Artificial intelligence captures clinicians’ adherence to asthma guidelines using EHRs
Published: November 16, 2021
Clinician’s asthma guideline adherence in primary care is low, missing opportunities for improving asthma care quality and outcome. However, assessing clinician’s guideline adherence requires manual chart review of electronic health records (EHRs), often infeasible and not scalable in asthma care. Natural language processing (NLP), a subset of artificial intelligence (AI), has a potential to automate chart review of EHRs and provide an innovative way to assess and improve clinicians’ adherence to evidence-based asthma management guidelines.
In the Mayo Clinic study, Sagheb et al demonstrated the feasibility of an AI tool using NLP, leveraging free text of EHRs of pediatric patients to extract key components of the 2007 National Asthma Education and Prevention Program guidelines. They designed a retrospective cross-sectional study using a birth cohort with asthma diagnosis between 2003 and 2016 (N=300, 1,039 clinical notes with an asthma diagnosis). Rule-based NLP algorithms were developed to identify asthma guideline elements by examining care description in EHR free text. This study was published in The Journal of Allergy and Clinical Immunology: In Practice, April 2022.
The NLP algorithms demonstrated the feasibility with high accuracy to identify asthma guideline elements in EHRs (sensitivity of 0.82 - 1.0, specificity of 0.95 - 1.0, positive predictive value of 0.86 -1.0, and negative protective value of 0.92 - 1.0). NLP technologies may enable automated assessment of clinicians’ documentation in EHRs regarding adherence to asthma guidelines and can be a useful tool for population management and research assessing and monitoring asthma care quality and outcomes.
The Journal of Allergy and Clinical Immunology: In Practice is an official journal of the AAAAI, focusing on practical information for the practicing clinician.