Gallego-Moll, Carlos, Carrasco-Ribelles, Lucía A., Casajuana, Marc, Maynou, Laia 
ORCID: 0000-0002-0447-2959, Arocena, Pablo, Violán, Concepción and Zabaleta-Del-Olmo, Edurne
(2025)
Predicting healthcare utilisation outcomes with artificial intelligence: a large scoping review.
Value in Health.
ISSN 1098-3015
(In Press)
Abstract
Objectives To broadly map the research landscape to identify trends, gaps, and opportunities in datasets, methodologies, outcomes, and reporting standards for AI-based healthcare utilisation prediction. Method We conducted a scoping review following the Joanna Briggs Institute methodology. We searched three major international databases (from inception to January 2025) for studies applying AI in predictive healthcare utilisation. Extracted data were categorised into datasets characteristics, AI methods and performance metrics, predicted outcomes, and adherence to TRIPOD+AI reporting guidelines. Results Among 1116 records, 121 met inclusion criteria. Most were conducted in the United States (62%). No study incorporated all six relevant variable groups: demographic, socioeconomic, health status, perceived need, provider characteristics, and prior utilisation. Only seven studies included five of these groups. The main data sources were electronic health records (60%) and claims (28%). Ensemble models were the most frequently used (66.9%), while deep learning models were less common (16.5%). AI methods were primarily employed to predict future events (90.1%), with hospitalisations (57.9%) and visits (33.1%) being the most predicted outcomes. Adherence to general reporting standards was moderate, but compliance with AI-specific TRIPOD+AI items was limited. Conclusion Future research should broaden predicted outcomes to include process- and logistics-oriented events, extend applications beyond prediction—such as cohort selection and matching—and explore underused AI methods, including distance-based algorithms and deep neural networks. Strengthening adherence to TRIPOD-AI reporting guidelines is also essential to enhance the reliability and impact of AI in healthcare planning and economic evaluation.
| Item Type: | Article |
|---|---|
| Additional Information: | © 2025, International Society for Pharmacoeconomics and Outcomes Research, Inc. Published by Elsevier Inc. |
| Divisions: | LSE |
| Subjects: | R Medicine > RA Public aspects of medicine > RA0421 Public health. Hygiene. Preventive Medicine H Social Sciences > HB Economic Theory Q Science > QA Mathematics > QA75 Electronic computers. Computer science |
| Date Deposited: | 27 Aug 2025 16:00 |
| Last Modified: | 27 Aug 2025 16:06 |
| URI: | http://eprints.lse.ac.uk/id/eprint/129293 |
Actions (login required)
 |
View Item |
