Multiple classifier systems for automatic sleep scoring in mice

Disrupted sleep-wake regulation in the MCI-Park mouse model of Parkinson's disease

Disrupted sleep has a profound adverse impact on lives of Parkinson's disease (PD) patients and their caregivers. Sleep disturbances are exceedingly common in PD, with substantial heterogeneity in type, timing, and severity. Among the most common sleep-related symptoms reported by PD patients are insomnia, excessive daytime sleepiness, and sleep fragmentation, characterized by interruptions and decreased continuity of sleep. Alterations in brain wave activity, as measured on the electroencephalogram (EEG), also occur in PD, with changes in the pattern and relative contributions of different frequency bands of the EEG spectrum to overall EEG activity in different vigilance states consistently observed. The mechanisms underlying these PD-associated sleep-wake abnormalities are poorly understood, and they are ineffectively treated by conventional PD therapies. To help fill this gap in knowledge, a new progressive model of PD - the MCI-Park mouse - was studied. Near the transition to the parkinsonian state, these mice exhibited significantly altered sleep-wake regulation, including increased wakefulness, decreased non-rapid eye movement (NREM) sleep, increased sleep fragmentation, reduced rapid eye movement (REM) sleep, and altered EEG activity patterns. These sleep-wake abnormalities resemble those identified in PD patients. Thus, this model may help elucidate the circuit mechanisms underlying sleep disruption in PD and identify targets for novel therapeutic approaches.

SlumberNet: deep learning classification of sleep stages using residual neural networks

Sleep research is fundamental to understanding health and well-being, as proper sleep is essential for maintaining optimal physiological function. Here we present SlumberNet, a novel deep learning model based on residual network (ResNet) architecture, designed to classify sleep states in mice using electroencephalogram (EEG) and electromyogram (EMG) signals. Our model was trained and tested on data from mice undergoing baseline sleep, sleep deprivation, and recovery sleep, enabling it to handle a wide range of sleep conditions. Employing k-fold cross-validation and data augmentation techniques, SlumberNet achieved high levels of overall performance (accuracy = 97%; F1 score = 96%) in predicting sleep stages and showed robust performance even with a small and diverse training dataset. Comparison of SlumberNet's performance to manual sleep stage classification revealed a significant reduction in analysis time (~ 50 × faster), without sacrificing accuracy. Our study showcases the potential of deep learning to facilitate sleep research by providing a more efficient, accurate, and scalable method for sleep stage classification. Our work with SlumberNet further demonstrates the power of deep learning in mouse sleep research.

A novel machine learning system for identifying sleep-wake states in mice

Research into sleep-wake behaviors relies on scoring sleep states, normally done by manual inspection of electroencephalogram (EEG) and electromyogram (EMG) recordings. This is a highly time-consuming process prone to inter-rater variability. When studying relationships between sleep and motor function, analyzing arousal states under a four-state system of active wake (AW), quiet wake (QW), nonrapid-eye-movement (NREM) sleep, and rapid-eye-movement (REM) sleep provides greater precision in behavioral analysis but is a more complex model for classification than the traditional three-state identification (wake, NREM, and REM sleep) usually used in rodent models. Characteristic features between sleep-wake states provide potential for the use of machine learning to automate classification. Here, we devised SleepEns, which uses a novel ensemble architecture, the time-series ensemble. SleepEns achieved 90% accuracy to the source expert, which was statistically similar to the performance of two other human experts. Considering the capacity for classification disagreements that are still physiologically reasonable, SleepEns had an acceptable performance of 99% accuracy, as determined blindly by the source expert. Classifications given by SleepEns also maintained similar sleep-wake characteristics compared to expert classifications, some of which were essential for sleep-wake identification. Hence, our approach achieves results comparable to human ability in a fraction of the time. This new machine-learning ensemble will significantly impact the ability of sleep researcher to detect and study sleep-wake behaviors in mice and potentially in humans.

Tfap2b acts in GABAergic neurons to control sleep in mice

Sleep is a universal state of behavioral quiescence in both vertebrates and invertebrates that is controlled by conserved genes. We previously found that AP2 transcription factors control sleep in C. elegans, Drosophila, and mice. Heterozygous deletion of Tfap2b, one of the mammalian AP2 paralogs, reduces sleep in mice. The cell types and mechanisms through which Tfap2b controls sleep in mammals are, however, not known. In mice, Tfap2b acts during early embryonic stages. In this study, we used RNA-seq to measure the gene expression changes in brains of Tfap2b^-/- embryos. Our results indicated that genes related to brain development and patterning were differentially regulated. As many sleep-promoting neurons are known to be GABAergic, we measured the expression of GAD1, GAD2 and Vgat genes in different brain areas of adult Tfap2b^+/- mice using qPCR. These experiments suggested that GABAergic genes are downregulated in the cortex, brainstem and cerebellum areas, but upregulated in the striatum. To investigate whether Tfap2b controls sleep through GABAergic neurons, we specifically deleted Tfap2b in GABAergic neurons. We recorded the EEG and EMG before and after a 6-h period of sleep deprivation and extracted the time spent in NREM and in REM sleep as well as delta and theta power to assess NREM and REM sleep, respectively. During baseline conditions, Vgat-tfap2b^-/- mice exhibited both shortened NREM and REM sleep time and reduced delta and theta power. Consistently, weaker delta and theta power were observed during rebound sleep in the Vgat-tfap2b^-/- mice after sleep deprivation. Taken together, the results indicate that Tfap2b in GABAergic neurons is required for normal sleep.

A Prebiotic Diet Alters the Fecal Microbiome and Improves Sleep in Response to Sleep Disruption in Rats

Sleep disruption is a challenging and exceedingly common physiological state that contributes to a wide range of biochemical and molecular perturbations and has been linked to numerous adverse health outcomes. Modern society exerts significant pressure on the sleep/wake cycle via myriad factors, including exposure to electric light, psychological stressors, technological interconnection, jet travel, shift work, and widespread use of sleep-affecting compounds. Interestingly, recent research has identified a link between the microbiome and the regulation of sleep, suggesting that interventions targeting the microbiome may offer unique therapeutic approaches to challenges posed by sleep disruption. In this study, we test the hypothesis that administration of a prebiotic diet containing galactooligosaccharides (GOS) and polydextrose (PDX) in adult male rats improves sleep in response to repeated sleep disruption and during recovery sleep. We found that animals fed the GOS/PDX prebiotic diet for 4 weeks exhibit increased non-rapid eye movement (NREM) and rapid eye movement (REM) sleep during 5 days of sleep disruption and increased total sleep time during 24 h of recovery from sleep disruption compared to animals fed a control diet, despite similar baseline sleep characteristics. Further, the GOS/PDX prebiotic diet led to significant changes in the fecal microbiome. Consistent with previous reports, the prebiotic diet increased the relative abundance of the species Parabacteroides distasonis, which positively correlated with sleep parameters during recovery sleep. Taken together, these findings suggest that the GOS/PDX prebiotic diet may offer an approach to improve resilience to the physiologic challenge of sleep disruption, in part through impacts on the microbiome.

Employing a Long-Short-Term Memory Neural Network to Improve Automatic Sleep Stage Classification of Pharmaco-EEG Profiles

An increasing problem in today’s society is the spiraling number of people suffering from various sleep disorders. The research results presented in this paper support the use of a novel method that employs techniques from the classification of sleep disorders for more accurate scoring. Applying this novel method will assist researchers with better analyzing subject profiles for recommending prescriptions or to alleviate sleep disorders. In biomedical research, the use of animal models is required to experimentally test the safety and efficacy of a drug in the pre-clinical stage. We have developed a novel LSTM Recurrent Neural Network to process Pharmaco-EEG Profiles of rats to automatically score their sleep–wake stages. The results indicate improvements over the current methods; for the case of combined channels, the model accuracy improved by 1% and 3% in binary or multiclass classifications, respectively, to accuracies of 93% and 82%. In the case of using a single channel, binary and multiclass LSTM models for identifying rodent sleep stages using single or multiple electrode positions for binary or multiclass problems have not been evaluated in prior literature. The results reveal that single or combined channels, and binary or multiclass classification tasks, can be applied in the automatic sleep scoring of rodents.

Validation of PiezoSleep Scoring Against EEG/EMG Sleep Scoring in Rats

INTRODUCTION

Current methods of sleep research in rodents involve invasive surgical procedures of EEG and EMG electrodes implantation. Recently, a new method of measuring sleep, PiezoSleep, has been validated against implanted electrodes in mice and rats. PiezoSleep uses a piezoelectric film transducer to detect the rodent's movements and respiration and employs an algorithm to automatically score sleep. Here, we validate PiezoSleep scoring versus EEG/EMG implanted electrodes sleep scoring in rats.

METHODS

Adult male Brown Norway and Wistar Kyoto rats were implanted with bilateral stainless-steel screws into the skull for EEG recording and bilateral wire electrodes into the nuchal muscles for EMG assessment. In Brown Norway rats, the EEG/EMG electrode leads were soldered to a miniature connector plug and fixed to the skull. In Wistar Kyoto rats, the EEG/EMG leads were tunneled subcutaneously to a telemetry transmitter implanted in the flank. Rats were allowed to recover from surgery for one week. Brown Norway rats were placed in PiezoSleep cages, and had their headsets connected to cable for recording EEG/EMG signals, which were then manually scored by a human scorer in 10-sec epochs. Wistar Kyoto rats were placed in PiezoSleep cages, and EEG/EMG signals were recorded using a telemetry system (DSI). Sleep was scored automatically in 4-sec epochs using NeuroScore software. PiezoSleep software recorded and scored sleep in the rats.

RESULTS

Rats implanted with corded EEG/EMG headsets had 85.6% concurrence of sleep-wake scoring with PiezoSleep. Rats implanted with EEG/EMG telemetry had 80.8% concurrence sleep-wake scoring with PiezoSleep. Sensitivity and specificity rates were similar between the EEG/EMG recording systems. Total sleep time and hourly sleep times did not differ in all three systems. However, automatic sleep detection by NeuroScore classified more sleep during the light period compared to the PiezoSleep.

CONCLUSION

We showed that PiezoSleep system can be a reliable alternative to both automatic and visual EEG/EMG- based sleep-wake scoring in rat.

Application of Machine Learning to Sleep Stage Classification

Sleep studies are imperative to recapitulate phenotypes associated with sleep loss and uncover mechanisms contributing to psychopathology. Most often, investigators manually classify the polysomnography into vigilance states, which is time-consuming, requires extensive training, and is prone to inter-scorer variability. While many works have successfully developed automated vigilance state classifiers based on multiple EEG channels, we aim to produce an automated and openaccess classifier that can reliably predict vigilance state based on a single cortical electroencephalogram (EEG) from rodents to minimize the disadvantages that accompany tethering small animals via wires to computer programs. Approximately 427 hours of continuously monitored EEG, electromyogram (EMG), and activity were labeled by a domain expert out of 571 hours of total data. Here we evaluate the performance of various machine learning techniques on classifying 10-second epochs into one of three discrete classes: paradoxical, slow-wave, or wake. Our investigations include Decision Trees, Random Forests, Naive Bayes Classifiers, Logistic Regression Classifiers, and Artificial Neural Networks. These methodologies have achieved accuracies ranging from approximately 74% to approximately 96%. Most notably, the Random Forest and the ANN achieved remarkable accuracies of 95.78% and 93.31%, respectively. Here we have shown the potential of various machine learning classifiers to automatically, accurately, and reliably classify vigilance states based on a single EEG reading and a single EMG reading.

Predicting Space Radiation Single Ion Exposure in Rodents: A Machine Learning Approach

This study presents a data-driven machine learning approach to predict individual Galactic Cosmic Radiation (GCR) ion exposure for ⁴He, ¹⁶O, ²⁸Si, ⁴⁸Ti, or ⁵⁶Fe up to 150 mGy, based on Attentional Set-shifting (ATSET) experimental tests. The ATSET assay consists of a series of cognitive performance tasks on irradiated male Wistar rats. The GCR ion doses represent the expected cumulative radiation astronauts may receive during a Mars mission on an individual ion basis. The primary objective is to synthesize and assess predictive models on a per-subject level through Machine Learning (ML) classifiers. The raw cognitive performance data from individual rodent subjects are used as features to train the models and to explore the capabilities of three different ML techniques for elucidating a range of correlations between received radiation on rodents and their performance outcomes. The analysis employs scores of selected input features and different normalization approaches which yield varying degrees of model performance. The current study shows that support vector machine, Gaussian naive Bayes, and random forest models are capable of predicting individual ion exposure using ATSET scores where corresponding Matthews correlation coefficients and F₁ scores reflect model performance exceeding random chance. The study suggests a decremental effect on cognitive performance in rodents due to ≤150 mGy of single ion exposure, inasmuch as the models can discriminate between 0 mGy and any exposure level in the performance score feature space. A number of observations about the utility and limitations in specific normalization routines and evaluation scores are examined as well as best practices for ML with imbalanced datasets observed.

An artificial neural network for automated behavioral state classification in rats

Accurate behavioral state classification is critical for many research applications. Researchers typically rely upon manual identification of behavioral state through visual inspection of electrophysiological signals, but this approach is time intensive and subject to low inter-rater reliability. To overcome these limitations, a diverse set of algorithmic approaches have been put forth to automate the classification process. Recently, novel machine learning approaches have been detailed that produce rapid and highly accurate classifications. These approaches however, are often computationally expensive, require significant expertise to implement, and/or require proprietary software that limits broader adoption. Here we detail a novel artificial neural network that uses electrophysiological features to automatically classify behavioral state in rats with high accuracy, sensitivity, and specificity. Common parameters of interest to sleep scientists, including state-dependent power spectra and homeostatic non-REM slow wave activity, did not significantly differ when using this automated classifier as compared to manual scoring. Flexible options enable researchers to further increase classification accuracy through manual rescoring of a small subset of time intervals with low model prediction certainty or further decrease researcher time by generalizing trained networks across multiple recording days. The algorithm is fully open-source and coded within a popular, and freely available, software platform to increase access to this research tool and provide additional flexibility for future researchers. In sum, we have developed a readily implementable, efficient, and effective approach for automated behavioral state classification in rats.

Immunization with a heat-killed bacterium, Mycobacterium vaccae NCTC 11659, prevents the development of cortical hyperarousal and a PTSD-like sleep phenotype after sleep disruption and acute stress in mice

STUDY OBJECTIVES

Sleep deprivation induces systemic inflammation that may contribute to stress vulnerability and other pathologies. We tested the hypothesis that immunization with heat-killed Mycobacterium vaccae NCTC 11659 (MV), an environmental bacterium with immunoregulatory and anti-inflammatory properties, prevents the negative impacts of 5 days of sleep disruption on stress-induced changes in sleep, behavior, and physiology in mice.

METHODS

In a 2 × 2 × 2 experimental design, male C57BL/6N mice were given injections of either MV or vehicle on days -17, -10, and -3. On days 1-5, mice were exposed to intermittent sleep disruption, whereby sleep was disrupted for 20 h per day. Immediately following sleep disruption, mice were exposed to 1-h social defeat stress or novel cage (control) conditions. Object location memory (OLM) testing was conducted 24 h after social defeat, and tissues were collected 6 days later to measure inflammatory markers. Sleep was recorded using electroencephalography (EEG) and electromyography (EMG) throughout the experiment.

RESULTS

In vehicle-treated mice, only the combination of sleep disruption followed by social defeat (double hit): (1) increased brief arousals and NREM beta (15-30 Hz) EEG power in sleep immediately post-social defeat compared to baseline; (2) induced an increase in the proportion of rapid-eye-movement (REM) sleep and number of state shifts for at least 5 days post-social defeat; and (3) induced hyperlocomotion and lack of habituation in the OLM task. Immunization with MV prevented most of these sleep and behavioral changes.

CONCLUSIONS

Immunization with MV ameliorates a stress-induced sleep and behavioral phenotype that shares features with human posttraumatic stress disorder.

A Review on Machine Learning for EEG Signal Processing in Bioengineering

Electroencephalography (EEG) has been a staple method for identifying certain health conditions in patients since its discovery. Due to the many different types of classifiers available to use, the analysis methods are also equally numerous. In this review, we will be examining specifically machine learning methods that have been developed for EEG analysis with bioengineering applications. We reviewed literature from 1988 to 2018 to capture previous and current classification methods for EEG in multiple applications. From this information, we are able to determine the overall effectiveness of each machine learning method as well as the key characteristics. We have found that all the primary methods used in machine learning have been applied in some form in EEG classification. This ranges from Naive-Bayes to Decision Tree/Random Forest, to Support Vector Machine (SVM). Supervised learning methods are on average of higher accuracy than their unsupervised counterparts. This includes SVM and KNN. While each of the methods individually is limited in their accuracy in their respective applications, there is hope that the combination of methods when implemented properly has a higher overall classification accuracy. This paper provides a comprehensive overview of Machine Learning applications used in EEG analysis. It also gives an overview of each of the methods and general applications that each is best suited to.

Functional Divergence of Mammalian TFAP2a and TFAP2b Transcription Factors for Bidirectional Sleep Control

Sleep is a conserved behavioral state. Invertebrates typically show quiet sleep, whereas in mammals, sleep consists of periods of nonrapid-eye-movement sleep (NREMS) and REM sleep (REMS). We previously found that the transcription factor AP-2 promotes sleep in Caenorhabditiselegans and Drosophila In mammals, several paralogous AP-2 transcription factors exist. Sleep-controlling genes are often conserved. However, little is known about how sleep genes evolved from controlling simpler types of sleep to govern complex mammalian sleep. Here, we studied the roles of Tfap2a and Tfap2b in sleep control in mice. Consistent with our results from C. elegans and Drosophila, the AP-2 transcription factors Tfap2a and Tfap2b also control sleep in mice. Surprisingly, however, the two AP-2 paralogs play contrary roles in sleep control. Tfap2a reduction of function causes stronger delta and theta power in both baseline and homeostasis analysis, thus indicating increased sleep quality, but did not affect sleep quantity. By contrast, Tfap2b reduction of function decreased NREM sleep time specifically during the dark phase, reduced NREMS and REMS power, and caused a weaker response to sleep deprivation. Consistent with the observed signatures of decreased sleep quality, stress resistance and memory were impaired in Tfap2b mutant animals. Also, the circadian period was slightly shortened. Taken together, AP-2 transcription factors control sleep behavior also in mice, but the role of the AP-2 genes functionally diversified to allow for a bidirectional control of sleep quality. Divergence of AP-2 transcription factors might perhaps have supported the evolution of more complex types of sleep.

Supervised and unsupervised machine learning for automated scoring of sleep-wake and cataplexy in a mouse model of narcolepsy

Despite commercial availability of software to facilitate sleep-wake scoring of electroencephalography (EEG) and electromyography (EMG) in animals, automated scoring of rodent models of abnormal sleep, such as narcolepsy with cataplexy, has remained elusive. We optimize two machine-learning approaches, supervised and unsupervised, for automated scoring of behavioral states in orexin/ataxin-3 transgenic mice, a validated model of narcolepsy type 1, and additionally test them on wild-type mice. The supervised learning approach uses previously labeled data to facilitate training of a classifier for sleep states, whereas the unsupervised approach aims to discover latent structure and similarities in unlabeled data from which sleep stages are inferred. For the supervised approach, we employ a deep convolutional neural network architecture that is trained on expert-labeled segments of wake, non-REM sleep, and REM sleep in EEG/EMG time series data. The resulting trained classifier is then used to infer on the labels of previously unseen data. For the unsupervised approach, we leverage data dimensionality reduction and clustering techniques. Both approaches successfully score EEG/EMG data, achieving mean accuracies of 95% and 91%, respectively, in narcoleptic mice, and accuracies of 93% and 89%, respectively, in wild-type mice. Notably, the supervised approach generalized well on previously unseen data from the same animals on which it was trained but exhibited lower performance on animals not present in the training data due to inter-subject variability. Cataplexy is scored with a sensitivity of 85% and 57% using the supervised and unsupervised approaches, respectively, when compared to manual scoring, and the specificity exceeds 99% in both cases.

NMDAR activation regulates the daily rhythms of sleep and mood

Study Objectives

The present studies examine the effects of NMDAR activation by NYX-2925 diurnal rhythmicity of both sleep and wake as well as emotion.

Methods

Twenty-four-hour sleep EEG recordings were obtained in sleep-deprived and non-sleep-deprived rats. In addition, the day–night cycle of both activity and mood was measured using home cage ultrasonic-vocalization recordings.

Results

NYX-2925 significantly facilitated non-REM (NREM) sleep during the lights-on (sleep) period, and this effect persisted for 3 days following a single dose in sleep-deprived rats. Sleep-bout duration and REM latencies were increased without affecting total REM sleep, suggesting better sleep quality. In addition, delta power during wake was decreased, suggesting less drowsiness. NYX-2925 also rescued learning and memory deficits induced by sleep deprivation, measured using an NMDAR-dependent learning task. Additionally, NYX-2925 increased positive affect and decreased negative affect, primarily by facilitating the transitions from sleep to rough-and-tumble play and back to sleep. In contrast to NYX-2925, the NMDAR antagonist ketamine acutely (1–4 hours post-dosing) suppressed REM and non-REM sleep, increased delta power during wake, and blunted the amplitude of the sleep-wake activity rhythm.

Discussion

These data suggest that NYX-2925 could enhance behavioral plasticity via improved sleep quality as well as vigilance during wake. As such, the facilitation of sleep by NYX-2925 has the potential to both reduce symptom burden on neurological and psychiatric disorders as well as serve as a biomarker for drug effects through restoration of sleep architecture.

Repeated sleep disruption in mice leads to persistent shifts in the fecal microbiome and metabolome

It has been established in recent years that the gut microbiome plays a role in health and disease, potentially via alterations in metabolites that influence host physiology. Although sleep disruption and gut dysbiosis have been associated with many of the same diseases, studies investigating the gut microbiome in the context of sleep disruption have yielded inconsistent results, and have not assessed the fecal metabolome. We exposed mice to five days of sleep disruption followed by four days of ad libitum recovery sleep, and assessed the fecal microbiome and fecal metabolome at multiple timepoints using 16S rRNA gene amplicons and untargeted LC-MS/MS mass spectrometry. We found global shifts in both the microbiome and metabolome in the sleep-disrupted group on the second day of recovery sleep, when most sleep parameters had recovered to baseline levels. We observed an increase in the Firmicutes:Bacteroidetes ratio, along with decreases in the genus Lactobacillus, phylum Actinobacteria, and genus Bifidobacterium in sleep-disrupted mice compared to control mice. The latter two taxa remained low at the fourth day post-sleep disruption. We also identified multiple classes of fecal metabolites that were differentially abundant in sleep-disrupted mice, some of which are physiologically relevant and commonly influenced by the microbiome. This included bile acids, and inference of microbial functional gene content suggested reduced levels of the microbial bile salt hydrolase gene in sleep-disrupted mice. Overall, this study adds to the evidence base linking disrupted sleep to the gut microbiome and expands it to the fecal metabolome, identifying sleep disruption-sensitive bacterial taxa and classes of metabolites that may serve as therapeutic targets to improve health after poor sleep.

EEG sleep stages identification based on weighted undirected complex networks

BACKGROUND AND OBJECTIVE

Sleep scoring is important in sleep research because any errors in the scoring of the patient's sleep electroencephalography (EEG) recordings can cause serious problems such as incorrect diagnosis, medication errors, and misinterpretations of patient's EEG recordings. The aim of this research is to develop a new automatic method for EEG sleep stages classification based on a statistical model and weighted brain networks.

METHODS

Each EEG segment is partitioned into a number of blocks using a sliding window technique. A set of statistical features are extracted from each block. As a result, a vector of features is obtained to represent each EEG segment. Then, the vector of features is mapped into a weighted undirected network. Different structural and spectral attributes of the networks are extracted and forwarded to a least square support vector machine (LS-SVM) classifier. At the same time the network's attributes are also thoroughly investigated. It is found that the network's characteristics vary with their sleep stages. Each sleep stage is best represented using the key features of their networks.

RESULTS

In this paper, the proposed method is evaluated using two datasets acquired from different channels of EEG (Pz-Oz and C3-A2) according to the R&K and the AASM without pre-processing the original EEG data. The obtained results by the LS-SVM are compared with those by Naïve, k-nearest and a multi-class-SVM. The proposed method is also compared with other benchmark sleep stages classification methods. The comparison results demonstrate that the proposed method has an advantage in scoring sleep stages based on single channel EEG signals.

CONCLUSIONS

An average accuracy of 96.74% is obtained with the C3-A2 channel according to the AASM standard, and 96% with the Pz-Oz channel based on the R&K standard.

Reconfigurable 3D-Printed headplates for reproducible and rapid implantation of EEG, EMG and depth electrodes in mice

BACKGROUND

Mouse models are beneficial to understanding neural networks given a wide array of transgenic mice and cell-selective techniques. However, instrumentation of mice for neurophysiological studies is difficult. Often surgery is prolonged with experimental error arising from non-concurrent and variable implantations.

NEW METHOD

We describe a method for the rapid, reproducible and customizable instrumentation of mice. We constructed a headplate that conforms to the mouse skull surface using script-based computer aided design. This headplate was then modified to enable the friction-fit assembly prior to surgery and printed with a high-resolution resin-based 3D printer. Using this approach, we describe an easily customized headplate with dural screws for electrocorticography (ECoG), electromyogram (EMG) electrodes, cannula hole and two microdrives for local field potential (LFP) electrodes.

RESULTS

Implantation of the headplate reliably takes less than 40 min, enabling a cohort of eight mice to be implanted in one day. Good quality recordings were obtained after surgical recovery and the headplate was stable for at least four weeks. LFP electrode placement was found to be accurate.

COMPARISON WITH EXISTING METHODS

While similar approaches with microelectrodes have been used in rats before, and related approaches exist for targeting one brain region with tetrodes, we do not know of similar head-plates for mice, nor a strictly source-code and easily reconfigurable approach.

CONCLUSIONS

3D printing and friction-fit pre-assembly of mouse headplates offers a rapid, easily reconfigurable, consistent, and cost-effective way to implant larger numbers of mice in a highly reproducible way, reducing surgical time and mitigating experimental error.

MC-SleepNet: Large-scale Sleep Stage Scoring in Mice by Deep Neural Networks

Automated sleep stage scoring for mice is in high demand for sleep research, since manual scoring requires considerable human expertise and efforts. The existing automated scoring methods do not provide the scoring accuracy required for practical use. In addition, the performance of such methods has generally been evaluated using rather small-scale datasets, and their robustness against individual differences and noise has not been adequately verified. This research proposes a novel automated scoring method named “MC-SleepNet”, which combines two types of deep neural networks. Then, we evaluate its performance using a large-scale dataset that contains 4,200 biological signal records of mice. The experimental results show that MC-SleepNet can automatically score sleep stages with an accuracy of 96.6% and kappa statistic of 0.94. In addition, we confirm that the scoring accuracy does not significantly decrease even if the target biological signals are noisy. These results suggest that MC-SleepNet is very robust against individual differences and noise. To the best of our knowledge, evaluations using such a large-scale dataset (containing 4,200 records) and high scoring accuracy (96.6%) have not been reported in previous related studies.

Distinct ipRGC subpopulations mediate light's acute and circadian effects on body temperature and sleep

The light environment greatly impacts human alertness, mood, and cognition by both acute regulation of physiology and indirect alignment of circadian rhythms. These processes require the melanopsin-expressing intrinsically photosensitive retinal ganglion cells (ipRGCs), but the relevant downstream brain areas involved remain elusive. ipRGCs project widely in the brain, including to the central circadian pacemaker, the suprachiasmatic nucleus (SCN). Here we show that body temperature and sleep responses to acute light exposure are absent after genetic ablation of all ipRGCs except a subpopulation that projects to the SCN. Furthermore, by chemogenetic activation of the ipRGCs that avoid the SCN, we show that these cells are sufficient for acute changes in body temperature. Our results challenge the idea that the SCN is a major relay for the acute effects of light on non-image forming behaviors and identify the sensory cells that initiate light’s profound effects on body temperature and sleep.

Light, whether natural or artificial, affects our everyday lives in several ways. Exposure to light impacts on our health and well-being. It plays a crucial but indirect role in helping to align our internal body clock with the 24-hour cycle of day and night, and a burst of bright light in the middle of the night can wake us up from sleep.

Decades of research have revealed the circuitry that controls the indirect effects of light on the body's internal clock. A tiny set of cells in the base of the brain called the suprachiasmatic nucleus (SCN for short) generates the body’s daily or “circadian” rhythm. A small group of nerve cells in the retina of the eye called intrinsically photosensitive retinal ganglion cells (ipRGCs) connect with the SCN. These ipRGCs relay information about light to the SCN to ensure that daily rhythms happen at the appropriate times of day. But scientists do not yet know if the same brain circuits regulate the direct effects of light on alertness.

Mice are often used in studies of circadian rhythms but, unlike humans, mice are normally active at night and sleep throughout the day. This means that a burst of bright light in the middle of the night causes mice to become less alert.

Now, in experiments with mice, Rupp et al. show there are two separate circuits from the retina to the brain that influence wakefulness. In the experiments, some mice were genetically engineered to only have ipRGCs that connect with the SCN and to lack those that connect with other brain areas. These mice lived in cages with a normal day/night cycle and their body temperature and sleep-related brain activity were monitored as Rupp et al. sporadically exposed them to bright light at night. These mice continued their normal routines and were unaffected by the bursts of light. In a second set of experiments, ipRGCs that do not connect with the SCN were activated in other mice. This caused an immediate and sustained drop in the body temperature of the mice, which is linked to them becoming less alert.

The experiments suggest that the circuit that connects ipRGCs to the SCN to align the body’s circadian rhythm with light does not control the direct effect of light on wakefulness. Instead, a separate circuit that extends from ipRGCs to an unknown part of the brain area influences wakefulness. Better understanding this second circuit could allow scientists to develop ways to keep people like emergency personnel or overnight shift workers awake and alert at night while avoiding harmful disruptions to their circadian rhythms.

Validation of 'Somnivore', a Machine Learning Algorithm for Automated Scoring and Analysis of Polysomnography Data

Manual scoring of polysomnography data is labor-intensive and time-consuming, and most existing software does not account for subjective differences and user variability. Therefore, we evaluated a supervised machine learning algorithm, Somnivore^TM, for automated wake–sleep stage classification. We designed an algorithm that extracts features from various input channels, following a brief session of manual scoring, and provides automated wake-sleep stage classification for each recording. For algorithm validation, polysomnography data was obtained from independent laboratories, and include normal, cognitively-impaired, and alcohol-treated human subjects (total n = 52), narcoleptic mice and drug-treated rats (total n = 56), and pigeons (n = 5). Training and testing sets for validation were previously scored manually by 1–2 trained sleep technologists from each laboratory. F-measure was used to assess precision and sensitivity for statistical analysis of classifier output and human scorer agreement. The algorithm gave high concordance with manual visual scoring across all human data (wake 0.91 ± 0.01; N1 0.57 ± 0.01; N2 0.81 ± 0.01; N3 0.86 ± 0.01; REM 0.87 ± 0.01), which was comparable to manual inter-scorer agreement on all stages. Similarly, high concordance was observed across all rodent (wake 0.95 ± 0.01; NREM 0.94 ± 0.01; REM 0.91 ± 0.01) and pigeon (wake 0.96 ± 0.006; NREM 0.97 ± 0.01; REM 0.86 ± 0.02) data. Effects of classifier learning from single signal inputs, simple stage reclassification, automated removal of transition epochs, and training set size were also examined. In summary, we have developed a polysomnography analysis program for automated sleep-stage classification of data from diverse species. Somnivore enables flexible, accurate, and high-throughput analysis of experimental and clinical sleep studies.

Iterative expert-in-the-loop classification of sleep PSG recordings using a hierarchical clustering

BACKGROUND

The classification of sleep signals is a subjective and time consuming task. A large number of automatic classifiers have been published in the past decade but a sleep community has no strong confidence to use them in clinical practice and still remains using a standard manual scoring according standardized rules.

NEW METHOD

We developed a semi-supervised data-driven approach for objective and efficient evaluation of polysomnographic (PSG) data. The proposed algorithm finds a representative set of signal segments that are subsequently scored by a sleep neurologist. The remaining part of the recording is then automatically classified using these templates.

RESULTS

The method was evaluated on 36 PSG recordings (18 chronic insomniacs, 18 healthy controls). We show a faster and objective evaluation of PSG data compared to the manual scoring that is over-performing automated classifiers (accuracy increases ∼14%). The classification results are comparable on both datasets.

COMPARISON WITH EXISTING METHOD(S)

The methodology that we propose has not yet been published in the area of sleep PSG data processing. The performance of our method is comparable to various published automated approaches (a typical published classification accuracy is ∼75-95%). The method allows the evaluation of PSG recordings in more general terms and across different recording devices and standards.

CONCLUSIONS

The proposed solution is not based on a single-purpose rules or heuristics and training model is not trained on other patient's sleep recordings. The method is applicable to wide range of similar tasks and various types of physiological signals.

Predicting chemo-brain in breast cancer survivors using multiple MRI features and machine-learning

PURPOSE

Breast cancer (BC) is the most common cancer in women worldwide. There exist various advanced chemotherapy drugs for BC; however, chemotherapy drugs may result in brain damage during treatment. When a patient's brain is changed in response to chemo drugs, it is termed chemo-brain. In this study, we aimed to construct machine-learning models to detect the subtle alternations of the brain in postchemotherapy BC patients.

METHODS

Nineteen BC patients undergoing chemotherapy and 20 healthy controls (HCs) were recruited for this study. Both groups underwent resting-state functional MRI and generalized q-sampling imaging (GQI).

RESULTS

Logistic regression (LR) with GQI indices in standardized voxel-wise analysis, LR with mean regional homogeneity in regional summation analysis, decision tree classifier (CART) with generalized fractional anisotropy in voxel-wise analysis, and XGBoost (XGB) with normalized quantitative anisotropy had formidable performances in classifying subjects into a chemo-brain group or an HC group. Classifying the brain MRIs of HC and postchemotherapy patients by conducting leave-one-out cross-validation resulted in the highest accuracy of 84%, which was attained by LR, CART, and XGB with multiple feature sets.

CONCLUSIONS

In our study, we constructed the machine-learning models that were able to identify chemo-brains from normal brains. We are hopeful that these results will be helpful in clinically tracking chemo-brains in the future.