Intersections of Machine Learning and Epidemiological Methods for Health Services Research

Overview

Journal Int J Epidemiol

Specialty Public Health

Date 2020 Apr 3

PMID 32236476

Citations 13

Authors

Sherri Rose

Affiliations

Soon will be listed here.

Abstract

The field of health services research is broad and seeks to answer questions about the health care system. It is inherently interdisciplinary, and epidemiologists have made crucial contributions. Parametric regression techniques remain standard practice in health services research with machine learning techniques currently having low penetrance in comparison. However, studies in several prominent areas, including health care spending, outcomes and quality, have begun deploying machine learning tools for these applications. Nevertheless, major advances in epidemiological methods are also as yet underleveraged in health services research. This article summarizes the current state of machine learning in key areas of health services research, and discusses important future directions at the intersection of machine learning and epidemiological methods for health services research.

Citing Articles

Explainable machine learning for health disparities: type 2 diabetes in the research program.

Kambara M, Chukka O, Choi K, Tsenum J, Gupta S, English N bioRxiv. 2025; .

PMID: 40027775 PMC: 11870513. DOI: 10.1101/2025.02.18.638789.

Unbound bilirubin and risk of severe neurodevelopmental impairment in extremely low birthweight newborns.

Arnold C, Maric I, Wong R, Tyson J, Stevenson D Pediatr Res. 2025; .

PMID: 39849115 DOI: 10.1038/s41390-025-03872-x.

Leveraging Machine Learning to Identify Subgroups of Misclassified Patients in the Emergency Department: Multicenter Proof-of-Concept Study.

Wyatt S, Lunde Markussen D, Haizoune M, Vestbo A, Sima Y, Sandboe M J Med Internet Res. 2024; 26():e56382.

PMID: 39451101 PMC: 11733519. DOI: 10.2196/56382.

Social Determinants of Health and the Use of Community-Based Rehabilitation Following Stroke: Methodologic Considerations.

Mormer E, Jones Berkeley S, Johnson A, Ressel K, Zhang S, Pastva A Arch Rehabil Res Clin Transl. 2024; 6(3):100358.

PMID: 39372247 PMC: 11447761. DOI: 10.1016/j.arrct.2024.100358.

Twenty-four-hour physical activity patterns associated with depressive symptoms: a cross-sectional study using big data-machine learning approach.

Nawrin S, Inada H, Momma H, Nagatomi R BMC Public Health. 2024; 24(1):1254.

PMID: 38714982 PMC: 11075341. DOI: 10.1186/s12889-024-18759-5.

References

Larney S, Hickman M, Fiellin D, Dobbins T, Nielsen S, Jones N . Using routinely collected data to understand and predict adverse outcomes in opioid agonist treatment: Protocol for the Opioid Agonist Treatment Safety (OATS) Study. BMJ Open. 2018; 8(8):e025204. PMC: 6078240. DOI: 10.1136/bmjopen-2018-025204. View

Lau L, Kankanige Y, Rubinstein B, Jones R, Christophi C, Muralidharan V . Machine-Learning Algorithms Predict Graft Failure After Liver Transplantation. Transplantation. 2016; 101(4):e125-e132. PMC: 7228574. DOI: 10.1097/TP.0000000000001600. View

Rose S, Zaslavsky A, McWilliams J . Variation In Accountable Care Organization Spending And Sensitivity To Risk Adjustment: Implications For Benchmarking. Health Aff (Millwood). 2016; 35(3):440-8. PMC: 5436972. DOI: 10.1377/hlthaff.2015.1026. View

Wyss R, Schneeweiss S, van der Laan M, Lendle S, Ju C, Franklin J . Using Super Learner Prediction Modeling to Improve High-dimensional Propensity Score Estimation. Epidemiology. 2017; 29(1):96-106. DOI: 10.1097/EDE.0000000000000762. View

Franklin J, Shrank W, Lii J, Krumme A, Matlin O, Brennan T . Observing versus Predicting: Initial Patterns of Filling Predict Long-Term Adherence More Accurately Than High-Dimensional Modeling Techniques. Health Serv Res. 2015; 51(1):220-39. PMC: 4722199. DOI: 10.1111/1475-6773.12310. View

Weber A, van der Laan M, Petersen M . Assumption Trade-Offs When Choosing Identification Strategies for Pre-Post Treatment Effect Estimation: An Illustration of a Community-Based Intervention in Madagascar. J Causal Inference. 2015; 3(1):109-130. PMC: 4470579. DOI: 10.1515/jci-2013-0019. View

Razavian N, Blecker S, Schmidt A, Smith-McLallen A, Nigam S, Sontag D . Population-Level Prediction of Type 2 Diabetes From Claims Data and Analysis of Risk Factors. Big Data. 2016; 3(4):277-87. DOI: 10.1089/big.2015.0020. View

McGuire T . Achieving Mental Health Care Parity Might Require Changes In Payments And Competition. Health Aff (Millwood). 2016; 35(6):1029-35. PMC: 5026763. DOI: 10.1377/hlthaff.2016.0012. View

Shrestha A, Bergquist S, Montz E, Rose S . Mental Health Risk Adjustment with Clinical Categories and Machine Learning. Health Serv Res. 2017; 53 Suppl 1:3189-3206. PMC: 6056578. DOI: 10.1111/1475-6773.12818. View

10.

van Veen S, van Kleef R, van de Ven W, van Vliet R . Exploring the predictive power of interaction terms in a sophisticated risk equalization model using regression trees. Health Econ. 2017; 27(2):e1-e12. DOI: 10.1002/hec.3523. View

11.

Mansoor H, Elgendy I, Segal R, Bavry A, Bian J . Risk prediction model for in-hospital mortality in women with ST-elevation myocardial infarction: A machine learning approach. Heart Lung. 2017; 46(6):405-411. DOI: 10.1016/j.hrtlng.2017.09.003. View

12.

Frakt A, Pizer S . The promise and perils of big data in healthcare. Am J Manag Care. 2016; 22(2):98-9. PMC: 4758464. View

13.

Kreif N, Grieve R, Diaz I, Harrison D . Evaluation of the Effect of a Continuous Treatment: A Machine Learning Approach with an Application to Treatment for Traumatic Brain Injury. Health Econ. 2015; 24(9):1213-28. PMC: 4744663. DOI: 10.1002/hec.3189. View

14.

Drozd E, Cromwell J, Gage B, Maier J, Greenwald L, Goldman H . Patient casemix classification for medicare psychiatric prospective payment. Am J Psychiatry. 2006; 163(4):724-32. DOI: 10.1176/ajp.2006.163.4.724. View

15.

Robinson J . Regression tree boosting to adjust health care cost predictions for diagnostic mix. Health Serv Res. 2008; 43(2):755-72. PMC: 2442380. DOI: 10.1111/j.1475-6773.2007.00761.x. View

16.

Park S, Basu A . Alternative evaluation metrics for risk adjustment methods. Health Econ. 2018; 27(6):984-1010. DOI: 10.1002/hec.3657. View

17.

Watkins S, Jonsson-Funk M, Brookhart M, Rosenberg S, OShea T, Daniels J . An empirical comparison of tree-based methods for propensity score estimation. Health Serv Res. 2013; 48(5):1798-817. PMC: 3796115. DOI: 10.1111/1475-6773.12068. View

18.

Bergquist S, Layton T, McGuire T, Rose S . Data transformations to improve the performance of health plan payment methods. J Health Econ. 2019; 66:195-207. PMC: 7442111. DOI: 10.1016/j.jhealeco.2019.05.005. View

19.

Pirracchio R, Petersen M, Carone M, Resche Rigon M, Chevret S, van der Laan M . Mortality prediction in intensive care units with the Super ICU Learner Algorithm (SICULA): a population-based study. Lancet Respir Med. 2014; 3(1):42-52. PMC: 4321691. DOI: 10.1016/S2213-2600(14)70239-5. View

20.

Schuler M, Rose S . Targeted Maximum Likelihood Estimation for Causal Inference in Observational Studies. Am J Epidemiol. 2016; 185(1):65-73. DOI: 10.1093/aje/kww165. View