A Multi-Dimensional Machine Learning Approach For Cardiovascular Disease Prediction In The UK Biobank Study
Hernandez-Morante, J. J.; Murcia-Garcia, E.; Martinez-Cortes, C.; Piernas, C.; Perez-Sanchez, H.
Show abstract
Cardiovascular diseases (CVD) are complex disorders involving the impaired function of blood vessels or the heart. Several risk factors contribute to CVD, including diet, body composition and physical activity. We developed an interpretable machine learning model integrating nongenetic factors from 502,134 UK Biobank participants, of whom 53,378 experienced a CVD event over eighteen years of follow-up. Age, cystatin C, and self-perceived health status emerged as the most relevant predictors of CVD. By combining these variables into a multidimensional model, we achieved excellent predictive performance, with an area under the ROC curve of 0.99 and both sensitivity and specificity above 0.97 in the validation cohort. Although cardiovascular events arise from multiple factors, our results show that data integration and machine learning can accurately predict individual risk using simple measurements. This approach could also support the prediction of other cardiovascular outcomes and aid personalized risk assessment and preventive care.
Matching journals
The top 7 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Metabolomics data improve 10-year cardiovascular risk prediction with the SCORE2 algorithm for the general population without cardiovascular disease or diabetes 96%
- Large-scale plasma proteomics in the UK Biobank modestly improves prediction of major cardiovascular events in a population without previous cardiovascular disease 93%
- Joint association of genetic risk and accelerometer-based step count with cardiovascular disease: a UK-Biobank cohort study 93%
Similar papers in this journal
- Estimation of Life’s Essential 8 Score with Incomplete Data of Individual Metrics 94%
- Polygenic risk, lifestyle, and cardiovascular mortality: a prospective population-based UK Biobank study 93%
- Development and validation of a cardiovascular diseases risk prediction model for Chinese males (CVDMCM) 92%
Similar papers in this journal
- Environment-wide association study (EWAS) on cardiometabolic traits: A systematic assessment of the association of lifestyle variables on a longitudinal setting 96%
- A multi-omics study of circulating phospholipid markers of blood pressure 95%
- Can machine learning improve risk prediction of incident hypertension? An internal method comparison and external validation of the Framingham risk model using HUNT Study data 94%
Similar papers in this journal
- The association between clonal hematopoiesis driver mutations, immune cell function and the vasculometabolic complications of obesity 95%
- Walking pace optimizes conventional cardiovascular disease risk prediction models among vulnerable subpopulations: a prospective cohort study 94%
- Effects of Age and Sex on Systemic Inflammation and Cardiometabolic Function in Individuals with Type 2 Diabetes 94%
Similar papers in this journal
- Using ECG Machine Learning for Detection of Cardiovascular Disease in African American Men and Women: the Jackson Heart Study 92%
- Accelerometer-derived sleep onset timing and cardiovascular disease incidence: a UK Biobank cohort study 91%
- Development and Multinational Validation of an Ensemble Deep Learning Algorithm for Detecting and Predicting Structural Heart Disease Using Noisy Single-lead Electrocardiograms 91%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.