arXiv 2306.021212023-07-11cs.LGcs.AIcs.CYmath.OC

使用基于真实生命体征数据的端到端多变量时间序列聚类算法识别ICU患者亚组

Identifying Subgroups of ICU Patients Using End-to-End Multivariate Time-Series Clustering Algorithm Based on Real-World Vital Signs Data

Soochow University（苏州大学）；Advanced Institute of Information Technology, Peking University（北京大学信息技术高等研究院）；National Institute of Health Data Science, Peking University（北京大学健康医疗大数据国家研究院）；Peking University People’s Hospital（北京大学人民医院）

Tongyue Shi, Zhilong Zhang, Wentie Liu, Junhua Fang, Jianguo Hao, Shuai Jin, Huiying Zhao, Guilan Kong

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

提出基于Time2Feat与K-Means的端到端多变量时间序列聚类方法，利用MIMIC-IV生命体征数据识别具有不同死亡风险的ICU患者亚组。

摘要：

本研究以MIMIC-IV数据库为数据源，探讨动态、高频、多变量时间序列生命体征数据的使用，包括体温、心率、平均血压、呼吸频率和SpO2，监测的是ICU住院最初8小时的数据。研究比较了多种聚类算法，并选择名为Time2Feat的端到端多变量时间序列聚类系统结合K-Means，作为对ICU患者进行聚类的最有效方法。在聚类分析中，2008年至2016年间入院的8,080例患者数据用于模型开发，2017年至2019年间入院的2,038例患者数据用于模型验证。通过分析不同类别之间临床死亡预后的差异，研究发现不同亚组之间存在不同的ICU死亡和院内死亡风险。此外，研究还将生命体征变化轨迹进行了可视化。本研究结果为多变量时间序列聚类系统在ICU环境下患者管理和监测中的潜在应用提供了有价值的见解。

英文摘要：

This study employed the MIMIC-IV database as data source to investigate the use of dynamic, high-frequency, multivariate time-series vital signs data, including temperature, heart rate, mean blood pressure, respiratory rate, and SpO2, monitored first 8 hours data in the ICU stay. Various clustering algorithms were compared, and an end-to-end multivariate time series clustering system called Time2Feat, combined with K-Means, was chosen as the most effective method to cluster patients in the ICU. In clustering analysis, data of 8,080 patients admitted between 2008 and 2016 was used for model development and 2,038 patients admitted between 2017 and 2019 for model validation. By analyzing the differences in clinical mortality prognosis among different categories, varying risks of ICU mortality and hospital mortality were found between different subgroups. Furthermore, the study visualized the trajectory of vital signs changes. The findings of this study provide valuable insights into the potential use of multivariate time-series clustering systems in patient management and monitoring in the ICU setting.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。