Identifying and characterizing high-risk clusters in a heterogeneous ICU population with deep embedded clustering

Abstract

Critically ill patients constitute a highly heterogeneous population, with seemingly distinct patients having similar outcomes, and patients with the same admission diagnosis having opposite clinical trajectories. We aimed to develop a machine learning methodology that identifies and provides better characterization of patient clusters at high risk of mortality and kidney injury. We analysed prospectively collected data including co-morbidities, clinical examination, and laboratory parameters from a minimally-selected population of 743 patients admitted to the ICU of a Dutch hospital between 2015 and 2017. We compared four clustering methodologies and trained a classifier to predict and validate cluster membership. The contribution of different variables to the predicted cluster membership was assessed using SHapley Additive exPlanations values. We found that deep embedded clustering yielded better results compared to the traditional clustering algorithms. The best cluster configuration was achieved for 6 clusters. All clusters were clinically recognizable, and differed in in-ICU, 30-day, and 90-day mortality, as well as incidence of acute kidney injury. We identified two high mortality risk clusters with at least 60%, 40%, and 30% increased. ICU, 30-day and 90-day mortality, and a low risk cluster with 25–56% lower mortality risk. This machine learning methodology combining deep embedded clustering and variable importance analysis, which we made publicly available, is a possible solution to challenges previously encountered by clustering analyses in heterogeneous patient populations and may help improve the characterization of risk groups in critical care.

Patient and hospital characteristics predict prolonged emergency department length of stay and in-hospital mortality: a nationwide analysis in Korea

“…However, the top ten primary diagnoses accounted for only 43.3% of all ICU admissions to the ED. Similar to other countries, our finding demonstrates that critically ill patients receiving care in a Korean ED setting represent a highly heterogeneous population [ 50 – 52 ], highlighting the challenges of providing critical care in such an environment [ 53 ].…”

Comparison of Machine Learning Models Including Preoperative, Intraoperative, and Postoperative Data and Mortality After Cardiac Surgery

“…Additionally, as discussed previously, we restricted intraoperative data to hemodynamics, temperature, and CPB and did not include interventional data, such as blood transfusion or the use of inotropes or insulin. The code used in this study is available online, and we encourage further replication and validation of the algorithm and findings of this study in other cohorts, as well as the addition of new preoperative and intraoperative data types to the analysis.…”

Cluster analysis integrating age and body temperature for mortality in patients with sepsis: a multicenter retrospective study

“…Recently, unsupervised cluster analysis has been reported to identify the phenotypes of study populations with heterogeneous characteristics: ICU patients 32 , sepsis patients 11 , and critically ill COVID-19 patients 33 . To the best of our knowledge, no previous study has applied cluster analysis to characterize phenotypes based on BT and age that are associated with mortality in sepsis patients.…”