Machine Learning Based Classification of Deep Brain Stimulation Outcomes in a Rat Model of Binge Eating Using Ventral Striatal Oscillations

Doucette, Wilder; Dwiel, Lucas L.; Boyce, Jared E.; Simon, Amanda A.; Khokhar, Jibran Y.; Green, Alan I.

doi:10.3389/fpsyt.2018.00336

Cited by 14 publications

(25 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These data highlight an important caveat impeding more widespread use of circuit-based therapies in clinical populations: highly variable treatment outcomes across individuals. The fact that many of our rats did not show decreases in alcohol consumption with NAcSh stimulation suggests that perhaps not all individuals respond to stimulation of the same brain target [as we have previously observed in a model of binge eating (Doucette et al, 2018)] or the same stimulation parameters. This caveat does not necessarily diminish the impact of the current results, but indicate that further advancement of circuit-based interventions requires that electrode target selection and stimulation parameters be personalized based on an individual's unique brain structure and function.…”

Section: Discussionmentioning

confidence: 53%

Corticostriatal oscillations predict high vs. low drinkers in a preclinical model of limited access alcohol consumption

Henricks

Dwiel²,

Deveau³

et al. 2018

Preprint

Self Cite

View full text Add to dashboard Cite

Alcohol use disorders (AUDs) affect a large proportion of individuals in the United States.Unfortunately, the current therapies to treat AUDs are largely ineffective. Deep brain stimulation (DBS) has been proposed as a promising therapy for AUDs, but the high individual variability in treatment response limits broader implementation of this approach.The corticostriatal circuit is key in processing the rewarding properties of alcohol and we hypothesize that we can identify neural features within this circuit that will predict individual response to DBS in order to maximize treatment outcomes. In the current experiment, local field potentials (LFPs) were recorded from the nucleus accumbens shell (NAcSh) and medial prefrontal cortex (mPFC) of male Sprague-Dawley rats (n=13). The impact of NAcSh and mPFC DBS on levels of alcohol consumption was subsequently evaluated. On a population level, DBS in either region failed to significantly alter alcohol drinking behavior due to high individual variability in response. However, when individual features of corticostriatal LFPs were used as predictors of alcohol drinking outcomes (decreasers, increasers, or nonresponders to DBS) for each rat using a machine-learning approach (lasso), response to DBS could be predicted with greater accuracy than expected by chance. These data suggest that individual differences in corticostriatal circuit activity prior to stimulation likely contributes to the variable responses to DBS therapy. Ultimately, we hope to use knowledge gained from these data to tailor DBS therapies to individuals, further enhancing treatment efficacy.All rights reserved. No reuse allowed without permission.was not peer-reviewed) is the author/funder, who has granted bioRxiv a license to display the preprint in perpetuity.

show abstract

Section: Discussionmentioning

confidence: 53%

Corticostriatal oscillations predict high vs. low drinkers in a preclinical model of limited access alcohol consumption

Henricks

Dwiel²,

Deveau³

et al. 2018

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…In order to link corticostriatal activity to biological sex or phase of estrous we used an unbiased machine learning approach similar to what we have published previously (30,31). We built predictive models using corticostriatal LFPs to classify rats by biological sex and female rats by phase of estrous.…”

Section: Discussionmentioning

confidence: 99%

Sex differences in the ability of corticostriatal oscillations to predict rodent alcohol consumption

Henricks

Sullivan²,

Dwiel³

et al. 2019

Preprint

Self Cite

View full text Add to dashboard Cite

Background: Although male and female rats differ in their patterns of alcohol use, little is known regarding the neural circuit activity that underlies these differences in behavior. The current study used a machine learning approach to characterize sex differences in local field potential (LFP) oscillations that may relate to sex differences in alcohol drinking behavior.Methods: LFP oscillations were recorded from the nucleus accumbens shell and the rodent medial prefrontal cortex of adult male and female Sprague-Dawley rats. Recordings occurred before rats were exposed to alcohol (n=10/sex X 2 recordings/rat) and during sessions of limited access to alcohol (n=5/sex X 5 recordings/rat). Oscillations were also recorded from each female rat in each phase of estrous prior to alcohol exposure. Using machine-learning, we built predictive models to classify rats based on: 1) biological sex; 2) phase of estrous; and 3) alcohol intake levels. We evaluated model performance from real data by comparing it to the performance of models built and tested on permutations of the data. Results:Our data demonstrate that corticostriatal oscillations were able to predict alcohol intake levels in males (p<0.01), but not in females (p=0.45). The accuracies of models predicting biological sex and phase of estrous were related to fluctuations observed in alcohol drinking levels; females in diestrus drank more alcohol than males (p=0.052), and the male vs. diestrus female model had the highest accuracy (71.01%) compared to chance estimates.Conversely, females in estrus drank similar amounts of alcohol to males (p=0.702), and the male vs. estrus female model had the lowest accuracy (56.14%) compared to chance estimates. Conclusions:The current data demonstrate that oscillations recorded from corticostriatal circuits contain significant information regarding alcohol drinking in males, but not alcohol drinking in females. Future work will focus on identifying where to record LFP oscillations in order to predict alcohol drinking in females, which may help elucidate sex-specific neural targets for future therapeutic development.

show abstract

“…they pooled data across subjects. For some predictions, using only individual datasets is impractical, such as determining the optimal target for stimulation [35]. However, when tuning stimulation parameters or trying to determine when stimulation would be most effective the data presented here suggest that using data from each individual would produce the best models as long as that data is sampled from across time and ideally represent different internal states (e.g., stress/anxiety or mood).…”

Section: Machine Learning and Deep Brain Stimulationmentioning

confidence: 99%

“…This work can be categorized into three domains: predicting treatment outcomes, defining treatment parameters, and actively optimizing treatment through time. Treatment outcomes have been successfully predicted using both structural and functional connectivity measures in Parkinsonian patients [47] as well as oscillatory activity in a rodent model of binge eating [35]. In a high throughput manner, machine learning has also been utilized to comb through the vast space of DBS parameters and medication combinations [48] and finding the set of DBS parameters that lead to the largest desired change in brain activity [49].…”

Section: Machine Learning and Deep Brain Stimulationmentioning

confidence: 99%

“…Following completion of a DBS intervention reported separately [35] and a 2 week washout period, animals established a baseline of binge-like feeding on powdered food within recording chambers. Once a stable baseline of palatable sweet-fat chow intake was established, two separate binge sessions were recorded (LFP and video).…”

Section: Feeding Behaviors and Dynamicsmentioning

confidence: 99%

See 1 more Smart Citation

Finding the balance between model complexity and performance: Using ventral striatal oscillations to classify feeding behavior in rats

Dwiel

Connerney

Green

et al. 2018

Preprint

Self Cite

View full text Add to dashboard Cite

Binge eating is a disruptive and treatment-resistant behavior that complicates the management of obesity and comorbid psychiatric disorders. The distributed network that governs feeding behavior, particularly of palatable food, has a nexus point within the ventral striatum (VS). This important structure integrates information from energy homeostasis circuits of the hypothalamus and brain stem, cognitive control regions of the prefrontal cortex and central nodes of learning and memory. The VS is thus an ideal target for neuromodulation-based interventions (e.g., deep brain stimulation) for the treatment of appetitive disorders. Here, we extracted information about feeding behavior from VS oscillations in a rat model of binge eating -a critical step in the development of responsive neuromodulation systems for appetitive disorders. Local field potentials (LFPs) were recorded from bilateral nucleus accumbens (NAc) core and shell (regions within the VS) during binge sessions across varying conditions. LFP features (n=58) were used as predictors in statistical (logistic regression) and machine learning (lasso) models to predict the type and quantity of food consumed, classify rat behavior (feeding or not feeding) in real time, and predict the onset of future feeding bouts. The complexity of real-time models was then manipulated to determine the impact on model stability and performance.Performance of models was quantified (effect size, d) by comparison to the performance of models built from permuted data. Models were able to predict the amount of food eaten at baseline (mean absolute error, MAE = 2.6 ± 0.08 gm; d = 0.43), the increase in binge size following food deprivation (MAE = 0.8% ± 0.01%; d = 1.1) and the type of food eaten (accuracy = 59 ± 1%; d = 0.55). Other models were able to predict whether initiation of feeding was imminent (area under the curve, AUC = 0.81 ± 0.03; d = 2.68) up to 42.5 seconds before feeding began and classify current behavior as feeding or not-feeding (AUC = 0.87 ± 0.01; d = 3.27). For real-time models, an optimal balance between model complexity and performance was achieved using 3 LFP features with the largest contributions from features in the alpha and peer-reviewed) is the author/funder. All rights reserved. No reuse allowed without permission.The copyright holder for this preprint (which was not . http://dx.doi.org/10.1101/241919 doi: bioRxiv preprint first posted online Jan. 2, 2018; high gamma frequencies. Similar models could be incorporated into algorithms used to improve treatment outcomes in adaptive neuromodulation systems for disorders of appetitive behavior.

show abstract

Machine Learning Based Classification of Deep Brain Stimulation Outcomes in a Rat Model of Binge Eating Using Ventral Striatal Oscillations

Cited by 14 publications

References 59 publications

Corticostriatal oscillations predict high vs. low drinkers in a preclinical model of limited access alcohol consumption

Corticostriatal oscillations predict high vs. low drinkers in a preclinical model of limited access alcohol consumption

Sex differences in the ability of corticostriatal oscillations to predict rodent alcohol consumption

Finding the balance between model complexity and performance: Using ventral striatal oscillations to classify feeding behavior in rats

Contact Info

Product

Resources

About