Educational content on VJNeurology is intended for healthcare professionals only. By visiting this website and accessing this information you confirm that you are a healthcare professional.

Share this video  

AAN 2025 | Machine learning-based behavioral analysis for Alzheimer’s mouse models

Stephanie Miller, PhD, Gladstone Institutes, San Francisco, CA, highlights the application of machine learning to characterize behavior in mouse models of Alzheimer’s disease. Traditional paradigms for assessing cognitive impairment often rely on constrained and task-specific behaviors. In contrast, Dr Miller’s team utilizes advanced computational approaches to analyze spontaneous, naturalistic behavior, enabling high-resolution quantification of subtle phenotypic changes associated with disease onset and progression. This interview took place at the 77th American Academy of Neurology (AAN) Annual Meeting in San Diego, CA..

These works are owned by Magdalen Medical Publishing (MMP) and are protected by copyright laws and treaties around the world. All rights are reserved.

Transcript

We study Alzheimer’s disease in mouse models and, in order to understand whether a mouse is experiencing symptoms associated with perhaps what would be dementia in people, we need to assess the mouse’s behavior. Conventional approaches would have us perhaps have the mouse solve a maze or something, in which we’re trying to determine whether it’s having a memory impairment...

We study Alzheimer’s disease in mouse models and, in order to understand whether a mouse is experiencing symptoms associated with perhaps what would be dementia in people, we need to assess the mouse’s behavior. Conventional approaches would have us perhaps have the mouse solve a maze or something, in which we’re trying to determine whether it’s having a memory impairment. Using these new machine learning methods, we’re able to assess the mouse’s what we call spontaneous or naturalistic behavior, in which the animal essentially walks around doing what it would like to do, which is actually an incredibly rich version of animal behavior. And by using the new machine learning approaches, we can identify subtle changes in the animal’s actions that are associated with disease progression and may be targeted when we’re trying to assess therapeutic efficacy.

 

This transcript is AI-generated. While we strive for accuracy, please verify this copy with the video.

Read more...