Development and Application of Natural Language Processing on Unstructured Data in Hypertension: A Scoping Review

Background Hypertension is a global health concern with a vast body of unstructured data, such as clinical notes, diagnosis reports, and discharge summaries, that can provide valuable insights. Natural Language Processing (NLP) has emerged as a powerful tool for extracting knowledge from unstructured data. This scoping review aims to explore the development and application of NLP on unstructured clinical data in hypertension, synthesizing existing research to identify trends, gaps, and underexplored areas for future investigation. Methods We conducted a systematic search of electronic databases, including PubMed/MEDLINE, Embase, Cochrane Library, Scopus, Web of Science, ACM Digital Library, and IEEE Xplore Digital Library, to identify relevant studies published until the end of 2022. The search strategy included keywords related to hypertension, NLP, and unstructured data. Data extraction included study characteristics, NLP methods, types of unstructured data sources, and key findings and limitations. Results The initial search yielded 951 articles, of which 45 met the inclusion criteria. The selected studies spanned various aspects of hypertension, including diagnosis, treatment, epidemiology, and clinical decision support. NLP was primarily used for extracting clinical information from unstructured electronic health records (EHRs) documents and text classification. Clinical notes were the most common sources of unstructured data. Key findings included improved diagnostic accuracy and the ability to comprehensively identify hypertensive patients with a combination of structured and unstructured data. However, the review revealed a lack of more advanced NLP techniques used in hypertension, generalization of NLP outside of benchmark datasets, and a limited focus on the integration of NLP tools into clinical practice. Discussion This scoping review highlights the diverse applications of NLP in hypertension research, emphasizing its potential to transform the field by harnessing valuable insights from unstructured data sources. There is a need to adopt and customize more advanced NLP for hypertension research. Future research should prioritize the development of NLP tools that can be seamlessly integrated into clinical settings to enhance hypertension management. Conclusion NLP demonstrates considerable promise in gleaning meaningful insights from the vast expanse of unstructured data within the field of hypertension, shedding light on diagnosis, treatment, and the identification of patient cohorts. As the field advances, there is a critical need to promote the use and development of advanced NLP methodologies that are tailored to hypertension and validated on real-world unstructured data. ### Competing Interest Statement The authors have declared no competing interest. ### Funding Statement This study did not receive any funding ### Author Declarations I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained. Yes I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals. Yes I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance). Yes I have followed all appropriate research reporting guidelines, such as any relevant EQUATOR Network research reporting checklist(s) and other pertinent material, if applicable. Yes All data produced in the present work are contained in the manuscript