Improving Cardiovascular Disease Prediction With Machine Learning Using Mental Health Data: A Prospective UK Biobank Study
Authors' conclusion
Incorporating mental health assessment data within an ensemble ML model results in a significantly improved, highly accurate, CVD prediction model, outperforming traditional risk factor prediction alone.
Study context
- Population
- UK Biobank subjects with normal health status and with cardiovascular disease (CVD) (hypertensive disease, ischaemic heart disease, HF, arrhythmias)
- Participants
- 375,145 subjects
- Comparison
- Traditional CVD risk factors alone vs traditional plus psychological risk factors
- Outcome
- Accuracy of ensemble ML model in predicting CVD
Methodological detailsensemble machine learning, UK Biobank
- Ensemble machine learning
- UK Biobank
Main finding
As reported in the abstract
CVD prediction accuracy of ensemble ML model
| Group | Accuracy |
|---|---|
| Traditional | 71.31% |
Traditional
Accuracy71.31%
Further findings
- Accuracy and robustness of the ensemble model outperformed all 5 constituent algorithms
Parts of this Brief are withheld: the automatic checks could not confirm them against the abstract.
Original publication
Improving Cardiovascular Disease Prediction With Machine Learning Using Mental Health Data: A Prospective UK Biobank Study. JACC Adv. Published 25 September 2024. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →