EVA-Net: Interpretable Brain Age Prediction via Continuous Aging Prototypes from EEG
This provides an interpretable framework for healthcare intelligence to detect brain anomalies like Alzheimer's disease using EEG, though it is incremental in combining existing techniques for a specific domain.
The paper tackled brain age prediction from EEG data by addressing challenges like imperfect medical data and lack of interpretability, proposing EVA-Net which achieved state-of-the-art accuracy on 1297 healthy subjects and validated anomaly detection on 27 MCI and AD patients with significant brain-age gaps.
The brain age is a key indicator of brain health. While electroencephalography (EEG) is a practical tool for this task, existing models struggle with the common challenge of imperfect medical data, such as learning a ``normal'' baseline from weakly supervised, healthy-only cohorts. This is a critical anomaly detection task for identifying disease, but standard models are often black boxes lacking an interpretable structure. We propose EVA-Net, a novel framework that recasts brain age as an interpretable anomaly detection problem. EVA-Net uses an efficient, sparsified-attention Transformer to model long EEG sequences. To handle noise and variability in imperfect data, it employs a Variational Information Bottleneck to learn a robust, compressed representation. For interpretability, this representation is aligned to a continuous prototype network that explicitly learns the normative healthy aging manifold. Trained on 1297 healthy subjects, EVA-Net achieves state-of-the-art accuracy. We validated its anomaly detection capabilities on an unseen cohort of 27 MCI and AD patients. This pathological group showed significantly higher brain-age gaps and a novel Prototype Alignment Error, confirming their deviation from the healthy manifold. EVA-Net provides an interpretable framework for healthcare intelligence using imperfect medical data.