Machine learning for cardiovascular disease improves when social and environmental factors are included

Credit: public domain CC0

Machine learning can accurately predict cardiovascular disease and guide treatment, but models that incorporate the social determinants of health can better capture risks and outcomes for diverse groups, according to a new study by researchers from the School of Global Public Health and the Tandon School of Engineering at New York University. The article, published in the American Journal of Preventive Medicinealso highlights opportunities to improve how social and environmental variables are factored into machine learning algorithms.

Cardiovascular disease is responsible for almost a third of all deaths worldwide and disproportionately affects lower socio-economic groups. The increase in cardiovascular disease and death is attributed, in part, to social and environmental conditions, also called social determinants of health, which influence diet and exercise.

“Cardiovascular disease is on the rise, especially in low- and middle-income countries and among communities of color in places like the United States,” said Rumi Chunara, associate professor of biostatistics at the NYU School of Global Public Health and of Computer Science and Engineering at NYU Tandon School of Engineering, as well as the lead author of the study. “Because these changes occur over such a short period of time, it is well known that our changing social and environmental factors, such as the increase in processed foods, are driving this change, as opposed to genetic factors. that would change over much longer timescales.”

Machine learning – a type of artificial intelligence used to detect patterns in data – is growing rapidly in cardiovascular research and care to predict disease risk, incidence and outcomes. Already, statistical methods are at the heart of American cardiovascular disease risk assessment and prevention guidelines. The development of predictive models provides healthcare professionals with actionable information by quantifying a patient’s risk and guiding the prescription of medications or other preventive measures.

Cardiovascular disease risk is usually calculated using clinical information, such as blood pressure and cholesterol levels, but rarely considers social determinants, such as neighborhood-level factors. Chunara and his colleagues sought to better understand how social and environmental factors are beginning to be incorporated into machine learning algorithms for cardiovascular disease – what factors are taken into account, how they are analyzed, and what methods improve these models.

“Social and environmental factors have complex, nonlinear interactions with cardiovascular disease,” Chunara said. “Machine learning can be particularly useful in capturing these complex relationships.”

The researchers analyzed existing research on machine learning and cardiovascular disease risk, reviewing over 1,600 papers and ultimately focusing on 48 peer-reviewed studies published in journals between 1995 and 2020.

They found that including social determinants of health in machine learning models improved the ability to predict cardiovascular outcomes such as rehospitalization, heart failure, and stroke. However, these models generally did not include the full list of community or environmental variables that are important in cardiovascular disease risk. Some studies included additional factors such as income, marital status, social isolation, pollution, and health insurance, but only five studies took into account environmental factors such as a community’s walkability and the availability of resources such as grocery stores.

The researchers also noted the lack of geographic diversity in the studies, as the majority used data from the United States, countries in Europe, and China, overlooking many parts of the world experiencing increases in cardiovascular disease.

“If you only research places like the United States or Europe, you will miss how social determinants and other environmental factors related to cardiovascular risk interact in different settings and the knowledge generated will be limited,” said said Chunara.

“Our study shows that it is possible to more systematically and comprehensively incorporate social determinants of health into statistical models for predicting cardiovascular disease risk,” said NYU assistant professor of biostatistics Stephanie Cook. School of Global Public Health and study author. “In recent years there has been an increasing emphasis on capturing data on the social determinants of health – such as employment, education, food and social support – in health records electronics, which creates an opportunity to use these variables in machine learning studies and further improve the performance of risk prediction, especially for vulnerable groups.”

“Including social determinants of health in machine learning models can help us untangle where disparities are rooted and draw attention to where we should intervene in the risk structure,” Chunara added. . “For example, it can improve clinical practice by helping healthcare professionals identify patients who need referrals to community resources like housing services and broadly reinforces the complex synergy between people’s health and our environmental resources.”

Machine learning algorithms can help identify people at risk of tooth loss

More information:
Yuan Zhao et al, Social determinants in machine learning cardiovascular disease prediction models: a systematic review, American Journal of Preventive Medicine (2021). DOI: 10.1016/j.amepre.2021.04.016

Provided by New York University

Quote: Machine learning for cardiovascular disease improves when social and environmental factors are included (2021, July 27) Retrieved March 10, 2022 from disease-social-environmental.html

This document is subject to copyright. Except for fair use for purposes of private study or research, no part may be reproduced without written permission. The content is provided for information only.