Fig. 1From: Screening and staging of chronic obstructive pulmonary disease with deep learning based on chest X-ray images and clinical parametersDiagram of the study procedure. (A) The inclusion and exclusion flow chart of the dataset; (B) Flowchart for proposed COPD detection and staging prediction model. Deep learning models were trained to classify COPD based on CXR images or clinical features only. The best two models were selected and mixed as a new model for simultaneously extracting clinical data and CXR images to identify COPD. COPD, chronic obstructive pulmonary disease; GOLD, the global initiative for chronic obstructive lung disease; PEF, pulmonary function test; CXR, chest X-ray; BMI, body mass index; AUC, area under the curveBack to article page