Systematic literature review of the use of generative AI in health economic evaluation

Generative AI (GenAI) has emerged in the current decade as a paradigm-shifting technology with potential to transform the process of health economic evaluation (HEE), a resource-intensive element of health technology assessment. This systematic literature review aims to identify the current applications of GenAI in HEE and its potential advantages, challenges and limitations. We searched Medline, Embase, EconLit, Cochrane Library, International HTA database and Epistemonikos for English-language, publicly available literature without date restrictions, and hand-searched the ISPOR presentations database (2023 to 2025) for articles describing or investigating the use of GenAI in HEE. Quantitative data on performance outcomes were collected along with qualitative data on stakeholder opinions and experience. We identified 25 eligible studies: 18 primary studies, 6 narrative reviews and 1 expert opinion piece. The primary studies comprised 16 case studies and 2 qualitative studies. Over 90% of studies were conference abstracts published in 2024 from commercial authors. The emphasis across studies was on early exploratory research, particularly model replication. Where reported, execution time (3 studies), accuracy and error rate (7 studies), and user experience (4 studies) showed promising results across multiple use cases but there is a high risk of bias inherent in relying on conference abstracts with limited reporting, which warrants cautious interpretation. The current evidence landscape has revealed potential benefits of GenAI across multiple applications to health economics, but only sparse dissemination of early case study findings via conference submissions. Further research is needed to validate all use cases and to address perceived barriers to implementation.