Li Yao, Zhou Siyuan, Ren Bichen, Ju Shuai, Li Xiaoyan, Li Wenqiang, Li Bingzhe, Cai Yunmin, Chang Chunlei, Huang Lihong, Dong Zhihui
Vascular Surgery & Wound Treatment Center, Jinshan Hospital of Fudan University, Shanghai, 201508, China.
Department of Vascular Surgery, Zhongshan Hospital, Fudan University, Shanghai, 200032, China.
BioData Min. 2025 Aug 21;18(1):57. doi: 10.1186/s13040-025-00477-2.
This study explores diabetic foot (DF), a severe complication in diabetes, by combining deep learning (DL) and machine learning (ML) to develop a multi-model prediction tool. Early identification of high-risk DF patients can reduce disability and mortality. The research also aims to create an integrated application to assist clinicians in precise, efficient risk assessment for early intervention. In this multicenter retrospective study, 6,180 elderly diabetic patients (aged 60-85) were enrolled from 11 community hospitals in Shanghai in 2024. Lasso regression was used to identify 16 key DF risk factors, including age, MMSE score, lower limb discomfort, ABI, and hematocrit. Fourteen ML models (RF, XGBoost, CART, MLP, etc.) and three DL models (DNN, CNN, Transformer) were trained, with hyperparameters optimized via cross-validation and grid search. An application was developed integrating these models, offering both single and batch prediction options with visualization tools for clinical use.Experimental results showed the Logistic regression ensemble model achieved robust performance, with AUC values of 0.943 (validation set, 95% CI: 0.935-0.951) and 0.938 (test set, 95% CI: 0.929-0.947), along with high accuracy, precision, recall, and F1 scores. SHAP analysis revealed key predictive features including ABI results, lower limb discomfort, and MMSE score. The developed app integrates multiple models, compares their predictions for different clinical scenarios, and enhances prediction transparency and reliability.The multi-model approach demonstrates strong predictive performance for DF risk, offering clinicians an intuitive and accurate assessment tool tailored to individual patients. By combining multiple models, we enhance result stability and clinical applicability compared to single-model approaches. Future work will focus on algorithm optimization, expanded datasets, and real-time monitoring integration to enable more precise, dynamic risk evaluation for improved DF prevention and early intervention.
本研究通过结合深度学习（DL）和机器学习（ML）来开发一种多模型预测工具，以探索糖尿病足（DF）这一糖尿病的严重并发症。早期识别高危DF患者可降低残疾率和死亡率。该研究还旨在创建一个集成应用程序，以协助临床医生进行精确、高效的风险评估，以便早期干预。在这项多中心回顾性研究中，2024年从上海11家社区医院招募了6180名老年糖尿病患者（年龄在60 - 85岁之间）。使用套索回归来识别16个关键的DF风险因素，包括年龄、简易精神状态检查表（MMSE）评分、下肢不适、踝臂指数（ABI）和血细胞比容。训练了14个ML模型（随机森林（RF）、极端梯度提升（XGBoost）、分类与回归树（CART）、多层感知器（MLP）等）和3个DL模型（深度神经网络（DNN）、卷积神经网络（CNN）、Transformer），通过交叉验证和网格搜索对超参数进行了优化。开发了一个集成这些模型的应用程序，提供单例和批量预测选项，并带有可视化工具以供临床使用。实验结果表明，逻辑回归集成模型表现出色，在验证集上的曲线下面积（AUC）值为0.943（95%置信区间：0.935 - 0.951），在测试集上为0.938（95%置信区间：0.929 - 0.947），同时具有较高的准确率、精确率、召回率和F1分数。SHAP分析揭示了关键预测特征，包括ABI结果、下肢不适和MMSE评分。所开发的应用程序集成了多个模型，可以比较它们在不同临床场景下的预测结果，并提高预测的透明度和可靠性。这种多模型方法对DF风险具有强大的预测性能，为临床医生提供了一种针对个体患者的直观且准确的评估工具。与单模型方法相比，通过结合多个模型，我们提高了结果的稳定性和临床适用性。未来的工作将集中在算法优化、扩展数据集以及整合实时监测，以实现更精确、动态的风险评估，从而改进DF的预防和早期干预。
