Global expert panel identifies 5 areas where machine learning can improve health economics and research outcomes


Credit: Unsplash/CC0 Public Domain

Value in health, the official journal of ISPOR – the Professional Association for Health Economics and Outcomes Research – today announced the publication of new guidelines for health economics and outcomes research (HEOR) and decision makers when using an important class of artificial intelligence techniques. The report, “Machine Learning Methods in Health Economics and Outcomes Research – The PALISADE Checklist: A Good Practices Report of the ISPOR Machine Learning Task Force”, is published in the July 2022 issue of Value in health

“Machine learning is a potentially valuable addition to the HEOR toolkit,” said task force co-chairs and lead authors William Crown, Ph.D., and William V. Padula, Ph.D. “It can facilitate the search for complex relationships in high-dimensional data sets, such as those generated by electronic health records or mobile health devices. These relationships can be used to improve disease detection and classification, to identify cohorts of patients share characteristics that may not be obvious when only a small set of variables are considered using traditional methods, and to explore trajectories of health outcomes among alternative personalized treatment options. In this report, the task force focused on the potential applications of machine learning in HEOR.”

The authors identified 5 methodological areas where machine learning could improve HEOR:

  1. cohort selection (i.e. identifying samples with greater specificity regarding inclusion criteria)
  2. identification of independent predictors and covariates of health outcomes
  3. predictive analytics of health outcomes, including high cost and/or life-threatening
  4. causal inference through methods, such as directed maximum probability estimation or double/unambiguous estimation, which allows faster production of reliable evidence about the effectiveness of treatments in the real world
  5. applying machine learning to economic model development to reduce structural, parameter and sample uncertainty in cost-effectiveness analysis

To investigate whether machine learning offers a useful and transparent solution for: healthcare analytics, the taskforce also developed the PALISADE Checklist. This checklist provides a series of considerations that researchers can use to explore whether machine learning adds value to traditional approaches to research. It can be a guide to balancing the many potential applications of machine learning with the need for transparency in method development and findings.

“Our report presents all of these considerations in an order that reflects a standard approach to performing HEOR: identifying a study population; classifying exposures that may alter outcomes; predicting the association between exposures and outcomes; assessing causal effects of interventions; and understanding whether or not interventions or health policy decisions add value,” said Crown and Padula.

“The intent is to introduce these concepts at a high level and direct readers to resources where they can learn more about theory and techniques that can support and advance the HEOR field. Increased collaboration between communities of HEOR scientists and computer scientists with expertise in the field of machine learning, we have been encouraged to learn from each other more quickly.”

Background information on the ISPOR machine learning methods in the HEOR Task Force

As the demand for research into the application of machine learning in healthcare has grown, so has the number of researchers conducting these studies and the researchers using the findings from these studies. Researchers conducting HEOR using machine learning methods come from diverse backgrounds and may lack basic training in the theory and methods of computer and data science. In addition, many of these researchers may not be aware of the range of machine learning methods available and the contexts in which they should be most appropriately used, recognizing both their strengths and limitations.

The overall objective of the Task Force is to provide guidelines for emerging good practices in the application of: machine learning methodology for traditional ISPOR methods, including economic evaluation, decision science and outcomes research to improve the value of health care.

Applying machine learning to biomedical science

More information:
Machine Learning Methods in Health Economics Research and Outcomes: The PALISADE Checklist: A Good Practice Report from an ISPOR Task Forcee (2022).

Provided by ISPOR—The Professional Society for Health Economics and Outcomes Research

Quote: Global expert panel identifies 5 areas where machine learning could improve health economics and research outcomes (2022, July 5), retrieved July 5, 2022 from – machine.html

This document is copyrighted. Other than fair dealing for personal study or research, nothing may be reproduced without written permission. The content is provided for informational purposes only.

Leave a Comment

Your email address will not be published. Required fields are marked *