Shi Ge, Gao Zhenxuan, Zhang Ze, Jin Quanyu, Li Sitong, Liu Jiaxin, Kou Lei, Aerman Abudurezhake, Yang Wenqiang, Wang Qi, Cai Furong, Zhang Li
China-Japan Friendship School of Clinical Medicine, Capital Medical University, Beijing, China.
Graduate School of Peking Union Medical College, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China.
J Diabetes Investig. 2025 Jun;16(6):1055-1064. doi: 10.1111/jdi.70010. Epub 2025 Mar 21.
Diabetic peripheral neuropathy (DPN) is a common chronic complication of diabetes, marked by symptoms like hyperalgesia, numbness, and swelling that impair quality of life. Nerve conduction abnormalities in DPN significantly increase the risk of neuropathic foot ulcers (NFU), which can progress rapidly and lead to severe outcomes, including infection, gangrene, and amputation. Early prediction of NFU in DPN patients is crucial for timely intervention.
Clinical data from 400 DPN patients treated at the China-Japan Friendship Hospital (September 2022-2024) were retrospectively analyzed. Data included medical histories, physical exams, biochemical tests, and imaging. After feature selection and data balancing, the dataset was split into training and validation subsets (8:2 ratio). Six machine learning algorithms-random forest, decision tree, logistic regression, K-nearest neighbor, extreme gradient boosting, and multilayer perceptron-were evaluated using k-fold cross-validation. Model performance was assessed via accuracy, precision, recall, F1 score, and AUC. The SHAP method was employed for interpretability.
The multilayer perceptron model showed the best performance (accuracy: 0.875; AUC: 0.901). SHAP analysis highlighted triglycerides, high-density lipoprotein cholesterol, diabetes duration, age, and fasting blood glucose as key predictors.
A machine learning-based prediction model using a multilayer perceptron algorithm effectively identifies DPN patients at high NFU risk, offering clinicians an accurate tool for early intervention.
糖尿病周围神经病变（DPN）是糖尿病常见的慢性并发症，其特征为痛觉过敏、麻木和肿胀等症状，会损害生活质量。DPN中的神经传导异常显著增加了神经性足溃疡（NFU）的风险，NFU可迅速发展并导致严重后果，包括感染、坏疽和截肢。对DPN患者的NFU进行早期预测对于及时干预至关重要。
回顾性分析了2022年9月至2024年在中国中日友好医院接受治疗的400例DPN患者的临床资料。数据包括病史、体格检查、生化检查和影像学检查。经过特征选择和数据平衡后，将数据集分为训练子集和验证子集（比例为8:2）。使用k折交叉验证评估了六种机器学习算法——随机森林、决策树、逻辑回归、K近邻、极端梯度提升和多层感知器。通过准确率、精确率、召回率、F1分数和AUC评估模型性能。采用SHAP方法进行可解释性分析。
多层感知器模型表现最佳（准确率：0.875；AUC：0.901）。SHAP分析突出了甘油三酯、高密度脂蛋白胆固醇、糖尿病病程、年龄和空腹血糖作为关键预测因素。
使用多层感知器算法的基于机器学习的预测模型能够有效识别NFU高风险的DPN患者，为临床医生提供了一种用于早期干预的准确工具。
