Automated acoustic detection of mouse scratching

Area of Science:

• Neuroscience
• Animal Behavior
• Bioacoustics

Background:

• Itch is a sensory perception that triggers scratching.
• Scratching behavior in animal models is a key indicator of itch.
• Current methods for quantifying scratching rely on manual video analysis, which is labor-intensive and prone to error.

Purpose of the Study:

• To develop and validate a novel automated method for detecting and quantifying mouse scratching behavior using acoustics.
• To address the limitations of manual scoring in animal models of itch.

Main Methods:

• Development of an automated system for acoustic detection of scratching sounds.
• Application of supervised learning techniques for scratch event classification.
• Quantification of chloroquine-induced scratching in C57BL/6 mice.

Main Results:

• The automated acoustic detection method achieved 85% sensitivity and 75% positive predictive value in quantifying scratching behavior.
• This method provides an accurate and objective measure of itch-related scratching.
• Demonstrated the feasibility of using supervised learning for acoustic scratch detection.

Conclusions:

• Automated acoustic detection offers a reliable and efficient alternative to manual scoring for assessing mouse scratching.
• This novel approach advances the objective quantification of itch in preclinical research.
• The study represents the first application of supervised learning for automated acoustic scratch detection.