EUVIMEDEUVIMED entdecken
Systematische ÜbersichtMetaanalyseOpen Access

Predictive Value of Machine Learning for Poststroke Mortality Risk: Systematic Review and Meta-Analysis

Vorhersagekraft von Machine Learning für die Mortalität nach Schlaganfall: systematische Übersicht und Metaanalyse

Yujie Chen iD, Zhujing Ou iD, Yiting Deng iD, Anling Luo iD, Xuzi Li iD, Yujia Yang iD, Qin Yang iD, Xintong Wu iD, Muke Zhou iD

Journal of Medical Internet Research · 02.04.2026 · 28 · e83821

DOI: 10.2196/83821 ↗

Auf einen Blick

68 Studien zeigen, dass ML-basierte Modelle die Mortalität nach Schlaganfall vorhersagen können. Die externe Validierung ergab für die stationäre und außerstationäre Mortalität C-Index-Werte von 0,727 bzw. 0,847.

Fragestellung

Wie gut sagt Machine Learning die Mortalität nach Schlaganfall voraus?

Methode

Systematische Übersicht und Metaanalyse; Suche in Cochrane Library, PubMed, Embase und Web of Science bis 23. Juni 2025; Risiko-bias mit PROBAST; random-effects, Hartung-Knapp-Sidik-Jonkman.

Ergebnisse

68 Studien: 23 zu stationärer und 45 zu außerstationärer Mortalität; 75 Modelle und 43 externe Validierungen. Externe Validierung: C-Index 0,727 (95 %-KI 0,677–0,781; 95 %-PI 0,521–1,000) bzw. 0,847 (95 %-KI 0,808–0,887; 95 %-PI 0,750–0,956).

Einschränkungen

Starke Heterogenität und relativ hohes Bias-Risiko; die Leistungsfähigkeit kann je nach Setting variieren.

Schlussfolgerung der Autor:innen

ML-basierte Vorhersagen der Schlaganfallmortalität sind laut Autor:innen machbar. ML kann als Hilfsmittel zur Identifikation von Hochrisikogruppen dienen; vor breiter Anwendung wird externe Validierung empfohlen.

Kernaussagen

  • 68 Studien mit 75 Vorhersagemodellen und 43 externen Validierungen
  • Externe Validierung: C-Index 0,727 und 0,847
  • Heterogenität und Bias-Risiko begrenzen die Übertragbarkeit

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

Kurz gefasst

Systematische Übersicht in der Zeitschrift Journal of Medical Internet Research, online erschienen am 02.04.2026. Verfasst von Yujie Chen und 8 weiteren Autor:innen. Beteiligte Einrichtung: Department of Neurology, West China Hospital, Sichuan University, Chengdu, China. Hauptthemen laut MEDLINE: Machine Learning, Stroke. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 142 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

Auf einen BlickAbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

People with stroke face a high mortality risk, and an accurate prediction model is essential to the guidance of clinical decision-making in this population. Recently, with growing attention paid to machine learning (ML) in stroke care, some researchers have investigated the effectiveness of ML in predicting the mortality risk in stroke. However, systematic evidence is still lacking for its effectiveness.

Objective

This systematic review aims to evaluate the value of ML in predicting the stroke mortality risk. The findings are expected to offer an evidence-based basis for developing and assessing clinical risk prediction tools.

Methods

A search was made in Cochrane Library, PubMed, Embase, and Web of Science up to June 23, 2025, and studies that reported a complete performance of ML in predicting stroke mortality were included. Studies with only risk factors analyzed were excluded. The risk of bias of the included studies was assessed using PROBAST (Prediction model Risk of Bias Assessment Tool). Pooled risk ratios with 95% CIs and prediction intervals (PIs) were derived using the Hartung-Knapp-Sidik-Jonkman method under a random-effects model. Subgroup analyses were also conducted by model type, stroke type, patient source, and treatment background. Moreover, a metaregression was conducted on the C-index for out-of-hospital mortality at different time points to explore the influence of time factors on the model’s predictive performance.

Results

Sixty-eight studies were included (23 predicting in-hospital mortality and 45 predicting out-of-hospital mortality), describing the development of 75 prediction models and 43 external validations. The follow-up period was 1 month to 15 years. For predicting in-hospital mortality, the external validation set had a pooled C-index of 0.727 (95% CI 0.677-0.781, 95% PI 0.521-1.000), with sensitivity and specificity of 0.64 (95% CI 0.57-0.70) and 0.74 (95% CI 0.70-0.77), respectively. For predicting out-of-hospital mortality, the pooled C-index was 0.847 (95% CI 0.808-0.887, 95% PI 0.750-0.956) in the external validation set, with sensitivity and specificity of 0.71 (95% CI 0.55-0.82) and 0.76 (95% CI 0.74-0.78), respectively. Comparatively, the overall pooled C-indexes were 0.788 (95% CI 0.766-0.810, 95% PI 0.621-0.999) and 0.812 (95% CI 0.798-0.826, 95% PI 0.693-0.952), respectively. The metaregression revealed a gradual decline in the predictive performance of the overall model and logistic regression model alone, whereas a random forest model maintained sustained performance. Age, National Institutes of Health Stroke Scale score, and stroke-related complications were the most frequently used variables for modeling.

Conclusions

This is the first meta-analysis to demonstrate that ML-based prediction of stroke mortality is feasible. The performance of ML supports its role as an auxiliary tool for identifying high-risk populations, thereby optimizing clinical monitoring and resource allocation. However, due to substantial heterogeneity and a relatively high risk of bias in available studies, caution is warranted in real-world application. The effectiveness of ML may vary across settings, and external validation is recommended before broader implementation. Trial Registration PROSPERO CRD420251086321; https://www.crd.york.ac.uk/PROSPERO/view/CRD420251086321

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningStrokeHumansPredictive Learning ModelsRisk Assessment

Stichwörter der Autor:innen

artificial intelligencelogistic regressionmortalityprediction modelprognosisstroke

Autor:innen und Institutionen

  • Department of Neurology, West China Hospital, Sichuan University, Chengdu, China.

ORCID-Profile: Yujie Chen, Zhujing Ou, Yiting Deng, Anling Luo, Xuzi Li, Yujia Yang, Qin Yang, Xintong Wu, Muke Zhou

Zitieren

APA

Chen, Y., Ou, Z., Deng, Y., Luo, A., Li, X., Yang, Y., Yang, Q., Wu, X., & Zhou, M. (2026). Predictive Value of Machine Learning for Poststroke Mortality Risk: Systematic Review and Meta-Analysis. Journal of Medical Internet Research, 28, e83821. https://doi.org/10.2196/83821

Vancouver

Chen Y, Ou Z, Deng Y, Luo A, Li X, Yang Y, et al. Predictive Value of Machine Learning for Poststroke Mortality Risk: Systematic Review and Meta-Analysis. Journal of Medical Internet Research. 2026;28:e83821. doi:10.2196/83821

BibTeX
@article{Chen2026,
  author = {Chen, Yujie and Ou, Zhujing and Deng, Yiting and Luo, Anling and Li, Xuzi and Yang, Yujia and Yang, Qin and Wu, Xintong and Zhou, Muke},
  title = {Predictive Value of Machine Learning for Poststroke Mortality Risk: Systematic Review and Meta-Analysis},
  journal = {Journal of Medical Internet Research},
  year = {2026},
  volume = {28},
  pages = {e83821},
  doi = {10.2196/83821}
}
Kostenlos starten →