Expert-level detection of low-voltage intervals in EEG as a robust biomarker of neonatal encephalopathy

A ConvNeXt model detected low-voltage intervals (LVIs) in neonatal EEG with an AUC of 0.996 and a Matthews correlation coefficient of 0.926 on held-out validation, according to an arXiv paper (arXiv:2610.12680v1) that trained on 654 hours of per-channel EEG from 123 neonates with 51,162 annotated LVIs. Model-reader agreement exceeded inter-reader agreement (Δκ = 0.025, 95% CI: 0.007 to 0.045, p<0.001), reaching expert-level equivalence, and on a combined dataset of 444 neonates percentage LVI correlated with EEG grades (Spearman's ρ=0.801), HIE grades (ρ=0.384) and seizure burden (ρ=0.244) while predicting seizures with an AUC of 0.872. The authors propose LVIs, defined solely by amplitude and duration, as a context-independent alternative to inter-burst intervals and a robust automated biomarker of neonatal encephalopathy.

arXiv:2610.12680v1 Announce Type: new Abstract: Background: Discontinuity in neonatal EEG is a critical marker of brain dysfunction but can be difficult to quantify visually. Inter-burst intervals IBIs are a key characteristic of discontinuity, yet their definition does not easily translate to AI detection. Objectives: To introduce low-voltage intervals LVIs , defined exclusively by amplitude and duration, as a context-independent alternative to IBIs, develop an AI detection method for LVIs, and assess their clinical utility as a marker of brain injury. Methods: We developed a ConvNeXt model to detect LVIs and compared its performance with existing methods. We then tested the clinical relevance of detected LVIs across four applications: 1 grading background EEG abnormalities on an open benchmark dataset, 2 classifying clinical hypoxic-ischaemic encephalopathy HIE grades and comparing with a normal EEG dataset, 3 seizure prediction, and 4 association with seizure burden. Results: For training and validation, 654 hours of per-channel EEG from 123 neonates were reviewed and 51,162 LVIs were annotated. On held-out validation, ConvNeXt had an AUC of 0.996 and a Matthews correlation coefficient of 0.926. Model-reader agreement exceeded inter-reader agreement $\Delta \kappa = 0.025$, 95% CI: 0.007 to 0.045, $p<0.001$ , attaining expert-level equivalence. On a combined dataset of 444 neonates, percentage LVI showed a strong association with EEG grades Spearman's $\rho=0.801$ , a moderate association with HIE grades $\rho=0.384$ , a weaker association with seizure burden $\rho=0.244$ , and a strong seizure prediction capacity AUC $=0.872$ . Conclusion: AI detection of LVIs achieves expert-level equivalence, whereas quantitative features do not. Automated LVI quantification provides a robust clinical biomarker of neonatal encephalopathy associated with background EEG activity, HIE severity, and seizure risk.