Division of Cardiology, West Virginia University Heart & Vascular Institute, Morgantown, West Virginia; Heart and Vascular Center, Semmelweis University, Budapest, Hungary.
Division of Cardiology, West Virginia University Heart & Vascular Institute, Morgantown, West Virginia.
JACC Cardiovasc Imaging. 2020 May;13(5):1119-1132. doi: 10.1016/j.jcmg.2019.12.018. Epub 2020 Mar 18.
The authors applied unsupervised machine-learning techniques for integrating echocardiographic features of left ventricular (LV) structure and function into a patient similarity network that predicted major adverse cardiac event(s) (MACE) in an individual patient.
Patient similarity analysis is an evolving paradigm for precision medicine in which patients are clustered or classified based on their similarities in several clinical features.
A retrospective cohort of 866 patients was used to develop a network architecture using 9 echocardiographic features of LV structure and function. The data for 468 patients from 2 prospective cohort registries were then added to test the model's generalizability.
The map of cross-sectional data in the retrospective cohort resulted in a looped patient network that persisted even after the addition of data from the prospective cohort registries. After subdividing the loop into 4 regions, patients in each region showed unique differences in LV function, with Kaplan-Meier curves demonstrating significant differences in MACE-related rehospitalization and death (both p < 0.001). Addition of network information to clinical risk predictors resulted in significant improvements in net reclassification, integrated discrimination, and median risk scores for predicting MACE (p < 0.05 for all). Furthermore, the network predicted the cardiac disease cycle in each of the 96 patients who had second echocardiographic evaluations. An improvement or remaining in low-risk regions was associated with lower MACE-related rehospitalization rates than worsening or remaining in high-risk regions (3% vs. 37%; p < 0.001).
Patient similarity analysis integrates multiple features of cardiac function to develop a phenotypic network in which patients can be mapped to specific locations associated with specific disease stage and clinical outcomes. The use of patient similarity analysis may have relevance for automated staging of cardiac disease severity, personalized prediction of prognosis, and monitoring progression or response to therapies.
作者应用无监督机器学习技术，将左心室（LV）结构和功能的超声心动图特征整合到一个患者相似性网络中，以预测个体患者的主要不良心脏事件（MACE）。
患者相似性分析是精准医学的一种新兴范例，根据患者在多个临床特征上的相似性对患者进行聚类或分类。
使用 9 个 LV 结构和功能的超声心动图特征，对 866 例患者的回顾性队列进行网络架构的开发。然后将来自 2 个前瞻性队列登记处的 468 例患者的数据添加到模型中进行验证。
在回顾性队列中，横截面数据的图谱产生了一个循环的患者网络，即使在加入前瞻性队列登记处的数据后，该网络仍然存在。将该循环分为 4 个区域后，每个区域的患者 LV 功能均显示出独特的差异，Kaplan-Meier 曲线显示在 MACE 相关再入院和死亡方面存在显著差异（均 p<0.001）。将网络信息添加到临床风险预测因子中，可显著提高 MACE 预测的净重新分类、综合判别力和中位数风险评分（均 p<0.05）。此外，该网络预测了 96 例接受第二次超声心动图评估的患者的心脏疾病周期。与恶化或保持在高危区域相比，低危区域的改善或保持与较低的 MACE 相关再入院率相关（3%比 37%；p<0.001）。
患者相似性分析整合了心脏功能的多个特征，以开发一个表型网络，患者可以被映射到与特定疾病阶段和临床结果相关的特定位置。患者相似性分析的应用可能与心脏疾病严重程度的自动分期、预后的个性化预测以及治疗进展或反应的监测有关。
