文献速递糖尿病

基于机器学习的2型糖尿病亚型可重复预测

Machine learning-based reproducible prediction of type 2 diabetes subtypes.
PubMed 文献 · Diabetologia · 2024-08-21

研究利用15个变量构建随机森林模型(T2DRF15),将619例日本2型糖尿病患者按Ahlqvist变量预标记为四种亚型,并在597例外部队列验证。模型预测准确率94%,外部验证86.3%,缺失胰岛素相关变量时插补后准确率82.9%,可预测糖尿病视网膜病变和慢性肾脏病累积风险。

要点

  • T2DRF15预测2型糖尿病亚型的准确率为94%,外部验证队列为86.3%。
  • 缺失胰岛素相关变量时,结合插补算法,T2DRF15准确率为82.9%。
  • 排除「不可判定」个体后,T2DRF15的亚型一致性高于T2Dkmeans。

核心结论

  • 新机器学习模型可对缺失HOMA2指数的个体进行Ahlqvist亚型分类,并利用常规可用变量预测血糖控制、糖尿病并发症和治疗结局,具有长期一致性。

研究设计与样本

  • 队列1包含619例日本2型糖尿病患者,按7:3比例分为训练集和测试集用于机器学习模型。
  • 队列2包含597例2型糖尿病患者,用于外部验证。
  • 参与者基于Ahlqvist变量(诊断年龄、BMI、HbA1c、HOMA2-B和HOMA2-IR)通过无监督k-means聚类预标记为四种亚型:严重胰岛素缺乏型糖尿病(SIDD)、严重胰岛素抵抗型糖尿病(SIRD)、轻度肥胖相关糖尿病(MOD)和轻度年龄相关糖尿病(MARD)。
  • 采用15个变量的多分类随机森林算法预测2型糖尿病亚型(T2DRF15)。

主要发现

  • T2DRF15预测T2Dkmeans亚型的准确率为94%,AUC≥0.99,F1分数≥0.9。
  • 外部验证队列中T2DRF15的预测性能为86.3%。
  • 在缺失胰岛素相关变量的假定子集中,结合插补算法,T2DRF15检测T2Dkmeans的准确率为82.9%。
  • 中位观察期11.6(4.5-18.3)年的Kaplan-Meier分析中,T2DRF15分类的SIDD亚型糖尿病视网膜病变和SIRD亚型慢性肾脏病的累积风险不同,与T2Dkmeans亚型相似。
  • 排除低预测概率的「不可判定」个体后,T2DRF15的一致性为SIDD 100%、SIRD 68.6%、MOD 94.4%、MARD 97.9%,高于T2Dkmeans。

临床怎么用

  • 原文未据此给出推荐。

局限性

  • 未来研究需要评估该方法是否适用于多民族人群的研究和/或临床实践。

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

AIMS/HYPOTHESIS: Clustering-based subclassification of type 2 diabetes, which reflects pathophysiology and genetic predisposition, is a promising approach for providing personalised and effective therapeutic strategies. Ahlqvist's classification is currently the most vigorously validated method because of its superior ability to predict diabetes complications but it does not have strong consistency over time and requires HOMA2 indices, which are not routinely available in clinical practice and standard cohort studies. We developed a machine learning (ML) model to classify individuals with type 2 diabetes into Ahlqvist's subtypes consistently over time. METHODS: Cohort 1 dataset comprised 619 Japanese individuals with type 2 diabetes who were divided into training and test sets for ML models in a 7:3 ratio. Cohort 2 dataset, comprising 597 individuals with type 2 diabetes, was used for external validation. Participants were pre-labelled (T2Dkmeans) by unsupervised k-means clustering based on Ahlqvist's variables (age at diagnosis, BMI, HbA1c, HOMA2-B and HOMA2-IR) to four subtypes: severe insulin-deficient diabetes (SIDD), severe insulin-resistant diabetes (SIRD), mild obesity-related diabetes (MOD) and mild age-related diabetes (MARD). We adopted 15 variables for a multiclass classification random forest (RF) algorithm to predict type 2 diabetes subtypes (T2DRF15). The proximity matrix computed by RF was visualised using a uniform manifold approximation and projection. Finally, we used a putative subset with missing insulin-related variables to test the predictive performance of the validation cohort, consistency of subtypes over time and prediction ability of diabetes complications. RESULTS: T2DRF15 demonstrated a 94% accuracy for predicting T2Dkmeans type 2 diabetes subtypes (AUCs ≥0.99 and F1 score [an indicator calculated by harmonic mean from precision and recall] ≥0.9) and retained the predictive performance in the external validation cohort (86.3%). T2DRF15 showed an accuracy of 82.9% for detecting T2Dkmeans, also in a putative subset with missing insulin-related variables, when used with an imputation algorithm. In Kaplan-Meier analysis, the diabetes clusters of T2DRF15 demonstrated distinct accumulation risks of diabetic retinopathy in SIDD and that of chronic kidney disease in SIRD during a median observation period of 11.6 (4.5-18.3) years, similarly to the subtypes using T2Dkmeans. The predictive accuracy was improved after excluding individuals with low predictive probability, who were categorised as an 'undecidable' cluster. T2DRF15, after excluding undecidable individuals, showed higher consistency (100% for SIDD, 68.6% for SIRD, 94.4% for MOD and 97.9% for MARD) than T2Dkmeans. CONCLUSIONS/INTERPRETATION: The new ML model for predicting Ahlqvist's subtypes of type 2 diabetes has great potential for application in clinical practice and cohort studies because it can classify individuals with missing HOMA2 indices and predict glycaemic control, diabetic complications and treatment outcomes with long-term consistency by using readily available variables. Future studies are needed to assess whether our approach is applicable to research and/or clinical practice in multiethnic populations.

来源:Diabetologia,查看原文。版权归原作者所有。

引用

  1. Tanabe H, Sato M, Miyake A, et al. Machine learning-based reproducible prediction of type 2 diabetes subtypes. Diabetologia. 2024. PMID: 39168869. doi:10.1007/s00125-024-06248-8

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。