Machine vision based frailty assessment for genetically diverse mice.

Area of Science:

• Gerontology
• Animal Behavior
• Biomedical Engineering

Background:

• Frailty indexes (FIs) assess health and aging in humans and model organisms.
• High-throughput methods are crucial for understanding aging and conducting interventional studies.
• A machine vision-based visual frailty index (vFI) was previously developed using C57BL/6J mice behavior.

Purpose of the Study:

• To extend the visual frailty index (vFI) to genetically diverse mouse populations.
• To enable scalable, high-throughput aging research in diverse genetic backgrounds.
• To develop accurate predictive models for frailty, chronological age, and lifespan proportion.

Main Methods:

• Collected frailty and behavior data from a large cohort of aged Diversity Outbred (DO) mice.
• Combined new data with previous datasets to create a large video-based aging behavior dataset.
• Developed predictive models using machine vision and behavioral data.

Main Results:

• Achieved accurate prediction of frailty, chronological age, and proportion of life lived in DO mice.
• Established one of the largest video-based aging behavior datasets to date.
• Demonstrated the efficacy of the vFI in genetically diverse populations.

Conclusions:

• Automated frailty assessment tools can be extended to genetically diverse mice.
• This advancement will improve aging mechanism modeling and facilitate high-throughput interventional aging studies.
• The vFI is a valuable tool for aging research in diverse animal models.