Multimodal Deep Learning for Pulmonary Nodule Detection on Chest Radiography in High-Risk Adults, With Secondary Validation for All-Cause and Cause-Specific Mortality Prediction: A Multicenter Cohort Study.
Authors
Affiliations (6)
Affiliations (6)
- Department of Blood Transfusion Key Laboratory of Cancer Prevention and Therapy in Tianjin National Clinical Research Center for Cancer Tianjin's Clinical Research Center for Cancer Tianjin Medical University Cancer Institute and Hospital Tianjin Medical University Tianjin China.
- Department of Cancer Epidemiology and Biostatistics, Tianjin Key Laboratory of Molecular Cancer Epidemiology, Clinical Research Center for Cancer, Key Laboratory of Cancer Prevention and Therapy, Tianjin's Clinical Research Center For Cancer Tianjin Medical University Cancer Institute and Hospital, Tianjin Medical University Tianjin China.
- Public Health Science and Engineering College Tianjin University of Traditional Chinese Medicine Tianjin China.
- Department of Epidemiology and Statistics, School of Public Health Hebei Medical University, Hebei Key Laboratory of Environment and Human Health Shijiazhuang China.
- Department of Radiology National Clinical Research Centre for Cancer Key Laboratory of Cancer Prevention and Therapy Tianjin's Clinical Research Center for Cancer Tianjin Medical University Cancer Institute and Hospital, Tianjin Medical University Tianjin China.
- Department of Lung Cancer, Key Laboratory of Cancer Prevention and Therapy National Clinical Research Center for Cancer Tianjin's Clinical Research Center for Cancer Tianjin Medical University Cancer Institute and Hospital, Tianjin Medical University Tianjin China.
Abstract
Chest radiographs (CXRs) may encode prognostic signals beyond pulmonary nodule detection. We developed LungProNet, a multimodal deep-learning (DL) model that fuses CXR features with four epidemiologic variables (age, sex, smoking history, and family history) for pulmonary nodule detection as the primary task, with secondary validation for all-cause and cause-specific mortality prediction. LungProNet was trained and internally validated on Tianjin Lung Cancer Imaging Dataset (TLCID) (70/30; <i>n</i> = 2852/1227) and externally validated on ChestDR (<i>n</i> = 4848), with stratified analyses across epidemiologic strata. Discrimination was quantified by area under the curve (AUC) (95% confidence intervals), with accuracy, sensitivity, and specificity reported, and results were benchmarked against contemporary machine learning/DL baselines. The pretrained multimodal encoder was transferred without fine-tuning to the Prostate, Lung, Colorectal and Ovarian Cancer Screening Trial (PLCO) (<i>n</i> = 24,697); its fused embeddings were used as covariates in Cox proportional-hazards models, and time-dependent AUCs were evaluated at 1-12 years. For nodule detection, AUCs were 0.979 (0.975-0.982) in TLCID and 0.849 (0.835-0.862) in ChestDR; the TLCID stratified model reached 0.990 (0.984-0.994). In PLCO, AUCs were 0.925 (0.892-0.952) for all-cause mortality and 0.939-0.985 for cardiac-, lung cancer-, and Chronic Obstructive Pulmonary Disease (COPD)-cause mortality, with robust subgroup performance. These results support CXR-based nodule flagging within screening workflows and suggest secondary opportunistic risk stratification potential.