A Machine Learning-Based Predictive Model to Identify Patients Who Failed to Attend a Follow-up Visit for Diabetes Care After Recommendations From a National Screening Program
A Machine Learning-Based Predictive Model to Identify Patients Who Failed to Attend a Follow-up Visit for Diabetes Care After Recommendations From a National Screening Program
复制标题
DOI：
10.2337/dc21-1841
复制
发表时间：
2022-06-01
期刊：
影响因子：
16.2
通讯作者：
Kadowaki, Takashi
中科院分区：
文献类型：
--
作者：
Okada, Akira;Hashimoto, Yohei;Kadowaki, Takashi
据报道，在日本，三分之二在筛查期间糖尿病阳性的患者未能参加糖尿病护理的随访。我们的目的是开发一个机器学习模型，预测人们的失败，参加后续visit.RESEARCH设计和METHODSWe进行了一项回顾性队列研究的成年人与新筛查的糖尿病在一个国家的筛查计划，使用一个大型的日本保险索赔数据库（JMDC，东京，日本）。我们将未能参加糖尿病护理随访定义为筛选后6个月内没有医生咨询。候选预测因子为患者人口统计学资料、合并症和用药史。在训练集中（随机选择80%的样本），我们开发了两个模型（先前报道的logistic回归模型和Lasso回归模型）。在测试集中（剩余的20%），预测性能进行了检查。我们确定了10，645例患者，包括5，450例未能参加糖尿病护理随访的患者。使用4个预测因子的Lasso回归模型比先前报道的使用13个预测因子的Logistic回归模型具有更好的区分能力（C-统计量：0.71 [95%CI 0.69-0.73] vs. 0.67 [0.65-0.69]; P
OBJECTIVEReportedly, two-thirds of the patients who were positive for diabetes during screening failed to attend a follow-up visit for diabetes care in Japan. We aimed to develop a machine-learning model for predicting people's failure to attend a follow-up visit.RESEARCH DESIGN AND METHODSWe conducted a retrospective cohort study of adults with newly screened diabetes at a national screening program using a large Japanese insurance claims database (JMDC, Tokyo, Japan). We defined failure to attend a follow-up visit for diabetes care as no physician consultation during the 6 months after the screening. The candidate predictors were patient demographics, comorbidities, and medication history. In the training set (randomly selected 80% of the sample), we developed two models (previously reported logistic regression model and Lasso regression model). In the test set (remaining 20%), prediction performance was examined.RESULTSWe identified 10,645 patients, including 5,450 patients who failed to attend follow-up visits for diabetes care. The Lasso regression model using four predictors had a better discrimination ability than the previously reported logistic regression model using 13 predictors (C-statistic: 0.71 [95% CI 0.69-0.73] vs. 0.67 [0.65-0.69]; P