Microglia regulate sleep through calcium-dependent modulation of norepinephrine transmission.

Sleep interacts reciprocally with immune system activity, but its specific relationship with microglia-the resident immune cells in the brain-remains poorly understood. Here, we show in mice that microglia can regulate sleep through a mechanism involving Gi-coupled GPCRs, intracellular Ca2+ signaling and suppression of norepinephrine transmission. Chemogenetic activation of microglia Gi signaling strongly promoted sleep, whereas pharmacological blockade of Gi-coupled P2Y12 receptors decreased sleep. Two-photon imaging in the cortex showed that P2Y12-Gi activation elevated microglia intracellular Ca2+, and blockade of this Ca2+ elevation largely abolished the Gi-induced sleep increase. Microglia Ca2+ level also increased at natural wake-to-sleep transitions, caused partly by reduced norepinephrine levels. Furthermore, imaging of norepinephrine with its biosensor in the cortex showed that microglia P2Y12-Gi activation significantly reduced norepinephrine levels, partly by increasing the adenosine concentration. These findings indicate that microglia can regulate sleep through reciprocal interactions with norepinephrine transmission.

Cardiovascular baroreflex circuit moonlights in sleep control.

Sleep disturbances are strongly associated with cardiovascular diseases. Baroreflex, a basic cardiovascular regulation mechanism, is modulated by sleep-wake states. Here, we show that neurons at key stages of baroreflex pathways also promote sleep. Using activity-dependent genetic labeling, we tagged neurons in the nucleus of the solitary tract (NST) activated by blood pressure elevation and confirmed their barosensitivity with optrode recording and calcium imaging. Chemogenetic or optogenetic activation of these neurons promoted non-REM sleep in addition to decreasing blood pressure and heart rate. GABAergic neurons in the caudal ventrolateral medulla (CVLM)-a downstream target of the NST for vasomotor baroreflex-also promote non-REM sleep, partly by inhibiting the sympathoexcitatory and wake-promoting adrenergic neurons in the rostral ventrolateral medulla (RVLM). Cholinergic neurons in the nucleus ambiguous-a target of the NST for cardiac baroreflex-promoted non-REM sleep as well. Thus, key components of the cardiovascular baroreflex circuit are also integral to sleep-wake brain-state regulation.

Machine learning early prediction of respiratory syncytial virus in pediatric hospitalized patients.

Respiratory syncytial virus (RSV) causes millions of infections among children in the US each year and can cause severe disease or death. Infections that are not promptly detected can cause outbreaks that put other hospitalized patients at risk. No tools besides diagnostic testing are available to rapidly and reliably predict RSV infections among hospitalized patients. We conducted a retrospective study from pediatric electronic health record (EHR) data and built a machine learning model to predict whether a patient will test positive to RSV by nucleic acid amplification test during their stay. Our model demonstrated excellent discrimination with an area under the receiver-operating curve of 0.919, a sensitivity of 0.802, and specificity of 0.876. Our model can help clinicians identify patients who may have RSV infections rapidly and cost-effectively. Successfully integrating this model into routine pediatric inpatient care may assist efforts in patient care and infection control.

Multitask Learning With Recurrent Neural Networks for Acute Respiratory Distress Syndrome Prediction Using Only Electronic Health Record Data: Model Development and Validation Study.

BACKGROUND: Acute respiratory distress syndrome (ARDS) is a condition that is often considered to have broad and subjective diagnostic criteria and is associated with significant mortality and morbidity. Early and accurate prediction of ARDS and related conditions such as hypoxemia and sepsis could allow timely administration of therapies, leading to improved patient outcomes. OBJECTIVE: The aim of this study is to perform an exploration of how multilabel classification in the clinical setting can take advantage of the underlying dependencies between ARDS and related conditions to improve early prediction of ARDS in patients. METHODS: The electronic health record data set included 40,703 patient encounters from 7 hospitals from April 20, 2018, to March 17, 2021. A recurrent neural network (RNN) was trained using data from 5 hospitals, and external validation was conducted on data from 2 hospitals. In addition to ARDS, 12 target labels for related conditions such as sepsis, hypoxemia, and COVID-19 were used to train the model to classify a total of 13 outputs. As a comparator, XGBoost models were developed for each of the 13 target labels. Model performance was assessed using the area under the receiver operating characteristic curve. Heat maps to visualize attention scores were generated to provide interpretability to the neural networks. Finally, cluster analysis was performed to identify potential phenotypic subgroups of patients with ARDS. RESULTS: The single RNN model trained to classify 13 outputs outperformed the individual XGBoost models for ARDS prediction, achieving an area under the receiver operating characteristic curve of 0.842 on the external test sets. Models trained on an increasing number of tasks resulted in improved performance. Earlier prediction of ARDS nearly doubled the rate of in-hospital survival. Cluster analysis revealed distinct ARDS subgroups, some of which had similar mortality rates but different clinical presentations. CONCLUSIONS: The RNN model presented in this paper can be used as an early warning system to stratify patients who are at risk of developing one of the multiple risk outcomes, hence providing practitioners with the means to take early action.

Assessing the effects of data drift on the performance of machine learning models used in clinical sepsis prediction.

Background: Data drift can negatively impact the performance of machine learning algorithms (MLAs) that were trained on historical data. As such, MLAs should be continuously monitored and tuned to overcome the systematic changes that occur in the distribution of data. In this paper, we study the extent of data drift and provide insights about its characteristics for sepsis onset prediction. This study will help elucidate the nature of data drift for prediction of sepsis and similar diseases. This may aid with the development of more effective patient monitoring systems that can stratify risk for dynamic disease states in hospitals. Methods: We devise a series of simulations that measure the effects of data drift in patients with sepsis. We simulate multiple scenarios in which data drift may occur, namely the change in the distribution of the predictor variables (covariate shift), the change in the statistical relationship between the predictors and the target (concept shift), and the occurrence of a major healthcare event (major event) such as the COVID-19 pandemic. We measure the impact of data drift on model performances, identify the circumstances that necessitate model retraining, and compare the effects of different retraining methodologies and model architecture on the outcomes. We present the results for two different MLAs, eXtreme Gradient Boosting (XGB) and Recurrent Neural Network (RNN). Results: Our results show that the properly retrained XGB models outperform the baseline models in all simulation scenarios, hence signifying the existence of data drift. In the major event scenario, the area under the receiver operating characteristic curve (AUROC) at the end of the simulation period is 0.811 for the baseline XGB model and 0.868 for the retrained XGB model. In the covariate shift scenario, the AUROC at the end of the simulation period for the baseline and retrained XGB models is 0.853 and 0.874 respectively. In the concept shift scenario and under the mixed labeling method, the retrained XGB models perform worse than the baseline model for most simulation steps. However, under the full relabeling method, the AUROC at the end of the simulation period for the baseline and retrained XGB models is 0.852 and 0.877 respectively. The results for the RNN models were mixed, suggesting that retraining based on a fixed network architecture may be inadequate for an RNN. We also present the results in the form of other performance metrics such as the ratio of observed to expected probabilities (calibration) and the normalized rate of positive predictive values (PPV) by prevalence, referred to as lift, at a sensitivity of 0.8. Conclusion: Our simulations reveal that retraining periods of a couple of months or using several thousand patients are likely to be adequate to monitor machine learning models that predict sepsis. This indicates that a machine learning system for sepsis prediction will probably need less infrastructure for performance monitoring and retraining compared to other applications in which data drift is more frequent and continuous. Our results also show that in the event of a concept shift, a full overhaul of the sepsis prediction model may be necessary because it indicates a discrete change in the definition of sepsis labels, and mixing the labels for the sake of incremental training may not produce the desired results.

Semisupervised Deep Learning Techniques for Predicting Acute Respiratory Distress Syndrome From Time-Series Clinical Data: Model Development and Validation Study.

BACKGROUND: A high number of patients who are hospitalized with COVID-19 develop acute respiratory distress syndrome (ARDS). OBJECTIVE: In response to the need for clinical decision support tools to help manage the next pandemic during the early stages (ie, when limited labeled data are present), we developed machine learning algorithms that use semisupervised learning (SSL) techniques to predict ARDS development in general and COVID-19 populations based on limited labeled data. METHODS: SSL techniques were applied to 29,127 encounters with patients who were admitted to 7 US hospitals from May 1, 2019, to May 1, 2021. A recurrent neural network that used a time series of electronic health record data was applied to data that were collected when a patient's peripheral oxygen saturation level fell below the normal range (<97%) to predict the subsequent development of ARDS during the remaining duration of patients' hospital stay. Model performance was assessed with the area under the receiver operating characteristic curve and area under the precision recall curve of an external hold-out test set. RESULTS: For the whole data set, the median time between the first peripheral oxygen saturation measurement of <97% and subsequent respiratory failure was 21 hours. The area under the receiver operating characteristic curve for predicting subsequent ARDS development was 0.73 when the model was trained on a labeled data set of 6930 patients, 0.78 when the model was trained on the labeled data set that had been augmented with the unlabeled data set of 16,173 patients by using SSL techniques, and 0.84 when the model was trained on the entire training set of 23,103 labeled patients. CONCLUSIONS: In the context of using time-series inpatient data and a careful model training design, unlabeled data can be used to improve the performance of machine learning models when labeled data for predicting ARDS development are scarce or expensive.

Correlation of Population SARS-CoV-2 Cycle Threshold Values to Local Disease Dynamics: Exploratory Observational Study.

BACKGROUND: Despite the limitations in the use of cycle threshold (CT) values for individual patient care, population distributions of CT values may be useful indicators of local outbreaks. OBJECTIVE: We aimed to conduct an exploratory analysis of potential correlations between the population distribution of cycle threshold (CT) values and COVID-19 dynamics, which were operationalized as percent positivity, transmission rate (Rt), and COVID-19 hospitalization count. METHODS: In total, 148,410 specimens collected between September 15, 2020, and January 11, 2021, from the greater El Paso area were processed in the Dascena COVID-19 Laboratory. The daily median CT value, daily Rt, daily count of COVID-19 hospitalizations, daily change in percent positivity, and rolling averages of these features were plotted over time. Two-way scatterplots and linear regression were used to evaluate possible associations between daily median CT values and outbreak measures. Cross-correlation plots were used to determine whether a time delay existed between changes in daily median CT values and measures of community disease dynamics. RESULTS: Daily median CT values negatively correlated with the daily Rt values (P<.001), the daily COVID-19 hospitalization counts (with a 33-day time delay; P<.001), and the daily changes in percent positivity among testing samples (P<.001). Despite visual trends suggesting time delays in the plots for median CT values and outbreak measures, a statistically significant delay was only detected between changes in median CT values and COVID-19 hospitalization counts (P<.001). CONCLUSIONS: This study adds to the literature by analyzing samples collected from an entire geographical area and contextualizing the results with other research investigating population CT values.

Astrocytic Modulation of Neuronal Activity in the Suprachiasmatic Nucleus: Insights from Mathematical Modeling.

The suprachiasmatic nucleus (SCN) of the hypothalamus consists of a highly heterogeneous neuronal population networked together to allow precise and robust circadian timekeeping in mammals. While the critical importance of SCN neurons in regulating circadian rhythms has been extensively studied, the roles of SCN astrocytes in circadian system function are not well understood. Recent experiments have demonstrated that SCN astrocytes are circadian oscillators with the same functional clock genes as SCN neurons. Astrocytes generate rhythmic outputs that are thought to modulate neuronal activity through pre- and postsynaptic interactions. In this study, we developed an in silico multicellular model of the SCN clock to investigate the impact of astrocytes in modulating neuronal activity and affecting key clock properties such as circadian rhythmicity, period, and synchronization. The model predicted that astrocytes could alter the rhythmic activity of neurons via bidirectional interactions at tripartite synapses. Specifically, astrocyte-regulated extracellular glutamate was predicted to increase neuropeptide signaling from neurons. Consistent with experimental results, we found that astrocytes could increase the circadian period and enhance neural synchronization according to their endogenous circadian period. The impact of astrocytic modulation of circadian rhythm amplitude, period, and synchronization was predicted to be strongest when astrocytes had periods between 0 and 2 h longer than neurons. Increasing the number of neurons coupled to the astrocyte also increased its impact on period modulation and synchrony. These computational results suggest that signals that modulate astrocytic rhythms or signaling (e.g., as a function of season, age, or treatment) could cause disruptions in circadian rhythm or serve as putative therapeutic targets.

A common hub for sleep and motor control in the substantia nigra.

The arousal state of the brain covaries with the motor state of the animal. How these state changes are coordinated remains unclear. We discovered that sleep-wake brain states and motor behaviors are coregulated by shared neurons in the substantia nigra pars reticulata (SNr). Analysis of mouse home-cage behavior identified four states with different levels of brain arousal and motor activity: locomotion, nonlocomotor movement, quiet wakefulness, and sleep; transitions occurred not randomly but primarily between neighboring states. The glutamic acid decarboxylase 2 but not the parvalbumin subset of SNr γ-aminobutyric acid (GABA)-releasing (GABAergic) neurons was preferentially active in states of low motor activity and arousal. Their activation or inactivation biased the direction of natural behavioral transitions and promoted or suppressed sleep, respectively. These GABAergic neurons integrate wide-ranging inputs and innervate multiple arousal-promoting and motor-control circuits through extensive collateral projections.

Cell-Autonomous Regulation of Astrocyte Activation by the Circadian Clock Protein BMAL1.

Circadian clock dysfunction is a common symptom of aging and neurodegenerative diseases, though its impact on brain health is poorly understood. Astrocyte activation occurs in response to diverse insults and plays a critical role in brain health and disease. We report that the core circadian clock protein BMAL1 regulates astrogliosis in a synergistic manner via a cell-autonomous mechanism and a lesser non-cell-autonomous signal from neurons. Astrocyte-specific Bmal1 deletion induces astrocyte activation and inflammatory gene expression in vitro and in vivo, mediated in part by suppression of glutathione-S-transferase signaling. Functionally, loss of Bmal1 in astrocytes promotes neuronal death in vitro. Our results demonstrate that the core clock protein BMAL1 regulates astrocyte activation and function in vivo, elucidating a mechanism by which the circadian clock could influence many aspects of brain function and neurological disease.

Astrocytes Regulate Daily Rhythms in the Suprachiasmatic Nucleus and Behavior.

Astrocytes are active partners in neural information processing [1, 2]. However, the roles of astrocytes in regulating behavior remain unclear [3, 4]. Because astrocytes have persistent circadian clock gene expression and ATP release in vitro [5-8], we hypothesized that they regulate daily rhythms in neurons and behavior. Here, we demonstrated that daily rhythms in astrocytes within the mammalian master circadian pacemaker, the suprachiasmatic nucleus (SCN), determine the period of wheel-running activity. Ablating the essential clock gene Bmal1 specifically in SCN astrocytes lengthened the circadian period of clock gene expression in the SCN and in locomotor behavior. Similarly, excision of the short-period CK1ε tau mutation specifically from SCN astrocytes resulted in lengthened rhythms in the SCN and behavior. These results indicate that astrocytes within the SCN communicate to neurons to determine circadian rhythms in physiology and in rest activity.