Feasibility of identifying factors related to Alzheimer's disease and related dementia in real-world data

A comprehensive understanding of factors associated with Alzheimers disease (AD) and AD-related dementias (AD/ADRD) will significantly enhance efforts when designing new studies to develop new treatments and identify high-risk populations for prevention. We reviewed existing meta-analyses and review articles on AD/ADRD risk and preventive factors, extracting 477 risk factors across 10 categories from 537 studies. An interactive knowledge graph was created to share our study findings. Most risk factors can be found in structured Electronic Health Records (EHRs), with clinical narratives also providing valuable information. However, assessing genomic risk factors using real-world data (RWD) like EHRs remains a challenge, as genetic testing for AD/ADRD is still not a common practice and poorly documented in both structured and unstructured EHRs. Given the constant and rapid evolution of AD/ADRD research, using natural language processing (NLP) for literature mining emerges as a viable method to continually and automatically update our knowledge graph.