Subspace Clustering of Physiological Data From Acute Traumatic Brain Injury Patients: Retrospective Analysis Based on the PROTECT III Trial.
Sina EhsaniChandan K ReddyBrandon P ForemanJonathan RatcliffVignesh SubbianPublished in: JMIR biomedical engineering (2021)
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. The results from this study provide a foundation to develop scalable clustering algorithms for further research and validation.
Keyphrases
- traumatic brain injury
- single cell
- clinical trial
- rna seq
- end stage renal disease
- ejection fraction
- machine learning
- chronic kidney disease
- liver failure
- phase ii
- electronic health record
- study protocol
- case report
- deep learning
- respiratory failure
- severe traumatic brain injury
- randomized controlled trial
- patient reported outcomes
- mechanical ventilation