基于AI算法的磁共振检查预约准时与迟到预测的可行性研究及其临床应用.pdfVIP

研究论著 RESEARCH WORK 基于AI算法的磁共振检查预约准时与迟到 预测的可行性研究及其临床应用 任昕，刘水，张晓东，王霄英 北京大学第一医院医学影像科，北京 100034 [摘 要] 目的 探究以人工智能算法为基础建立磁共振检查预约迟到预测模型，对磁共振检查预约患者做出准时与迟到预测的 可行性。方法 回顾性从放射科信息系统收集2018年1月1 日—12月31 日连续的已完成磁共振检查的患者预约信息共9087例， 经过数据清洗后分为准时组（患者到达时间早于患者预约时间，n=8265 ），和迟到组（患者到达时间晚于患者预约时间， n=822 ）。使用XGBoost （Extreme Gradient Boosting ）算法作为分类预测模型的基础架构，并结合梯度提升算法中的特征重 要性分数生成特征重要性排序列表，训练二分类模型。数据随机分为训练集（70% ）和测试集（30% ）。以测试集的预测 结果检测磁共振检查预约迟到分类预测模型的效能。结果 在测试集中，准时者2488例，迟到者239例，磁共振检查预约迟 到模型预测准时与迟到的精确度分别为0.994和0.941 ，召回率分别为0.994和0.933 ，F1-分数分别为0.994和0.937 ，ROC 曲线 下面积均为0.99 。结论 使用基于XGBoost算法分类模型可对磁共振检查预约做出准时与迟到的预测，为实际临床工作中进 一步根据检查项目、检查人数等智能化地分配医学影像科的设备资源、人力资源，以提供更加高效优质的影像检查服务提 供了可能。 [关键词] 人工智能；放射科信息系统；磁共振检查预约；准时与迟到；预测 Feasibility Study of On-Time and Late Prediction of MR Examination Appointments Based on Artificial Intelligence Algorithm and Its Clinical Application REN Xin, LIU Shui, ZHANG Xiaodong, WANG Xiaoying Department of Radiology, Peking University First Hospital, Beijing 100034, China Abstract: Objective To explore the feasibility of establishing a late prediction model for MR appointment based on artificial intelligence algorithm to predict the punctuality and lateness of MR appointment patients. Methods The appointment data of 9087 consecutive patients who had completed MR examinations from January 1, 2018 to December 31, 2018 was collected retrospectively from the hospital radiology information system, and after data cleaning, the patients were divided into on time group (patient arrival time earlier than patient appointment time, n=8265) and late group (patient arrival time later than patient appointment time, n=822). The XGBoost (Extreme Gradient Boosting) algorithm was used as the infrastructure for the classification prediction model and combined with the feature impo