IDEAS home Printed from https://ideas.repec.org/a/plo/pone00/0174944.html
   My bibliography  Save this article

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

Author

Listed:
  • Stephen F Weng
  • Jenna Reps
  • Joe Kai
  • Jonathan M Garibaldi
  • Nadeem Qureshi

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 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.

Suggested Citation

  • Stephen F Weng & Jenna Reps & Joe Kai & Jonathan M Garibaldi & Nadeem Qureshi, 2017. "Can machine-learning improve cardiovascular risk prediction using routine clinical data?," PLOS ONE, Public Library of Science, vol. 12(4), pages 1-14, April.
    • Handle: RePEc:plo:pone00:0174944
    DOI: 10.1371/journal.pone.0174944
    as

    Download full text from publisher

    File URL: https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0174944
    Download Restriction: no
    File URL: https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0174944&type=printable
    Download Restriction: no
    File URL: https://libkey.io/10.1371/journal.pone.0174944?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    References listed on IDEAS

    as
    1. Roger Newson, 2006. "Confidence intervals for rank statistics: Somers' D and extensions," Stata Journal, StataCorp LLC, vol. 6(3), pages 309-334, September.
    2. Roger B. Newson, 2010. "Comparing the predictive powers of survival models using Harrell’s C or Somers’ D," Stata Journal, StataCorp LLC, vol. 10(3), pages 339-358, September.
    3. Roger Newson, 2006. "Confidence intervals for rank statistics: Percentile slopes, differences, and ratios," Stata Journal, StataCorp LLC, vol. 6(4), pages 497-520, December.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Gala, Kaushik & Schwab, Andreas & Mueller, Brandon A., 2024. "Star entrepreneurs on digital platforms: Heavy-tailed performance distributions and their generative mechanisms," Journal of Business Venturing, Elsevier, vol. 39(1).
    2. Ichiro Kunitsugu & Masayuki Okuda & Shinichi Sugiyama & Norikazu Yoshitake & Yukio Tanizawa & Satoshi Sasaki & Tatsuya Hobara, 2012. "Meat intake frequency and anemia in Japanese children and adolescents," Nursing & Health Sciences, John Wiley & Sons, vol. 14(2), pages 197-203, June.
    3. repec:plo:pmed00:1002096 is not listed on IDEAS
    4. Roger Newson, 2016. "The role of Somers's D in propensity modeling," United Kingdom Stata Users' Group Meetings 2016 01, Stata Users Group.
    5. Orth, Walter, 2012. "The predictive accuracy of credit ratings: Measurement and statistical inference," International Journal of Forecasting, Elsevier, vol. 28(1), pages 288-296.
    6. Marszalec, Daniel, 2018. "Fear not the simplicity - An experimental analysis of auctions for complements," Journal of Economic Behavior & Organization, Elsevier, vol. 152(C), pages 81-97.
    7. Jeannette Brosig‐Koch & Heike Hennig‐Schmidt & Nadja Kairies‐Schwarz & Daniel Wiesen, 2017. "The Effects of Introducing Mixed Payment Systems for Physicians: Experimental Evidence," Health Economics, John Wiley & Sons, Ltd., vol. 26(2), pages 243-262, February.
    8. Navarro, Noemí & Veszteg, Róbert F., 2020. "On the empirical validity of axioms in unstructured bargaining," Games and Economic Behavior, Elsevier, vol. 121(C), pages 117-145.
    9. Roger Newson, 2019. "Bland–Altman plots, rank parameters, and calibration ridit splines," London Stata Conference 2019 01, Stata Users Group.
    10. Dirk Tasche, 2009. "Estimating discriminatory power and PD curves when the number of defaults is small," Papers 0905.3928, arXiv.org, revised Mar 2010.
    11. Roger Newson, 2014. "Easy-to-use packages for estimating rank and spline parameters," United Kingdom Stata Users' Group Meetings 2014 01, Stata Users Group.
    12. Hanna Karolina Szymborska, 2018. "Household wealth structures and position in the income distribution – econometric analysis for the USA, 1989-2013," Working Papers PKWP1806, Post Keynesian Economics Society (PKES).
    13. Ahdesmäki Miika & Lancashire Lee & Proutski Vitali & Wilson Claire & Davison Timothy S. & Harkin D. Paul & Kennedy Richard D., 2013. "Model selection for prognostic time-to-event gene signature discovery with applications in early breast cancer data," Statistical Applications in Genetics and Molecular Biology, De Gruyter, vol. 12(5), pages 619-635, October.
    14. Roger Newson, 2015. "Somers' D: A common currency for associations," United Kingdom Stata Users' Group Meetings 2015 01, Stata Users Group.
    15. Löschel, Andreas & Sturm, Bodo & Uehleke, Reinhard, 2017. "Revealed preferences for voluntary climate change mitigation when the purely individual perspective is relaxed – evidence from a framed field experiment," Journal of Behavioral and Experimental Economics (formerly The Journal of Socio-Economics), Elsevier, vol. 67(C), pages 149-160.
    16. Alice Guerra & Enya Turrini, 2025. "Social norms on unethical behaviors in the workplace: a lab experiment," International Review of Economics, Springer;Happiness Economics and Interpersonal Relations (HEIRS), vol. 72(1), pages 1-25, June.
    17. Alena MINÃ ROVÃ, 2012. "Evaluation Of Dependence Of Occurrence Of Risk Events In Logistics On Risk Factors By Means Of Somers' D Coefficient," Journal of Applied Economic Sciences, Spiru Haret University, Faculty of Financial Management and Accounting Craiova, vol. 7(1(19)/ Sp), pages 73-86.
    18. Cogneau, Philippe & Hübner, Georges, 2015. "The prediction of fund failure through performance diagnostics," Journal of Banking & Finance, Elsevier, vol. 50(C), pages 224-241.
    19. repec:plo:pone00:0085466 is not listed on IDEAS
    20. Diego Rios-Zertuche & Jose Cuchilla & Paola Zúñiga-Brenes & Bernardo Hernández & Patricia Jara & Ali H. Mokdad & Emma Iriarte, 2017. "Alcohol abuse and other factors associated with risky sexual behaviors among adolescent students from the poorest areas in Costa Rica," International Journal of Public Health, Springer;Swiss School of Public Health (SSPH+), vol. 62(2), pages 271-282, March.
    21. Marco Lollobrigida & Livia Ottolenghi & Denise Corridore & Gianluca Pingitore & Cecilia Damiano & Giorgio Serafini & Alberto De Biase, 2022. "Student Evaluation of Distance Learning during the COVID-19 Pandemic: A Cross-Sectional Survey on Medical, Dental, and Healthcare Students at Sapienza University of Rome," IJERPH, MDPI, vol. 19(16), pages 1-10, August.
    22. Daniel Marszalec, 2016. "Auctions For Complements –An Experimental Analysis," CIRJE F-Series CIRJE-F-1018, CIRJE, Faculty of Economics, University of Tokyo.

    More about this item

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:plo:pone00:0174944. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: plosone (email available below). General contact details of provider: https://journals.plos.org/plosone/ .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.