Which information derived from the Coma Recovery Scale-Revised provides the most reliable prediction of clinical diagnosis and recovery of consciousness? A comparative study using machine learning techniques.
Silvia Campagnini, Roberto Llorens, M Dolores Navarro and 5 others
PMID 38193722WHAT IT FOUND
For patients with prolonged disorders of consciousness, the detailed scores from each subscale of the CRS-R predicted recovery of consciousness and diagnosis at discharge more reliably than the overall CRS-R total score or the initial clinical diagnosis alone.
Use subscale profiles for prognostication.
Key findings
01CRS-R subscale scores and the CRS-R Index provided the best results for predicting clinical diagnosis at discharge, outperforming the total score and initial diagnosis.
02The initial clinical diagnosis was the least accurate predictor for both discharge diagnosis and recovery of consciousness, while subscale scores and the Consciousness Domain Index were the most accurate for predicting emergence.
03The study used retrospective medical records from a long-term neurorehabilitation program, meaning the results apply to patients with prolonged disorders of consciousness rather than acute injuries.
STILL TO COME
How it was doneWhat they foundWhat it means for PTsWhat it means for OTsWhat it means for SLPs
Read the rest of this summary
You get three full summaries a month, free, and we do not ask for a card. Search, the TL;DRs and your library stay unlimited either way.
What it does not show
The sample consisted of patients with prolonged disorders of consciousness in a long-term rehabilitation setting, so the findings may not apply to patients with acute brain injuries. The number of participants who recovered consciousness (57) was much smaller than those who did not, creating an unbalanced dataset for predicting emergence. The CRS-R Modified Score and CRS-R Index were estimated from conventional subscale scores because the raw data on the number of neurobehavioral responses were not available in the medical records. The study was retrospective, relying on data collected for clinical care rather than a controlled research protocol.
Declared interests
The authors declare no conflicts of interest. The study was supported by the European Commission and the Conselleria d’Innovació, Universitats, Ciència i Societat Digital of Generalitat Valenciana.
The easy way to misread this
Do not assume that a single total CRS-R score or the initial diagnosis of UWS versus MCS is sufficient for predicting recovery. The study shows these are less reliable than the detailed subscale scores. Also, note that these results apply to patients in long-term rehabilitation, not necessarily to those in the acute phase of injury.