Identifying Distinct Subgroups of ICU Patients: A Machine Learning Approach*

Abstract

Objective Identifying subgroups of intensive care unit (ICU) patients with similar clinical needs and trajectories may provide a framework for more efficient ICU care through the design of care platforms tailored around patients’ shared needs. However, objective methods for identifying these ICU patient subgroups are lacking. We used a machine learning approach to empirically identify ICU patient subgroups through clustering analysis and evaluate whether these groups might represent appropriate targets for care redesign efforts. Design We performed clustering analysis using data from patients’ hospital stays to retrospectively identify patient subgroups from a large, heterogeneous ICU population. Setting Kaiser Permanente Northern California (KPNC), a healthcare delivery system serving 3.9 million members. Patients ICU patients aged ≥ 18 years with an ICU admission between January 1, 2012 and December 31, 2012 at one of 21 KPNC hospitals. Interventions none. Measurements and Main Results We used clustering analysis to identify putative clusters among 5,000 patients randomly selected from 24,884 ICU patients. To assess cluster validity, we evaluated the distribution and frequency of patient characteristics, and the need for invasive therapies. We then applied a classifier built from the sample cohort to the remaining 19,884 patients to compare the derivation and validation clusters. Clustering analysis successfully identified six clinically-recognizable subgroups that differed significantly in all baseline characteristics and clinical trajectories, despite sharing common diagnoses. In the validation cohort, the proportion of patients assigned to each cluster was similar and demonstrated significant differences across clusters for all variables. Conclusions A machine learning approach revealed important differences between empirically-derived subgroups of ICU patients that are not typically revealed by admitting diagnosis or severity of illness alone. Similar data-driven approaches may provide a framework for future organizational innovations in ICU care tailored around patients’ shared needs.

eDoctor: machine learning and the future of medicine

“…looked at the data heavy setting of the intensive care unit where resource burden and outcome prediction are not inconsiderable problems. By retrospectively analysing patient variables using an unsupervised algorithm (clustering), they were able to identify patient subgroups that had significantly different clinical courses despite similar diagnoses and when applying the predictive clusters to a separate, unseen data set, the predictive capability persisted .…”

An overview of deep learning in medical imaging focusing on MRI

“…Healthcare applications of deep learning range from one-dimensional biosignal analysis [17] and the prediction of medical events, e.g. seizures [18] and cardiac arrests [19], to computer-aided detection [20] and diagnosis [21] supporting clinical decision making and survival analysis [22], to drug discovery [23] and as an aid in therapy selection and pharmacogenomics [24], to increased operational efficiency [25], stratified care delivery [26], and analysis of electronic health records [27,28].…”

Towards a decision support tool for intensive care discharge: machine learning algorithm development using electronic health care data from MIMIC-III and Bristol, UK.

“…Under the logistic classifier certain features, such as body temperature and creatinine, appeared to be less important than we expected. This may be, in part, a consequence of patient heterogeneity on the general intensive care unit [36]. For example, body temperature may be predictive for patients with infection yet much of this predictive power is lost in our attempt to fit a general model for the whole ICU population.…”

“…During a patient's stay in ICU, many of their physiological parameters are controlled by clinical intervention, and their expected physiological state is dependent on their medical history (see, for example, guidelines on acceptable levels of Hb in different patient types [38]). Therefore, conditioning features on medical interventions and applying methods for patient sub-typing [36,39] are two improvements that we expect could significantly boost performance. Also, although the complete case analysis did not qualitatively alter our results, the development of a more sophisticated multiple-imputation strategy [40] would likely improve performance by making best use of the available training data and exploiting the value in missingness [41].…”