Automating cost-effectiveness models with agentic artificial intelligence: Case study and implications for value assessment.
TL;DR
Findings support a hybrid paradigm in which AI augments, but does not replace, health economists in value assessment and formulary decision support within managed care settings.
Abstract
Background
Health economic modeling is conceptually sophisticated but operationally repetitive and resource intensive. Recent advances in large language models suggest potential for automating components of cost-effectiveness model development.
Objective
To evaluate whether an agentic artificial intelligence (AI) system can reliably automate cost-effectiveness model development in the context of targeted therapies for anaplastic lymphoma kinase-positive (ALK+) non-small cell lung cancer (NSCLC).
Methods
We developed the Agentic Health Economic Modeling Platform (A-HEMP) to construct a cost-effectiveness model for ALK+ NSCLC therapies without access to existing models in that clinical context. Modeling decisions and extracted parameters were compared with a previously published manual cost-effectiveness analysis. A-HEMP automated PICO-based scoping, modeling approach recommendation, systematic literature review, and structured parameter extraction. Performance was evaluated across 3 domains: model structure concordance, evidence identification concordance, and parameter value alignment. Deterministic cost-effectiveness outputs were calculated externally for benchmarking.
Results
A-HEMP identified a modeling framework aligned with the published cost-effective analysis and retrieved all primary clinical trials used for clinical efficacy inputs. Concordance in model structure and assumptions was observed in 27% of modeling dimensions, with 36% partially concordant and 36% divergent. Divergences were most prominent in survival extrapolation and intracranial progression handling. Evidence identification concordance was high for primary clinical trials (100%) but moderate for cost inputs, with 25% of evidence domains fully concordant and 38% partially concordant. Parameter value alignment was high for clinical efficacy inputs and progression-free health state utilities (<2% deviation), whereas greater variability was observed for sicker health states (12% deviation) and downstream disease management costs (25%-55% deviation).
Conclusions
Agentic AI can reliably automate upstream components of cost-effectiveness model development. However, nuanced modeling decisions with less standardized methodological guidance remain areas requiring expert oversight. These findings support a hybrid paradigm in which AI augments, but does not replace, health economists in value assessment and formulary decision support within managed care settings.