Neural network classification of Barnes maze search strategy utilization.

Area of Science:

• Neuroscience
• Cognitive Psychology
• Machine Learning

Background:

• The Barnes maze is a standard tool for assessing spatial memory.
• Non-spatial search strategies can confound traditional Barnes maze outcome measures.
• Traumatic brain injury (TBI) is known to impair spatial learning and memory.

Purpose of the Study:

• To develop a machine learning algorithm for unbiased quantification of Barnes maze search strategies.
• To investigate the impact of repetitive mild TBI on spatial and non-spatial search strategies.
• To enhance the understanding of factors influencing Barnes maze performance after TBI.

Main Methods:

• Development of a machine learning algorithm for automated search strategy analysis.
• Utilizing a rodent model of repetitive mild TBI.
• Assessing search strategies 3 months post-TBI using the Barnes maze.

Main Results:

• The machine learning algorithm successfully quantified search strategy utilization.
• Repetitive mild TBI significantly impaired the use of both spatial and systematic non-spatial search strategies.
• Deficits in strategy utilization were observed 3 months after TBI.

Conclusions:

• Quantifying search strategies provides a more sensitive measure of cognitive deficits than traditional Barnes maze metrics.
• TBI-induced impairments extend to the ability to employ systematic non-spatial search strategies.
• This approach can improve the assessment of cognitive dysfunction in TBI and neurodegenerative diseases.