Medicine and Health

The predictive performance of artificial intelligence on the outcome of stroke: a systematic review and meta-analysis

Y. Yang, L. Tang, et al.

This innovative study conducted by Yujia Yang and colleagues reveals the promising accuracy of artificial intelligence models in predicting stroke outcomes, with a pooled AUC of 0.872. Discover how AI technologies, particularly SVM and Xgboost, can enhance the decision-making process for physicians in stroke prognosis.

00:00

Playback language: English

Index

Abstract

This study assessed the accuracy of artificial intelligence (AI) models in predicting stroke prognosis. Seven studies were included in a meta-analysis. The pooled area under the curve (AUC) was 0.872 (95% CI 0.862–0.881), indicating good predictive accuracy. Subgroup analysis showed varying AUCs across different AI algorithms (SVM, RF, LR, DL, Xgboost), with SVM and Xgboost performing best. AI models offer a valuable assistive tool for physicians in predicting stroke outcomes.

Publisher

Frontiers in Neuroscience

Published On

Sep 07, 2023

Authors

Yujia Yang, Li Tang, Yiting Deng, Xuzi Li, Anling Luo, Zhao Zhang, Li He, Cairong Zhu, Muke Zhou, Ni Zhang, Xia Zhang, Qifu Li

Related Publications

Explore these studies to deepen your understanding of the subject.

Medicine and Health

Systematic review and meta-analysis of performance of wearable artificial intelligence in detecting and predicting depression

A. Abd-alrazaq, R. Alsaad, et al.

Medicine and Health

The effect of exercise on blood concentrations of angiogenesis markers in older adults: a systematic review and meta-analysis

B. X. Song, L. Azhar, et al.

Psychology

The effects of mindfulness-based interventions on anxiety, depression, stress, and mindfulness in menopausal women: A systematic review and meta-analysis

Hl, Hz, et al.

Psychology

Learned Nocebo Effects on Cutaneous Sensations of Pain and Itch: A Systematic Review and Meta-analysis of Experimental Behavioral Studies on Healthy Humans

M. A. Thomaidou, J. S. Blythe, et al.

Listen, Learn & Level Up

Over 10,000 hours of research content in 25+ fields, available in 12+ languages.

No more digging through PDFs, just hit play and absorb the world's latest research in your language, on your time.

listen to research audio papers with researchbunny