Can machine-learning improve cardiovascular risk prediction using routine clinical data
Background Current approaches to predict cardiovascular risk fail to identify many people who would benefit from preventive treatment, while others receive unnecessary intervention. Machine-learning offers opportunity to improve accuracy by exploiting complex interactions between risk factors. We a...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Published: |
Public Library of Science
2017
|
| Online Access: | https://eprints.nottingham.ac.uk/41609/ |
| _version_ | 1848796314462060544 |
|---|---|
| author | Weng, Stephen Reps, Jenna M. Kai, Joe Garibaldi, Jonathan M. Quereshi, Nadeem |
| author_facet | Weng, Stephen Reps, Jenna M. Kai, Joe Garibaldi, Jonathan M. Quereshi, Nadeem |
| author_sort | Weng, Stephen |
| building | Nottingham Research Data Repository |
| collection | Online Access |
| description | Background
Current approaches to predict cardiovascular risk fail to identify many people who would benefit from preventive treatment, while others receive unnecessary intervention. Machine-learning offers opportunity to improve accuracy by exploiting complex interactions between risk factors. We assessed whether machine-learning can improve cardiovascular risk prediction.
Methods
Prospective cohort study using routine clinical data of 378,256 patients from UK family practices, free from cardiovascular disease at outset. Four machine-learning algorithms (random forest, logistic regression, gradient boosting machines, neural networks) were compared to an established algorithm (American College of Cardiology guidelines) to predict first cardiovascular event over 10-years. Predictive accuracy was assessed by area under the ‘receiver operating curve’ (AUC); and sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) to predict 7.5% cardiovascular risk (threshold for initiating statins).
Findings
24,970 incident cardiovascular events (6.6%) occurred. Compared to the established risk prediction algorithm (AUC 0.728, 95% CI 0.723–0.735), machine-learning algorithms improved prediction: random forest +1.7% (AUC 0.745, 95% CI 0.739–0.750), logistic regression +3.2% (AUC 0.760, 95% CI 0.755–0.766), gradient boosting +3.3% (AUC 0.761, 95% CI 0.755–0.766), neural networks +3.6% (AUC 0.764, 95% CI 0.759–0.769). The 78 highest achieving (neural networks) algorithm predicted 4,998/7,404 cases (sensitivity
79 67.5%, PPV 18.4%) and 53,458/75,585 non-cases (specificity 70.7%, NPV 95.7%), correctly predicting 355 (+7.6%) more patients who developed cardiovascular disease compared to the established algorithm.
Conclusions
Machine-learning significantly improves accuracy of cardiovascular risk prediction, increasing the number of patients identified who could benefit from preventive treatment, while avoiding unnecessary treatment of others. |
| first_indexed | 2025-11-14T19:46:01Z |
| format | Article |
| id | nottingham-41609 |
| institution | University of Nottingham Malaysia Campus |
| institution_category | Local University |
| last_indexed | 2025-11-14T19:46:01Z |
| publishDate | 2017 |
| publisher | Public Library of Science |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | nottingham-416092020-05-04T18:40:50Z https://eprints.nottingham.ac.uk/41609/ Can machine-learning improve cardiovascular risk prediction using routine clinical data Weng, Stephen Reps, Jenna M. Kai, Joe Garibaldi, Jonathan M. Quereshi, Nadeem Background Current approaches to predict cardiovascular risk fail to identify many people who would benefit from preventive treatment, while others receive unnecessary intervention. Machine-learning offers opportunity to improve accuracy by exploiting complex interactions between risk factors. We assessed whether machine-learning can improve cardiovascular risk prediction. Methods Prospective cohort study using routine clinical data of 378,256 patients from UK family practices, free from cardiovascular disease at outset. Four machine-learning algorithms (random forest, logistic regression, gradient boosting machines, neural networks) were compared to an established algorithm (American College of Cardiology guidelines) to predict first cardiovascular event over 10-years. Predictive accuracy was assessed by area under the ‘receiver operating curve’ (AUC); and sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) to predict 7.5% cardiovascular risk (threshold for initiating statins). Findings 24,970 incident cardiovascular events (6.6%) occurred. Compared to the established risk prediction algorithm (AUC 0.728, 95% CI 0.723–0.735), machine-learning algorithms improved prediction: random forest +1.7% (AUC 0.745, 95% CI 0.739–0.750), logistic regression +3.2% (AUC 0.760, 95% CI 0.755–0.766), gradient boosting +3.3% (AUC 0.761, 95% CI 0.755–0.766), neural networks +3.6% (AUC 0.764, 95% CI 0.759–0.769). The 78 highest achieving (neural networks) algorithm predicted 4,998/7,404 cases (sensitivity 79 67.5%, PPV 18.4%) and 53,458/75,585 non-cases (specificity 70.7%, NPV 95.7%), correctly predicting 355 (+7.6%) more patients who developed cardiovascular disease compared to the established algorithm. Conclusions Machine-learning significantly improves accuracy of cardiovascular risk prediction, increasing the number of patients identified who could benefit from preventive treatment, while avoiding unnecessary treatment of others. Public Library of Science 2017-04-04 Article PeerReviewed Weng, Stephen, Reps, Jenna M., Kai, Joe, Garibaldi, Jonathan M. and Quereshi, Nadeem (2017) Can machine-learning improve cardiovascular risk prediction using routine clinical data. PLoS ONE, 12 (4). e0174944/1- e0174944/14. ISSN 1932-6203 http://journals.plos.org/plosone/article?id=10.1371/journal.pone.0174944 doi:10.1371/journal.pone.0174944 doi:10.1371/journal.pone.0174944 |
| spellingShingle | Weng, Stephen Reps, Jenna M. Kai, Joe Garibaldi, Jonathan M. Quereshi, Nadeem Can machine-learning improve cardiovascular risk prediction using routine clinical data |
| title | Can machine-learning improve cardiovascular risk prediction using routine clinical data |
| title_full | Can machine-learning improve cardiovascular risk prediction using routine clinical data |
| title_fullStr | Can machine-learning improve cardiovascular risk prediction using routine clinical data |
| title_full_unstemmed | Can machine-learning improve cardiovascular risk prediction using routine clinical data |
| title_short | Can machine-learning improve cardiovascular risk prediction using routine clinical data |
| title_sort | can machine-learning improve cardiovascular risk prediction using routine clinical data |
| url | https://eprints.nottingham.ac.uk/41609/ https://eprints.nottingham.ac.uk/41609/ https://eprints.nottingham.ac.uk/41609/ |