Artificial Intelligence-Powered Identification, Access, and Utility Mapping of Real-World Data Sources for Alzheimer's Disease in Europe

Author(s)

Hogg L1, Low KW2, Tan K2, Toh M2, Gras A2, Jain V3, Escalante V4
1Ipsos, Singapore, 01, Singapore, 2Ipsos, Singapore, Singapore, 3Ipsos, London, United Kingdom, UK, 4Ipsos, Warsaw, MZ, Poland

Presentation Documents

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

METHODS: AI-powered systematic literature review of academic publications (2014-2024, PubMed) to identify RWD sources for AD in Europe. 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: 225 citations were retrieved. 158 unique data sources were identified after manual validation; coverage was highest in France (18%), followed by Sweden (16%), Spain (14%) and Germany (13%). Europe-wide databases contributed 5% of all data sources. Registries represented the largest category (39%), encompassing epidemiological registries, dementia research and pre-clinical dementia research registries. This was followed by Hospital/ Electronic Medical Records (EMRs) (33%) and population surveys (11%). Data access, assessed by the number of publications, was greatest in Sweden, followed by France and Spain. 17 data sources were prioritized for utility assessment. Data utility, determined by the number of variables available, was greatest in Denmark, followed by Spain, Germany, and Sweden. The most widely reported variables include demographics and treatment information; least reported were indirect cost and quality of life 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. France, Sweden, Spain, Germany, and Denmark are key contributors of AD RWD, offering diverse datasets for better understanding and management of AD. RWD sources for AD across Europe are associated with data gaps and variable access, highlighting the importance of collaborative efforts in comprehensive data collection.

Conference/Value in Health Info

2024-11, ISPOR Europe 2024, Barcelona, Spain

Value in Health, Volume 27, Issue 12, S2 (December 2024)

Code

RWD140

Topic

Epidemiology & Public Health, Methodological & Statistical Research, Real World Data & Information Systems, Study Approaches

Topic Subcategory

Artificial Intelligence, Machine Learning, Predictive Analytics, Distributed Data & Research Networks, Literature Review & Synthesis

Disease

Neurological Disorders

Explore Related HEOR by Topic


Your browser is out-of-date

ISPOR recommends that you update your browser for more security, speed and the best experience on ispor.org. Update my browser now

×