Related Experiment Video
Updated: Jun 24, 2026
09:10
Determining the Functional Status of the Corticospinal Tract Within One Week of Stroke
Published on: February 22, 2020
Machine learning based prediction models for first stroke in community primary care: a systematic review and
Zijiao Zhang1, Yuru Zhang1, Zheng Li2
1School of Public Health, Southwest Medical University, No.1, Section 1, Xianglin Road, Longmatan District, Sichuan, 646000, China.
BMC Medical Informatics and Decision Making
|June 23, 2026
Summary
Machine learning models for first-stroke risk prediction show no significant advantage over traditional methods in community healthcare. Further research is needed for standardized validation and real-world clinical analysis to improve stroke prevention.
Area of Science:
- Medical Informatics
- Public Health
- Cardiovascular Research
Background:
- Stroke is a leading global cause of death and disability, with a rising burden in low- and middle-income countries.
- Accurate prediction of first-stroke events is critical for effective prevention strategies.
- The clinical utility of artificial intelligence (AI) and machine learning (ML) models in primary community healthcare for stroke risk prediction remains largely unverified.
Purpose of the Study:
- To systematically review and analyze the application of algorithms, particularly ML-based ones, in first-stroke risk prediction models within community settings.
- To assess the performance and clinical utility of various predictive models in primary care.
Main Methods:
- A comprehensive literature search was conducted in PubMed, EMBASE, and the Cochrane Library up to June 30, 2024.
- Studies developing or validating multivariable stroke risk models for primary care were included.
- Meta-analysis of AUC/C-statistic values with 95% confidence intervals was performed to evaluate model performance.
Main Results:
- A total of 43 studies with 93 models were analyzed; Cox regression was the most common traditional method.
- Machine learning models, including logistic regression, random forest, and eXtreme Gradient Boosting, showed comparable performance to traditional models (pooled AUCs ranging from 0.76 to 0.77).
- A high risk of bias (76.7%) and concerns regarding applicability to community settings (20.9%) were noted in the included studies; ML models did not outperform traditional regression models.
Conclusions:
- The clinical utility of ML models for first-stroke risk prediction in community primary healthcare is currently unverified.
- Current ML models offer no significant advantage over traditional regression methods and face challenges in innovation, standardization, and validation.
- Methodological flaws and applicability concerns necessitate caution; future research should prioritize standardized validation and real-world clinical analysis for effective stroke prevention tools.