Abstract
Precision health economics and outcomes research (P-HEOR) integrates economic and clinical value assessment by explicitly discovering distinct clinical and health care utilization phenotypes among patients. Through a conceptualized example, the objective of this review is to highlight the capabilities and limitations of machine learning (ML) applications to P-HEOR and to contextualize the potential opportunities and challenges for the wide adoption of ML for health economics. We outline a P-HEOR conceptual framework extending the ML methodology to comparatively assess the economic value of treatment regimens. Latest methodology developments on bias and confounding control in ML applications to precision medicine are also summarized.
Highlights
Technological advancements in the availability of big data can play an important role in health economics and outcomes research (HEOR) as well,[3] where precision medicine applications can help discover and align treatment pathways with the highest likelihood of treatment success and quality of life for specific patient clusters.[1]
We summarize the latest methodology developments on how bias and confounding can be controlled for when machine learning (ML) techniques are applied to nonrandomized data for Precision health economics and outcomes research (P-HEOR) research purposes
In the era of big data, P-HEOR can benefit from ML optimization to identify patient cohorts with different risk-benefit profiles in terms of both clinical and economic outcomes
Summary
Contemporary medical big data open the door for precision medicine ( known as stratified medicine and personalized medicine)—that is, evaluating and aligning health care for individual patients based on their disease susceptibility, prognostic and diagnostic information, and treatment response.[1,2] Technological advancements in the availability of big data can play an important role in health economics and outcomes research (HEOR) as well,[3] where precision medicine applications can help discover and align treatment pathways with the highest likelihood of treatment success and quality of life for specific patient clusters.[1]. Practical and methodological challenges exist in using medical big data for economic evaluations of precision medicine.[6,7] Challenges relate to the presence of bias and confounding in observational studies, handling of missing data and clinical miscoding, absence of available health state utility values (used to calculate quality-adjusted life years [QALYs]) for population subgroups of interest,[6] as well as lack of clear evidence on willingness-to-pay thresholds and reimbursement.[7] While these challenges are present in traditional applications of health technology assessment, which perhaps may explain why patient heterogeneity is rarely looked into in cost-effectiveness assessments,[8] making causal inferences in the context of multiple identified P-HEOR cohorts could compound the problem
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
