Predicting outcome from subacute unresponsive wakefulness syndrome or vegetative state

A novel scoring system to predict the outcomes of adult patients with hypoxic-ischemic encephalopathy

BACKGROUND

Adult patients with hypoxic-ischemic encephalopathy (HIE) often incur large costs, but their outcomes are poor. Currently, there is lack of a comprehensive quantitative approach to predict patient prognoses.

METHODS

A total of 73 adult patients with HIE participated in this prospective, observational study. Clinical assessments, laboratory tests, and electrophysiological examinations were conducted within 3 days after HIE occurred. Logistic regression model was used to identify independent factors associated with patient outcomes.

RESULTS

After a 6-month follow-up, 44 (61.1%) patients survived, 28 (38.9%) patients died, and one patient was lost to follow-up. The level of blood calcium and lactate, the presence of electroencephalography reactivity, and Glasgow Coma Scale (GCS) score were significantly associated with the patient's outcome. Based on the regression coefficients from logistic regression analysis, we constructed a scoring system (CEGL; C: calcium, E: EEG reactivity, G: GCS, L: lactate) to predict the possibility of a patient's death. The area under the receiver operating characteristic curve was 0.91 (P < 0.001, 95% CI [0.87-0.95]) with a specificity of 97.7% and a positive predictive value of 97.4%.

CONCLUSION

CEGL score can provide clinicians useful information for assessment of patient prognosis within 6 months after HIE.

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

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.