Cross-patient Seizure Onset Zone Classification by Patient-Dependent Weight

2025-08-05

AI Summary

Precise presurgical localization of the seizure onset zone (SOZ) in focal epilepsy faces a “cross-patient generalization” challenge: substantial inter-individual variability in EEG patterns and clinical characteristics causes generic models to suffer severe performance degradation on unseen patients. Method: We propose a patient-specific weighted fine-tuning framework grounded in feature similarity. A pre-trained model extracts intermediate-layer representations; similarity between a test patient and each training patient is computed, and training samples are dynamically reweighted accordingly for full-parameter fine-tuning. Crucially, no patient-specific labeled data are required—only a single EEG recording suffices for adaptation. Results: Under leave-one-patient-out cross-validation, SOZ classification accuracy improves for all subjects, with an average gain exceeding 10%. This substantially mitigates cross-patient performance drop and establishes a generalizable, individualized machine learning paradigm for epilepsy focus localization.

Technology Category

• Machine Learning: Semi-Supervised Learning
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Search and Optimization: Learning to Search

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Web Mining and Content Analysis: Large pretrained models with web data
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Identifying the seizure onset zone (SOZ) in patients with focal epilepsy is essential for surgical treatment and remains challenging due to its dependence on visual judgment by clinical experts. The development of machine learning can assist in diagnosis and has made promising progress. However, unlike data in other fields, medical data is usually collected from individual patients, and each patient has different illnesses, physical conditions, and medical histories, which leads to differences in the distribution of each patient's data. This makes it difficult for a machine learning model to achieve consistently reliable performance in every new patient dataset, which we refer to as the "cross-patient problem." In this paper, we propose a method to fine-tune a pretrained model using patient-specific weights for every new test patient to improve diagnostic performance. First, the supervised learning method is used to train a machine learning model. Next, using the intermediate features of the trained model obtained through the test patient data, the similarity between the test patient data and each training patient's data is defined to determine the weight of each training patient to be used in the following fine-tuning. Finally, we fine-tune all parameters in the pretrained model with training data and patient weights. In the experiment, the leave-one-patient-out method is used to evaluate the proposed method, and the results show improved classification accuracy for every test patient, with an average improvement of more than 10%.

Problem

• Classifying seizure onset zones across diverse patient data distributions
• Improving machine learning reliability for individual epilepsy patients
• Adapting pretrained models using patient-specific weighting for better diagnosis

Innovation

• Patient-specific weights for fine-tuning
• Similarity-based training patient weighting
• Leave-one-patient-out evaluation method