Department of Neurosurgery, Seoul National University Bundang Hospital, Seoul National University College of Medicine, Seongnam-si, Republic of Korea.
Department of Applied Statistics, The University of Suwon, Hwaseong-si, Republic of Korea.
Sci Rep. 2020 Apr 24;10(1):6921. doi: 10.1038/s41598-020-63906-8.
An efficient method for identifying subjects at high risk of an intracranial aneurysm (IA) is warranted to provide adequate radiological screening guidelines and effectively allocate medical resources. We developed a model for pre-diagnosis IA prediction using a national claims database and health examination records. Data from the National Health Screening Program in Korea were utilized as input for several machine learning algorithms: logistic regression (LR), random forest (RF), scalable tree boosting system (XGB), and deep neural networks (DNN). Algorithm performance was evaluated through the area under the receiver operating characteristic curve (AUROC) using different test data from that employed for model training. Five risk groups were classified in ascending order of risk using model prediction probabilities. Incidence rate ratios between the lowest- and highest-risk groups were then compared. The XGB model produced the best IA risk prediction (AUROC of 0.765) and predicted the lowest IA incidence (3.20) in the lowest-risk group, whereas the RF model predicted the highest IA incidence (161.34) in the highest-risk group. The incidence rate ratios between the lowest- and highest-risk groups were 49.85, 35.85, 34.90, and 30.26 for the XGB, LR, DNN, and RF models, respectively. The developed prediction model can aid future IA screening strategies.
需要一种有效的方法来识别颅内动脉瘤（IA）高危患者，以便提供充分的影像学筛查指南，并有效分配医疗资源。我们使用国家索赔数据库和健康检查记录开发了一种用于预测颅内动脉瘤的模型。利用韩国国家健康筛查计划的数据作为输入，使用了几种机器学习算法：逻辑回归（LR）、随机森林（RF）、可扩展树提升系统（XGB）和深度神经网络（DNN）。通过使用不同的测试数据对不同模型进行评估，计算了接收器操作特征曲线（AUROC）下的面积。根据模型预测概率，将五个风险组按风险从低到高进行分类。然后比较最低风险组和最高风险组之间的发病率比值。XGB 模型产生了最佳的颅内动脉瘤风险预测（AUROC 为 0.765），预测出最低风险组的颅内动脉瘤发病率最低（3.20），而 RF 模型预测出最高风险组的颅内动脉瘤发病率最高（161.34）。XGB、LR、DNN 和 RF 模型的最低风险组和最高风险组之间的发病率比值分别为 49.85、35.85、34.90 和 30.26。开发的预测模型可以辅助未来的颅内动脉瘤筛查策略。
