A narrative review of the use of PROMs and machine learning to impact value-based clinical decision-making

Aug 3, 2026

Upload by Quinn

This narrative review summarizes studies that combine Patient Reported Outcome Measures (PROMs) with machine learning methods to predict patient outcomes after interventions. The work aims to support value-based healthcare stakeholders in applying machine learning alongside PROM data for clinical practice. Search and screening were conducted systematically across multiple databases with independent review. Results cover diverse PROM instruments and varied algorithms, with some predictive success but no consistently best-performing approach.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages20

Reading Time50 min

AccessFree to download

Abstract

Purpose

Methods

Results

Conclusion

Background

Patient reported outcome measures in Wales

Machine learning as a modelling approach

Value-based healthcare and prudent principles

Pruski etal. BMC Medical Informatics and Decision Making (2025) 25:250 [https://doi.org/10.1186/s12911-025-03083-8](https://doi.org/10.1186/s12911-025-03083-8) BMC Medical Informatics and Decision Making REVIEW Open Access A narrative review of the use of PROMs and machine learning to impact value-based clinical decision-making Michal Pruski 1,2, Simone Willis3* and Kathleen Withers2,4 Abstract Purpose This review summarises the studies which combined Patient Reported Outcome Measures (PROMs) and Machine Learning statistical computational techniques, to predict patient post-intervention outcomes. The aim of the project was to inform those working in value-based healthcare how Machine Learning can be used with PROMs to inform clinical practice. Methods A systematic search strategy was developed and run in six databases. The records were reviewed by areviewer if they matched the review scope, and these decisions were scrutinised by a second reviewer. Results 82 records pertaining to 73 studies were identified. The review highlights the breadth of PROMs tools investigated, and the wide variety of Machine Learning techniques utilised across the studies. The findings suggest that there has been some success in predicting post-intervention patient outcomes. Nevertheless, there is no clear best performing Machine Learning approach to analyse this data, and while baseline PROMs scores are often a key predictor of post-intervention scores, this cannot always be assumed to be the case. Moreover, even when studies looked at similar conditions and patient groups, often different Machine Learning techniques performed best in each study. Conclusion This review highlights that there is a potential for PROMs and Machine Learning methodology to predict patient post-intervention outcomes, but that best performing models from other previous studies cannot simply be adopted in new clinical contexts. Keywords Prudent healthcare, Decision-making, Value in health, Algorithms, Prediction, Patient reported outcomes *Correspondence: Simone Willis [WillisS5@cardiff.ac.uk](WillisS5@cardiff.ac.uk) 1School of Health Sciences, The University of Manchester, Manchester, UK 2CEDAR, Cardiff and Vale UHB, Cardiff, UK 3Specialist Unit for Review Evidence, Cardiff University, Cardiff, UK 4School of Engineering, Cardiff University, Cardiff, UK © The Author(s) 2025. Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit [http://creativecommons.org/l](http://creativecommons.org/l)icenses/by/4.0/. Pruski et al. BMC Medical Informatics and Decision Making (2025) 25:250 Page 2 of 20 Background Wales is at the forefront of collecting patient reported outcome measures (PROMs) in clinical practice on a national level [1–4]. As the digital revolution progresses, novel technologies, such as machine learning (ML) and other artificial intelligence (AI) techniques, offer new possibilities of utilising healthcare data. This includes both facilitating big data research using routinely collected data, and the application of these findings to facilitate patient care. Being a subset of AI, ML is a group of computational techniques which allows researchers to better scrutinise their data. While ML techniques

FAQs

What does the review aim to achieve?

The review summarizes studies combining PROMs with machine learning to predict post-intervention patient outcomes, and to inform stakeholders in value-based healthcare on how such methods can support clinical practice.

How were the studies identified and selected?

A systematic search strategy was run across six databases, and records matching the review scope were reviewed, with decisions scrutinized by a second reviewer.

What were the main findings about predictive performance?

The review identified 73 studies and found some success in predicting outcomes, but there was no clear best-performing machine learning approach. Baseline PROMs scores often—but not always—predicted post-intervention scores.

Aug 3, 2026

Upload by Quinn