Can a computer model predict heart disease deaths?

Original Title

Statins and risk of incident diabetes: a collaborative meta-analysis of randomised statin trials.

Not medical advice. For informational purposes only. Always consult a healthcare professional. Terms

Summary

Scientists built a computer model to guess how likely people are to die from heart disease or any cause over 10 years using known risk factors.

Sign up to see full results

Get access to research results, context, and detailed analysis.

Surprising Findings

ROC analysis, typically used for diagnostic tests, was successfully applied to validate a long-term disease simulation model.

Most disease models rely only on survival curves; using ROC AUC (a measure of individual risk discrimination) is rare and innovative in this context.

Practical Takeaways

Policymakers and health systems could use models like CVD PREDICT to prioritize prevention programs for high-risk populations.

medium confidence

Unlock Full Study Analysis

Sign up free to access quality scores, evidence strength analysis, and detailed methodology breakdowns.

0%
Lower QualityOverall Score

Publication

Journal

Lancet

Year

2010

Authors

N. Sattar, D. Preiss, Heather Murray, P. Welsh, B. Buckley, A. de Craen, S. Seshasai, John J McMurray, Dilys J. Freeman, J. Jukema, Peter W Macfarlane, C. J. Packard, D. Stott, R. Westendorp, James Shepherd, Barry R Davis, S. Pressel, R. Marchioli, R. Marfisi, Aldo P Maggioni, L. Tavazzi, G. Tognoni, J. Kjekshus, T. Pedersen, T. Cook, Antonio M. Gotto, Michael Clearfield, J. R. Downs, Haruo Nakamura, Yasuo Ohashi, Kyoichi Mizuno, Kausik K. Ray, Ian Ford

2154 citations
Analysis v1