一个基于贝叶斯网络的预测模型,用于冠状动脉旁路移植后的术后妄
Lei Xu1,2,3, Yang Zhang1,4, Jin Zhang1,4
1The Second Department of Critical Care Medicine, The Second Affiliated Hospital of Anhui Medical University, Hefei, Anhui, China.
BMC psychiatry
|August 26, 2025
概括
研究人员开发了一种贝叶斯网络 (BN) 模型,用于预测冠状动脉旁路移植 (CABG) 后的妄想. 这种可解释的模型显示出有希望的结果,用于识别患有术后妄想风险的患者.
科学领域:
- 计算生物学和医学
- 医疗保健中的人工智能
- 临床信息学
背景情况:
- 术后妄想是冠状动脉旁路移植 (CABG) 的常见并发症.
- 精确预测妄想风险对于及时干预和改善患者结果至关重要.
- 现有的预测模型可能缺乏可解释性或可靠的验证.
研究的目的:
- 开发和验证贝叶斯网络 (BN) 模型,用于预测CABG患者的术后妄想.
- 根据已知的机器学习算法评估BN模型的预测性能.
- 使用概率图形模型提高妄想预测的可解释性.
主要方法:
- 使用MIMIC-IV和eICU-CRD数据库进行模型培训,内部和外部验证.
- 使用BM模型的Max-Min登算法构建了一个定向非循环图.
- 使用接收器操作特征曲线下的区域 (AUROC) 评估模型性能,并与后勤回归和LightGBM进行比较.
主要成果:
- 包含14个节点和22个定向边的BN模型实现了0.79的AUROC (内部) 和0.72 (外部验证).
- 确定的关键预测因素包括里士满兴奋镇静量表和序列器官衰竭评估分数.
- 基于经过验证的BN模型开发了一个用户友好的Shiny平台应用程序.
结论:
- 在CABG患者中成功开发了一种可靠和可解释的贝叶斯网络模型来预测术后妄想.
- 在确定高风险患者方面,BN模型具有显著的临床应用潜力.
- 这种方法为心脏手术后的妄想症提供了有价值的工具.
相关概念视频
Cardiomyopathy VII: Pre and Post Operative Nursing Management
27
Patients with hypertrophic cardiomyopathy (HCM) and left ventricular outflow tract (LVOT) obstruction who remain symptomatic despite optimal medical therapy may undergo a septal myectomy (Morrow procedure). This procedure involves excising a portion of the hypertrophied septum below the aortic valve using a heart-lung machine to improve blood flow through the LVOT. Effective preoperative and postoperative nursing management ensures successful patient outcomes, minimizes complications, and...
27
Peripheral Artery Disease V: Postoperative Nursing Management
25
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...
25


