Wang Yimin, Li Yicong, Chen Wenya, Zhang Changzheng, Liang Lijuan, Huang Ruibo, Jian Wenhua, Liang Jianling, Zhu Senhua, Tu Dandan, Gao Yi, Zhong Nanshan, Zheng Jinping
National Center for Respiratory Medicine, State Key Laboratory of Respiratory Disease, National Clinical Research Center for Respiratory Disease, Guangzhou Institute of Respiratory Health, First Affiliated Hospital of Guangzhou Medical University, Guangzhou, China,
Tsinghua-Berkeley Shenzhen Institute, Tsinghua University, Shenzhen, China.
Respiration. 2022;101(9):841-850. doi: 10.1159/000524598. Epub 2022 May 12.
Due to the similar symptoms of upper airway obstruction to asthma, misdiagnosis is common. Spirometry is a cost-effective screening test for upper airway obstruction and its characteristic patterns involving fixed, variable intrathoracic and extrathoracic lesions. We aimed to develop a deep learning model to detect upper airway obstruction patterns and compared its performance with that of lung function clinicians.
Spirometry records were reviewed to detect the possible condition of airway stenosis. Then they were confirmed by the gold standard (e.g., computed tomography, endoscopy, or clinic diagnosis of upper airway obstruction). Images and indices derived from flow-volume curves were used for training and testing the model. Clinicians determined cases using spirometry records from the test set. The deep learning model evaluated the same data.
Of 45,831 patients' spirometry records, 564 subjects with curves suggesting upper airway obstruction, after verified by the gold standard, 351 patients were confirmed. These cases and another 200 cases without airway stenosis were used as the training and testing sets. 432 clinicians evaluated 20 cases of each of the three patterns and 20 no airway stenosis cases (n = 80). They assigned an accuracy of 41.2% (±15.4) (interquartile range: 27.5-52.5%), with poor agreements (κ = 0.12). For the same cases, the model generated a correct detection of 81.3% (p < 0.0001).
Deep learning could detect upper airway obstruction patterns from other classic patterns of ventilatory defects with high accuracy, whereas clinicians presented marked errors and variabilities. The model may serve as a support tool to enhance clinicians' correct diagnosis of upper airway obstruction using spirometry.
由于上气道梗阻与哮喘症状相似，误诊很常见。肺量计检查是对上气道梗阻及其涉及固定、可变胸内和胸外病变的特征模式进行筛查的一种经济有效的检查方法。我们旨在开发一种深度学习模型来检测上气道梗阻模式，并将其性能与肺功能临床医生的性能进行比较。
回顾肺量计记录以检测气道狭窄的可能情况。然后通过金标准（如计算机断层扫描、内窥镜检查或上气道梗阻的临床诊断）进行确认。从流量-容积曲线得出的图像和指标用于训练和测试模型。临床医生使用测试集的肺量计记录来确定病例。深度学习模型对相同数据进行评估。
在45831例患者的肺量计记录中，有564例受试者的曲线提示上气道梗阻，经金标准验证后，确诊351例患者。这些病例和另外200例无气道狭窄的病例用作训练集和测试集。432名临床医生对三种模式中的每种模式各20例以及20例无气道狭窄病例（n = 80）进行评估。他们给出的准确率为41.2%（±15.4）（四分位间距：27.5 - 52.5%），一致性较差（κ = 0.12）。对于相同的病例，模型的正确检测率为81.3%（p < 0.0001）。
深度学习能够高精度地从上气道通气缺陷的其他经典模式中检测出上气道梗阻模式，而临床医生则存在明显的错误和变异性。该模型可作为一种辅助工具，以提高临床医生使用肺量计对上气道梗阻的正确诊断。
