基于机器学习的预测模型的构建和评估,用于ICU患者的肠道营养食不耐受风险
Gaimei Wang1, Cendi Lu1, Owusu Mensah Solomon2
1Department of Neurosurgery Unit, The Second Affiliated Hospital of Zhejiang Chinese Medical University, Hangzhou, China.
机器学习模型预测了ICU患者的肠道营养食不耐受. 随机森林模型在识别有食不耐受风险的患者方面表现最好.
科学领域:
- 临界护理医学 临界护理医学
- 生物统计学 生物统计学
- 机器学习应用 机器学习应用
背景情况:
- 肠道营养不耐受 (ENFI) 是重症患者常见的并发症.
- 有效预测和管理ENFI对于改善重症监护室 (ICU) 患者的治疗结果至关重要.
研究的目的:
- 为了调查影响ENFI的因素,在重症患者.
- 开发和比较基于机器学习的ENFI在ICU患者的风险预测模型.
主要方法:
- 分析了487名ICU患者的队列.
- 使用后勤回归 (LR),支持向量机 (SVM) 和随机森林 (RF) 算法来构建预测模型.
- 用AUC,准确性,精度,回忆和F1分数来评估模型性能.
主要成果:
- 随机森林 (RF) 模型实现了最高的预测性能,AUC为0.9511,准确率为96.1%,精度为97.7%,回忆率为91.4%,F1得分为0.9446.
- 后勤回归 (LR) 模型显示AUC为0.9308,支持向量机 (SVM) 模型显示AUC为0.9241.
- 所有模型都显示出强大的ENFI风险预测能力.
结论:
- 随机森林模型在确定ICU患者的ENFI风险方面表现出卓越的预测性能.
- 机器学习算法,特别是随机森林,显示出作为预防和管理ENFI的工具的希望.
更多相关视频
04:09Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
Published on: October 10, 2018
06:21Concept Development and Use of an Automated Food Intake and Eating Behavior Assessment Method
Published on: February 19, 2021
相关概念视频
Enteral Nutrition II: Nasointestinal and Gastrostomy Feeding
Nasointestinal Feeding
Nasointestinal feeding involves placing a tube...
Enteral Nutrition I: Orogastric and Nasogastric Feeding
Orogastric (OG) and nasogastric (NG) feeding are two standard methods used for enteral nutrition. Enteral nutrition is often preferred over...
Inflammatory Bowel Disease III: Diagnostic Studies and Management I-Nutritional Therapy
Diagnostic studies
A colonoscopy is the definitive screening test, distinguishing ulcerative colitis from other colon diseases with similar symptoms. During a colonoscopy test, inflamed mucosa with exudate ulcerations can be observed, and biopsies are taken to determine the histologic characteristics of the...
One-Compartment Open Model for IV Bolus Administration: Estimation of Clearance
In the one-compartment open model for intravenous (IV) bolus administration, clearance is estimated by dividing the elimination rate by the plasma drug concentration. This equation leverages the elimination rate constant and the apparent...
One-Compartment Open Model for IV Bolus Administration: General Considerations
The drug's presence in the body is defined by an equation representing the difference between the rates of drug entry and exit. Key parameters—elimination rate constant,...
Two-Compartment Open Model: IV Bolus Administration
The disparity between drug input and the sum of drug transfer rates between...
