JMIR Publications

ABSTRACT

Background:

With advances in digital health technologies and proliferation of biomedical data in recent years, applications of machine learning in healthcare and medicine have gained significant attention. While inpatient settings are equipped to generate rich clinical data from patients, there is a dearth of actionable information that can be used for pursuing secondary research for specific clinical conditions.

Objective:

This study focuses on applying unsupervised machine learning techniques for Traumatic Brain Injury (TBI), which is the leading cause of death and disability among children and adults of age less than 44. Specifically, we present a case study to demonstrate the feasibility and applicability of subspace clustering techniques for extracting patterns from data collected from TBI patients.

Methods:

Data for this study were obtained from the Progesterone for Traumatic Brain Injury, Experimental Clinical Treatment – Phase III (PROTECT III) study, which a cohort of 882 TBI patients. We applied these subspace clustering methods (density-based, cell-based, and clustering-oriented) to this dataset and compared the performance of the different clustering methods.

Results:

The analyses showed three clusters of laboratory physiological data: (1) International Normalized Ratio (INR), (2) INR, chloride, creatinine, and (3) hemoglobin and hematocrit. While all subclustering algorithms had a reasonable accuracy in classifying patients by mortality status, density-based algorithm had higher F1 score and coverage.

Conclusions:

Clustering approaches serve as an important step for phenotype definition and validation in clinical domains such as TBI, where patient and injury heterogeneity are among the major reasons for failure of clinical trials. Results from this study also provide the foundation to develop scalable clustering algorithms for further research and validation.