NeuroDx-LM: A Clinical Large-Scale Model for EEG-based Neurological Disorder Detection

2025-08-11

AI Summary

To address the critical bottlenecks of scarce EEG annotations and poor clinical generalizability, this paper proposes a large-scale EEG modeling framework for neurological disorder detection. The method introduces a selective time-frequency embedding mechanism to explicitly capture EEG’s spatiotemporal-spectral characteristics and adopts a progressive feature-aware training strategy that hierarchically optimizes foundational representations and fine-grained discriminative features. By integrating self-supervised pretraining with joint time-frequency domain feature modeling, the framework significantly enhances adaptability to low-resource clinical settings. Evaluated on the CHB-MIT (epilepsy) and Schizophrenia datasets, it achieves state-of-the-art performance, improving diagnostic accuracy by 3.2% and 4.7%, respectively. These results demonstrate both strong clinical utility and robust cross-dataset generalization.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Multimodal Learning
• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models

Application Category

• Web Mining and Content Analysis: Large pretrained models with web data
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

Large-scale models pre-trained on Electroencephalography (EEG) have shown promise in clinical applications such as neurological disorder detection. However, the practical deployment of EEG-based large-scale models faces critical challenges such as limited labeled EEG data and suboptimal performance in clinical scenarios. To address these issues, we propose NeuroDx-LM, a novel large-scale model specifically designed for detecting EEG-based neurological disorders. Our key contributions include (i) a Selective Temporal-Frequency Embedding mechanism that adaptively captures complex temporal and spectral patterns in EEG signals; and (ii) a Progressive Feature-Aware Training strategy that refines feature representation in a two-stage process. In the first stage, our model learns the fundamental discriminative features of EEG activities; in the second stage, the model further extracts more specialized fine-grained features for accurate diagnostic performance. We evaluated NeuroDx-LM on the CHB-MIT and Schizophrenia datasets, achieving state-of-the-art performance in EEG-based seizure and schizophrenia detection, respectively. These results demonstrate the great potential of EEG-based large-scale models to advance clinical applicability. Our code is available at https://github.com/LetItBe12345/NeuroDx-LM.

Problem

• Detecting neurological disorders using EEG data efficiently
• Overcoming limited labeled EEG data for clinical use
• Improving EEG model performance in real-world scenarios

Innovation

• Selective Temporal-Frequency Embedding for EEG patterns
• Progressive Feature-Aware Training in two stages
• State-of-the-art EEG-based disorder detection performance