Treffer: Visual detection of seizures in mice using supervised machine learning.

Title:
Visual detection of seizures in mice using supervised machine learning.
Authors:
Sabnis GS; The Jackson Laboratory, Bar Harbor, ME 04609, USA., Hession L; The Jackson Laboratory, Bar Harbor, ME 04609, USA., Mahoney JM; The Jackson Laboratory, Bar Harbor, ME 04609, USA., Mobley A; The Jackson Laboratory, Bar Harbor, ME 04609, USA., Santos M; The Jackson Laboratory, Bar Harbor, ME 04609, USA., Geuther B; The Jackson Laboratory, Bar Harbor, ME 04609, USA., Kumar V; The Jackson Laboratory, Bar Harbor, ME 04609, USA; School of Graduate Biomedical Sciences, Tufts University School of Medicine, Boston, MA 02111, USA; Graduate School of Biomedical Sciences and Engineering, University of Maine, Orono, ME 04469, USA. Electronic address: vivek.kumar@jax.org.
Source:
Cell reports methods [Cell Rep Methods] 2025 Dec 15; Vol. 5 (12), pp. 101242. Date of Electronic Publication: 2025 Nov 26.
Publication Type:
Journal Article
Language:
English
Journal Info:
Publisher: Elsevier Inc Country of Publication: United States NLM ID: 9918227360606676 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 2667-2375 (Electronic) Linking ISSN: 26672375 NLM ISO Abbreviation: Cell Rep Methods Subsets: MEDLINE
Imprint Name(s):
Original Publication: [New York] : Elsevier Inc., [2021]-
MeSH Terms:
Seizures*/diagnosis , Seizures*/chemically induced , Seizures*/physiopathology , Supervised Machine Learning*, Animals ; Mice ; Pentylenetetrazole ; Disease Models, Animal ; Male ; Video Recording ; Machine Learning ; Mice, Inbred C57BL
Comments:
Update of: bioRxiv. 2024 May 30:2024.05.29.596520. doi: 10.1101/2024.05.29.596520.. (PMID: 38868170)
Contributed Indexing:
Keywords: CP: computational biology; CP: neuroscience; computer vision; epilepsy; high throughput; machine learning; mouse models; open field; seizure; supervised learning
Substance Nomenclature:
WM5Z385K7T (Pentylenetetrazole)
Entry Date(s):
Date Created: 20251127 Date Completed: 20251216 Latest Revision: 20260202
Update Code:
20260202
PubMed Central ID:
PMC12859513
DOI:
10.1016/j.crmeth.2025.101242
PMID:
41308647
Database:
MEDLINE

Weitere Informationen

Seizures are caused by abnormal synchronous brain activity. The resulting changes in muscle tone, such as twitching, stiffness, or jerking, are used in visual scoring systems such as the Racine scale to quantify seizure intensity. However, visual inspection is time consuming, low throughput, and partially subjective, and there is a need for scalable and rigorous quantitative approaches. We used supervised machine learning approaches to develop automated classifiers to predict seizure severity directly from non-invasive video data. Using the pentylenetetrazole (PTZ)-induced seizure model in mice, we trained video-only classifiers to predict ictal events and combined these events to predict composite seizure intensity for a recording session, as well as time-localized seizure intensity scores. Our results show that seizure events and overall intensity can be rigorously quantified directly from overhead video of mice in a standard open field using supervised approaches. These results enable high-throughput, non-invasive, and standardized seizure scoring for neurogenetics and therapeutic discovery.
(Copyright © 2025 The Authors. Published by Elsevier Inc. All rights reserved.)

Declaration of interests The authors declare no competing interests.