Identifying Patients With Hypoglycemia Using Natural Language Processing: Systematic Literature Review

• Published in: JMIR diabetes Vol. 7; no. 2; p. e34681
• Main Authors: Zheng, Yaguang, Dickson, Victoria Vaughan, Blecker, Saul, Ng, Jason M, Rice, Brynne Campbell, Melkus, Gail D’Eramo, Shenkar, Liat, Mortejo, Marie Claire R, Johnson, Stephen B
• Format: Journal Article
• Language: English
• Published: Canada JMIR Publications 16.05.2022
• Subjects: Algorithms; Artificial intelligence; Data mining; Deep learning; Diabetes; Electronic health records; Glucose; Hypoglycemia; Insulin; Language; Machine learning; Medical records; Metadata; Mortality; Natural language processing; Patients; Questionnaires; Review; Subject heading schemes; Systematic review; Text analysis; United States > US; electronic health records; natural language processing; diabetes; hypoglycemia
• ISSN: 2371-4379; 2371-4379
• DOI: 10.2196/34681

Accurately identifying patients with hypoglycemia is key to preventing adverse events and mortality. Natural language processing (NLP), a form of artificial intelligence, uses computational algorithms to extract information from text data. NLP is a scalable, efficient, and quick method to extract hypoglycemia-related information when using electronic health record data sources from a large population. The objective of this systematic review was to synthesize the literature on the application of NLP to extract hypoglycemia from electronic health record clinical notes. Literature searches were conducted electronically in PubMed, Web of Science Core Collection, CINAHL (EBSCO), PsycINFO (Ovid), IEEE Xplore, Google Scholar, and ACL Anthology. Keywords included hypoglycemia, low blood glucose, NLP, and machine learning. Inclusion criteria included studies that applied NLP to identify hypoglycemia, reported the outcomes related to hypoglycemia, and were published in English as full papers. This review (n=8 studies) revealed heterogeneity of the reported results related to hypoglycemia. Of the 8 included studies, 4 (50%) reported that the prevalence rate of any level of hypoglycemia was 3.4% to 46.2%. The use of NLP to analyze clinical notes improved the capture of undocumented or missed hypoglycemic events using International Classification of Diseases, Ninth Revision (ICD-9), and International Classification of Diseases, Tenth Revision (ICD-10), and laboratory testing. The combination of NLP and ICD-9 or ICD-10 codes significantly increased the identification of hypoglycemic events compared with individual methods; for example, the prevalence rates of hypoglycemia were 12.4% for International Classification of Diseases codes, 25.1% for an NLP algorithm, and 32.2% for combined algorithms. All the reviewed studies applied rule-based NLP algorithms to identify hypoglycemia. The findings provided evidence that the application of NLP to analyze clinical notes improved the capture of hypoglycemic events, particularly when combined with the ICD-9 or ICD-10 codes and laboratory testing.