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

Summary

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 highest achieving (neural networks) algorithm predicted 4,998/7,404 cases (sensitivity 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.

Related articles

• The relationship between physical literacy and physical activity: A systematic review and meta- analysis

  This systematic review and meta-analysis investigates the correlation between physical literacy and physical activity, identifying potential moderators that may influence this relationship.

• GM26 · GOLD-STANDARD SERIES BASIC SCIENCE MODEL ANSWERS Chapter 1 - Cardiovascular Physiology

  This document provides model answers for a series of medical examination questions focused on cardiovascular physiology, formatted in the Cornell note-taking style. It includes detailed explanations of key concepts, diagrams, and clinical implications related to heart function and related topics.

• Practice Questions for Nursing

  This document consists of a comprehensive set of practice questions designed for nursing professionals, covering various concepts in nursing education, regulatory provisions, roles, and professional development.

• Foundations of Nursing Research

  This document consists of practice questions focused on various research methodologies, leadership styles, and administrative principles within the context of nursing. It aims to enhance understanding of the application of research in nursing practice and administrative decision-making.

• Anti-Infective Pharmacotherapy and Advanced Cardiovascular Pharmacotherapy

  This document covers critical topics in pharmacotherapy, including the management of infectious diseases, antibiotic principles, complications associated with drug therapies, and cardiovascular medications' effects and protocols. It aims to educate healthcare professionals on effective drug administration, potential side effects, and management strategies in various clinical scenarios.