Zhang Junli, Xu Zhenghui, Fu Yu, Chen Lu
Department of Endocrinology and Metabolism, The Third Affiliated Hospital of Soochow University, Changzhou, People's Republic of China.
Department of Clinical Nutrition, The Third Affiliated Hospital of Soochow University, Changzhou, People's Republic of China.
Diabetes Metab Syndr Obes. 2023 Sep 19;16:2885-2898. doi: 10.2147/DMSO.S422515. eCollection 2023.
There remains a lack of a machine learning (ML) model incorporating body composition to assess the risk of bone mineral density (BMD) decreases in type 2 diabetes mellitus (T2DM) patients. We aimed to use ML algorithms and the traditional multivariate logistic regression to establish prediction models for BMD decreases in T2DM patients over 50 years of age, and compare the performance of the two methods.
This cross-sectional study was conducted among 450 patients with T2DM from 1 August 2016 to 31 December 2022. The participants were divided into a normal BMD group and a decreased BMD group. Traditional multivariate logistic regression and six ML algorithms were selected to construct male and female models. Two nomograms were constructed to evaluate the risk of BMD decreases in the male and female T2DM patients, respectively. The ML models with the highest area under the curve (AUC) were compared with the traditional multivariate logistic regression models in terms of discriminant ability and clinical applicability.
The optimal ML model was the extreme gradient boost (XGBoost) model. The AUCs of the traditional multivariate logistic regression and the XGBoost models were 0.722 and 0.800 in the male testing dataset, respectively, and 0.876 and 0.880 in the female testing dataset, respectively. The decision curve analysis results suggested that using the XGBoost models to predict the risk of BMD decreases obtained more net benefits compared with the traditional models in both sexes.
We preliminarily proved that the XGBoost models outperformed most other ML models in both sexes and achieved higher accuracy than traditional analyses. Due to the limited sample size in the study, it is necessary to validate our findings in larger prospective cohort studies.
目前仍缺乏一种纳入身体成分的机器学习（ML）模型来评估2型糖尿病（T2DM）患者骨密度（BMD）降低的风险。我们旨在使用ML算法和传统多变量逻辑回归来建立50岁以上T2DM患者BMD降低的预测模型，并比较这两种方法的性能。
本横断面研究于2016年8月1日至2022年12月31日期间对450例T2DM患者进行。参与者被分为骨密度正常组和骨密度降低组。选择传统多变量逻辑回归和六种ML算法来构建男性和女性模型。构建了两个列线图，分别评估男性和女性T2DM患者BMD降低的风险。将曲线下面积（AUC）最高的ML模型与传统多变量逻辑回归模型在判别能力和临床适用性方面进行比较。
最佳ML模型是极端梯度提升（XGBoost）模型。在男性测试数据集中，传统多变量逻辑回归模型和XGBoost模型的AUC分别为0.722和0.800，在女性测试数据集中分别为0.876和0.880。决策曲线分析结果表明，使用XGBoost模型预测BMD降低的风险在两性中均比传统模型获得更多净效益。
我们初步证明，XGBoost模型在两性中均优于大多数其他ML模型，且比传统分析具有更高的准确性。由于本研究样本量有限，有必要在更大规模的前瞻性队列研究中验证我们的发现。
