使用新型机器学习工具来预测穿透导管大动脉替换后的最佳放电
Ahmad Mustafa1, Chapman Wei1, Radu Grovu1
1Department of Cardiology, Northwell Health, 2000 Marcus Avenue, Suite 300, New Hyde Park, NY, 11042-1069, USA.
Archives of cardiovascular diseases
|October 18, 2024
概括
机器学习模型准确地预测了透气管大动脉置换 (TAVR) 后的最佳医院出院情况. 这些模型,包括人工神经网络和 eXtreme Gradient Boost,显示出改善患者流量和资源管理的前景.
科学领域:
- 心血管医学 心血管医学
- 医疗信息学 医疗信息学
- 医疗保健中的人工智能
背景情况:
- 过导管大动脉置换 (TAVR) 是手术大动脉置换的一个重要替代方案.
- 优化住院时间至关重要,因为TAVR的医疗资源利用量很大.
- 预测最佳出院对于有效的患者管理和资源分配至关重要.
研究的目的:
- 评估新型机器学习模型的预测准确性,以获得最佳的TAVR后医院出院.
- 为了比较人工神经网络 (ANN) 和 eXtreme Gradient Boost (XGBoost) 模型与传统物流回归的性能.
- 确定影响TAVR后最佳放电时间的关键因素.
主要方法:
- 利用2016-2018年国家住院样本数据库来获取TAVR患者数据.
- 将患者分为最佳 (0-3天) 和晚期 (4-9天) 退院组.
- 采用后勤回归,ANN和XGBoost模型来预测最佳放电,通过AUC和F1得分来评估性能.
主要成果:
- 分析了25874名TAVR患者;所有模型都实现了0.80.8的曲线下的面积 (AUC).
- 患者的倾向和选择性手术状态是最佳出院的最重要的预测因素.
- 凝血障碍成为最佳出院的最强并发症预测因素.
结论:
- 在预测最佳 TAVR 排放时,ANN 和 XGBoost 模型表现出令人满意的性能和与后勤回归可比的准确性.
- 这些机器学习模型显示了优化医院出院的临床应用潜力.
- 建议进一步验证和完善这些预测工具的更广泛的临床采用.
更多相关视频
07:46Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility
Published on: August 9, 2024
657
08:50Technique and Patient Selection Criteria of Right Anterior Mini-Thoracotomy for Minimal Access Aortic Valve Replacement
Published on: March 26, 2018
11.6K
相关概念视频
Cardiomyopathy V: Interprofessional Care
1
Managing cardiomyopathy involves addressing underlying or precipitating causes, treating heart failure with medications, and implementing dietary changes and a balanced exercise and rest regimen.Lifestyle ModificationsCardiomyopathy patients should adopt a low-sodium diet to reduce fluid retention and manage heart failure. A personalized exercise and rest plan helps maintain physical fitness without overstraining the heart. Avoiding alcohol and tobacco is essential to prevent further damage to...
1
Mitral Valve Prolapse II: Assessment and Management
3
IntroductionA range of clinical features characterizes Mitral Valve Prolapse (MVP), but it is important to note that many individuals with MVP are asymptomatic and may remain so throughout their lives. For those who do exhibit symptoms, the following are the key clinical features:Palpitations: This is a common symptom where individuals feel an irregular or rapid heartbeat. Palpitations in MVP are often due to arrhythmias such as premature ventricular contractions or supraventricular...
3
