OWL: an optimized and independently validated machine learning prediction model for lung cancer screening based on the UK Biobank, PLCO, and NLST populations

作者：Zoucheng Pan, Ruyang Zhang, Sipeng Shen, Yunzhi Lin, Longyao Zhang, Xiang Wang, Qian Ye, Xuan Wang, Jiajin Chen, Yang Zhao, David C. Christiani, Yi Li, Feng Chen, Yongyue Wei · 发表于：EBioMedicine · 年份：2023 · DOI：10.1016/j.ebiom.2023.104443 · 被引用次数：39 · 研究领域：Lung Cancer Diagnosis and Treatment、Radiomics and Machine Learning in Medical Imaging、AI in cancer detection

Background A reliable risk prediction model is critically important for identifying individuals with high risk of developing lung cancer as candidates for low-dose chest computed tomography (LDCT) screening. Leveraging a cutting-edge machine learning technique that accommodates a wide list of questionnaire-based predictors, we sought to optimize and validate a lung cancer prediction model. Methods We developed an O ptimized early W arning model for L ung cancer risk (OWL) using the XGBoost algorithm with 323,344 participants from the England area in UK Biobank (training set), and independently validated it with 93,227 participants from UKB Scotland and Wales area (validation set 1), as well as 70,605 and 66,231 participants in the Prostate, Lung, Colorectal, and Ovarian cancer screening trial (PLCO) control and intervention subpopulations, respectively (validation sets 2 & 3) and 23,138 and 18,669 participants in the United States National Lung Screening Trial (NLST) control and intervention subpopulations, respectively (validation sets 4 & 5). By comparing with three competitive prediction models, i.e., PLCO modified 2012 (PLCO m2012 ), PLCO modified 2014 (PLCO all2014 ), and the Liverpool Lung cancer Project risk model version 3 (LLPv3), we assessed the discrimination of OWL by the area under receiver operating characteristic curve (AUC) at the designed time point. We further evaluated the calibration using relative improvement in the ratio of expected to observed lung canc...