Automated detection of complex zebrafish seizure behavior at scale.

Abstract

Convulsive seizure behaviors are a hallmark feature of epilepsy, but automated detection of these events in freely moving animals is difficult. Here, we employed a high-resolution multi-camera array microscope with high-speed video acquisition and custom supervised machine learning (ML) for automated detection of larval zebrafish between 3- and 7-days post-fertilization (dpf). We assessed data from over 2700 zebrafish either exposed to a chemoconvulsant (pentylenetetrazole, PTZ) or genetic zebrafish lines representing Developmental Epileptic Encephalopathy (DEE) syndromes. Using eight-point skeletal body pose estimation for tracking individual larvae arrayed in a 96-well format, we report reliable, quantitative and age-dependent changes in maximum swim speed, as well as eye-, head- and tail- angle kinematics. Finally, we employed an ML-based algorithm to automatically identify normal and abnormal behaviors in an unbiased manner. Our results offer a robust framework for automated detection of zebrafish seizure-associated behaviors.