相关实验视频
Updated: Apr 6, 2026

Mouse Model of Pressure Ulcers After Spinal Cord Injury
Published on: March 9, 2019
可解释的SHAP-XGBoost模型用于重症监护室中需要机械通风的患者的压力损伤
Li Zheng1, Yu-Juan Xue2, Zhen-Nan Yuan3
1Department of Intensive Care Unit, National Clinical Research Center for Cancer/Cancer Hospital, National Cancer Center, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, 100021, China.
机器学习准确地预测机械通风ICU患者的压力损伤. 关键的危险因素包括败血症,年龄和血小板计数,使得早期干预和改善的结果.
科学领域:
- 关键护理医学 关键护理医学
- 医疗信息学医学信息学
- 机器学习在医疗保健中的应用.
背景情况:
- 压力损伤对在重症监护室 (ICU) 接受机械通风的患者构成重大风险.
- 早期预测压力对于改善患者的治疗结果和减少医疗保健支出至关重要.
- 识别关键风险因素对于制定有针对性的预防策略至关重要.
研究的目的:
- 开发和验证一种机器学习模型,用于预测机械通风ICU患者的压力损伤.
- 通过SHAP分析,在这个患者队列中确定导致压力发育的主要危险因素.
- 评估开发模型的临床实用性和预测性能.
主要方法:
- 利用了MIMIC-IV 2.2数据库,包括29448名机械通风ICU患者.
- 开发了一个使用XGBoost算法与SHAP分析进行风险因素识别的预测模型.
- 将数据分为训练 (70%) 和内部验证 (30%) 集;2052名患者出现压力损伤.
主要成果:
- XGBoost模型确定了主要的危险因素:败血症,年龄,血小板计数,ICU停留时间,PaO2/FiO2比率,血红蛋白,入院类型,病,白蛋白和种族.
- 在训练组中达到0.797的ROC曲线下的面积 (AUC),在验证组中达到0.739.
- 校准曲线和决策曲线分析表明模型适合性和临床实用性良好.
结论:
- 一个强大的机器学习模型有效地预测机械通风ICU患者的压力损伤风险.
- SHAP分析提供了对压力发展最有影响力的因素的宝贵见解.
- 该模型可以作为指导早期干预和减少高风险人群中压力损伤发生率的实际工具.
更多相关视频
08:39Fabrication of Compressed Hosiery and Measurement of its Pressure Characteristic Exerted on the Lower Limbs
Published on: May 27, 2020
06:45Development of a Benchtop Model for Evaluating the Compatibility of Wound Dressing Materials with Negative Pressure Wound Therapy Systems
Published on: May 2, 2025
相关概念视频
Mechanical Ventilation I: Indication and Settings
Mechanical Ventilation II: Invasive Ventilation
Negative-Pressure Ventilators
Negative-pressure ventilators create a vacuum around the chest or body to draw air into the lungs, simulating breathing. This method does not require an...
Mechanical Ventilation III: Noninvasive Ventilation
Noninvasive Positive-Pressure Ventilation...
Ventilatory Modes
There are three ventilatory modes: full support, partial support, and spontaneous. These are described below.
Full Support Modes
Full support modes include controlled mechanical ventilation, continuous mandatory...