Automated classification of acoustic startle reflex waveforms in young CBA/CaJ mice using machine learning
Introduction
The acoustic startle reflex (ASR) and modification using pre-pulse stimuli has consistently been one of the most used diagnostic tools for assessing laboratory animals’ internal state over the past several decades (Davis, 1984, Koch, 1999). Modification of this simple reflex resulting from a brief loud sound has been used in many neuropsychological disciplines for evaluating hearing (Lauer et al., 2017), tinnitus (Galazyuk and Hébert, 2015, Gerum et al., 2019, Turner et al., 2006), many neuropsychiatric disorders such as schizophrenia, bi-polar disorder, autism, and many other disorders that disrupt sensory-motor gating (Braff et al., 2001, Kohl et al., 2013, Kohl et al., 2014). Unfortunately, a standardized method of how to record, measure, process, and analyze startle reflex waveforms has yet to be standardized, which leads to high variability within and between laboratories using this assessment tool. Reasons for this variability within a lab are numerous but include animal awareness, habituation/sensitization rates, neural plasticity, anxiety/stress levels, and neuro-muscular interactions. Even more explanations for variability exists between laboratories and include: species/strain variations, loudspeaker/wav file sound quality, recording platform type, platform sensitivity, and mode of assessment which varies between whole body startle in mice/rats (Horlington, 1968, Grimsley et al., 2015), to the Preyer reflex (small ear movements) in guinea pigs (Berger et al., 2013, Böhmer, 1988), and eye blink reflex in humans and primate research (Säring and von Cramon, 1981, Filion et al., 1993, Grillon et al., 1997, Winslow et al., 2002). These factors result in variable ASR waveform measurements, which if processed/analyzed with the same methodology, could result in verifiable comparisons between experiments and laboratories using completely different techniques. This is due to likely differences in the characteristics of the startle waveforms which are included in the analysis.
Standardization of ASR waveform classification is extremely important for many reasons (Lauer et al., 2017). Previous work has included the elimination of the highest and lowest startle responses for each frequency (Longenecker and Galazyuk, 2011), using Grubb's test for outliers (Longenecker and Galazyuk, 2012), elimination of startle responses with maximum magnitude after startle presentation less than that before startle presentation, elimination of startle responses whose RMS after startle presentation is less than that before startle presentation, template matching (Grimsley et al., 2015), and discarding invalid trials containing movement in excess of a threshold prior to stimulus presentation (Schilling et al., 2017) as effective procedures for cleaning startle data by removing “non-startles,” which occur frequently in animal or humans continually presented with loud sounds. Non-startles occur more often when animals are presented low intensity startle stimuli as well as when an intense pre-pulse is presented prior to the startle stimulus (Longenecker et al., 2016). Since pre-pulse inhibition using stimuli placed before the startle elicitor is one of the most critical aspects of the startle reflex studied, proper classification of startles when pre-pulses are presented can dramatically influence the results. However, because each laboratory might utilize different hardware (sensors, filters, etc.) and/or waveform filter configurations which records animals startle-related movements, it makes it problematic to suggest a standardized template. Thus, an alternative approach should be used to classify startle response waveforms.
Machine learning is an evolving field of computational algorithms which learn from data in order to improve their performance on a particular classification or prediction task (Mjolsness and DeCoste, 2001, El Naqa and Murphy, 2015, Kotsiantis et al., 2006). Machine learning has been successfully used in genomics (Libbrecht and Noble, 2015), medical imaging and pathology (Komura and Ishikawa, 2019, Shen et al., 2017), as well as in the diagnosis and treatment of cancer (Goldenberg et al., 2019, Bejnordi et al., 2017). Machine learning could even be used in clinical settings to aid the navigation of the complex health trajectory of an individual patient through machine learning performed on data from many patients (Rajkomar et al., 2019). In this paper, we describe an automated, supervised machine learning approach to classify ASR waveforms acquired using various stimulus protocols and levels, eliciting ASRs of various magnitudes and shapes.
Section snippets
Experimental procedure
Mice were individually tested in wire mesh cages resting on a custom-built platform connected to piezoelectric transducers, located inside one of eight identical sound attenuated chambers. The custom-built 3D-printed platforms consist of a base and four piezoelectric transducers, one in each of the four quadrants of the platform. The piezoelectric transducers are in physical contact with the top animal compartment via four 3D printed rods. Acoustic stimuli were presented through Fostex model
Acoustic startle response waveform preprocessing
Due to the variability in the ASR waveforms shown in Fig. 1, all ASR waveforms were centered (by subtracting the mean) and scaled (by dividing the centered waveform by the standard deviation) using the mean and standard deviation of the ASR waveform before the SES is presented (t < 0), producing normalized ASR waveforms with units of the number of standard deviations from the mean before the SES is presented (Halaki and Gi, 2012, Lee et al., 2019, Lara-Cueva et al., 2016, Hartmann et al., 2019
Results
Several classification performance metrics are presented in Table 2 including the mean receiver operating characteristics (ROC) and the area under the ROC curve (AUC) when predicting a normalized ASR waveform to be a startle or non-startle with the training dataset as well as the accuracy of predicting the correct classification on the testing dataset for each of the individual machine learning methods described above. All mean ROCs were over 0.95 with random forests demonstrating the greatest
Discussion
The startle reflex has been measured for almost 100 years (Landis and Hunt, 1939) and is still used in many disciplines across hundreds of laboratories as a quick and effective measure of the internal state of animals and humans. However, ASR-related data between these disciplines, or even between researchers in the same discipline, are not easily compared. Since resource and data sharing is a key component for making progress in any scientific field, it was our goal to develop a universal
Conflict of interest
The authors declare that there is no conflict of interest.
Acknowledgements
This work was supported by the National Institutes of Health [NIH-NIA AG00954]. The authors would like to acknowledge the use of the services provided by Research Computing at the University of South Florida. We thank Dimitri Brunnell and Mary Reith for their technical assistance and oversight of behavioral experiments and Rachal Love for oversight of animal care.
References (76)
Short term spectral analysis, synthesis, and modification by discrete Fourier transform
IEEE Trans. Acoust. Speech Signal Process.
(1977)- et al.
Diagnostic assessment of deep learning algorithms for detection of lymph node metastases in women with breast cancer
JAMA
(2017) - et al.
A novel behavioural approach to detecting tinnitus in the guinea pig
J. Neurosci. Methods
(2013) - et al.
Feature selection for high-dimensional data – a Pearson redundancy based filter
Adv. Soft Comput.
(2006) Fourier Analysis of Time Series: An Introduction
Wiley Series in Probability and Statistics
(2011)The Preyer reflex – an easy estimate of hearing function in guinea pigs
Acta Oto-Laryngol.
(1988)- et al.
Impact of prepulse characteristics on the detection of sensorimotor gating deficits in schizophrenia
Schizophr. Res.
(2001) Bagging predictors
Mach. Learn.
(1995)Prediction games and arcing algorithms
Neural Comput.
(1999)Random forests
Mach. Learn.
(2000)
Population theory for boosting ensembles
Ann. Stat.
Feature selection in machine learning: a new perspective
Neurocomputing
Ensemble Selection from Libraries of Models
XGBoost
xgboost: Extreme Gradient Boosting. Technical Report
Support-vector networks
Mach. Learn.
Tree-based methods
High-Dimensional Data Analysis in Cancer Research
The mammalian startle response
Neural Mechanisms of Startle Behavior
caretEnsemble: Ensembles of Caret Models
An experimental comparison of three methods for constructing ensembles of decision trees: bagging, boosting, and randomization
Mach. Learn.
An Introduction to Generalized Linear Models
What is machine learning?
Machine Learning in Radiation Oncology
Modification of the acoustic startle-reflex eyeblink: a tool for investigating early and late attentional processes
Biol. Psychol.
Gap-prepulse inhibition of the acoustic startle reflex (GPIAS) for tinnitus assessment: current status and future directions
Front. Neurol.
Open(G)PIAS: an open-source solution for the construction of a high-precision acoustic startle response setup for tinnitus screening and threshold estimation in rodents
Front. Behav. Neurosci.
A new era: artificial intelligence and machine learning in prostate cancer
Nat. Rev. Urol.
Spectral estimation using modified Daniell method
Int. J. Electron.
Darkness facilitates the acoustic startle reflex in humans
Biol. Psychiatry
An improved approach to separating startle data from noise
J. Neurosci. Methods
An introduction to variable and feature selection
Mach. Learn. Res.
Normalization of EMG signals: to normalize or not to normalize and what to normalize to?
Computational Intelligence in Electromyography Analysis – A Perspective on Current Applications and Future Challenges
Quantitative comparison of photoplethysmographic waveform characteristics: effect of measurement site
Front. Physiol.
The Elements of Statistical Learning
Springer Series in Statistics
A method for measuring acoustic startle response latency and magnitude in rats: detection of a single stimulus effect using latency measurements
Physiol. Behav.
Applied Logistic Regression
Modulation of prepulse inhibition by an augmented acoustic environment in DBA/2J mice
Behav. Neurosci.
Provisional mapping of quantitative trait loci modulating the acoustic startle response and prepulse inhibition of acoustic startle
Neuropsychopharmacology
The neurobiology of startle
Prog. Neurobiol.
Cited by (5)
Universal automated classification of the acoustic startle reflex using machine learning
2023, Hearing ResearchCitation Excerpt :Thus, a more systematic and generalized approach to SR analysis would aid in comparing results from different laboratories and species and advance the discipline. To address this issue, we have adapted a machine learning model to automatically classify SR waveforms from various species, paradigms, and modalities (Fawcett et al., 2020; 2021). The relative magnitude of neuro-muscular responses varies between species; thus, the stereotypical startle response waveform varies between species.
Machine learning, waveform preprocessing and feature extraction methods for classification of acoustic startle waveforms
2021, MethodsXCitation Excerpt :Fig. 22 shows the mean CWT power across all times at 2048 Hz versus that at 100 Hz. A total of 17 features were extracted from the ASR waveforms as described in Fawcett et al. [[4], Table 1] with their distributions presented in Figs. 11,14,16–20, and 22. Feature variability was assessed to ascertain which, if any, features have little to no variability.
Implementation of Ensemble Deep Learning Coupled with Remote Sensing for the Quantitative Analysis of Changes in Arable Land Use in a Mining Area
2021, Journal of the Indian Society of Remote SensingCongenital Deafness and Recent Advances Towards Restoring Hearing Loss
2021, Current Protocols