Extracting Cognitive Impairment Assessment Information From Unstructured Notes in Electronic Health Records Using Natural Language Processing Tools: Validation with Clinical Assessment Data

Kuan-Yuan Wang,1– 3,* Mufaddal Mahesri,4,* John Novoa-Laurentiev,4 Lily G Bessette,4 Cassandra York,4 Heidi Zakoul,4 Su Been Lee,4 Kerry Ngan,4 Li Zhou,4,5,* Dae Hyun Kim,2,3,5,* Kueiyu Joshua Lin4– 6,* 1National Cheng Kung University Hospital, College of Medicine, National Cheng Kung University, Tainan, Taiwan; 2Marcus Institute for Aging Research, Hebrew SeniorLife, Boston, MA, USA; 3Beth Israel Deaconess Medical Center, Boston, MA, USA; 4Brigham and Women’s Hospital, Boston, MA, USA; 5Harvard Medical School, Boston, MA, USA; 6Massachusetts General Hospital, Boston, MA, USA*These authors contributed equally to this workCorrespondence: Kueiyu Joshua Lin, Division of Pharmacoepidemiology and Pharmacoeconomics, Department of Medicine, Brigham and Women’s Hospital, Harvard Medical School, 1620 Tremont St. Suite 3030, Boston, MA, 02120, USA, Tel +1 (617) 278-0930, Fax +1 (617) 232-8602, Email [email protected]: We aimed to develop a Natural Language Processing (NLP) algorithm to extract cognitive scores from electronic health records (EHR) data and compare them with cognitive function recorded by Centers for Medicare & Medicaid Services (CMS)-mandated clinical assessments in nursing homes and home health visits.Patients and Methods: We identified a cohort of Medicare beneficiaries who had either the Minimum Data Set (MDS) or Outcome and Assessment Information Set (OASIS) linked to EHR data from the Research Patient Data Registry (Mass General Brigham, Boston, MA) from 2010 to 2019. We applied an NLP approach to identify the Montreal Cognitive Assessment (MoCA) and the Mini-Mental State Examination (MMSE) scores from unstructured clinician notes in EHR. Using the NLP-extracted MoCA or MMSE scores from EHR, we compared mean differences of extracted MoCA or MMSE by cognition status determined by MDS (impaired vs intact cognition) and OASIS (severe impairment vs intact cognition) data, respectively.Results: Our study cohort had 7419 patients who had MDS (19.7%) or OASIS (80.3%) assessments, with a mean age of 80 (SD=7) years and 60% female. In EHR, the NLP algorithm extracted cognitive test scores with 97% accuracy (95% CI: 92– 99%) for MoCA and 100% accuracy (95% CI: 84– 100%) for MMSE. In MDS, the mean difference in extracted MoCA was − 5.6 (95% CI: − 8.7, − 2.4, p=0.0008), and the mean difference in extracted MMSE was − 7.9 (95% CI: − 12.4, − 3.5, p=0.0012). In OASIS, the mean difference in extracted MoCA and extracted MMSE was − 4.8 (95% CI: − 9.1, − 0.6, p=0.0006) and − 4.5 (95% CI: − 9.5, − 0.5, p=0.0182), respectively.Conclusion: We developed an NLP algorithm to accurately extract cognitive scores from unstructured EHR, and these extracted cognitive scores were well correlated with cognition function recorded in CMS-mandated clinical assessments. This could help researchers identify patients with various degrees of cognitive impairment in EHR-based research.Keywords: natural language processing, electronic health records, cognitive impairment, mini-mental status examination, Montreal Cognitive Assessment