Identifying and characterizing a chronic cough cohort through electronic health records.

Identifying and characterizing a chronic cough cohort through electronic health records. Chest. 2020 Dec 17;: Authors: Weiner M, Dexter PR, Heithoff K, Roberts AR, Liu Z, Griffith A, Hui S, Schelfhout J, Dicpinigaitis P, Doshi I, Weaver JP Abstract BACKGROUND: Chronic cough (CC) of eight or more weeks affects about 10% of adults and may lead to expensive treatments and reduced quality of life. Incomplete diagnostic coding complicates identifying CC in electronic health records (EHRs). Natural language processing (NLP) of EHR text could improve detection. RESEARCH QUESTION: We assessed NLP in identifying cough in EHRs, and characterized adults and encounters with CC. STUDY DESIGN AND METHODS: A Midwestern EHR system identified patients aged 18-85 during 2005-2015. NLP evaluated text notes except prescriptions and instructions, for mentions of cough. Two clinicians and a biostatistician reviewed twelve sets of 50 encounters each, with iterative refinements, until the positive predictive value for cough encounters exceeded 90%. NLP, ICD-10, or medication identified cough. Three encounters spanning 56 to 120 days defined CC. Descriptive statistics summarized patients and encounters, including referrals. RESULTS: Optimizing NLP required identifying and eliminating cough denials, instructions, and historical references. Of 235,457 cough encounters, 23% had a relevant diagnostic code or medication. Applying chronicit...
Source: Chest - Category: Respiratory Medicine Authors: Tags: Chest Source Type: research