Deep learning predicts cardiovascular disease risks from lung cancer screening low dose computed tomography

• Published in: Nature communications Vol. 12; no. 1; pp. 2963 - 10
• Main Authors: Chao, Hanqing, Shan, Hongming, Homayounieh, Fatemeh, Singh, Ramandeep, Khera, Ruhani Doda, Guo, Hengtao, Su, Timothy, Wang, Ge, Kalra, Mannudeep K., Yan, Pingkun
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 20.05.2021; Nature Publishing Group; Nature Portfolio
• Subjects: 692/499; 692/53/2423; Adult; Aged; Aged, 80 and over; Calcification; Calcification (ectopic); Cancer screening; Cardiovascular disease; Cardiovascular diseases; Cardiovascular Diseases - diagnosis; Cardiovascular Diseases - epidemiology; Cardiovascular Diseases - etiology; Clinical Trials as Topic; Computed tomography; Coronary artery; Coronary Vessels - diagnostic imaging; Datasets as Topic; Deep Learning; Dosage; EKG; Electrocardiography; Female; Follow-Up Studies; Health risks; Heart diseases; Human performance; Humanities and Social Sciences; Humans; Image Processing, Computer-Assisted - methods; Lung - diagnostic imaging; Lung cancer; Lung diseases; Lung Neoplasms - complications; Lung Neoplasms - diagnosis; Male; Mass Screening - methods; Mass Screening - statistics & numerical data; Medical screening; Middle Aged; Mortality; Mortality risk; multidisciplinary; Prediction models; Retrospective Studies; Risk; Risk Assessment - methods; Risk Assessment - statistics & numerical data; Risk Factors; Risk groups; ROC Curve; Science; Science (multidisciplinary); Tomography; Tomography, X-Ray Computed - statistics & numerical data
• ISSN: 2041-1723; 2041-1723
• DOI: 10.1038/s41467-021-23235-4

Cancer patients have a higher risk of cardiovascular disease (CVD) mortality than the general population. Low dose computed tomography (LDCT) for lung cancer screening offers an opportunity for simultaneous CVD risk estimation in at-risk patients. Our deep learning CVD risk prediction model, trained with 30,286 LDCTs from the National Lung Cancer Screening Trial, achieves an area under the curve (AUC) of 0.871 on a separate test set of 2,085 subjects and identifies patients with high CVD mortality risks (AUC of 0.768). We validate our model against ECG-gated cardiac CT based markers, including coronary artery calcification (CAC) score, CAD-RADS score, and MESA 10-year risk score from an independent dataset of 335 subjects. Our work shows that, in high-risk patients, deep learning can convert LDCT for lung cancer screening into a dual-screening quantitative tool for CVD risk estimation. Low dose computed tomography (LDCT) for lung cancer screening offers an opportunity for simultaneous CVD risk estimation in at-risk patients. Here, the authors develop a deep learning model to perform this task, showing human-level performance.