Pediatric cardiac arrest outcome prediction using data-driven machine learning of early quantitative electroencephalogram (qEEG) features.

Abstract

Hypoxic-ischemic brain injury drives poor outcomes after pediatric cardiac arrest, highlighting the need for early prognostication. This study evaluates whether machine learning models using a high-dimensional set of quantitative EEG (qEEG) features improve prediction of unfavorable neurologic outcome compared to a previously studied 7-feature model. We also assessed performance stability over time and the added value of clinical variables. Single-center retrospective cohort study of children aged 3 months to 18 years who experienced cardiac arrest and received EEG monitoring within 24 h post-arrest. Patients with pre-arrest Pediatric Cerebral Performance Category (PCPC) >3 were excluded. Unfavorable outcome was defined as death or PCPC ≥4 at hospital discharge or 30 days post-arrest. We extracted 164 qEEG features and trained models using three established algorithms. Performance was evaluated using area under the ROC curve (AUROC). Seventy patients were included (median age 7.0 years, IQR 1.5-11.5); 53 % had unfavorable outcomes. Models using 164 qEEG features outperformed the 7-feature model: LASSO [0.81 (95 % CI: 0.69-0.91) vs 0.45 (0.31-0.58)] and Random Forest [0.80 (0.67-0.90) vs 0.65 (0.50-0.78)]. Adding clinical variables did not improve performance. AUROCs were stable across 6-h epochs from 6 to 24 h. Higher phase locking value, fractal exponent, and coherence were associated with better outcomes; higher delta power and suppression ratio variability were associated with worse outcomes. Data-driven models using 164 qEEG features accurately predicted neurologic outcomes after pediatric cardiac arrest, with stable performance over time. Future work includes external validation to assess generalizability.