相关实验视频

Updated: Sep 14, 2025

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

用eXtreme渐变增强算法和SHapley添加式扩张来预测糖尿病足的预测模型和风险分析

Lei Gao¹, Zi-Xuan Liu², Jiang-Ning Wang³

¹Department of Orthopedics Surgery, Beijing Shijitan Hospital Affiliated to Capital Medical University, Beijing 100038, China.

World journal of diabetes

|July 23, 2025

概括

使用XGBoost的可解释的人工智能模型有效预测糖尿病足截肢风险. 关键因素如瓦格纳4/5级,骨髓炎和高C反应蛋白被确定用于个性化治疗.

科学领域:

人工智能在医学中的应用
糖尿病并发症研究研究研究
在医疗保健中的预测建模.

背景情况:

糖尿病足 (DFU) 是一种严重的糖尿病并发症,截肢率高,对社会产生重大影响.
早期识别风险因素和及时干预对于减少DFU相关的截肢至关重要.
人工智能的进步为开发高效,可解释的预测模型提供了潜力,以提高DFU护理.

研究的目的:

开发和验证一种可解释的预测模型,用于糖尿病足患者的截肢风险.
为了利用人工智能,改善DFU管理中的临床决策.
通过数据驱动的方法识别与DFU截肢相关的关键风险因素.

主要方法:

一项回顾性研究,涉及599名来自北京石家庄医院的DFU患者 (2015年1月 - 2024年6月).
数据随机分为训练和测试集,并进行五次交叉验证.
使用 eXtreme渐变增强 (XGBoost) 算法构建的三种二进制变量模型,具有超参数优化和SHapley添加式扩展 (SHAP) 的解释性.

主要成果:

在599名患者中,157名 (26.2%) 患有轻度截肢,50名 (8.3%) 患有重大截肢.
所有XGBoost模型都显示出良好的区分能力 (AUC>0.7).
主要截肢预测模型获得了最高的性能 (AUC = 0.977),其次是次要 (AUC = 0.800) 和非截肢 (AUC = 0.772) 模型. 重要的预测因素包括瓦格纳4/5级,骨髓炎和高C反应蛋白.

结论:

XGBoost模型在预测糖尿病脚截肢风险方面表现出有效性.
该模型提供可解释的见解,支持DFU患者的个性化治疗策略.
由人工智能驱动的预测模型可以显著帮助管理DFU并发症并减少截肢率.

关键词:

截肢风险分层的分层是截肢风险的分层.临床风险预测和预测糖尿病足部糖尿病足部机器学习是机器学习.沙普利添加剂扩展法沙普利添加剂扩展法极端梯度提升极端梯度提升

更多相关视频

A Simplified Technique for Producing an Ischemic Wound Model

A Simplified Technique for Producing an Ischemic Wound Model

Published on: May 2, 2012

Predicting Amputation using Local Circulating Mononuclear Progenitor Cells in Angioplasty-treated Patients with Critical Limb Ischemia

Predicting Amputation using Local Circulating Mononuclear Progenitor Cells in Angioplasty-treated Patients with Critical Limb Ischemia

Published on: September 22, 2020

相关概念视频

Receiver Operating Characteristic Plot

Receiver Operating Characteristic Plot

A ROC (Receiver Operating Characteristic) plot is a graphical tool used to assess the performance of a binary classification model by illustrating the trade-off between sensitivity (true positive rate) and specificity (false positive rate). By plotting sensitivity against 1 - specificity across various threshold settings, the ROC curve shows how well the model distinguishes between classes, with a curve closer to the top-left corner indicating a more accurate model. The area under the ROC curve...

Peripheral Artery Disease V: Postoperative Nursing Management

Peripheral Artery Disease V: Postoperative Nursing Management

During the postoperative period, it is crucial to focus on maintaining circulation, identifying and managing potential complications, and planning for discharge.Nursing AssessmentVital signs monitoring: Regularly monitor vital signs, including blood pressure, heart rate, respiratory rate, and temperature, to detect early signs of complications such as bleeding and infection.Circulation assessment: Monitor pulses, perform Doppler assessments, and check capillary refill, color, temperature, and...