Classification of Exacerbation Frequency in the COPDGene Cohort Using Deep Learning With Deep Belief Networks

• Published in: IEEE journal of biomedical and health informatics Vol. 24; no. 6; pp. 1805 - 1813
• Main Authors: Ying, Jun, Dutta, Joyita, Guo, Ning, Hu, Chenhui, Zhou, Dan, Sitek, Arkadiusz, Li, Quanzheng
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.06.2020; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Belief networks; Chronic obstructive pulmonary disease; Chronic obstructive pulmonary disease (COPD); Classification; Cohort Studies; deep belief network (DBN); Deep Learning; Disease Progression; Diseases; exacerbation; Feature extraction; fisher score; Humans; Lung diseases; Lungs; Machine learning; Obstructive lung disease; Optimization; Pulmonary Disease, Chronic Obstructive - classification; Pulmonary Disease, Chronic Obstructive - epidemiology; Pulmonary Disease, Chronic Obstructive - genetics; Pulmonary Disease, Chronic Obstructive - physiopathology; Risk assessment; Sensitivity and Specificity; Support Vector Machine
• ISSN: 2168-2194; 2168-2208; 2168-2208
• DOI: 10.1109/JBHI.2016.2642944

This study aims to develop an automatic classifier based on deep learning for exacerbation frequency in patients with chronic obstructive pulmonary disease (COPD). A three-layer deep belief network (DBN) with two hidden layers and one visible layer was employed to develop classification models and the models' robustness to exacerbation was analyzed. Subjects from the COPDGene cohort were labeled with exacerbation frequency, defined as the number of exacerbation events per year. A total of 10 300 subjects with 361 features each were included in the analysis. After feature selection and parameter optimization, the proposed classification method achieved an accuracy of 91.99%, using a ten-fold cross validation experiment. The analysis of DBN weights showed that there was a good visual spatial relationship between the underlying critical features of different layers. Our findings show that the most sensitive features obtained from the DBN weights are consistent with the consensus showed by clinical rules and standards for COPD diagnostics. We, thus, demonstrate that DBN is a competitive tool for exacerbation risk assessment for patients suffering from COPD.