Resources: Value in Health Offers Special Issue on AI in Health Economics (November 2025)

 Value in Health, the official journal of ISPOR, the international pharmacoeconomics/HEOR organization, focuses on AI in HEOR for November 2025.

I clip the article list below; many are open access.

I also clip an AI summary of the TOC below.

###

AI Corner

###

The November AI HEOR Special Issue

This special issue of Value in Health is devoted to the accelerating role of generative and analytical artificial intelligence in health economics and outcomes research (HEOR). Two ISPOR Working Group Reports anchor the issue. The first proposes a taxonomy of generative AI and large language models (LLMs) for HEOR, aiming to standardize terminology and clarify use cases across evidence synthesis, modeling, and decision frameworks. The companion report introduces ELEVATE-GenAI, a structured reporting guideline and checklist to improve transparency, reproducibility, and methodological rigor when LLMs are used in HEOR studies.

A themed section of research articles and editorials then explores how AI is reshaping HEOR practice. An introductory editorial highlights the rapid evolution of AI methods and the corresponding need for standards, validation, and governance. Another article recognizes early-career researchers whose work advances AI-enabled HEOR.

Several empirical studies examine AI’s performance in systematic reviews, traditionally one of the most labor-intensive components of HEOR. Validating “Loon Lens 1.0,” investigators demonstrate 99% recall with confidence-guided human-in-the-loop checks, reducing manual review requirements to <6%. Other teams show that LLMs can accurately extract CEA data, select statistical models, and even execute components of network meta-analyses. The A4SLR framework offers a formalized, agentic AI-supported workflow for systematic literature reviews and HTA evidence synthesis, while a large systematic review finds that generative AI is useful for question formulation and data extraction but still unreliable for literature search, study selection, and bias assessment.

Beyond evidence synthesis, additional studies explore how AI may adapt Excel-based health economic models, generate technical reports, and create synthetic datasets to expand research accessibility and privacy protection. A final survey of public preferences in Australia finds that for AI-driven mobile health apps, accuracy remains the dominant factor, followed by how well clinicians and AI systems collaborate.

###

###

Value in Health, Volume 28, Issue 11 November 2025

ISPOR REPORT https://www.valueinhealthjournal.com/issue/S1098-3015(25)X0012-7

A Taxonomy of Generative Artificial Intelligence in Health Economics and Outcomes Research: An ISPOR Working Group Report Rachael L. Fleurence, Xiaoyan Wang, Jiang Bian, Mitchell K. Higashi, Turgay Ayer, Hua Xu, Dalia Dawoud, and Jagpreet Chhatwal, on behalf of the ISPOR Working Group on Generative AI Editor's Choice l Free This report is about a taxonomy of generative artificial intelligence and large language models for health economics and outcomes research. ELEVATE-GenAI: Reporting Guidelines for the Use of Large Language Models in HEOR: An ISPOR Working Group Report Rachael L. Fleurence, Dalia Dawoud, Jiang Bian, Mitchell K. Higashi, Xiaoyan Wang, Hua Xu, Jagpreet Chhatwal, and Turgay Ayer, on behalf of the ISPOR Working Group on Generative AI Editor's Choice l Free The article introduces the ELEVATE-GenAI framework and checklist, providing structured guidance for reporting large-language-model-assisted research in health economics and outcomes research.

THEMED SECTION: ARTIFICIAL INTELLIGENCE IN HEALTH ECONOMICS AND OUTCOMES RESEARCH

Health Economics and Outcomes Research in the New Era of Artificial Intelligence: Catch Me If You Can Jaime Caro, Jagpreet Chhatwal, and Rachael L. Fleurence Free This editorial comments on the articles in this special section highlighting the rapid pace of development and the opportunities and challenges this presents for health economics and outcomes research. Artificial Intelligence in Health Economics and Outcomes Research: Highlighting the Contributions of Early Career Researchers Amy M. Miller and Emily Ortman Free The PhRMA Foundation awards 4 trainee authors with Challenge Awards for their outstanding articles on artificial intelligence in health economics and outcomes research. Validating Loon Lens 1.0 for Autonomous Abstract Screening and Confidence-Guided Human-in-the-Loop Workflows in Systematic Reviews Ghayath Janoudi, Mara Uzun, Tim Disher, Mia Jurdana, Ena Fuzul, Josip Ivkovic, and Brian Hutton Validating an agentic artificial intelligence abstract screener across 8 reviews showed 99% recall, calibrated confidence scores, and a sub-6% human check, lifting precision to 90%. Use of Large Language Models to Extract Cost-Effectiveness Analysis Data: A Case Study Xujun Gu, Hanwen Zhang, Divya Patil, Zafar Zafari, Julia Slejko, and Eberechukwu Onukwugha Open Access The current data extraction for cost-effectiveness analyses (CEA) data is time-consuming and prone to make mistakes. This study showed large language models match CEVR in extracting CEA data. The “Artificial Intelligence Statistician”: Utilizing Generative Artificial Intelligence to Select an Appropriate Model and Execute Network Meta-Analyses Tim Reason, Yunchou Wu, Cheryl Jones, Emma Benbow, Kasper Johannesen, and Bill Malcolm Open Access With the enhanced capabilities of large language models, their potential for selecting an appropriate statistical model and conducting a network meta-analysis was assessed. A4SLR: An Agentic Artificial Intelligence-Assisted Systematic Literature Review Framework to Augment Evidence Synthesis for Health Economics and Outcomes Research and Health Technology Assessment Kyeryoung Lee, Hunki Paek, Nneka Ofoegbu, Steven Rube, Mitchell K. Higashi, Dalia Dawoud, Hua Xu, Lizheng Shi, and Xiaoyan Wang This study reports the development, implementation, and validation of A4SLR, an artificial intelligence-assisted framework for health economics and outcomes research and health technology assessments. Role of Generative Artificial Intelligence in Assisting Systematic Review Process in Health Research: A Systematic Review Muhammed Rashid, Cheng Su Yi, Thipsukhon Sathapanasiri, Sariya Udayachalerm, Kansak Boonpattharatthiti, Suppachai Insuk, Sajesh K. Veettil, Nai Ming Lai, Nathorn Chaiyakunapruk, and Teerapon Dhippayom, on behalf of the Generative AI for Navigating Systematic Reviews working group Open Access Generative artificial intelligence supports systematic reviews in question formulation and data extraction, but lacks reliability for literature search, study selection and risk of bias assessment. Generative Artificial Intelligence to Automate the Adaptation of Excel Health Economic Models and Word Technical Reports William Rawlinson, Siguroli Teitsson, Tim Reason, Bill Malcolm, Andy Gimblett, and Sven L. Klijn Open Access Large language models have the potential to perform routine adaptations of Excel-based health economic models and technical reports accurately and rapidly at a low cost. Roles of Artificial Intelligence-Based Synthetic Data in Health Economics and Outcomes Research Tim C. Lai and Surachat Ngorsuraches Open Access Artificial-intelligence/machine-learning-driven synthetic data have the potential to enhance data accessibility and facilitate more robust analyses in health economics and outcomes research. Unravelling Public Preferences for the Use of Artificial Intelligence Mobile Health Applications in Australia Vinh Vo, Maame E. Woode, Stacy M. Carter, Chris Degeling, and Gang Chen Open Access Artificial-intelligence-based mobile health apps for heart disease and depression reveal that artificial intelligence accuracy matters the most, followed by doctor and artificial intelligence interaction.