Clinical and Experimental Pediatrics

Original Article

Neurology

Patient-independent automated pediatric seizure monitoring based on expert-labeled electrographic ictal data as core reference knowledge

Yoon Gi Chung, Jaeso Cho, Anna Cho, Hunmin Kim, Byung Chan Lim

Clin Exp Pediatr. 2026;69(8):665-675. Published online July 14, 2026

Question: Can deep learning models trained on expert-verified electroencephalography segments reliably detect seizures and be applied to single-channel wearable monitoring?
Finding: This technique demonstrated 80.1%–100% sensitivity and low false-alarm rates. On 1,604 expert-labeled segments, the model outperformed previous studies in terms of latency and accuracy across unseen datasets.
Meaning: Expert-labeled data are essential for achieving universal seizure detection. This channel-specific approach enabled efficient and continuous monitoring using wearable devices.

DOI: https://doi.org/10.3345/cep.2026.01011

Review Article

Neurology

Big data analysis and artificial intelligence in epilepsy – common data model analysis and machine learning-based seizure detection and forecasting

Yoon Gi Chung, Yonghoon Jeon, Sooyoung Yoo, Hunmin Kim, Hee Hwang

Clin Exp Pediatr. 2022;65(6):272-282. Published online November 26, 2021

Web of Science 11 Crossref 13

· Big data analysis, such as common data model and artificial intelligence, can solve relevant questions and improve clinical care.
· Recent deep learning studies achieved 0.887–0.996 areas under the receiver operating characteristic curve for automated interictal epileptiform discharge detection.
· Recent deep learning studies achieved 62.3%–99.0% accuracy for interictal-ictal classification in seizure detection and 75.0%– 87.8% sensitivity with a 0.06–0.21/hr false positive rate in seizure forecasting.

DOI: https://doi.org/10.3345/cep.2021.00766

Other

Knowledge-guided artificial intelligence technologies for decoding complex multiomics interactions in cells

Dohoon Lee, Sun Kim

Clin Exp Pediatr. 2022;65(5):239-249. Published online November 26, 2021

Web of Science 6 Crossref 6

· The need for data-driven modeling of multiomics interactions was recently highlighted.
· Many artificial intelligence-driven models have been developed, but only a few have incorporated biological domain knowledge within model architectures or training procedures.
· Here we provide a comprehensive review of deep learning models to decipher complex multiomics interactions regarding the biological guidance imposed upon them to facilitate further development of biological knowledge-guided deep learning models.

DOI: https://doi.org/10.3345/cep.2021.01438

Cited By 59	Prevalence of anxiety, depression, and stress among parents of neonates admitted to neonatal intensive care unit: a systematic review and meta-analysis
Cited By 37	Community-acquired pneumonia in children: updated perspectives on its etiology, diagnosis, and treatment
Cited By 37	Metabolic complications of obesity in children and adolescents
Cited By 34	Microplastic and human health with focus on pediatric well-being: a comprehensive review and call for future studies
Cited By 34	Neonatal family-centered care: evidence and practice models

Search