“Look at my classifier's result”: Disentangling unresponsive from (minimally) conscious patients

- Machine learning may help predict diagnosis and outcome in consciousness disorders.
- Repeated behavioral assessments (CRS-R) and CRS-R at recording time must be reported.
- Outcome after one year is a potential candidate for a gold standard.
- Probabilistic, multi-class classifiers better match clinical requirements.

Given the fact that clinical bedside examinations can have a high rate of misdiagnosis, machine learning techniques based on neuroimaging and electrophysiological measurements are increasingly being considered for comatose patients and patients with unresponsive wakefulness syndrome, a minimally conscious state or locked-in syndrome. Machine learning techniques have the potential to move from group-level statistical results to personalized predictions in a clinical setting. They have been applied for the purpose of (1) detecting changes in brain activation during functional tasks, equivalent to a behavioral command-following test and (2) estimating signs of consciousness by analyzing measurement data obtained from multiple subjects in resting state. In this review, we provide a comprehensive overview of the literature on both approaches and discuss the translation of present findings to clinical practice. We found that most studies struggle with the difficulty of establishing a reliable behavioral assessment and fluctuations in the patient's levels of arousal. Both these factors affect the training and validation of machine learning methods to a considerable degree. In studies involving more than 50 patients, small to moderate evidence was found for the presence of signs of consciousness or good outcome, where one study even showed strong evidence for good outcome.