Introduction
Cardiovascular disease is the leading cause of death worldwide, and cardiovascular
disease burden is increasing in low-resource settings and for lower socioeconomic
groups. Machine learning algorithms are being developed rapidly and incorporated into
clinical practice for cardiovascular disease prediction and treatment decisions. Significant
opportunities for reducing death and disability from cardiovascular disease worldwide
lie with accounting for the social determinants of cardiovascular outcomes. This study
reviews how social determinants of health are being included in machine learning algorithms
to inform best practices for the development of algorithms that account for social
determinants.
Methods
A systematic review using 5 databases was conducted in 2020. English language articles
from any location published from inception to April 10, 2020, which reported on the
use of machine learning for cardiovascular disease prediction that incorporated social
determinants of health, were included.
Results
Most studies that compared machine learning algorithms and regression showed increased
performance of machine learning, and most studies that compared performance with or
without social determinants of health showed increased performance with them. The
most frequently included social determinants of health variables were gender, race/ethnicity,
marital status, occupation, and income. Studies were largely from North America, Europe,
and China, limiting the diversity of the included populations and variance in social
determinants of health.
Discussion
Given their flexibility, machine learning approaches may provide an opportunity to
incorporate the complex nature of social determinants of health. The limited variety
of sources and data in the reviewed studies emphasize that there is an opportunity
to include more social determinants of health variables, especially environmental
ones, that are known to impact cardiovascular disease risk and that recording such
data in electronic databases will enable their use.
To read this article in full you will need to make a payment
Purchase one-time access:
Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online accessOne-time access price info
- For academic or personal research use, select 'Academic and Personal'
- For corporate R&D use, select 'Corporate R&D Professionals'
Subscribe:
Subscribe to American Journal of Preventive MedicineAlready a print subscriber? Claim online access
Already an online subscriber? Sign in
Register: Create an account
Institutional Access: Sign in to ScienceDirect
REFERENCES
- Cardiovascular Diseases (CVDs).WHO, Geneva, SwitzerlandPublished May 17, 2017 (Accessed March 8, 2021)
- The global burden of cardiovascular disease.Eur J Cardiovasc Nurs. 2011; 10: S5-S13https://doi.org/10.1016/S1474-5151(11)00111-3
- Forecasting the impact of heart failure in the United States: a policy statement from the American Heart Association.Circ Heart Fail. 2013; 6: 606-619https://doi.org/10.1161/HHF.0b013e318291329a
- Explaining the increase in coronary heart disease mortality in Beijing between 1984 and 1999.Circulation. 2004; 110: 1236-1244https://doi.org/10.1161/01.CIR.0000140668.91896.AE
- Epidemiologic studies of coronary heart disease and stroke in Japanese men living in Japan, Hawaii and California: mortality.Am J Epidemiol. 1975; 102: 481-490https://doi.org/10.1093/oxfordjournals.aje.a112186
- Impact of migration on coronary heart disease risk factors: comparison of Gujaratis in Britain and their contemporaries in villages of origin in India.Atherosclerosis. 2006; 185: 297-306https://doi.org/10.1016/j.atherosclerosis.2005.06.005
- Migration and coronary heart disease: a study of Finnish twins living in Sweden and their co-twins residing in Finland.Scand J Public Health. 2007; 35: 468-474https://doi.org/10.1080/14034940701256875
- Reducing the global burden of cardiovascular disease: the role of risk factors.Prev Cardiol. 2002; 5: 188-199https://doi.org/10.1111/j.1520-037x.2002.00564.x
- Modifiable risk factors, cardiovascular disease, and mortality in 155 722 individuals from 21 high-income, middle-income, and low-income countries (PURE): a prospective cohort study [published correction appears in Lancet. 2020;395(10226):784].Lancet. 2020; 395: 795-808https://doi.org/10.1016/S0140-6736(19)32008-2
- Closing the gap in a generation: health equity through action on the social determinants of health: commission on social determinants of health.WHO, Geneva, SwitzerlandPublished August 27, 2008 (Accessed March 8, 2021)
- Social determinants of risk and outcomes for cardiovascular disease: a scientific statement from the American Heart Association.Circulation. 2015; 132: 873-898https://doi.org/10.1161/CIR.0000000000000228
- Reducing the global burden of cardiovascular disease, part 1: the epidemiology and risk factors.Circ Res. 2017; 121: 677-694https://doi.org/10.1161/CIRCRESAHA.117.308903
- Psychosocial and socioeconomic determinants of cardiovascular mortality in Eastern Europe: a multicentre prospective cohort study.PLoS Med. 2017; 14e1002459https://doi.org/10.1371/journal.pmed.1002459
- CHD risk minimization through lifestyle control: machine learning gateway.Sci Rep. 2020; 10: 4090https://doi.org/10.1038/s41598-020-60786-w
- Clinical applications of machine learning algorithms: beyond the black box.BMJ. 2019; 364: I886https://doi.org/10.1136/bmj.l886
- Cardiovascular disease risk prediction using automated machine learning: a prospective study of 423,604 UK Biobank participants.PLoS One. 2019; 14e0213653https://doi.org/10.1371/journal.pone.0213653
- Machine learning methodologies versus cardiovascular risk scores, in predicting disease risk.BMC Med Res Methodol. 2018; 18: 179https://doi.org/10.1186/s12874-018-0644-1
- Machine learning outperforms ACC/AHA CVD risk calculator in MESA.J Am Heart Assoc. 2018; 7e009476https://doi.org/10.1161/JAHA.118.009476
- Further insight into the cardiovascular risk calculator: the roles of statins, revascularizations, and underascertainment in the Women's Health Study.JAMA Intern Med. 2014; 174: 1964-1971https://doi.org/10.1001/jamainternmed.2014.5336
- Intersections of machine learning and epidemiological methods for health services research.Int J Epidemiol. 2021; 49: 1763-1770https://doi.org/10.1093/ije/dyaa035
- Advanced analytical methodologies for measuring healthy ageing and its determinants, using factor analysis and machine learning techniques: the ATHLOS project.Sci Rep. 2017; 7: 43955https://doi.org/10.1038/srep43955
- Machine learning approaches to the social determinants of health in the health and retirement study.SSM Popul Health. 2018; 4: 95-99https://doi.org/10.1016/j.ssmph.2017.11.008
- The impact of social determinants on cardiovascular disease.Can J Cardiol. 2010; 26: 8C-13Chttps://doi.org/10.1016/s0828-282x(10)71075-8
- Environmental determinants of cardiovascular disease.Circ Res. 2017; 121: 162-180https://doi.org/10.1161/CIRCRESAHA.117.306458
- Correlations between health insurance status and risk factors for cardiovascular disease in the elderly Asian American population.Cureus. 2018; 10: e2303https://doi.org/10.7759/cureus.2303
- Association of birthplace and coronary heart disease and stroke among U.S. adults: National Health Interview Survey, 2006 to 2014.J Am Heart Assoc. 2018; 7e008153https://doi.org/10.1161/JAHA.117.008153
- Religion and cardiovascular disease risk.J Relig Health. 1997; 36: 155-164https://doi.org/10.1023/A:1027444621177
- Supervised machine learning: a review of classification techniques.Emerg Artif Intell Appl Comput Eng. 2007; 160 (Accessed March 8, 2021): 3-24
- Deep learning.Nature. 2015; 521: 436-444https://doi.org/10.1038/nature14539
- Global, regional, and national age-sex-specific mortality for 282 causes of death in 195 countries and territories, 1980-2017: a systematic analysis for the Global Burden of Disease Study 2017 [published correction appears in Lancet. 2019;393(10190):e44].Lancet. 2018; 392: 1736-1788https://doi.org/10.1016/S0140-6736(18)32203-7
- How to develop machine learning models for healthcare.Nat Mater. 2019; 18: 410-414https://doi.org/10.1038/s41563-019-0345-0
- The use of deep learning to predict stroke patient mortality.Int J Environ Res Public Health. 2019; 16: 1876https://doi.org/10.3390/ijerph16111876
- Alternating decision trees for early diagnosis of heart disease.in: Paper presented at: International Conference on Circuits, Communication, Control and Computing, Bangalore, IndiaNovember 21–22, 2014https://doi.org/10.1109/CIMCA.2014.7057816
- Integrative predictive model of coronary artery calcification in arteriosclerosis.Circulation. 2009; 120: 2448-2454https://doi.org/10.1161/CIRCULATIONAHA.109.865501
- A study of generalizability of recurrent neural network-based predictive models for heart failure onset risk using a large and heterogeneous EHR data set.J Biomed Inform. 2018; 84: 11-16https://doi.org/10.1016/j.jbi.2018.06.011
- Machine learning-based forecast of hemorrhagic stroke healthcare service demand considering air pollution.J Healthc Eng. 2019; 20197463242https://doi.org/10.1155/2019/7463242
- Biologically plausible deep learning—but how far can we go with shallow networks?.Neural Netw. 2019; 118: 90-101https://doi.org/10.1016/j.neunet.2019.06.001
- Artificial neural network models for prediction of acute coronary syndromes using clinical data from the time of presentation.Ann Emerg Med. 2005; 46: 431-439https://doi.org/10.1016/j.annemergmed.2004.09.012
- Machine learning assessment of myocardial ischemia using angiography: development and retrospective validation.PLoS Med. 2018; 15e1002693https://doi.org/10.1371/journal.pmed.1002693
- Does feature selection improve classification accuracy? Impact of sample size and feature selection on classification using anatomical magnetic resonance images.Neuroimage. 2012; 60: 59-70https://doi.org/10.1016/j.neuroimage.2011.11.066
- Bayesian methods for Neural Networks.Neural Computing Research Group, Department of Computer Engineering and Applied Mathematics, Aston University, Birmingham, United KingdomPublished 1995https://www.microsoft.com/en-us/research/wp-content/uploads/1995/01/NCRG_95_009.pdfDate accessed: May 6, 2021
- Logistic regression and artificial neural network classification models: a methodology review.J Biomed Inform. 2002; 35: 352-359https://doi.org/10.1016/s1532-0464(03)00034-0
- Cardiovascular event prediction by machine learning: the multi-ethnic study of atherosclerosis.Circ Res. 2017; 121: 1092-1101https://doi.org/10.1161/CIRCRESAHA.117.311312
- Using machine learning algorithms in cardiovascular disease risk evaluation.J Appl Comput Sci Math. 2009; 1 (Accessed March 8, 2021.): 29-32
- Can machine-learning improve cardiovascular risk prediction using routine clinical data?.PLoS One. 2017; 12e0174944https://doi.org/10.1371/journal.pone.0174944
- Interpretable machine learning in healthcare.in: Proceedings of the 2018 ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics; 2018 Aug 15. Association for Computing Machinery, Washington, DC. New York2018https://doi.org/10.1145/3233547.3233667
- Effects of obesity on cardiovascular hemodynamics, cardiac morphology, and ventricular function.Curr Obes Rep. 2016; 5: 424-434https://doi.org/10.1007/s13679-016-0235-6
- Effects of changes in smoking and other characteristics on clotting factors and the risk of ischaemic heart disease.Lancet. 1987; 2: 986-988https://doi.org/10.1016/s0140-6736(87)92556-6
- Capturing Social and Behavioral Domains in Electronic Health Records: Phase 1.The National Academies Press, Washington, DC2014https://doi.org/10.17226/18709
- Accountable health communities—addressing social needs through Medicare and Medicaid.N Engl J Med. 2016; 374: 8-11https://doi.org/10.1056/NEJMp1512532
- Determinants of cardiovascular disease and other non-communicable diseases in Central and Eastern Europe: rationale and design of the HAPIEE study.BMC Public Health. 2006; 6: 255https://doi.org/10.1186/1471-2458-6-255
- Social determinants and the decline of cardiovascular diseases: understanding the links.Annu Rev Public Health. 2011; 32: 39-69https://doi.org/10.1146/annurev-publhealth-031210-101234
- Clinical implications of revised pooled cohort equations for estimating atherosclerotic cardiovascular disease risk.Ann Intern Med. 2018; 169: 20-29https://doi.org/10.7326/M17-3011
- Algorithmic fairness.AEA Pap Proc. 2018; 108: 22-27https://doi.org/10.1257/pandp.20181018
- Addressing social determinants of health at well child care visits: a cluster RCT.Pediatrics. 2015; 135: e296-e304https://doi.org/10.1542/peds.2014-2888
- Moving electronic medical records upstream: incorporating social determinants of health.Am J Prev Med. 2015; 48: 215-218https://doi.org/10.1016/j.amepre.2014.07.009
- Perspectives in primary care: a conceptual framework and path for integrating social determinants of health into primary care practice.Ann Fam Med. 2016; 14: 104-108https://doi.org/10.1370/afm.1903
- Causal multi-level fairness.in: Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society (AIES ’21), New York2021 May 19–21https://doi.org/10.1145/3461702.3462587
- Social determinants of mental disorders and the Sustainable Development Goals: a systematic review of reviews.The Lancet Psychiatry. 2018; 5: 357-369
Article Info
Publication History
Published online: July 27, 2021
Identification
Copyright
© 2021 American Journal of Preventive Medicine. Published by Elsevier Inc. All rights reserved.
