. 2021 Mar 19;18(6):3187.

doi: 10.3390/ijerph18063187.

Predicting Australian Adults at High Risk of Cardiovascular Disease Mortality Using Standard Risk Factors and Machine Learning

Shelda Sajeev^{1

2}, Stephanie Champion¹, Alline Beleigoli^{1

3}, Derek Chew⁴, Richard L Reed⁴, Dianna J Magliano^{5

6}, Jonathan E Shaw^{5

6

7}, Roger L Milne^{8

9

10}, Sarah Appleton^{11

12}, Tiffany K Gill¹², Anthony Maeder¹

Affiliations

¹ Flinders Digital Health Research Centre, College of Nursing & Health Sciences, Flinders University, Adelaide SA 5001, Australia.
² Chifley Business School, Torrens University, Australia, Adelaide, SA 5000, Australia.
³ Caring Futures Institute, Flinders University, Adelaide, SA 5001, Australia.
⁴ College of Medicine and Public Health, Flinders University, Adelaide, SA 5001, Australia.
⁵ Baker Heart and Diabetes Institute, Melbourne, VIC 3004, Australia.
⁶ School of Public Health and Preventive Medicine, Monash University, Melbourne, VIC 3004, Australia.
⁷ School of Life Sciences, La Trobe University, Melbourne, VIC 3086, Australia.
⁸ Cancer Epidemiology Division, Cancer Council Victoria, 615 St Kilda Road, Melbourne, VIC 3004, Australia.
⁹ Centre for Epidemiology and Biostatistics, Melbourne School of Population and Global Health, The University of Melbourne, 207 Bouverie Street, Melbourne, VIC 3010, Australia.
¹⁰ Precision Medicine, School of Clinical Sciences at Monash Health, Monash University, Clayton, VIC 3168, Australia.
¹¹ Flinders Health and Medical Research Institute (Sleep Health)/Adelaide Institute for Sleep Health (AISH), College of Medicine and Public Health, Flinders University, Adelaide, SA 5042, Australia.
¹² Adelaide Medical School, The University of Adelaide, Adelaide, SA 5005, Australia.

PMID: 33808743
PMCID: PMC8003399
DOI: 10.3390/ijerph18063187

Predicting Australian Adults at High Risk of Cardiovascular Disease Mortality Using Standard Risk Factors and Machine Learning

Shelda Sajeev et al. Int J Environ Res Public Health. 2021.

. 2021 Mar 19;18(6):3187.

doi: 10.3390/ijerph18063187.

Authors

Affiliations

¹ Flinders Digital Health Research Centre, College of Nursing & Health Sciences, Flinders University, Adelaide SA 5001, Australia.
² Chifley Business School, Torrens University, Australia, Adelaide, SA 5000, Australia.
³ Caring Futures Institute, Flinders University, Adelaide, SA 5001, Australia.
⁴ College of Medicine and Public Health, Flinders University, Adelaide, SA 5001, Australia.
⁵ Baker Heart and Diabetes Institute, Melbourne, VIC 3004, Australia.
⁶ School of Public Health and Preventive Medicine, Monash University, Melbourne, VIC 3004, Australia.
⁷ School of Life Sciences, La Trobe University, Melbourne, VIC 3086, Australia.
⁸ Cancer Epidemiology Division, Cancer Council Victoria, 615 St Kilda Road, Melbourne, VIC 3004, Australia.
⁹ Centre for Epidemiology and Biostatistics, Melbourne School of Population and Global Health, The University of Melbourne, 207 Bouverie Street, Melbourne, VIC 3010, Australia.
¹⁰ Precision Medicine, School of Clinical Sciences at Monash Health, Monash University, Clayton, VIC 3168, Australia.
¹¹ Flinders Health and Medical Research Institute (Sleep Health)/Adelaide Institute for Sleep Health (AISH), College of Medicine and Public Health, Flinders University, Adelaide, SA 5042, Australia.
¹² Adelaide Medical School, The University of Adelaide, Adelaide, SA 5005, Australia.

PMID: 33808743
PMCID: PMC8003399
DOI: 10.3390/ijerph18063187

Abstract

Effective cardiovascular disease (CVD) prevention relies on timely identification and intervention for individuals at risk. Conventional formula-based techniques have been demonstrated to over- or under-predict the risk of CVD in the Australian population. This study assessed the ability of machine learning models to predict CVD mortality risk in the Australian population and compare performance with the well-established Framingham model. Data is drawn from three Australian cohort studies: the North West Adelaide Health Study (NWAHS), the Australian Diabetes, Obesity, and Lifestyle study, and the Melbourne Collaborative Cohort Study (MCCS). Four machine learning models for predicting 15-year CVD mortality risk were developed and compared to the 2008 Framingham model. Machine learning models performed significantly better compared to the Framingham model when applied to the three Australian cohorts. Machine learning based models improved prediction by 2.7% to 5.2% across three Australian cohorts. In an aggregated cohort, machine learning models improved prediction by up to 5.1% (area-under-curve (AUC) 0.852, 95% CI 0.837-0.867). Net reclassification improvement (NRI) was up to 26% with machine learning models. Machine learning based models also showed improved performance when stratified by sex and diabetes status. Results suggest a potential for improving CVD risk prediction in the Australian population using machine learning models.

Keywords: artificial intelligence; cardiovascular disease; cardiovascular risk factors; clinical decision support; machine learning; risk prediction.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest. The funders had no role in the design of the study; in the collection, analyses, or interpretation of data; in the writing of the manuscript, or in the decision to publish the results.

Figures

**Figure 1**
Flowchart describing the machine learning approach. CVD indicates cardiovascular disease; Synthetic Minority Over Sampling Technique (SMOTE); Machine Learning (ML); logistic regression (LR); linear discriminant analysis (LDA); support vector machine with linear kernel (SVM); random forest (RF).

See this image and copyright information in PMC

Cited by

Pitfalls in Developing Machine Learning Models for Predicting Cardiovascular Diseases: Challenge and Solutions.
Cai YQ, Gong DX, Tang LY, Cai Y, Li HJ, Jing TC, Gong M, Hu W, Zhang ZW, Zhang X, Zhang GW. Cai YQ, et al. J Med Internet Res. 2024 Jul 26;26:e47645. doi: 10.2196/47645. J Med Internet Res. 2024. PMID: 38869157 Free PMC article.
Prediction of cardiovascular risk using machine-learning methods. Sex-specific differences.
Castel-Feced S, Aguilar-Palacio I, Malo S, González-García J, Maldonado L, Rabanaque-Hernández MJ. Castel-Feced S, et al. Front Cardiovasc Med. 2025 Jun 19;12:1579947. doi: 10.3389/fcvm.2025.1579947. eCollection 2025. Front Cardiovasc Med. 2025. PMID: 40612375 Free PMC article.
Enhanced cardiovascular risk prediction in the Western Pacific: A machine learning approach tailored to the Malaysian population.
Kasim S, Amir Rudin PNF, Malek S, Ibrahim N, Kiew XN, Nasir NM, Ibrahim KS, Raja Shariff RE. Kasim S, et al. PLoS One. 2025 Jun 17;20(6):e0323949. doi: 10.1371/journal.pone.0323949. eCollection 2025. PLoS One. 2025. PMID: 40526616 Free PMC article.
Post-Analysis of Predictive Modeling with an Epidemiological Example.
Brester C, Voutilainen A, Tuomainen TP, Kauhanen J, Kolehmainen M. Brester C, et al. Healthcare (Basel). 2021 Jun 24;9(7):792. doi: 10.3390/healthcare9070792. Healthcare (Basel). 2021. PMID: 34202622 Free PMC article.
Using Machine Learning of Online Expression to Explain Recovery Trajectories: Content Analytic Approach to Studying a Substance Use Disorder Forum.
Yang EF, Kornfield R, Liu Y, Chih MY, Sarma P, Gustafson D, Curtin J, Shah D. Yang EF, et al. J Med Internet Res. 2023 Aug 22;25:e45589. doi: 10.2196/45589. J Med Internet Res. 2023. PMID: 37606984 Free PMC article.

See all "Cited by" articles

References

1. Australian Institute of Health and Welfare Cardiovascular Disease. Canberra: Australian Institute of Health and Welfare. [(accessed on 15 October 2020)]; Available online: https://www.aihw.gov.au/reports/heart-stroke-vascular-diseases/cardiovas....
1. World Health Organisation . Cardiovascular Diseases (CVDs) World Health Organisation; Geneva, Switzerland: 2017. [(accessed on 15 October 2020)]. Available online: https://www.who.int/news-room/fact-sheets/detail/cardiovascular-diseases...
1. Damen J.A.A.G., Hooft L., Schuit E., Debray T.P.A., Collins G.S., Tzoulaki I., Lassale C.M., Siontis G.C.M., Chiocchia V., Roberts C., et al. Prediction models for cardiovascular disease risk in the general population: Systematic review. BMJ. 2016;353:i2416. doi: 10.1136/bmj.i2416. - DOI - PMC - PubMed
1. Pylypchuk R., Wells S., Kerr A., Poppe K., Riddell T., Harwood M., Exeter D., Mehta S., Grey C., Wu B.P., et al. Cardiovascular disease risk prediction equations in 400 000 primary care patients in New Zealand: A derivation and validation study. Lancet. 2018;391:1897–1907. doi: 10.1016/S0140-6736(18)30664-0. - DOI - PubMed
1. Weng S.F., Reps J., Kai J., Garibaldi J.M., Qureshi N. Can machine-learning improve cardiovascular risk prediction using routine clinical data? PLoS ONE. 2017;12:e0174944. doi: 10.1371/journal.pone.0174944. - DOI - PMC - PubMed

Publication types

Actions

MeSH terms

Actions
Actions
Actions
Actions
Actions
Actions
Actions
Actions
Actions

LinkOut - more resources

Full Text Sources
Other Literature Sources
- scite Smart Citations

Save citation to file

Email citation

Add to Collections

Add to My Bibliography

Your saved search

Create a file for external citation management software

Your RSS Feed

Predicting Australian Adults at High Risk of Cardiovascular Disease Mortality Using Standard Risk Factors and Machine Learning

Affiliations

Predicting Australian Adults at High Risk of Cardiovascular Disease Mortality Using Standard Risk Factors and Machine Learning

Authors

Affiliations

Abstract

Conflict of interest statement

Figures

Similar articles

Cited by

References

Publication types

MeSH terms

LinkOut - more resources

Full Text Sources

Other Literature Sources

Abstract

Conflict of interest statement

Figures

Similar articles

Cited by

References

Publication types

MeSH terms

Related information

LinkOut - more resources

Full Text Sources

Other Literature Sources