OBJECTIVES: To identify real-world data (RWD) sources for Alzheimer’s Disease (AD) in Asia Pacific (AP) and determine access and utility for conducting evidence generation studies.

METHODS: Artificial Intelligence (AI)-powered systematic literature review of academic publications (2014-2024, PubMed) to identify AP RWD sources for AD. Leveraging Large Language Models (LLMs), our AI system harnessed a semantic search protocol to identify relevant data sources and extract key information including database type, coverage, demographics, treatments, clinical, humanistic, and economic data. Results were manually validated by two independent reviewers. Data sources with the highest number of publications (top 10%) were prioritized for assessment of data utility.

RESULTS: 156 citations were retrieved. 121 unique data sources across 9 AP countries were identified after manual validation; almost one-third cover South Korea (29%), followed by China (25%), Japan (24%) Australia (8%), Taiwan (7%), Thailand (3%), Hong Kong (2%), Singapore (1%) and Malaysia (1%). Hospital/ Electronic Medical Records (EMRs) account for the largest proportion (49%), followed by registries (25%), insurance databases (8%) and population surveys (7%). Data access, assessed by number of publications, was greatest in South Korea, followed by China and Japan. 10 data sources were prioritized for utility assessment. Data utility, determined by the number of variables available, was greatest in South Korea, followed by Australia and Taiwan. The most widely reported variables were demographics and treatment information; least reported were quality of life and indirect cost indicators.

CONCLUSIONS: There is significant value in mapping AD RWD for assessing the feasibility of health economic outcome research and informing downstream evidence generation activities. South Korea, China, Japan, and Australia are key contributors of AD RWD, offering diverse datasets for better understanding and management of AD in AP. RWD sources for AD in AP are associated with data gaps and variable access, highlighting the importance of collaborative efforts in comprehensive data collection.