Stabilność predykcji przypadku do przypadku w osobniczym detektorze wyładowań padaczkowych opartym na głębokim uczeniu maszynowym z EEG-MEG
Event-Wise Stability of Patient-Specific EEG-MEG Deep Learning Spike Detection in Clinical MEG
W skrócie
[Preprint - wstępne wyniki] Badacze opracowali system do wykrywania charakterystycznych dla epilepsji zmian w rejestrach mózgu (wyładowań padaczkowych) z wykorzystaniem sztucznej inteligencji, który łączy dwie metody pomiaru aktywności mózgu: EEG i MEG. Wyniki pokazały, że dodanie EEG do pomiarów MEG poprawiło dokładność wykrywania wyładowań, szczególnie u pacjentów, u których te wyładowania były widoczne głównie w MEG. System działał stabilnie i niezawodnie zarówno dla różnych algorytmów, jak i dla poszczególnych pacjentów.
Oryginalny abstract (angielski)
Objective: Computational magnetoencephalography (MEG) interictal epileptiform discharge (IED) detectors have mainly used generalized MEG-only models, whereas clinical MEG interpretation routinely integrates simultaneous electroencephalography (EEG) and includes MEG-unique or MEG-dominant discharges. We developed a patient-specific EEG-MEG IED detector and evaluated event-wise prediction stability across models and the effect of adding EEG to MEG-based prediction. Methods: Seventeen patients undergoing clinical EEG-MEG evaluation for epilepsy were retrospectively analyzed. Clinically accepted dipole-review IEDs were treated as positive events, and nonannotated events were sampled as negatives. Logistic regression (LR), random forest (RF), and a lightweight three-dimensional ResNet were trained separately within each patient using EEG-only, MEG-only, and combined EEG-MEG (EMEG) inputs. Primary performance metrics were the area under the receiver operating characteristic curve (ROC-AUC) and average precision. Event-wise stability was assessed using rank disagreement, rank volatility, and class-aware distribution quotient analysis. Results: Aggregate discrimination was high across models and modalities. Median ROC-AUCs for EEG, MEG, and EMEG were 0.850, 0.890, and 0.880 for LR; 0.880, 0.860, and 0.910 for RF; and 0.920, 0.960, and 0.960 for ResNet. Despite comparable aggregate performance, event-wise analysis revealed model-dependent prediction behavior. ResNet showed significantly lower non-IED rank volatility than classical machine learning models and lower non-IED rank disagreement, particularly compared with RF. Adding EEG to MEG was associated with more favorable class-aware event-wise positioning in most events, while MEG-unique/dominant cases showed greater relative MEG contribution. Conclusions: Patient-specific EEG-MEG IED detection revealed clinically meaningful event-wise differences not captured by aggregate metrics. Simultaneous EEG complemented MEG-based detection, while MEG contribution remained prominent in MEG-dominant cases, supporting multimodal patient-specific IED event prioritization.