incorporated 28 original studies comprising 80,143 patients undergoing cardiac surgery, of whom 6326 developed POD. Meta-analysis revealed that, in validation datasets, the c-index, sensitivity, and specificity for delirium prediction reached 0.805 (95% CI 0.759‐0.852), 0.72 (95% CI 0.65‐0.79), and 0.78 (95% CI 0.71‐0.83), respectively. Logistic regression was the primary modeling method. In validation datasets, the c-index, sensitivity, and specificity reached 0.773 (95% CI 0.724‐0.823), 0.73 (95% CI 0.64‐0.80), and 0.70 (95% CI 0.65‐0.74), respectively.

Conclusions

ML-based prediction tools for POD following cardiac surgery demonstrate promising performance. However, the limited number of studies and validation approaches necessitate cautious interpretation of these findings. Future multicenter studies are warranted to develop more robust ML-based prediction tools, enabling precise risk stratification and targeted preventive interventions for POD.

Subjects

MeSH terms (MEDLINE)

Machine LearningDeliriumCardiac Surgical ProceduresPostoperative ComplicationsHumansPredictive Learning ModelsPrediction Algorithms

Author keywords

cardiac surgerydeliriummachine learningpredictive modelsystematic review

Authors and institutions

  • Department of Anesthesiology, Norinco General Hospital, Xi'an, China.
  • Department of Operating Room, Norinco General Hospital, Xi'an, China.
  • Department of Hepatobiliary and Vascular Surgery, Norinco General Hospital, No. 12, Zhangba East Road, Yanta District, Xi'an, China, 86 17792723769.

Cite

APA

Guo, Y., Xu, H., Wang, A., Zhang, M., Zhang, S., & Xie, P. (2026). The Predictive Value of Machine Learning for Postoperative Delirium in Cardiac Surgery: Systematic Review and Meta-Analysis. Journal of Medical Internet Research, 28, e72304-e72304. https://doi.org/10.2196/72304

Vancouver

Guo Y, Xu H, Wang A, Zhang M, Zhang S, Xie P. The Predictive Value of Machine Learning for Postoperative Delirium in Cardiac Surgery: Systematic Review and Meta-Analysis. Journal of Medical Internet Research. 2026;28:e72304-e72304. doi:10.2196/72304

BibTeX
@article{Guo2026,
  author = {Guo, Yi and Xu, Hong and Wang, Ankui and Zhang, Mingming and Zhang, Shuai and Xie, Peng},
  title = {The Predictive Value of Machine Learning for Postoperative Delirium in Cardiac Surgery: Systematic Review and Meta-Analysis},
  journal = {Journal of Medical Internet Research},
  year = {2026},
  volume = {28},
  pages = {e72304--e72304},
  doi = {10.2196/72304}
}
Start for free →