指南与共识糖尿病

基于机器学习的预测模型识别国家筛查项目推荐后未参加糖尿病随访的患者

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.
指南 / 共识 · Diabetes Care · 2022-01-01

在日本国家筛查项目中,利用大型保险索赔数据库回顾性纳入10,645例新筛查糖尿病患者(5,450例未随访)。开发Lasso回归模型(4个预测因子)与既往逻辑回归模型(13个预测因子),Lasso模型区分能力更优(C统计量0.71 vs 0.67,P<0.001)。四因子包括既往就诊频率低、HbA1c水平低、无降脂或降压治疗史。

要点

  • Lasso模型(4因子)预测未随访的C统计量为0.71,优于逻辑回归模型(13因子)的0.67。
  • 四因子为既往就诊频率低、HbA1c水平低、无降脂治疗史、无降压治疗史。
  • 研究基于日本大型保险索赔数据库的回顾性队列,样本量10,645例。

核心结论

  • 基于4个预测因子的机器学习模型对筛查项目后未参加糖尿病随访的患者具有良好预测能力。

研究设计与样本

  • 回顾性队列研究,使用日本大型保险索赔数据库(JMDC,东京,日本),纳入国家筛查项目中新筛查的成人糖尿病患者10,645例。
  • 未随访定义为筛查后6个月内无医生就诊。
  • 候选预测因子包括患者人口学特征、合并症和用药史。
  • 训练集为随机选取的80%样本,开发了既往报道的逻辑回归模型和Lasso回归模型;测试集为剩余20%样本,用于评估预测性能。

主要发现

  • 共识别10,645例患者,其中5,450例未参加糖尿病随访。
  • Lasso回归模型(4个预测因子)区分能力优于既往逻辑回归模型(13个预测因子):C统计量0.71(95%CI 0.69-0.73) vs 0.67(95%CI 0.65-0.69),P<0.001。
  • Lasso回归模型选出的4个预测因子为:既往一年医生就诊频率低、HbA1c水平低、无降脂治疗史、无降压治疗史。

临床怎么用

  • 原文未据此给出推荐。

局限性

  • 原文未报告局限性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

OBJECTIVE: Reportedly, 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 METHODS: We 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. RESULTS: We 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 < 0.001). The four selected predictors in the Lasso regression model were lower frequency of physician visits in the previous year, lower HbA1c levels, and negative history of antidyslipidemic or antihypertensive treatment. CONCLUSIONS: The developed machine-learning model using four predictors had a good predictive ability to identify patients who failed to attend a follow-up visit for diabetes care after a screening program.

来源:Diabetes Care,查看原文。版权归原作者所有。

引用

  1. Okada A, Hashimoto Y, Goto T, et al. 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. Diabetes Care. 2022. PMID: 35435949. doi:10.2337/dc21-1841

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。