Department of Medicine, Duke University Medical Center, Durham, NC, United States of America.
Department of Cognitive Science, Case Western University, Cleveland, OH, United States of America.
PLoS One. 2024 Jan 29;19(1):e0297519. doi: 10.1371/journal.pone.0297519. eCollection 2024.
Pulmonary function tests (PFTs) are usually interpreted by clinicians using rule-based strategies and pattern recognition. The interpretation, however, has variabilities due to patient and interpreter errors. Most PFTs have recognizable patterns that can be categorized into specific physiological defects. In this study, we developed a computerized algorithm using the python package (pdfplumber) and validated against clinicians' interpretation. We downloaded PFT reports in the electronic medical record system that were in PDF format. We digitized the flow volume loop (FVL) and extracted numeric values from the reports. The algorithm used FEV1/FVC<0.7 for obstruction, TLC<80%pred for restriction and <80% or >120%pred for abnormal DLCO. The algorithm also used a small airway disease index (SADI) to quantify late expiratory flattening of the FVL to assess small airway dysfunction. We devised keywords for the python Natural Language Processing (NLP) package (spaCy) to identify obstruction, restriction, abnormal DLCO and small airway dysfunction in the reports. The algorithm was compared to clinicians' interpretation in 6,889 PFTs done between March 1st, 2018, and September 30th, 2020. The agreement rates (Cohen's kappa) for obstruction, restriction and abnormal DLCO were 94.4% (0.868), 99.0% (0.979) and 87.9% (0.750) respectively. In 4,711 PFTs with FEV1/FVC≥0.7, the algorithm identified 190 tests with SADI < lower limit of normal (LLN), suggesting small airway dysfunction. Of these, the clinicians (67.9%) also flagged 129 tests. When SADI was ≥ LLN, no clinician's reports indicated small airway dysfunction. Our results showed the computerized algorithm agreed with clinicians' interpretation in approximately 90% of the tests and provided a sensitive objective measure for assessing small airway dysfunction. The algorithm can improve efficiency and consistency and decrease human errors in PFT interpretation. The computerized algorithm works directly on PFT reports in PDF format and can be adapted to incorporate a different interpretation strategy and platform.
肺功能测试 (PFTs) 通常由临床医生使用基于规则的策略和模式识别进行解释。然而，由于患者和解释者的错误，解释存在变异性。大多数 PFT 都有可识别的模式，可以归类为特定的生理缺陷。在这项研究中，我们使用 python 包 (pdfplumber) 开发了一种计算机算法，并与临床医生的解释进行了验证。我们从电子病历系统中下载了以 PDF 格式保存的 PFT 报告。我们对流量容积环 (FVL) 进行了数字化，并从报告中提取了数值。该算法使用 FEV1/FVC<0.7 表示阻塞，TLC<80%pred 表示限制，<80%或>120%pred 表示异常 DLCO。该算法还使用小气道疾病指数 (SADI) 来量化 FVL 的后期呼气平坦度，以评估小气道功能障碍。我们为 python 自然语言处理 (NLP) 包 (spaCy) 设计了关键词，以识别报告中的阻塞、限制、异常 DLCO 和小气道功能障碍。该算法在 2018 年 3 月 1 日至 2020 年 9 月 30 日期间对 6889 次 PFT 进行了比较，与临床医生的解释相吻合。阻塞、限制和异常 DLCO 的一致率（Cohen 的 kappa）分别为 94.4%（0.868）、99.0%（0.979）和 87.9%（0.750）。在 190 次 FEV1/FVC≥0.7 的 PFT 中，该算法发现了 190 次 SADI<正常值下限 (LLN)，提示小气道功能障碍。其中，临床医生（67.9%）还标记了 129 次。当 SADI≥LLN 时，没有临床医生的报告表明存在小气道功能障碍。我们的结果表明，该计算机算法在大约 90%的测试中与临床医生的解释相吻合，并为评估小气道功能障碍提供了一种敏感的客观测量方法。该算法可以提高 PFT 解释的效率和一致性，减少人为错误。该算法可以直接在 PDF 格式的 PFT 报告上运行，并可以适应不同的解释策略和平台。
