aiqbench analysis
RobustSeiz introduces a critical open-source framework for stress-testing EEG seizure detectors against real-world artifacts and distribution shifts before clinical deployment. By standardizing evaluation protocols across multiple public datasets, this tool moves the field beyond clean-data accuracy to assess model reliability under adversarial conditions. This work directly advances machine learning robustness in medical diagnostics, offering a reproducible pipeline essential for safe AI integration in healthcare.
RobustSeiz: An Open-Source Framework for Benchmarking the Robustness of EEG Seizure Detection Models
arXiv:2609.04007v1 Announce Type: new Abstract: Despite strong performance on held-out electroencephalography (EEG) data, seizure detectors may fail under real-world acquisition variability, artifacts, and adversarial inputs. We introduce RobustSeiz, an open-source, model-agnostic framework that provides a standardized, reproducible protocol for stress-testing and comparing seizure detectors under controlled, clinically motivated distribution shifts before deployment. We standardize four public scalp-EEG corpora (CHB-MIT, TUSZ, Siena, and SeizeIT1) into BIDS-EEG trees and evaluate subject-independent detectors on held-out splits. Environment, noise, and adversarial transforms are swept over predefined hyperparameter grids. Each run reports sample- and event-level sensitivity, precision, F1, false positives per 24 h, Lead and Lag onset timing, and Monte Carlo dropout predictive agreement. RobustSeiz includes a Dockerized GPU pipeline, experiment registry, and full-evaluation and research-subset modes. We demonstrate the framework with a contemporary seizure detector on TUSZ across the complete implemented shift grid; an AWGN analysis illustrates how perturbation severity changes detection quality, onset timing, and predictive agreement. RobustSeiz provides a shared benchmarking standard for evaluating seizure-detector robustness under realistic clinical stressors, extending pre-deployment assessment beyond clean-data accuracy.
Abstract:Despite strong performance on held-out electroencephalography (EEG) data, seizure detectors may fail under real-world acquisition variability, artifacts, and adversarial inputs. We introduce RobustSeiz, an open-source, model-agnostic framework that provides a standardized, reproducible protocol for stress-testing and comparing seizure detectors under controlled, clinically motivated distribution shifts before deployment. We standardize four public scalp-EEG corpora (CHB-MIT, TUSZ, Siena, and SeizeIT1) into BIDS-EEG trees and evaluate subject-independent detectors on held-out splits. Environment, noise, and adversarial transforms are swept over predefined hyperparameter grids. Each run reports sample- and event-level sensitivity, precision, F1, false positives per 24 h, Lead and Lag onset timing, and Monte Carlo dropout predictive agreement. RobustSeiz includes a Dockerized GPU pipeline, experiment registry, and full-evaluation and research-subset modes. We demonstrate the framework with a contemporary seizure detector on TUSZ across the complete implemented shift grid; an AWGN analysis illustrates how perturbation severity changes detection quality, onset timing, and predictive agreement. RobustSeiz provides a shared benchmarking standard for evaluating seizure-detector robustness under realistic clinical stressors, extending pre-deployment assessment beyond clean-data accuracy.
28 pages, 13 numbered figures, 9 tables; full-page graphical abstract and supplementary material included. Submitted to the Journal of the American Medical Informatics Association (JAMIA)
Machine Learning (cs.LG); Signal Processing (eess.SP)
arXiv:2609.04007 [cs.LG]
(or arXiv:2609.04007v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2609.04007 arXiv-issued DOI via DataCite (pending registration)
From: Mohammad Mohammadi Mr. [view email] [v1] Thu, 3 Sep 2026 15:45:52 UTC (12,779 KB)
Full text under the publisher's open licence · 230 words
