SPINDLE: End-to-end learning from EEG/EMG to extrapolate animal sleep scoring across experimental settings, labs and species

mCLAS adaptively rescues disease-specific sleep and wake phenotypes in neurodegeneration

Sleep alterations are hallmarks of prodromal Alzheimer's (AD) and Parkinson's disease (PD), with fundamental neuropathological processes of both diseases showing susceptibility of change upon deep sleep modulation. However, promising pharmacological deep sleep enhancement results are hindered by specificity and scalability issues, thus advocating for noninvasive slow-wave activity (SWA) boosting methods to investigate the links between deep sleep and neurodegeneration. Accordingly, we have recently introduced mouse closed-loop auditory stimulation (mCLAS), which is able to successfully boost SWA during deep sleep in neurodegeneration models. Here, we aim at further exploring mCLAS' acute effect onto disease-specific sleep and wake alterations in AD (Tg2576) and PD (M83) mice. We found that mCLAS adaptively rescues pathological sleep and wake traits depending on the disease-specific impairments observed at baseline in each model. Notably, in AD mice mCLAS significantly increases NREM long/short bout ratio, decreases vigilance state distances by decreasing transition velocities and increases the percentage of cumulative time spent in NREM sleep in the last 3h of the dark period. Contrastingly, in PD mice mCLAS significantly decreases NREM sleep consolidation, by potentiating faster and more frequent transitions between vigilance states, decreases average EMG muscle tone during REM sleep and increases alpha power in WAKE and NREM sleep. Overall, our results indicate that mCLAS selectively prompts an acute alleviation of neurodegeneration-associated sleep and wake phenotypes, by either potentiating sleep consolidation and vigilance state stability in AD or by rescuing bradysomnia and decreasing cortical hyperexcitability in PD. Further experiments assessing the electrophysiological, neuropathological and behavioural long-term effects of mCLAS in neurodegeneration may majorly impact the clinical establishment of sleep-based therapies.

Cerebellar deep brain stimulation as a dual-function therapeutic for restoring movement and sleep in dystonic mice

Dystonia arises with cerebellar dysfunction, which plays a key role in the emergence of multiple pathophysiological deficits that range from abnormal movements and postures to disrupted sleep. Current therapeutic interventions typically do not simultaneously address both the motor and non-motor symptoms of dystonia, underscoring the necessity for a multi-functional therapeutic strategy. Deep brain stimulation (DBS) is effectively used to reduce motor symptoms in dystonia, with existing parallel evidence arguing for its potential to correct sleep disturbances. However, the simultaneous efficacy of DBS for improving sleep and motor dysfunction, specifically by targeting the cerebellum, remains underexplored. Here, we test the effect of cerebellar DBS in two genetic mouse models with dystonia that exhibit sleep defects-Ptf1aCre;Vglut2fx/fx and Pdx1Cre;Vglut2fx/fx-which have overlapping cerebellar circuit miswiring defects but differing severity in motor phenotypes. By targeting DBS to the fiber tracts located between the cerebellar fastigial and the interposed nuclei (FN ​+ ​INT-DBS), we modulated sleep dysfunction by enhancing sleep quality and timing. This DBS paradigm improved wakefulness and rapid eye movement sleep in both mutants. Additionally, the latency to reach REM sleep, a deficit observed in human dystonia patients, was reduced in both models. Cerebellar DBS also induced alterations in the electrocorticogram (ECoG) patterns that define sleep states. As expected, DBS reduced the severe dystonic twisting motor symptoms that are observed in the Ptf1aCre;Vglut2fx/fx mice. These findings highlight the potential for using cerebellar DBS to simultaneously improve sleep and reduce motor dysfunction in dystonia and uncover its potential as a dual-effect in vivo therapeutic strategy.

An automated sleep staging tool based on simple statistical features of mice electroencephalography (EEG) and electromyography (EMG) data

Electroencephalogram (EEG) and electromyogram (EMG) are fundamental tools in sleep research. However, investigations into the statistical properties of rodent EEG/EMG signals in the sleep-wake cycle have been limited. The lack of standard criteria in defining sleep stages forces researchers to rely on human expertise to inspect EEG/EMG. The recent increasing demand for analysing large-scale and long-term data has been overwhelming the capabilities of human experts. In this study, we explored the statistical features of EEG signals in the sleep-wake cycle. We found that the normalized EEG power density profile changes its lower and higher frequency powers to a comparable degree in the opposite direction, pivoting around 20-30 Hz between the NREM sleep and the active brain state. We also found that REM sleep has a normalized EEG power density profile that overlaps with wakefulness and a characteristic reduction in the EMG signal. Based on these observations, we proposed three simple statistical features that could span a 3D space. Each sleep-wake stage formed a separate cluster close to a normal distribution in the 3D space. Notably, the suggested features are a natural extension of the conventional definition, making it useful for experts to intuitively interpret the EEG/EMG signal alterations caused by genetic mutations or experimental treatments. In addition, we developed an unsupervised automatic staging algorithm based on these features. The developed algorithm is a valuable tool for expediting the quantitative evaluation of EEG/EMG signals so that researchers can utilize the recent high-throughput genetic or pharmacological methods for sleep research.

Maternal immune activation exerts long-term effects on activity and sleep in male offspring mice

Exposure to infectious or non-infectious immune activation during early development is a serious risk factor for long-term behavioural dysfunctions. Mouse models of maternal immune activation (MIA) have increasingly been used to address neuronal and behavioural dysfunctions in response to prenatal infections. One commonly employed MIA model involves administering poly(I:C) (polyriboinosinic-polyribocytdilic acid), a synthetic analogue of double-stranded RNA, during gestation, which robustly induces an acute viral-like inflammatory response. Using electroencephalography (EEG) and infrared (IR) activity recordings, we explored alterations in sleep/wake, circadian and locomotor activity patterns on the adult male offspring of poly(I:C)-treated mothers. Our findings demonstrate that these offspring displayed reduced home cage activity during the (subjective) night under both light/dark or constant darkness conditions. In line with this finding, these mice exhibited an increase in non-rapid eye movement (NREM) sleep duration as well as an increase in sleep spindles density. Following sleep deprivation, poly(I:C)-exposed offspring extended NREM sleep duration and prolonged NREM sleep bouts during the dark phase as compared with non-exposed mice. Additionally, these mice exhibited a significant alteration in NREM sleep EEG spectral power under heightened sleep pressure. Together, our study highlights the lasting effects of infection and/or immune activation during pregnancy on circadian activity and sleep/wake patterns in the offspring.

Novel murine closed-loop auditory stimulation paradigm elicits macrostructural sleep benefits in neurodegeneration

Boosting slow-wave activity (SWA) by modulating slow waves through closed-loop auditory stimulation (CLAS) might provide a powerful non-pharmacological tool to investigate the link between sleep and neurodegeneration. Here, we established mouse CLAS (mCLAS)-mediated SWA enhancement and explored its effects on sleep deficits in neurodegeneration, by targeting the up-phase of slow waves in mouse models of Alzheimer's disease (AD, Tg2576) and Parkinson's disease (PD, M83). We found that tracking a 2 Hz component of slow waves leads to highest precision of non-rapid eye movement (NREM) sleep detection in mice, and that its combination with a 30° up-phase target produces a significant 15-30% SWA increase from baseline in wild-type (WTAD) and transgenic (TGAD) mice versus a mock stimulation group. Conversely, combining 2 Hz with a 40° phase target yields a significant increase ranging 30-35% in WTPD and TGPD mice. Interestingly, these phase-target-triggered SWA increases are not genotype dependent but strain specific. Sleep alterations that may contribute to disease progression and burden were described in AD and PD lines. Notably, pathological sleep traits were rescued by mCLAS, which elicited a 14% decrease of pathologically heightened NREM sleep fragmentation in TGAD mice, accompanied by a steep decrease in microarousal events during both light and dark periods. Overall, our results indicate that model-tailored phase targeting is key to modulate SWA through mCLAS, prompting the acute alleviation of key neurodegeneration-associated sleep phenotypes and potentiating sleep regulation and consolidation. Further experiments assessing the long-term effect of mCLAS in neurodegeneration may majorly impact the establishment of sleep-based therapies.

MLS-Net: An Automatic Sleep Stage Classifier Utilizing Multimodal Physiological Signals in Mice

Over the past decades, feature-based statistical machine learning and deep neural networks have been extensively utilized for automatic sleep stage classification (ASSC). Feature-based approaches offer clear insights into sleep characteristics and require low computational power but often fail to capture the spatial-temporal context of the data. In contrast, deep neural networks can process raw sleep signals directly and deliver superior performance. However, their overfitting, inconsistent accuracy, and computational cost were the primary drawbacks that limited their end-user acceptance. To address these challenges, we developed a novel neural network model, MLS-Net, which integrates the strengths of neural networks and feature extraction for automated sleep staging in mice. MLS-Net leverages temporal and spectral features from multimodal signals, such as EEG, EMG, and eye movements (EMs), as inputs and incorporates a bidirectional Long Short-Term Memory (bi-LSTM) to effectively capture the spatial-temporal nonlinear characteristics inherent in sleep signals. Our studies demonstrate that MLS-Net achieves an overall classification accuracy of 90.4% and REM state precision of 91.1%, sensitivity of 84.7%, and an F1-Score of 87.5% in mice, outperforming other neural network and feature-based algorithms in our multimodal dataset.

Workflow for the unsupervised clustering of sleep stages identifies light and deep sleep in electrophysiological recordings in mice

BACKGROUND

Sleep physiology plays a critical role in brain development and aging. Accurate sleep staging, which categorizes different sleep states, is fundamental for sleep physiology studies. Traditional methods for sleep staging rely on manual, rule-based scoring techniques, which limit their accuracy and adaptability.

NEW METHOD

We describe, test and challenge a workflow for unsupervised clustering of sleep states (WUCSS) in rodents, which uses accelerometer and electrophysiological data to classify different sleep states. WUCSS utilizes unsupervised clustering to identify sleep states using six features, extracted from 4-second epochs.

RESULTS

We gathered high-quality EEG recordings combined with accelerometer data in diverse transgenic mouse lines (male ApoE3 versus ApoE4 knockin; male CNTNAP2 KO versus wildtype littermates). WUCSS showed high recall, precision, and F1-score against manual scoring on awake, NREM, and REM sleep states. Within NREM, WUCSS consistently identified two additional clusters that qualify as deep and light sleep states.

COMPARISON WITH EXISTING METHODS

The ability of WUCSS to discriminate between deep and light sleep enhanced the precision and comprehensiveness of the current mouse sleep physiology studies. This differentiation led to the discovery of an additional sleep phenotype, notably in CNTNAP2 KO mice, showcasing the method's superiority over traditional scoring methods.

CONCLUSIONS

WUCSS, with its unsupervised approach and classification of deep and light sleep states, provides an unbiased opportunity for researchers to enhance their understanding of sleep physiology. Its high accuracy, adaptability, and ability to save time and resources make it a valuable tool for improving sleep staging in both clinical and preclinical research.

BDNF-TrkB signaling orchestrates the buildup process of local sleep

Sleep debt accumulates during wakefulness, leading to increased slow wave activity (SWA) during sleep, an encephalographic marker for sleep need. The use-dependent demands of prior wakefulness increase sleep SWA locally. However, the circuitry and molecular identity of this "local sleep" remain unclear. Using pharmacology and optogenetic perturbations together with transcriptomics, we find that cortical brain-derived neurotrophic factor (BDNF) regulates SWA via the activation of tyrosine kinase B (TrkB) receptor and cAMP-response element-binding protein (CREB). We map BDNF/TrkB-induced sleep SWA to layer 5 (L5) pyramidal neurons of the cortex, independent of neuronal firing per se. Using mathematical modeling, we here propose a model of how BDNF's effects on synaptic strength can increase SWA in ways not achieved through increased firing alone. Proteomic analysis further reveals that TrkB activation enriches ubiquitin and proteasome subunits. Together, our study reveals that local SWA control is mediated by BDNF-TrkB-CREB signaling in L5 excitatory cortical neurons.

Purkinje cell dysfunction causes disrupted sleep in ataxic mice

Purkinje cell dysfunction disrupts movement and causes disorders such as ataxia. Recent evidence suggests that Purkinje cell dysfunction may also alter sleep regulation. Here, we used an ataxic mouse model generated by silencing Purkinje cell neurotransmission (L7Cre;Vgatfx/fx) to better understand how cerebellar dysfunction impacts sleep physiology. We focused our analysis on sleep architecture and electrocorticography (ECoG) patterns based on their relevance to extracting physiological measurements during sleep. We found that circadian activity was unaltered in the mutant mice, although their sleep parameters and ECoG patterns were modified. The L7Cre;Vgatfx/fx mutant mice had decreased wakefulness and rapid eye movement (REM) sleep, whereas non-REM sleep was increased. The mutants had an extended latency to REM sleep, which is also observed in human patients with ataxia. Spectral analysis of ECoG signals revealed alterations in the power distribution across different frequency bands defining sleep. Therefore, Purkinje cell dysfunction may influence wakefulness and equilibrium of distinct sleep stages in ataxia. Our findings posit a connection between cerebellar dysfunction and disrupted sleep and underscore the importance of examining cerebellar circuit function in sleep disorders.

Single-nucleus RNA-seq identifies one galanin neuronal subtype in mouse preoptic hypothalamus activated during recovery from sleep deprivation

The preoptic area of the hypothalamus (POA) is essential for sleep regulation. However, the cellular makeup of the POA is heterogeneous, and the molecular identities of the sleep-promoting cells remain elusive. To address this question, this study compares mice during recovery sleep following sleep deprivation to mice allowed extended sleep. Single-nucleus RNA sequencing (single-nucleus RNA-seq) identifies one galanin inhibitory neuronal subtype that shows upregulation of rapid and delayed activity-regulated genes during recovery sleep. This cell type expresses higher levels of growth hormone receptor and lower levels of estrogen receptor compared to other galanin subtypes. single-nucleus RNA-seq also reveals cell-type-specific upregulation of purinergic receptor (P2ry14) and serotonin receptor (Htr2a) during recovery sleep in this neuronal subtype, suggesting possible mechanisms for sleep regulation. Studies with RNAscope validate the single-nucleus RNA-seq findings. Thus, the combined use of single-nucleus RNA-seq and activity-regulated genes identifies a neuronal subtype functionally involved in sleep regulation.

Sleep-Deep-Learner is taught sleep-wake scoring by the end-user to complete each record in their style

Sleep-wake scoring is a time-consuming, tedious but essential component of clinical and preclinical sleep research. Sleep scoring is even more laborious and challenging in rodents due to the smaller EEG amplitude differences between states and the rapid state transitions which necessitate scoring in shorter epochs. Although many automated rodent sleep scoring methods exist, they do not perform as well when scoring new datasets, especially those which involve changes in the EEG/EMG profile. Thus, manual scoring by expert scorers remains the gold standard. Here we take a different approach to this problem by using a neural network to accelerate the scoring of expert scorers. Sleep-Deep-Learner creates a bespoke deep convolution neural network model for individual electroencephalographic or local-field-potential (LFP) records via transfer learning of GoogLeNet, by learning from a small subset of manual scores of each EEG/LFP record as provided by the end-user. Sleep-Deep-Learner then automates scoring of the remainder of the EEG/LFP record. A novel REM sleep scoring correction procedure further enhanced accuracy. Sleep-Deep-Learner reliably scores EEG and LFP data and retains sleep-wake architecture in wild-type mice, in sleep induced by the hypnotic zolpidem, in a mouse model of Alzheimer's disease and in a genetic knock-down study, when compared to manual scoring. Sleep-Deep-Learner reduced manual scoring time to 1/12. Since Sleep-Deep-Learner uses transfer learning on each independent recording, it is not biased by previously scored existing datasets. Thus, we find Sleep-Deep-Learner performs well when used on signals altered by a drug, disease model, or genetic modification.

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.

Sleep scoring in rodents: Criteria, automatic approaches and outstanding issues

There is nothing we spend as much time on in our lives as we do sleeping, which makes it even more surprising that we currently do not know why we need to sleep. Most of the research addressing this question is performed in rodents to allow for invasive, mechanistic approaches. However, in contrast to human sleep, we currently do not have shared and agreed upon standards on sleep states in rodents. In this article, we present an overview on sleep stages in humans and rodents and a historical perspective on the development of automatic sleep scoring systems in rodents. Further, we highlight specific issues in rodent sleep that also call into question some of the standards used in human sleep research.

Dopamine pathways mediating affective state transitions after sleep loss

The pathophysiology of affective disorders-particularly circuit-level mechanisms underlying bidirectional, periodic affective state transitions-remains poorly understood. In patients, disruptions of sleep and circadian rhythm can trigger transitions to manic episodes, whereas depressive states are reversed. Here, we introduce a hybrid automated sleep deprivation platform to induce transitions of affective states in mice. Acute sleep loss causes mixed behavioral states, featuring hyperactivity, elevated social and sexual behaviors, and diminished depressive-like behaviors, where transitions depend on dopamine (DA). Using DA sensor photometry and projection-targeted chemogenetics, we reveal that elevated DA release in specific brain regions mediates distinct behavioral changes in affective state transitions. Acute sleep loss induces DA-dependent enhancement in dendritic spine density and uncaging-evoked dendritic spinogenesis in the medial prefrontal cortex, whereas optically mediated disassembly of enhanced plasticity reverses the antidepressant effects of sleep deprivation on learned helplessness. These findings demonstrate that brain-wide dopaminergic pathways control sleep-loss-induced polymodal affective state transitions.

Somnotate: A probabilistic sleep stage classifier for studying vigilance state transitions

Electrophysiological recordings from freely behaving animals are a widespread and powerful mode of investigation in sleep research. These recordings generate large amounts of data that require sleep stage annotation (polysomnography), in which the data is parcellated according to three vigilance states: awake, rapid eye movement (REM) sleep, and non-REM (NREM) sleep. Manual and current computational annotation methods ignore intermediate states because the classification features become ambiguous, even though intermediate states contain important information regarding vigilance state dynamics. To address this problem, we have developed "Somnotate"-a probabilistic classifier based on a combination of linear discriminant analysis (LDA) with a hidden Markov model (HMM). First we demonstrate that Somnotate sets new standards in polysomnography, exhibiting annotation accuracies that exceed human experts on mouse electrophysiological data, remarkable robustness to errors in the training data, compatibility with different recording configurations, and an ability to maintain high accuracy during experimental interventions. However, the key feature of Somnotate is that it quantifies and reports the certainty of its annotations. We leverage this feature to reveal that many intermediate vigilance states cluster around state transitions, whereas others correspond to failed attempts to transition. This enables us to show for the first time that the success rates of different types of transition are differentially affected by experimental manipulations and can explain previously observed sleep patterns. Somnotate is open-source and has the potential to both facilitate the study of sleep stage transitions and offer new insights into the mechanisms underlying sleep-wake dynamics.

Sleep-Deep-Net learns sleep wake scoring from the end-user and completes each record in their style

Sleep-wake scoring is a time-consuming, tedious but essential component of clinical and pre-clinical sleep research. Sleep scoring is even more laborious and challenging in rodents due to the smaller EEG amplitude differences between states and the rapid state transitions which necessitate scoring in shorter epochs. Although many automated rodent sleep scoring methods exist, they do not perform as well when scoring new data sets, especially those which involve changes in the EEG/EMG profile. Thus, manual scoring by expert scorers remains the gold-standard. Here we take a different approach to this problem by using a neural network to accelerate the scoring of expert scorers. Sleep-Deep-Net (SDN) creates a bespoke deep convolution neural network model for individual electroencephalographic or local-field-potential records via transfer learning of GoogleNet, by learning from a small subset of manual scores of each EEG/LFP record as provided by the end-user. SDN then automates scoring of the remainder of the EEG/LFP record. A novel REM scoring correction procedure further enhanced accuracy. SDN reliably scores EEG and LFP data and retains sleep-wake architecture in wild-type mice, in sleep induced by the hypnotic zolpidem, in a mouse model of Alzheimer's disease and in a genetic knock-down study, when compared to manual scoring. SDN reduced manual scoring time to 1/12. Since SDN uses transfer learning on each independent recording, it is not biased by previously scored existing data sets. Thus, we find SDN performs well when used on signals altered by a drug, disease model or genetic modification.

Chronic dietary supplementation with nicotinamide riboside reduces sleep need in the laboratory mouse

Non-rapid eye movement sleep (NREMS) is accompanied by a reduction in cerebral glucose utilization. Enabling this metabolic change may be a central function of sleep. Since the reduction in glucose metabolism is inevitably accompanied by deceleration of downstream oxidation/reduction reactions involving nicotinamide adenine dinucleotide (NAD), we hypothesized a role for NAD in regulating the homeostatic dynamics of sleep at the biochemical level. We applied dietary nicotinamide riboside (NR), a NAD precursor, in a protocol known to improve neurological outcome measures in mice. Long-term (6-10 weeks) dietary supplementation with NR reduced the time that mice spent in NREMS by 17 percent and accelerated the rate of discharge of sleep need according to a mathematical model of sleep homeostasis (Process S). These findings suggest that increasing redox capacity by increasing nicotinamide availability reduces sleep need and increases the cortical capacity for energetically demanding high-frequency oscillations. In turn, this work demonstrates the impact of redox substrates on cortical circuit properties related to fatigue and sleep drive, implicating redox reactions in the homeostatic dynamics of cortical network events across sleep-wake cycles.

Cerebellar deep brain stimulation as a dual-function therapeutic for restoring movement and sleep in dystonic mice

Dystonia arises with cerebellar dysfunction, which plays a key role in the emergence of multiple pathophysiological deficits that range from abnormal movements and postures to disrupted sleep. Current therapeutic interventions typically do not simultaneously address both the motor and non-motor (sleep-related) symptoms of dystonia, underscoring the necessity for a multi-functional therapeutic strategy. Deep brain stimulation (DBS) is effectively used to reduce motor symptoms in dystonia, with existing parallel evidence arguing for its potential to correct sleep disturbances. However, the simultaneous efficacy of DBS for improving sleep and motor dysfunction, specifically by targeting the cerebellum, remains underexplored. Here, we test the effect of cerebellar DBS in two genetic mouse models with dystonia that exhibit sleep defects- Ptf1a Cre ;Vglut2 fx/fx and Pdx1 Cre ;Vglut2 fx/fx -which have overlapping cerebellar circuit miswiring defects but differing severity in motor phenotypes. By targeting DBS to the cerebellar fastigial and interposed nuclei, we modulated sleep dysfunction by enhancing sleep quality and timing in both models. This DBS paradigm improved wakefulness (decreased) and rapid eye movement (REM) sleep (increased) in both mutants. Additionally, the latency to reach REM sleep, a deficit observed in human dystonia patients, was reduced in both models. Cerebellar DBS also induced alterations in the electrocorticogram (ECoG) patterns that define sleep states. As expected, DBS reduced the severe dystonic twisting motor symptoms that are observed in the Ptf1a Cre ;Vglut2 fx/fx mutant mice. These findings highlight the potential for using cerebellar DBS to improve sleep and reduce motor dysfunction in dystonia and uncover its potential as a dual-effect in vivo therapeutic strategy.

A wireless and battery-less implant for multimodal closed-loop neuromodulation in small animals

Fully implantable wireless systems for the recording and modulation of neural circuits that do not require physical tethers or batteries allow for studies that demand the use of unconstrained and freely behaving animals in isolation or in social groups. Moreover, feedback-control algorithms that can be executed within such devices without the need for remote computing eliminate virtual tethers and any associated latencies. Here we report a wireless and battery-less technology of this type, implanted subdermally along the back of freely moving small animals, for the autonomous recording of electroencephalograms, electromyograms and body temperature, and for closed-loop neuromodulation via optogenetics and pharmacology. The device incorporates a system-on-a-chip with Bluetooth Low Energy for data transmission and a compressed deep-learning module for autonomous operation, that offers neurorecording capabilities matching those of gold-standard wired systems. We also show the use of the implant in studies of sleep-wake regulation and for the programmable closed-loop pharmacological suppression of epileptic seizures via feedback from electroencephalography. The technology can support a broader range of applications in neuroscience and in biomedical research with small animals.

Purkinje cell dysfunction causes disrupted sleep in ataxic mice

Purkinje cell dysfunction causes movement disorders such as ataxia, however, recent evidence suggests that Purkinje cell dysfunction may also alter sleep regulation. Here, we used an ataxia mouse model generated by silencing Purkinje cell neurotransmission ( L7 Cre ;Vgat fx/fx ) to better understand how cerebellar dysfunction impacts sleep physiology. We focused our analysis on sleep architecture and electrocorticography (ECoG) patterns based on their relevance to extracting physiological measurements during sleep. We found that circadian activity is unaltered in the mutant mice, although their sleep parameters and ECoG patterns are modified. The L7 Cre ;Vgat fx/fx mutant mice have decreased wakefulness and rapid eye movement (REM) sleep, while non-rapid eye movement (NREM) sleep is increased. The mutant mice have an extended latency to REM sleep, which is also observed in human ataxia patients. Spectral analysis of ECoG signals revealed alterations in the power distribution across different frequency bands defining sleep. Therefore, Purkinje cell dysfunction may influence wakefulness and equilibrium of distinct sleep stages in ataxia. Our findings posit a connection between cerebellar dysfunction and disrupted sleep and underscore the importance of examining cerebellar circuit function in sleep disorders.

Summary Statement

Utilizing a precise genetic mouse model of ataxia, we provide insights into the cerebellum's role in sleep regulation, highlighting its potential as a therapeutic target for motor disorders-related sleep disruptions.

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.

Effect of N-Acetylcysteine on Sleep: Impacts of Sex and Time of Day

Non-rapid eye movement sleep (NREMS) is accompanied by a decrease in cerebral metabolism, which reduces the consumption of glucose as a fuel source and decreases the overall accumulation of oxidative stress in neural and peripheral tissues. Enabling this metabolic shift towards a reductive redox environment may be a central function of sleep. Therefore, biochemical manipulations that potentiate cellular antioxidant pathways may facilitate this function of sleep. N-acetylcysteine increases cellular antioxidant capacity by serving as a precursor to glutathione. In mice, we observed that intraperitoneal administration of N-acetylcysteine at a time of day when sleep drive is naturally high accelerated the onset of sleep and reduced NREMS delta power. Additionally, N-acetylcysteine administration suppressed slow and beta electroencephalographic (EEG) activities during quiet wake, further demonstrating the fatigue-inducing properties of antioxidants and the impact of redox balance on cortical circuit properties related to sleep drive. These results implicate redox reactions in the homeostatic dynamics of cortical network events across sleep/wake cycles, illustrating the value of timing antioxidant administration relative to sleep/wake cycles. A systematic review of the relevant literature, summarized herein, indicates that this "chronotherapeutic hypothesis" is unaddressed within the clinical literature on antioxidant therapy for brain disorders such as schizophrenia. We, therefore, advocate for studies that systematically address the relationship between the time of day at which an antioxidant therapy is administered relative to sleep/wake cycles and the therapeutic benefit of that antioxidant treatment in brain disorders.

IntelliSleepScorer, a software package with a graphic user interface for automated sleep stage scoring in mice based on a light gradient boosting machine algorithm

Machine learning has been applied in recent years to categorize sleep stages (NREM, REM, and wake) using electroencephalogram (EEG) recordings; however, a well-validated sleep scoring automatic pipeline in rodent research is still not publicly available. Here, we present IntelliSleepScorer, a software package with a graphic user interface to score sleep stages automatically in mice. IntelliSleepScorer uses the light gradient boosting machine (LightGBM) to score sleep stages for each epoch of recordings. We developed LightGBM models using a large cohort of data, which consisted of 5776 h of sleep EEG and electromyogram (EMG) signals across 519 unique recordings from 124 mice. The LightGBM model achieved an overall accuracy of 95.2% and a Cohen's kappa of 0.91, which outperforms the baseline models such as the logistic regression model (accuracy = 93.3%, kappa = 0.88) and the random forest model (accuracy = 94.3%, kappa = 0.89). The overall performance of the LightGBM model as well as the performance across different sleep stages are on par with that of the human experts. Most importantly, we validated the generalizability of the LightGBM models: (1) The LightGBM model performed well on two publicly available, independent datasets (kappa >  = 0.80), which have different sampling frequency and epoch lengths; (2) The LightGBM model performed well on data recorded at a lower sampling frequency (kappa = 0.90); (3) The performance of the LightGBM model is not affected by the light/dark cycle; and (4) A modified LightGBM model performed well on data containing only one EEG and one EMG electrode (kappa >  = 0.89). Taken together, the LightGBM models offer state-of-the-art performance for automatic sleep stage scoring in mice. Last, we implemented the IntelliSleepScorer software package based on the validated model to provide an out-of-box solution to sleep researchers (available for download at https://sites.broadinstitute.org/pan-lab/resources ).

Disrupted sleep in dystonia depends on cerebellar function but not motor symptoms in mice

Although dystonia is the third most common movement disorder, patients often also experience debilitating nonmotor defects including impaired sleep. The cerebellum is a central component of a "dystonia network" that plays various roles in sleep regulation. Importantly, the primary driver of sleep impairments in dystonia remains poorly understood. The cerebellum, along with other nodes in the motor circuit, could disrupt sleep. However, it is unclear how the cerebellum might alter sleep and mobility. To disentangle the impact of cerebellar dysfunction on motion and sleep, we generated two mouse genetic models of dystonia that have overlapping cerebellar circuit miswiring but show differing motor phenotype severity: Ptf1a ^Cre ;Vglut2 ^fx/fx and Pdx1 ^Cre ;Vglut2 ^fx/fx mice. In both models, excitatory climbing fiber to Purkinje cell neurotransmission is blocked, but only the Ptf1a ^Cre ;Vglut2 ^fx/fx mice have severe twisting. Using in vivo ECoG and EMG recordings we found that both mutants spend greater time awake and in NREM sleep at the expense of REM sleep. The increase in awake time is driven by longer awake bouts rather than an increase in bout number. We also found a longer latency to reach REM in both mutants, which is similar to what is reported in human dystonia. We uncovered independent but parallel roles for cerebellar circuit dysfunction and motor defects in promoting sleep quality versus posture impairments in dystonia.

Pupil Dynamics-derived Sleep Stage Classification of a Head-fixed Mouse Using a Recurrent Neural Network

The standard method for sleep state classification is thresholding the amplitudes of electroencephalography (EEG) and electromyography (EMG) data, followed by manual correction by an expert. Although popular, this method has some shortcomings: (1) the time-consuming manual correction by human experts is sometimes a bottleneck hindering sleep studies, (2) EEG electrodes on the skull interfere with wide-field imaging of the cortical activity of a head-fixed mouse under a microscope, (3) invasive surgery to fix the electrodes on the thin mouse skull risks brain tissue injury, and (4) metal electrodes for EEG and EMG recording are difficult to apply to some experimental apparatus such as that for functional magnetic resonance imaging. To overcome these shortcomings, we propose a pupil dynamics-based vigilance state classification method for a head-fixed mouse using a long short-term memory (LSTM) model, a variant of a recurrent neural network, for multi-class labeling of NREM, REM, and WAKE states. For supervisory hypnography, EEG and EMG recording were performed on head-fixed mice. This setup was combined with left eye pupillometry using a USB camera and a markerless tracking toolbox, DeepLabCut. Our open-source LSTM model with feature inputs of pupil diameter, pupil location, pupil velocity, and eyelid opening for 10 s at a 10 Hz sampling rate achieved vigilance state estimation with a higher classification performance (macro F1 score, 0.77; accuracy, 86%) than a feed-forward neural network. Findings from a diverse range of pupillary dynamics implied possible subdivision of the vigilance states defined by EEG and EMG. Pupil dynamics-based hypnography can expand the scope of alternatives for sleep stage scoring of head-fixed mice.

Antisense oligonucleotide therapy rescues disturbed brain rhythms and sleep in juvenile and adult mouse models of Angelman syndrome

UBE3A encodes ubiquitin protein ligase E3A, and in neurons its expression from the paternal allele is repressed by the UBE3A antisense transcript (UBE3A-ATS). This leaves neurons susceptible to loss-of-function of maternal UBE3A. Indeed, Angelman syndrome, a severe neurodevelopmental disorder, is caused by maternal UBE3A deficiency. A promising therapeutic approach to treating Angelman syndrome is to reactivate the intact paternal UBE3A by suppressing UBE3A-ATS. Prior studies show that many neurological phenotypes of maternal Ube3a knockout mice can only be rescued by reinstating Ube3a expression in early development, indicating a restricted therapeutic window for Angelman syndrome. Here, we report that reducing Ube3a-ATS by antisense oligonucleotides in juvenile or adult maternal Ube3a knockout mice rescues the abnormal electroencephalogram (EEG) rhythms and sleep disturbance, two prominent clinical features of Angelman syndrome. Importantly, the degree of phenotypic improvement correlates with the increase of Ube3a protein levels. These results indicate that the therapeutic window of genetic therapies for Angelman syndrome is broader than previously thought, and EEG power spectrum and sleep architecture should be used to evaluate the clinical efficacy of therapies.

Down-phase auditory stimulation is not able to counteract pharmacologically or physiologically increased sleep depth in traumatic brain injury rats

Modulation of slow-wave activity, either via pharmacological sleep induction by administering sodium oxybate or sleep restriction followed by a strong dissipation of sleep pressure, has been associated with preserved posttraumatic cognition and reduced diffuse axonal injury in traumatic brain injury rats. Although these classical strategies provided promising preclinical results, they lacked the specificity and/or translatability needed to move forward into clinical applications. Therefore, we recently developed and implemented a rodent auditory stimulation method that is a scalable, less invasive and clinically meaningful approach to modulate slow-wave activity by targeting a particular phase of slow waves. Here, we assessed the feasibility of down-phase targeted auditory stimulation of slow waves and evaluated its comparative modulatory strength in relation to the previously employed slow-wave activity modulators in our rat model of traumatic brain injury. Our results indicate that, in spite of effectively reducing slow-wave activity in both healthy and traumatic brain injury rats via down-phase targeted stimulation, this method was not sufficiently strong to counteract the boost in slow-wave activity associated with classical modulators, nor to alter concomitant posttraumatic outcomes. Therefore, the usefulness and effectiveness of auditory stimulation as potential standalone therapeutic strategy in the context of traumatic brain injury warrants further exploration.

Validation of Deep Learning-based Sleep State Classification

Deep learning methods have been developed to classify sleep states of mouse electroencephalogram (EEG) and electromyogram (EMG) recordings with accuracy reported as high as 97%. However, when applied to independent datasets, with a variety of experimental and recording conditions, sleep state classification accuracy often drops due to distributional shift. Mixture z-scoring, a pre-processing standardization of EEG/EMG signals, has been suggested to account for these variations. This study sought to validate mixture z-scoring in combination with a deep learning method on an independent dataset. The open-source software Accusleep, which implements mixture z-scoring in combination with deep learning via a convolutional neural network, was used to classify sleep states in 12, three-hour EEG/EMG recordings from mice sleeping in a head-fixed position. Mixture z-scoring with deep learning classified sleep states on two independent recordings with 85-92% accuracy and a Cohen's κ of 0.66-0.71. These results validate mixture z-scoring in combination with deep learning to classify sleep states with the potential for widespread use.

An attention-based temporal convolutional network for rodent sleep stage classification across species, mutants and experimental environments with single-channel electroencephalogram

Objective.Sleep perturbation by environment, medical procedure and genetic background is under continuous study in biomedical research. Analyzing brain states in animal models such as rodents relies on categorizing electroencephalogram (EEG) recordings. Traditionally, sleep experts have classified these states by visual inspection of EEG signatures, which is laborious. The heterogeneity of sleep patterns complicates the development of a generalizable solution across different species, genotypes and experimental environments.Approach.To realize a generalizable solution, we proposed a cross-species rodent sleep scoring network called CSSleep, a robust deep-learning model based on single-channel EEG. CSSleep starts with a local time-invariant information learning convolutional neural network. The second module is the global transition rules learning temporal convolutional network (TRTCN), stacked with bidirectional attention-based temporal convolutional network modules. The TRTCN simultaneously captures positive and negative time direction information and highlights relevant in-sequence features. The dataset for model evaluation comprises the single-EEG signatures of four cohorts of 16 mice and 8 rats from three laboratories.Main results.In leave-one-cohort-out cross-validation, our model achieved an accuracy of 91.33%. CSSleep performed well on generalization across experimental environments, mutants and rodent species by using single-channel EEG.Significance.This study aims to promote well-standardized cross-laboratory sleep studies to improve our understanding of sleep. Our source codes and supplementary materials will be disclosed later.

Sleep-Wake Rhythm and Oscillatory Pattern Analysis in a Multiple Hit Schizophrenia Rat Model (Wisket)

Electroencephalography studies in schizophrenia reported impairments in circadian rhythm and oscillatory activity, which may reflect the deficits in cognitive and sensory processing. The current study evaluated the circadian rhythm and the state-dependent oscillatory pattern in control Wistar and a multiple hit schizophrenia rat model (Wisket) using custom-made software for identification of the artifacts and the classification of sleep-wake stages and the active and quiet awake substages. The Wisket animals have a clear light-dark cycle similar to controls, and their sleep-wake rhythm showed only a tendency to spend more time in non-rapid eye movement (NREM) and less in rapid eye movement (REM) stages. In spite of the weak diurnal variation in oscillation in both groups, the Wisket rats had higher power in the low-frequency delta, alpha, and beta bands and lower power in the high-frequency theta and gamma bands in most stages. Furthermore, the significant differences between the two groups were pronounced in the active waking substage. These data suggest that the special changes in the oscillatory pattern of this schizophrenia rat model may have a significant role in the impaired cognitive functions observed in previous studies.

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.

Deep Learning End-to-End Approach for the Prediction of Tinnitus based on EEG Data. ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. ANNUAL INTERNATIONAL CONFERENCE 2021;2021:816-819. [PMID: 34891415 DOI: 10.1109/embc46164.2021.9629964]

Tinnitus is attributed by the perception of a sound without any physical source causing the symptom. Symptom profiles of tinnitus patients are characterized by a large heterogeneity, which is a major obstacle in developing general treatments for this chronic disorder. As tinnitus patients often report severe constraints in their daily life, the lack of general treatments constitutes such a challenge that patients crave for any kind of promising method to cope with their tinnitus, even if it is not based on evidence. Another drawback constitutes the lack of objective measurements to determine the individual symptoms of patients. Many data sources are therefore investigated to learn more about the heterogeneity of tinnitus patients in order to develop methods to measure the individual situation of patients more objectively. As research assumes that tinnitus is caused by processes in the brain, electroencephalography (EEG) data are heavily investigated by researchers. Following this, we address the question whether EEG data can be used to classify tinnitus using a deep neural network. For this purpose, we analyzed 16,780 raw EEG samples from 42 subjects (divided into tinnitus patients and control group), with a duration of one second per sample. Four different procedures (with or without noise reduction and down-sampling or up-sampling) for automated preprocessing were used and compared. Subsequently, a neural network was trained to classify whether a sample refers to a tinnitus patient or the control group. We obtain a maximum accuracy in the test set of 75.6% using noise reduction and down-sampling. Our findings highlight the potential of deep learning approaches to detect EEG patterns for tinnitus patients as they are difficult to be recognized by humans.

High-throughput visual assessment of sleep stages in mice using machine learning

STUDY OBJECTIVES

Sleep is an important biological process that is perturbed in numerous diseases, and assessment its substages currently requires implantation of electrodes to carry out electroencephalogram/electromyogram (EEG/EMG) analysis. Although accurate, this method comes at a high cost of invasive surgery and experts trained to score EEG/EMG data. Here, we leverage modern computer vision methods to directly classify sleep substages from video data. This bypasses the need for surgery and expert scoring, provides a path to high-throughput studies of sleep in mice.

METHODS

We collected synchronized high-resolution video and EEG/EMG data in 16 male C57BL/6J mice. We extracted features from the video that are time and frequency-based and used the human expert-scored EEG/EMG data to train a visual classifier. We investigated several classifiers and data augmentation methods.

RESULTS

Our visual sleep classifier proved to be highly accurate in classifying wake, non-rapid eye movement sleep (NREM), and rapid eye movement sleep (REM) states, and achieves an overall accuracy of 0.92 +/- 0.05 (mean +/- SD). We discover and genetically validate video features that correlate with breathing rates, and show low and high variability in NREM and REM sleep, respectively. Finally, we apply our methods to non-invasively detect that sleep stage disturbances induced by amphetamine administration.

CONCLUSIONS

We conclude that machine learning based visual classification of sleep is a viable alternative to EEG/EMG based scoring. Our results will enable non-invasive high-throughput sleep studies and will greatly reduce the barrier to screening mutant mice for abnormalities in sleep.

Closed-loop auditory stimulation method to modulate sleep slow waves and motor learning performance in rats

Slow waves and cognitive output have been modulated in humans by phase-targeted auditory stimulation. However, to advance its technical development and further our understanding, implementation of the method in animal models is indispensable. Here, we report the successful employment of slow waves' phase-targeted closed-loop auditory stimulation (CLAS) in rats. To validate this new tool both conceptually and functionally, we tested the effects of up- and down-phase CLAS on proportions and spectral characteristics of sleep, and on learning performance in the single-pellet reaching task, respectively. Without affecting 24 hr sleep-wake behavior, CLAS specifically altered delta (slow waves) and sigma (sleep spindles) power persistently over chronic periods of stimulation. While up-phase CLAS does not elicit a significant change in behavioral performance, down-phase CLAS exerted a detrimental effect on overall engagement and success rate in the behavioral test. Overall CLAS-dependent spectral changes were positively correlated with learning performance. Altogether, our results provide proof-of-principle evidence that phase-targeted CLAS of slow waves in rodents is efficient, safe, and stable over chronic experimental periods, enabling the use of this high-specificity tool for basic and preclinical translational sleep research.

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.

A deep learning algorithm for sleep stage scoring in mice based on a multimodal network with fine-tuning technique

Sleep stage scoring is important to determine sleep structure in preclinical and clinical research. The aim of this study was to develop an automatic sleep stage classification system for mice with a new deep neural network algorithm. For the purpose of base feature extraction, wake-sleep and rapid eye movement (REM) and non- rapid eye movement (NREM) models were developed by extracting defining features from mouse-derived electromyogram (EMG) and electroencephalogram (EEG) signals, respectively. The wake-sleep model and REM-NREM sleep model were integrated into three different algorithms including a rule-based integration approach, an ensemble stacking approach, and a multimodal with fine-tuning approach. The deep learning algorithm assessing sleep stages in animal experiments by the multimodal with fine-tuning approach showed high potential for increasing accuracy in sleep stage scoring in mice and promoting sleep research.

Automated scoring of pre-REM sleep in mice with deep learning

Reliable automation of the labor-intensive manual task of scoring animal sleep can facilitate the analysis of long-term sleep studies. In recent years, deep-learning-based systems, which learn optimal features from the data, increased scoring accuracies for the classical sleep stages of Wake, REM, and Non-REM. Meanwhile, it has been recognized that the statistics of transitional stages such as pre-REM, found between Non-REM and REM, may hold additional insight into the physiology of sleep and are now under vivid investigation. We propose a classification system based on a simple neural network architecture that scores the classical stages as well as pre-REM sleep in mice. When restricted to the classical stages, the optimized network showed state-of-the-art classification performance with an out-of-sample F1 score of 0.95 in male C57BL/6J mice. When unrestricted, the network showed lower F1 scores on pre-REM (0.5) compared to the classical stages. The result is comparable to previous attempts to score transitional stages in other species such as transition sleep in rats or N1 sleep in humans. Nevertheless, we observed that the sequence of predictions including pre-REM typically transitioned from Non-REM to REM reflecting sleep dynamics observed by human scorers. Our findings provide further evidence for the difficulty of scoring transitional sleep stages, likely because such stages of sleep are under-represented in typical data sets or show large inter-scorer variability. We further provide our source code and an online platform to run predictions with our trained network.

WaveSleepNet: An interpretable deep convolutional neural network for the continuous classification of mouse sleep and wake

BACKGROUND

Recent advancement in deep learning provides a pivotal opportunity to potentially supplement or supplant the limiting step of manual sleep scoring.

NEW METHOD

In this paper, we characterize the WaveSleepNet (WSN), a deep convolutional neural network (CNN) that uses wavelet transformed images of mouse EEG/EMG signals to autoscore sleep and wake.

RESULTS

WSN achieves an epoch by epoch mean accuracy of 0.86 and mean F1 score of 0.82 compared to manual scoring by a human expert. In mice experiencing mechanically induced sleep fragmentation, an overall epoch by epoch mean accuracy of 0.80 is achieved by WSN and classification of non-REM (NREM) sleep is not compromised, but the high level of sleep fragmentation results in WSN having greater difficulty differentiating REM from NREM sleep. We also find that WSN achieves similar levels of accuracy on an independent dataset of externally acquired EEG/EMG recordings with an overall epoch by epoch accuracy of 0.91. We also compared conventional summary sleep metrics in mice sleeping ad libitum. WSN systematically biases sleep fragmentation metrics of bout number and bout length leading to an overestimated degree of sleep fragmentation.

COMPARISON WITH EXISTING METHODS

In a cross-validation, WSN has a greater macro and stage-specific accuracy compared to a conventional random forest classifier. Examining the WSN, we find that it automatically learns spectral features consistent with manual scoring criteria that are used to define each class.

CONCLUSION

These results suggest to us that WSN is capable of learning visually agreeable features and may be useful as a supplement to human manual scoring.

Quantitative Assessment of Resting-State for Mild Cognitive Impairment Detection: A Functional Near-Infrared Spectroscopy and Deep Learning Approach

BACKGROUND

Mild cognitive impairment (MCI) is considered a prodromal stage of Alzheimer's disease. Early diagnosis of MCI can allow for treatment to improve cognitive function and reduce modifiable risk factors.

OBJECTIVE

This study aims to investigate the feasibility of individual MCI detection from healthy control (HC) using a minimum duration of resting-state functional near-infrared spectroscopy (fNIRS) signals.

METHODS

In this study, nine different measurement durations (i.e., 30, 60, 90, 120, 150, 180, 210, 240, and 270 s) were evaluated for MCI detection via the graph theory analysis and traditional machine learning approach, such as linear discriminant analysis, support vector machine, and K-nearest neighbor algorithms. Moreover, feature representation- and classification-based transfer learning (TL) methods were applied to identify MCI from HC through the input of connectivity maps with 30 and 90 s duration.

RESULTS

There was no significant difference among the nine various time windows in the machine learning and graph theory analysis. The feature representation-based TL showed improved accuracy in both 30 and 90 s cases (i.e., 30 s: 81.27% and 90 s: 76.73%). Notably, the classification-based TL method achieved the highest accuracy of 95.81% using the pre-trained convolutional neural network (CNN) model with the 30 s interval functional connectivity map input.

CONCLUSION

The results indicate that a 30 s measurement of the resting-state with fNIRS could be used to detect MCI. Moreover, the combination of neuroimaging (e.g., functional connectivity maps) and deep learning methods (e.g., CNN and TL) can be considered as novel biomarkers for clinical computer-assisted MCI diagnosis.

A real-time sleep scoring framework for closed-loop sleep manipulation in mice

Subtle changes in sleep architecture can accompany and be symptomatic of many diseases or disorders. In order to probe and understand the complex interactions between sleep and health, the ability to model, track, and modulate sleep in preclinical animal models is vital. While various methods have been described for scoring experimental sleep recordings, few are designed to work in real time - a prerequisite for closed-loop sleep manipulation. In the present study, we have developed algorithms and software to classify sleep in real time and validated it on C57BL/6 mice (n = 8). Hidden Markov models of baseline sleep dynamics were fitted using an unsupervised algorithm to electroencephalogram (EEG) and electromyogram (EMG) data for each mouse, and were able to classify sleep in a manner highly concordant with manual scoring (Cohen's Kappa >75%) up to 3 weeks after model construction. This approach produced reasonably accurate estimates of common sleep metrics (proportion, mean duration, and number of bouts). After construction, the models were used to track sleep in real time and accomplish selective rapid eye movement (REM) sleep restriction by triggering non-invasive somatosensory stimulation. During REM restriction trials, REM bout duration was significantly reduced, and the classifier continued to perform satisfactorily despite the disrupted sleep patterns. The software can easily be tailored for use with other commercial or customised methods of sleep disruption (e.g. stir bar, optogenetic stimulation, etc.) and could serve as a robust platform to facilitate closed-loop experimentation. The source code and documentation are freely available upon request from the authors.

Identification of the sleep-wake states in rats using the high-frequency activity of the electroencephalogram

The electroencephalographic signal constitutes the main sign classically used for the identification of states of alertness. However, activities in the high frequency (>100 Hz) range have not been properly studied despite their high potential for sleep scoring in rodents. In the present study, we designed a method for the identification of the sleep-wake states in rats by exclusively using high-frequency activities of the electroencephalogram. By calculating the ratio between the amplitude of the electroencephalographic signal from 110 to 200 Hz and from 110 to 300 Hz, we obtained an index that had values that were low during wakefulness, intermediate during non-REM sleep and high during REM sleep. This high-frequency index (HiFI) allowed the identification of each state without the need to study other signs such as muscle activity or eye movements. To evaluate the performance of the index, we compared it with the conventional scoring of the sleep-wake cycle based upon the study of the electromyogram and delta (0.5-4 Hz), theta (6-9 Hz) and sigma (10-14 Hz) bands of the electroencephalogram. The index had an accuracy of 90.43 ± 1.91% (Cohen's kappa value of 0.82), confirming that the study of the high-frequency activities of the electroencephalogram was sufficient to reliably identify alertness states in the rat. Compared to other sleep-scoring methods, the HiFI has several advantages. It only requires one electroencephalography electrode, thus reducing the severity of the surgical preparation of the experimental animal, and its calculation is very simple, so it can be easily implemented online to classify sleep-wake states in real time.

Circadian VIPergic Neurons of the Suprachiasmatic Nuclei Sculpt the Sleep-Wake Cycle

Although the mammalian rest-activity cycle is controlled by a "master clock" in the suprachiasmatic nucleus (SCN) of the hypothalamus, it is unclear how firing of individual SCN neurons gates individual features of daily activity. Here, we demonstrate that a specific transcriptomically identified population of mouse VIP+ SCN neurons is active at the "wrong" time of day-nighttime-when most SCN neurons are silent. Using chemogenetic and optogenetic strategies, we show that these neurons and their cellular clocks are necessary and sufficient to gate and time nighttime sleep but have no effect upon daytime sleep. We propose that mouse nighttime sleep, analogous to the human siesta, is a "hard-wired" property gated by specific neurons of the master clock to favor subsequent alertness prior to dawn (a circadian "wake maintenance zone"). Thus, the SCN is not simply a 24-h metronome: specific populations sculpt critical features of the sleep-wake cycle.

Robust, automated sleep scoring by a compact neural network with distributional shift correction

Studying the biology of sleep requires the accurate assessment of the state of experimental subjects, and manual analysis of relevant data is a major bottleneck. Recently, deep learning applied to electroencephalogram and electromyogram data has shown great promise as a sleep scoring method, approaching the limits of inter-rater reliability. As with any machine learning algorithm, the inputs to a sleep scoring classifier are typically standardized in order to remove distributional shift caused by variability in the signal collection process. However, in scientific data, experimental manipulations introduce variability that should not be removed. For example, in sleep scoring, the fraction of time spent in each arousal state can vary between control and experimental subjects. We introduce a standardization method, mixture z-scoring, that preserves this crucial form of distributional shift. Using both a simulated experiment and mouse in vivo data, we demonstrate that a common standardization method used by state-of-the-art sleep scoring algorithms introduces systematic bias, but that mixture z-scoring does not. We present a free, open-source user interface that uses a compact neural network and mixture z-scoring to allow for rapid sleep scoring with accuracy that compares well to contemporary methods. This work provides a set of computational tools for the robust automation of sleep scoring.

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.