Regenstrief Institute, Inc., Indianapolis, IN; Indiana University, Indianapolis, IN; Center for Health Information and Communication, US Department of Veterans Affairs, Veterans Health Administration, Health Services Research and Development Service CIN 13-416, Richard L. Roudebush VA Medical Center, Indianapolis, IN.
Regenstrief Institute, Inc., Indianapolis, IN; Indiana University, Indianapolis, IN; Eskenazi Health, Indianapolis, IN.
Chest. 2021 Jun;159(6):2346-2355. doi: 10.1016/j.chest.2020.12.011. Epub 2020 Dec 17.
Chronic cough (CC) of 8 weeks or more 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.
Can NLP be used to identify cough in EHRs, and to characterize adults and encounters with CC?
A Midwestern EHR system identified patients aged 18 to 85 years during 2005 to 2015. NLP was used to evaluate text notes, except prescriptions and instructions, for mentions of cough. Two physicians and a biostatistician reviewed 12 sets of 50 encounters each, with iterative refinements, until the positive predictive value for cough encounters exceeded 90%. NLP, International Classification of Diseases, 10th revision, or medication was used to identify cough. Three encounters spanning 56 to 120 days defined CC. Descriptive statistics summarized patients and encounters, including referrals.
Optimizing NLP required identifying and eliminating cough denials, instructions, and historical references.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 chronicity to cough encounters identified 23,371 patients (61% women) with CC. NLP alone identified 74% of these patients; diagnoses or medications alone identified 15%. The positive predictive value of NLP in the reviewed sample was 97%. Referrals for cough occurred for 3.0% of patients; pulmonary medicine was most common initially (64% of referrals).
Some patients with diagnosis codes for cough, encounters at intervals greater than 4 months, or multiple acute cough episodes may have been misclassified.
NLP successfully identified a large cohort with CC. Most patients were identified through NLP alone, rather than diagnoses or medications. NLP improved detection of patients nearly sevenfold, addressing the gap in ability to identify and characterize CC disease burden. Nearly all cases appeared to be managed in primary care. Identifying these patients is important for characterizing treatment and unmet needs.
8 周或以上的慢性咳嗽（CC）影响约 10%的成年人，并可能导致昂贵的治疗和生活质量下降。电子健康记录（EHR）中不完全的诊断编码使 CC 的识别变得复杂。EHR 文本的自然语言处理（NLP）可以提高检测能力。
NLP 是否可用于识别 EHR 中的咳嗽，并对 CC 患者和就诊情况进行特征描述？
中西部的 EHR 系统在 2005 年至 2015 年期间确定了 18 至 85 岁的患者。使用 NLP 评估文本记录，除处方和医嘱外，还评估与咳嗽相关的记录。两位医生和一位生物统计学家对 12 组每组 50 次就诊进行了回顾，通过迭代改进，直到咳嗽就诊的阳性预测值超过 90%。使用 NLP、国际疾病分类第 10 版或药物来识别咳嗽。三次就诊跨越 56 至 120 天，定义为 CC。描述性统计总结了患者和就诊情况，包括转诊情况。
优化 NLP 需要识别和消除咳嗽否认、医嘱和历史参考。在 235457 次咳嗽就诊中，23%有相关诊断代码或药物。对咳嗽就诊应用慢性期，确定了 23371 例 CC 患者（61%为女性）。NLP 单独识别了 74%的患者；诊断或药物单独识别了 15%的患者。在回顾样本中，NLP 的阳性预测值为 97%。3.0%的患者因咳嗽就诊；最初最常见的是肺病转诊（64%的转诊）。
一些有咳嗽诊断代码、就诊间隔超过 4 个月或多次急性咳嗽发作的患者可能被误诊。
NLP 成功地识别了大量 CC 患者。大多数患者通过 NLP 单独识别，而不是通过诊断或药物。NLP 将患者的检出率提高了近 7 倍，解决了识别和描述 CC 疾病负担能力的差距。几乎所有的病例似乎都在初级保健中得到了管理。识别这些患者对于描述治疗和未满足的需求非常重要。
