Can machine-learning improve cardiovascular risk prediction using routine clinical data

Weng, Stephen and Reps, Jenna M. and Kai, Joe and 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

[img]
Preview
PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
Available under Licence Creative Commons Attribution.
Download (763kB) | Preview

Abstract

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.

Item Type: Article
Schools/Departments: University of Nottingham, UK > Faculty of Medicine and Health Sciences > School of Medicine > Division of Primary Care
Identification Number: 10.1371/journal.pone.0174944
Depositing User: Eprints, Support
Date Deposited: 28 Mar 2017 11:47
Last Modified: 06 Apr 2017 04:29
URI: http://eprints.nottingham.ac.uk/id/eprint/41609

Actions (Archive Staff Only)

Edit View Edit View