Department of Endocrinology and Metabolism, Kyung Hee University Medical Center, Kyung Hee University College of Medicine, Seoul, Republic of Korea.
Center for Digital Health, Medical Science Research Institute, Kyung Hee University Medical Center, Kyung Hee University College of Medicine, Seoul, Republic of Korea.
J Med Internet Res. 2024 Oct 3;26:e56922. doi: 10.2196/56922.
Several machine learning (ML) prediction models for neurodegenerative diseases (NDs) in type 2 diabetes mellitus (T2DM) have recently been developed. However, the predictive power of these models is limited by the lack of multiple risk factors.
This study aimed to assess the validity and use of an ML model for predicting the 3-year incidence of ND in patients with T2DM.
We used data from 2 independent cohorts-the discovery cohort (1 hospital; n=22,311) and the validation cohort (2 hospitals; n=2915)-to predict ND. The outcome of interest was the presence or absence of ND at 3 years. We selected different ML-based models with hyperparameter tuning in the discovery cohort and conducted an area under the receiver operating characteristic curve (AUROC) analysis in the validation cohort.
The study dataset included 22,311 (discovery) and 2915 (validation) patients with T2DM recruited between 2008 and 2022. ND was observed in 133 (0.6%) and 15 patients (0.5%) in the discovery and validation cohorts, respectively. The AdaBoost model had a mean AUROC of 0.82 (95% CI 0.79-0.85) in the discovery dataset. When this result was applied to the validation dataset, the AdaBoost model exhibited the best performance among the models, with an AUROC of 0.83 (accuracy of 78.6%, sensitivity of 78.6%, specificity of 78.6%, and balanced accuracy of 78.6%). The most influential factors in the AdaBoost model were age and cardiovascular disease.
This study shows the use and feasibility of ML for assessing the incidence of ND in patients with T2DM and suggests its potential for use in screening patients. Further international studies are required to validate these findings.
最近已经开发出了几种用于 2 型糖尿病（T2DM）神经退行性疾病（ND）的机器学习（ML）预测模型。然而，这些模型的预测能力受到缺乏多种危险因素的限制。
本研究旨在评估一种用于预测 T2DM 患者 3 年内发生 ND 的 ML 模型的有效性和实用性。
我们使用来自 2 个独立队列的数据分析，包括发现队列（1 家医院；n=22311）和验证队列（2 家医院；n=2915），以预测 ND。感兴趣的结局是 3 年内是否存在 ND。我们在发现队列中选择了不同的基于 ML 的模型并进行了超参数调整，然后在验证队列中进行了接受者操作特征曲线（AUROC）分析。
研究数据集包括 2008 年至 2022 年期间招募的 22311 名（发现）和 2915 名（验证）T2DM 患者。在发现和验证队列中，分别观察到 133 名（0.6%）和 15 名患者（0.5%）患有 ND。AdaBoost 模型在发现数据集中的平均 AUROC 为 0.82（95%CI 0.79-0.85）。当将该结果应用于验证数据集时，AdaBoost 模型在所有模型中表现最佳，AUROC 为 0.83（准确率为 78.6%，敏感度为 78.6%，特异度为 78.6%，平衡准确率为 78.6%）。AdaBoost 模型中最具影响力的因素是年龄和心血管疾病。
本研究表明 ML 可用于评估 T2DM 患者 ND 的发生率，并显示其用于筛选患者的潜力。需要进一步的国际研究来验证这些发现。
