Popis: |
Yu Pu,1,* Xiuxiu Zhou,1,* Di Zhang,1,* Yu Guan,1,* Yi Xia,1 Wenting Tu,1 Yang Lu,2 Weidong Zhang,2 Chi-Cheng Fu,2 Qu Fang,2 Geertruida H de Bock,3 Shiyuan Liu,1 Li Fan1 1Department of Radiology, Changzheng Hospital, Naval Medical University, Shanghai, People’s Republic of China; 2Department of Scientific Research, Shanghai Aitrox Technology Corporation Limited, Shanghai, People’s Republic of China; 3Department of Epidemiology, University Medical Center Groningen, Groningen, the Netherlands*These authors contributed equally to this workCorrespondence: Shiyuan Liu; Li Fan, Department of Radiology, ChangZheng Hospital, Naval Medical University, No. 415 Fengyang Road, Shanghai, 200003, People’s Republic of China, Tel +86 21 81886012 ; Tel +86 21 81886012, Fax +86 21 63587668, Email cjr.liushiyuan@vip.163.com; fanli0930@163.comPurpose: To explore optimal threshold of FEV1% predicted value (FEV1%pre) for high-risk chronic obstructive pulmonary disease (COPD) using the parameter response mapping (PRM) based on machine learning classification model.Patients and Methods: A total of 561 consecutive non-COPD subjects who were screened for chest diseases in our hospital between August and October 2018 and who had complete questionnaire surveys, pulmonary function tests (PFT), and paired respiratory chest CT scans were enrolled retrospectively. The CT quantitative parameter for small airway remodeling was PRM, and 72 parameters were obtained at the levels of whole lung, left and right lung, and five lobes. To identify a more reasonable thresholds of FEV1% predicted value for distinguishing high-risk COPD patients from the normal, 80 thresholds from 50% to 129% were taken with a partition of 1% to establish a random forest classification model under each threshold, such that novel PFT-parameter-based high-risk criteria would be more consistent with the PRM-based machine learning classification model.Results: Machine learning-based PRM showed that consistency between PRM parameters and PFT was better able to distinguish high-risk COPD from the normal, with an AUC of 0.84 when the threshold was 72%. When the threshold was 80%, the AUC was 0.72 and when the threshold was 95%, the AUC was 0.64.Conclusion: Machine learning-based PRM is feasible for redefining high-risk COPD, and setting the optimal FEV1% predicted value lays the foundation for redefining high-risk COPD diagnosis.Keywords: chronic obstructive pulmonary disease, computed tomography, pulmonary function test, quantitative imaging, artificial intelligence |