arXiv:2402.15515v1 Announce Type: new
Abstract: A comprehensive view of factors associated with AD/ADRD will significantly aid in studies to develop new treatments for AD/ADRD and identify high-risk populations and patients for prevention efforts. In our study, we summarized the risk factors for AD/ADRD by reviewing existing meta-analyses and review articles on risk and preventive factors for AD/ADRD. In total, we extracted 477 risk factors in 10 categories from 537 studies. We constructed an interactive knowledge map to disseminate our study results. Most of the risk factors are accessible from structured Electronic Health Records (EHRs), and clinical narratives show promise as information sources. However, evaluating genomic risk factors using RWD remains a challenge, as genetic testing for AD/ADRD is still not a common practice and is poorly documented in both structured and unstructured EHRs. Considering the constantly evolving research on AD/ADRD risk factors, literature mining via NLP methods offers a solution to automatically update our knowledge map.

Expert Commentary: Understanding Risk Factors for AD/ADRD

Alzheimer’s disease and related dementias (AD/ADRD) pose significant challenges to both healthcare professionals and researchers. To address this, a comprehensive view of the factors associated with AD/ADRD is crucial. This not only aids in the development of new treatments but also helps identify high-risk populations and individuals for preventive efforts.

In a recent study, researchers aimed to summarize the risk factors for AD/ADRD by reviewing existing meta-analyses and review articles. They extracted a total of 477 risk factors across 10 categories from 537 studies. By constructing an interactive knowledge map, they aimed to disseminate their study results effectively.

The multidisciplinary nature of studying AD/ADRD risk factors is evident in this research. It brings together various domains, including epidemiology, genetics, clinical medicine, and information technology, to provide a comprehensive understanding of this complex condition.

Data Sources: Electronic Health Records (EHRs) and Clinical Narratives

The study highlights the potential of using structured Electronic Health Records (EHRs) as a rich resource for accessing most of the identified risk factors. EHRs contain valuable clinical data that can be leveraged to identify patterns and associations with AD/ADRD. However, it is essential to recognize that mining this data requires robust data management systems, privacy considerations, and standardized documentation practices.

Moreover, the study acknowledges the promise of clinical narratives as information sources. Clinical narratives, such as physician notes and patient records, provide valuable insights that may not be captured in structured data alone. Analyzing these unstructured narratives using Natural Language Processing (NLP) methods can offer a more comprehensive understanding of risk factors for AD/ADRD.

The Challenge of Genomic Risk Factors

The evaluation of genomic risk factors remains a challenge. As the study emphasizes, genetic testing for AD/ADRD is not yet a common practice, and the documentation of these results in both structured and unstructured EHRs is inadequate. Consequently, accessing and analyzing genomic data using Real-World Data (RWD) requires substantial improvements in genetic testing practices and data capture.

Literature Mining via NLP

Given the constantly evolving research on AD/ADRD risk factors, it is crucial to keep knowledge maps up to date. Literature mining, enabled by NLP methods, can be a valuable tool for automatically updating our understanding of risk factors. By analyzing new research articles and incorporating relevant findings into the knowledge map, researchers can stay abreast of the latest advancements in this field.

In conclusion, this study provides a valuable overview of the risk factors for AD/ADRD, incorporating a multi-disciplinary approach. The use of EHRs, clinical narratives, and NLP methods demonstrates the interconnectedness of various domains in studying this complex condition. Moving forward, efforts should focus on improving genomic data capture and mining literature to continually update our knowledge and advance the development of effective treatments and preventive strategies for AD/ADRD.

Read the original article