A scoping review on the use of machine learning in research on social determinants of health: Trends and research prospects

Abstract

Background Machine learning (ML) has spread rapidly from computer science to several disciplines. Given the predictive capacity of ML, it offers new opportunities for health, behavioral, and social scientists. However, it remains unclear how and to what extent ML is being used in studies of social determinants of health (SDH). Methods Using four search engines, we conducted a scoping review of studies that used ML to study SDH (published before May 1, 2020). Two independent reviewers analyzed the relevant studies. For each study, we identified the research questions, Results, data, and algorithms. We synthesized our findings in a narrative report. Results Of the initial 8097 hits, we identified 82 relevant studies. The number of publications has risen during the past decade. More than half of the studies (n = 46) used US data. About 80% (n = 66) utilized surveys, and 70% (n = 57) employed ML for common prediction tasks. Although the number of studies in ML and SDH is growing rapidly, only a few studies used ML to improve causal inference, curate data, or identify social bias in predictions (i.e., algorithmic fairness). Conclusions While ML equips researchers with new ways to measure health outcomes and their determinants from non-conventional sources such as text, audio, and image data, most studies still rely on traditional surveys. Although there are no guarantees that ML will lead to better social epidemiological research, the potential for innovation in SDH research is evident as a result of harnessing the predictive power of ML for causality, data curation, or algorithmic fairness.

COVID-19 vaccine hesitancy and refusal and associated factors in an adult population in Saskatchewan, Canada: Evidence from predictive modelling

“…Classification and regression tree. Given the predictive capacity of machine learning and its limited application in population health research [23], a decision tree analysis was conducted in SAS JMP TM version 16.0 (SAS Cary, NC, USA) to complement and validate the multinomial regression models [24]. The plurality of methods gives more confidence to the study findings.…”

The International Monetary Fund’s intervention in education systems and its impact on children’s chances of completing school

“…This validation procedure involves estimating a model on a portion of the sample, and then evaluating predictive performance in another sample. Such models have been used in a variety in applications in the social and behavioral sciences (Daoud, Kim, and Subramanian 2019;Kino et al 2021).…”

“…An additional CATE analysis unpacks this effect heterogeneity across children's country, family, and individual characteristics. To identify CATE, we use a data-driven approach relying on statistical models for causal inference and machine learning-algorithms that find patterns in the data (Athey and Imbens 2017;Daoud and Dubhashi 2021;Hill 2011;Kino et al 2021;Mullainathan and Spiess 2017).…”

Counterfactual Analysis of the Impact of the IMF Program on Child Poverty in the Global-South Region using Causal-Graphical Normalizing Flows

“…As poverty hinders individuals to flourish, many studies have deepened our understanding of the causes and consequences that push vulnerable groups such as children into poverty (Banerjee et al, 2011). However, there is lacking knowledge about how to optimally tailor public policies to alleviate poverty for such vulnerable groups in times of macroeconomic volatility (Halleröd et al, 2013;Kino et al, 2021). A key question is then, to what extent can policymakers tailor policies to each child's circumstances and to what extent is it viable to articulate one policy for a population.…”