Adaptive EEG-based stroke diagnosis with a GRU-TCN classifier and deep Q-learning thresholding

TL;DR

This paper introduces an adaptive EEG-based stroke diagnosis system combining a GRU-TCN classifier with deep Q-learning thresholding, achieving high accuracy and robustness for rapid bedside stroke triage.

Contribution

It presents a novel adaptive multitask EEG classifier with real-time threshold tuning using deep Q-learning, improving stroke diagnosis accuracy and interpretability.

Findings

Stroke-type accuracy reached 89.3% baseline, increased to 98.0% with DQN.

High robustness demonstrated on independent EEG cohort.

Adaptive thresholding improves sensitivity-specificity balance.

Abstract

Rapid triage of suspected stroke needs accurate, bedside-deployable tools; EEG is promising but underused at first contact. We present an adaptive multitask EEG classifier that converts 32-channel signals to power spectral density features (Welch), uses a recurrent-convolutional network (GRU-TCN) to predict stroke type (healthy, ischemic, hemorrhagic), hemispheric lateralization, and severity, and applies a deep Q-network (DQN) to tune decision thresholds in real time. Using a patient-wise split of the UCLH Stroke EIT/EEG data set (44 recordings; about 26 acute stroke, 10 controls), the primary outcome was stroke-type performance; secondary outcomes were severity and lateralization. The baseline GRU-TCN reached 89.3% accuracy (F1 92.8%) for stroke type, about 96.9% (F1 95.9%) for severity, and about 96.7% (F1 97.4%) for lateralization. With DQN threshold adaptation, stroke-type accuracy increased to about 98.0% (F1 97.7%). We also tested robustness on an independent, low-density EEG cohort (ZJU4H) and report paired patient-level statistics. Analyses follow STARD 2015 guidance for diagnostic accuracy studies (index test: GRU-TCN+DQN; reference standard: radiology/clinical diagnosis; patient-wise evaluation). Adaptive thresholding shifts the operating point to clinically preferred sensitivity-specificity trade-offs, while integrated scalp-map and spectral visualizations support interpretability.