Acoustilytix™: A Web-Based Automated Ultrasonic Vocalization Scoring Platform.
addiction; automated scoring; dopamine; drug development; drug discovery; machine learning; mental health; ultrasonic vocalization
Ultrasonic vocalizations (USVs) are known to reflect emotional processing, brain neurochemistry, and brain function. Collecting and processing USV data is manual, time-intensive, and costly, creating a significant bottleneck by limiting researchers' ability to employ fully effective and nuanced experimental designs and serving as a barrier to entry for other researchers. In this report, we provide a snapshot of the current development and testing of Acoustilytix™, a web-based automated USV scoring tool. Acoustilytix implements machine learning methodology in the USV detection and classification process and is recording-environment-agnostic. We summarize the user features identified as desirable by USV researchers and how these were implemented. These include the ability to easily upload USV files, output a list of detected USVs with associated parameters in csv format, and the ability to manually verify or modify an automatically detected call. With no user intervention or tuning, Acoustilytix achieves 93% sensitivity (a measure of how accurately Acoustilytix detects true calls) and 73% precision (a measure of how accurately Acoustilytix avoids false positives) in call detection across four unique recording environments and was superior to the popular DeepSqueak algorithm (sensitivity = 88%; precision = 41%). Future work will include integration and implementation of machine-learning-based call type classification prediction that will recommend a call type to the user for each detected call. Call classification accuracy is currently in the 71-79% accuracy range, which will continue to improve as more USV files are scored by expert scorers, providing more training data for the classification model. We also describe a recently developed feature of Acoustilytix that offers a fast and effective way to train hand-scorers using automated learning principles without the need for an expert hand-scorer to be present and is built upon a foundation of learning science. The key is that trainees are given practice classifying hundreds of calls with immediate corrective feedback based on an expert's USV classification. We showed that this approach is highly effective with inter-rater reliability (i.e., kappa statistics) between trainees and the expert ranging from 0.30-0.75 (average = 0.55) after only 1000-2000 calls of training. We conclude with a brief discussion of future improvements to the Acoustilytix platform.
Ashley CB; Snyder RD; Shepherd JE; Cervantes C; Mittal N; Fleming S; Bailey J; Nievera MD; Souleimanova SI; Nyaoga B; Lichtenfeld L; Chen AR; Maddox WT; Duvauchelle CL
Brain Sciences
2021
2021-06-29
Article information provided for research and reference use only. All rights are retained by the journal listed under publisher and/or the creator(s).
journalArticle
<a href="http://doi.org/10.3390/brainsci11070864" target="_blank" rel="noreferrer noopener">10.3390/brainsci11070864</a>
Sex differences in cognitive performance and alcohol consumption in High Alcohol-Drinking (HAD-1) rats
Alcohol use disorders; Attention; Exploratory behavior; Novel object recognition; Object recognition test; Selectively bred high alcohol-drinking rats
Excessive alcohol (ethanol) consumption negatively impacts social, emotional, as well as cognitive function and well-being. Thus, identifying behavioral and/or biological predictors of excessive ethanol consumption is important for developing prevention and treatment strategies against alcohol use disorders (AUDs). Sex differences in alcohol consumption patterns are observed in humans, primates, and rodents. Selectively bred high alcohol-drinking rat lines, such as the "HAD-1" lines are recognized animal models of alcoholism. The present work examined sex differences in alcohol consumption, object recognition, and exploratory behavior in male and female HAD-1 rats. Naïve male and female HAD-1 rats were tested in an object recognition test (ORT) prior to a chronic 24 h intermittent ethanol access procedure for five weeks. Object recognition parameters measured included exploratory behavior, object investigation, and time spent near objects. During the initial training trial, rearing, active object investigation and amount of time spent in the object-containing section was significantly greater in female HAD-1 rats compared to their male counterparts. During the subsequent testing trial, time spent in the object-containing section was greater in female, compared to male, rats; but active object investigation and rearing did not statistically differ between females and males. In addition, female HAD-1 rats consumed significantly more ethanol than their male counterparts, replicating previous findings. Moreover, across all animals there was a significant positive correlation between exploratory behavior in ORT and ethanol consumption level. These results indicate there are significant sex differences in cognitive performance and alcohol consumption in HAD-1 rats, which suggests neurobiological differences as well.
Mittal N; Fleming S M; Martinez A; Thakore N; Bell R L; Maddox W T; Schallert T; Duvauchelle C L
Behavioural Brain Research
2019
2019-12-28
Journal Article
<a href="http://doi.org/10.1016/j.bbr.2019.112456" target="_blank" rel="noreferrer noopener">10.1016/j.bbr.2019.112456</a>
PMID: 31891743