Machine learning based prediction models for first stroke in community primary care: a systematic review and meta-analysis
Zijiao Zhang, Yuru Zhang, Zheng Li, Chenghua Tian, Jun Liang, Jun Xie, Jianbo Lei · 2026
Read Machine learning based prediction models for first stroke in community primary care: a systematic review and meta-analysis by Zijiao Zhang, Yuru Zhang, Zheng Li, Chenghua Tian, Jun Liang, Jun Xie, Jianbo Lei (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13540839.txt.
Description
Zijiao Zhang and six colleagues review, in a 2026 meta-analysis, whether machine learning predicts a first stroke in community primary care better than older statistical models. Stroke prevention depends on spotting high-risk people early in ordinary clinics.
Forty-three studies holding ninety-three models met the criteria. Traditional Cox regression was the commonest approach, and its pooled accuracy matched or beat the machine learning entries, including random forests and gradient boosting. Three quarters of the studies carried a high risk of bias, and applicability to real community care raised concerns in a fifth. The authors conclude that machine learning's clinical value here remains unproven.
Catalog record
| CREATOR | Zijiao Zhang, Yuru Zhang, Zheng Li, Chenghua Tian, Jun Liang, Jun Xie, Jianbo Lei |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 29848 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |