Finding The Balance Between Model Complexity And Performance: Using Ventral Striatal Oscillations To Classify Feeding Behavior In Rats

The ventral striatum (VS) is a central node within a distributed network that controls appetitive behavior, and neuromodulation of the VS has demonstrated therapeutic potential for appetitive disorders. Local field potential (LFP) oscillations recorded from deep brain stimulation (DBS) electrodes within the VS are a pragmatic source of neural systems-level information about appetitive behavior that could be used in responsive neuromodulation systems. Here, we recorded LFPs from the bilateral nucleus accumbens core and shell (subregions of the VS) during limited access to palatable food across varying conditions of hunger and food palatability in male rats. We used standard statistical methods (logistic regression) as well as the machine learning algorithm lasso to predict aspects of feeding behavior using VS LFPs. We were able to predict the amount of food eaten, the increase in consumption following food deprivation, and the type of food eaten. Further, we were able to predict whether the initiation of feeding was imminent up to 42.5 seconds before feeding began and classify current behavior as either feeding or not-feeding. In classifying feeding behavior, we found an optimal balance between model complexity and performance with models using 3 LFP features primarily from the alpha and high gamma frequencies. As shown here, unbiased methods can identify systems-level neural activity linked to domains of mental illness with potential application to the development and personalization of novel treatments.Author summary As neuropsychiatry begins to leverage the power of computational methods to understand disease states and to develop better therapies, it is vital that we acknowledge the trade-offs between model complexity and performance. We show that computational methods can elucidate a neural signature of feeding behavior and we show how these methods could be used to discover neural patterns related to other behaviors and reveal new potential therapeutic targets. Further, our results help to contextualize both the limitations and potential of applying computational methods to neuropsychiatry by showing how changing the data being used to train predictive models (e.g., population vs. individual data) can have a large impact on how model performance generalizes across time, internal states, and individuals.