Binary Classification of Consciousness Using Cerebral Blood Flow and EEG Features.

BACKGROUND

Assessing consciousness at the bedside in the neurocritical care unit is complicated by sedation and other treatment effects. While EEG is commonly used, it offers a limited view of the neurovascular unit. We evaluated whether combining cerebral blood flow (CBF) features with EEG improves binary classification of consciousness in patients with severe brain injury.

METHODS

We retrospectively analyzed 35 adults who underwent multimodal neuromonitoring. Signals were segmented into 30-min windows after each probe recalibration. We used parameters including CBF low-frequency bands (Band IV 0.027-0.073 Hz, Band V 0.01-0.027 Hz, and Band All 0-0.5 Hz) and EEG band powers (delta-beta), alpha-delta ratio (ADR), alpha/(delta+theta) (ADTR), total power. A random forest (RF) model trained using K-fold cross-validation achieved optimal classification. Highly correlated features (r > 0.8) were excluded from simultaneous use. Performance was summarized with ROC-AUC and accuracy, with confusion matrices shown for the best combinations.

RESULTS

Multimodal feature combinations significantly improved classification compared to EEG features alone. The best-performing combination (EEG ADR, total EEG power, and CBF Band V) achieved a ROC-AUC of 0.86 and an accuracy of 82%, representing up to 69% improvement over EEG-only models. This model also performed well on noninvasive optical blood flow data.

CONCLUSIONS

Combining EEG and CBF metrics, particularly low-frequency oscillations in perfusion fluctuations, enhances classification of consciousness in critically ill patients and may support future bedside tools for real-time neurovascular monitoring and in decision making about treatment and rehabilitation.