文献速递心外重症与机械循环支持

机器学习分析持久性左心室辅助装置植入后不良事件

Machine Learning Approaches to Analyzing Adverse Events Following Durable LVAD Implantation.
PubMed 文献 · Ann Thorac Surg · 2020-11-20

本研究从ENDURANCE与ENDURANCE Supplemental临床试验中提取植入HeartWare HVAD持久性左心室辅助装置患者的5年随访数据,采用时间间隔分析、转移概率分析、桑基图及基于最长公共子序列的层次聚类分析不良事件序列。568例患者共发生3590次不良事件,出血与右心衰占术后早期不良事件比例最高,感染与出血占3个月后不良事件多数;聚类识别出5个具有不同事件间隔、转移率与临床结局的患者簇。

要点

  • 出血与右心衰是HVAD植入术后早期最主要的不良事件
  • 感染至感染转移概率最高(0.34),其次为出血至出血(0.31)
  • 基于事件序列的聚类可识别5类不同不良事件模式与结局的患者

核心结论

  • 机器学习方法可改善左心室辅助装置植入后不良事件负担的可视化与理解,识别出的不同模式与关系可能对质量改进工作有重要意义。

研究设计与样本

  • 回顾性分析ENDURANCE与ENDURANCE Supplemental临床试验中植入HeartWare HVAD持久性左心室辅助装置的患者数据,随访至5年。
  • 采用时间间隔分析与转移概率分析,绘制桑基图可视化不良事件间转移,并基于最长公共子序列的不相似矩阵进行层次聚类。

主要发现

  • 共568例患者接受HVAD植入,发生3590次不良事件。
  • 出血与右心衰占术后早期不良事件比例最高,感染与出血占3个月后发生的不良事件多数。
  • 转移概率最高者为感染至感染(0.34)、出血至出血(0.31)、右心衰至出血(0.31)、右心衰至感染(0.28)、出血至感染(0.26)。
  • 生成5个不同的患者簇,各簇在不良事件间时间间隔模式、转移率及临床结局上存在差异。

临床怎么用

  • 可将不良事件序列分析与聚类结果用于左心室辅助装置植入后质量改进,识别高风险事件链与患者亚群。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

BACKGROUND: This study employed machine learning approaches to analyze sequences of adverse events (AEs) after left ventricular assist device (LVAD) implantation. METHODS: Data on patients implanted with the HeartWare HVAD durable LVAD were extracted from the ENDURANCE and ENDURANCE Supplemental clinical trials, with follow-up through 5 years. Major AEs included device malfunction, major bleeding, major infection, neurological dysfunction, renal dysfunction, respiratory dysfunction, and right heart failure (RHF). Time interval and transition probability analyses were performed. We created a Sankey diagram to visualize transitions between AEs. Hierarchical clustering was applied to dissimilarity matrices based on the longest common subsequence to identify clusters of patients with similar AE profiles. RESULTS: A total of 568 patients underwent HVAD implantation with 3590 AEs. Bleeding and RHF comprised the highest proportion of early AEs after surgery whereas infection and bleeding accounted for most AEs occurring after 3 months. The highest transition probabilities were observed with infection to infection (0.34), bleeding to bleeding (0.31), RHF to bleeding (0.31), RHF to infection (0.28), and bleeding to infection (0.26). Five distinct clusters of patients were generated, each with different patterns of time intervals between AEs, transition rates between AEs, and clinical outcomes. CONCLUSIONS: Machine learning approaches allow for improved visualization and understanding of AE burden after LVAD implantation. Distinct patterns and relationships provide insights that may be important for quality improvement efforts.

来源:Ann Thorac Surg,查看原文。版权归原作者所有。

引用

  1. Kilic A, Macickova J, Duan L, et al. Machine Learning Approaches to Analyzing Adverse Events Following Durable LVAD Implantation. Ann Thorac Surg. 2020. PMID: 33221198. doi:10.1016/j.athoracsur.2020.09.040

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。