Investigating Receptivity and Affect Using Machine Learning: Ecological Momentary Assessment and Wearable Sensing Study

BACKGROUND

As mobile health (mHealth) studies become increasingly productive owing to the advancements in wearable and mobile sensor technology, our ability to monitor and model human behavior will be constrained by participant receptivity. Many health constructs are dependent on subjective responses, and without such responses, researchers are left with little to no ground truth to accompany our ever-growing biobehavioral data. This issue can significantly impact the quality of a study, particularly for populations known to exhibit lower compliance rates. To address this challenge, researchers have proposed innovative approaches that use machine learning (ML) and sensor data to modify the timing and delivery of surveys. However, an overarching concern is the potential introduction of biases or unintended influences on participants' responses when implementing new survey delivery methods.

OBJECTIVE

This study aims to demonstrate the potential impact of an ML-based ecological momentary assessment (EMA) delivery system (using receptivity as the predictor variable) on the participants' reported emotional state. We examine the factors that affect participants' receptivity to EMAs in a 10-day wearable and EMA-based emotional state-sensing mHealth study. We study the physiological relationships indicative of receptivity and affect while also analyzing the interaction between the 2 constructs.

METHODS

We collected data from 45 healthy participants wearing 2 devices measuring electrodermal activity, accelerometer, electrocardiography, and skin temperature while answering 10 EMAs daily, containing questions about perceived mood. Owing to the nature of our constructs, we can only obtain ground truth measures for both affect and receptivity during responses. Therefore, we used unsupervised and supervised ML methods to infer affect when a participant did not respond. Our unsupervised method used k-means clustering to determine the relationship between physiology and receptivity and then inferred the emotional state during nonresponses. For the supervised learning method, we primarily used random forest and neural networks to predict the affect of unlabeled data points as well as receptivity.

RESULTS

Our findings showed that using a receptivity model to trigger EMAs decreased the reported negative affect by >3 points or 0.29 SDs in our self-reported affect measure, scored between 13 and 91. The findings also showed a bimodal distribution of our predicted affect during nonresponses. This indicates that this system initiates EMAs more commonly during states of higher positive emotions.

CONCLUSIONS

Our results showed a clear relationship between affect and receptivity. This relationship can affect the efficacy of an mHealth study, particularly those that use an ML algorithm to trigger EMAs. Therefore, we propose that future work should focus on a smart trigger that promotes EMA receptivity without influencing affect during sampled time points.

The organization of sleep-wake patterns around daily schedules in college students

Time is a zero-sum game, and consequently, sleep is often sacrificed for waking activities. For college students, daily activities, comprised of scheduled classes, work, study, social and other extracurricular events, are major contributors to insufficient and poor-quality sleep. We investigated the impact of daily schedules on sleep-wake timing in 223 undergraduate students (age: 18-27 years, 37% females) from a United States (U.S.) university, monitored for approximately 30 days. Sleep-wake timing and daily recorded activities (attendance at academic, studying, exercise-based and/or extracurricular activities) were captured by a twice-daily internet-based diary. Wrist-worn actigraphy was conducted to confirm sleep-wake timing. Linear mixed models were used to quantify associations between daily schedule and sleep-wake timing at between-person and within-person levels. Later schedule start time predicted later sleep onset (between and within: p<.001), longer sleep duration on the previous night (within: p<.001), and later wake time (between and within: p<.001). Later schedule end time predicted later sleep onset (between: p<.05, within: p<.001) and shorter sleep duration that night (within: p<.001). For every 1 hour that recorded activities extended beyond 10pm, sleep onset was delayed by 15 minutes at the within-person level and 45 minutes at the between-person level, and sleep duration was shortened by 5 and 23 minutes, respectively. Increased daily documented total activity time predicted earlier wake (between and within: p<.001), later sleep onset that night (within: p<.05), and shorter sleep duration (within: p<.001). These results indicate that daily schedules are an important factor in shaping sleep timing and duration in college students.

AMPAR receptor inhibitors suppress proliferation of human small cell lung cancer cell lines

BACKGROUND

Small cell lung cancer (SCLC) is a neuroendocrine tumor with poor prognosis. Neuroendocrine tumors possess characteristics of both nerve cells and hormone-secreting cells; therefore, targeting the neuronal properties of these tumors may lead to the development of new therapeutic options. Among the endogenous signaling pathways in the nervous system, targeting the glutamate pathway may be a useful strategy for glioblastoma treatment. Perampanel, an antagonist of the synaptic glutamate α-amino-3-hydroxy-5-methyl-4-isoxazole propionic acid receptor (AMPAR), has been reported to be effective in patients with glioblastoma. In this study, we aimed to investigate the antitumor effects of AMPAR antagonists in human SCLC cell lines.

METHODS

We performed to examine the expression of AMPAR using Western blot and immunohistochemical analysis. The antitumor effects of AMPAR antagonists on human SCLC cell lines were investigated in vitro and in vivo. We also analyzed the signaling pathway of AMPAR antagonists in SCLC cell lines. Statistical analysis was performed by the GraphPad Prism 6 software.

RESULTS

We first examined the expression of endogenous AMPAR in six human SCLC cell lines, detecting AMPAR proteins in all of them. Next, we tested the anti-proliferative effect of two AMPAR antagonists, talampanel and cyanquixaline, using SCLC cells in vitro and in vivo. Both AMPAR antagonists inhibited cell proliferation and mitogen-activated protein kinase (MAPK) phosphorylation in SCLC cells in vitro. Further, we observed reduced proliferation of implanted cell lines in an in vivo setting, assessed by Ki-67 immunohistochemistry. Additionally, using immunohistochemical analysis we confirmed AMPAR protein expression in human SCLC samples.

CONCLUSION

AMPAR may be a potential therapeutic target for SCLC.

Effect of an Internet-Delivered Cognitive Behavioral Therapy-Based Sleep Improvement App for Shift Workers at High Risk of Sleep Disorder: Single-Arm, Nonrandomized Trial

BACKGROUND

Shift workers are at high risk of developing sleep disorders such as shift worker sleep disorder or chronic insomnia. Cognitive behavioral therapy (CBT) is the first-line treatment for insomnia, and emerging evidence shows that internet-based CBT is highly effective with additional features such as continuous tracking and personalization. However, there are limited studies on internet-based CBT for shift workers with sleep disorders.

OBJECTIVE

This study aimed to evaluate the impact of a 4-week, physician-assisted, internet-delivered CBT program incorporating machine learning-based well-being prediction on the sleep duration of shift workers at high risk of sleep disorders. We evaluated these outcomes using an internet-delivered CBT app and fitness trackers in the intensive care unit.

METHODS

A convenience sample of 61 shift workers (mean age 32.9, SD 8.3 years) from the intensive care unit or emergency department participated in the study. Eligible participants were on a 3-shift schedule and had a Pittsburgh Sleep Quality Index score ≥5. The study comprised a 1-week baseline period, followed by a 4-week intervention period. Before the study, the participants completed questionnaires regarding the subjective evaluation of sleep, burnout syndrome, and mental health. Participants were asked to wear a commercial fitness tracker to track their daily activities, heart rate, and sleep for 5 weeks. The internet-delivered CBT program included well-being prediction, activity and sleep chart, and sleep advice. A job-based multitask and multilabel convolutional neural network-based model was used for well-being prediction. Participant-specific sleep advice was provided by sleep physicians based on daily surveys and fitness tracker data. The primary end point of this study was sleep duration. For continuous measurements (sleep duration, steps, etc), the mean baseline and week-4 intervention data were compared. The 2-tailed paired t test or Wilcoxon signed rank test was performed depending on the distribution of the data.

RESULTS

In the fourth week of intervention, the mean daily sleep duration for 7 days (6.06, SD 1.30 hours) showed a statistically significant increase compared with the baseline (5.54, SD 1.36 hours; P=.02). Subjective sleep quality, as measured by the Pittsburgh Sleep Quality Index, also showed statistically significant improvement from baseline (9.10) to after the intervention (7.84; P=.001). However, no significant improvement was found in the subjective well-being scores (all P>.05). Feature importance analysis for all 45 variables in the prediction model showed that sleep duration had the highest importance.

CONCLUSIONS

The physician-assisted internet-delivered CBT program targeting shift workers with a high risk of sleep disorders showed a statistically significant increase in sleep duration as measured by wearable sensors along with subjective sleep quality. This study shows that sleep improvement programs using an app and wearable sensors are feasible and may play an important role in preventing shift work-related sleep disorders.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

RR2-10.2196/24799.

Exploiting social graph networks for emotion prediction

Emotion prediction plays an essential role in mental healthcare and emotion-aware computing. The complex nature of emotion resulting from its dependency on a person's physiological health, mental state, and his surroundings makes its prediction a challenging task. In this work, we utilize mobile sensing data to predict self-reported happiness and stress levels. In addition to a person's physiology, we also incorporate the environment's impact through weather and social network. To this end, we leverage phone data to construct social networks and develop a machine learning architecture that aggregates information from multiple users of the graph network and integrates it with the temporal dynamics of data to predict emotion for all users. The construction of social networks does not incur additional costs in terms of ecological momentary assessments or data collection from users and does not raise privacy concerns. We propose an architecture that automates the integration of the user's social network in affect prediction and is capable of dealing with the dynamic distribution of real-life social networks, making it scalable to large-scale networks. The extensive evaluation highlights the prediction performance improvement provided by the integration of social networks. We further investigate the impact of graph topology on the model's performance.

Dynamics of AMPA receptors regulate epileptogenesis in patients with epilepsy

The excitatory glutamate α-amino-3-hydroxy-5-methyl-4-isoxazole propionic acid receptors (AMPARs) contribute to epileptogenesis. Thirty patients with epilepsy and 31 healthy controls are scanned using positron emission tomography with our recently developed radiotracer for AMPARs, [¹¹C]K-2, which measures the density of cell-surface AMPARs. In patients with focal-onset seizures, an increase in AMPAR trafficking augments the amplitude of abnormal gamma activity detected by electroencephalography. In contrast, patients with generalized-onset seizures exhibit a decrease in AMPARs coupled with increased amplitude of abnormal gamma activity. Patients with epilepsy had reduced AMPAR levels compared with healthy controls, and AMPARs are reduced in larger areas of the cortex in patients with generalized-onset seizures compared with those with focal-onset seizures. Thus, epileptic brain function can be regulated by the enhanced trafficking of AMPAR due to Hebbian plasticity with increased simultaneous neuronal firing and compensational downregulation of cell-surface AMPARs by the synaptic scaling.

Psychotic Relapse Prediction in Schizophrenia Patients Using a Personalized Mobile Sensing-Based Supervised Deep Learning Model

Mobile sensing-based modeling of behavioral changes could predict an oncoming psychotic relapse in schizophrenia patients for timely interventions. Deep learning models could complement existing non-deep learning models for relapse prediction by modeling latent behavioral features relevant to the prediction. However, given the inter-individual behavioral differences, model personalization might be required for a predictive model. In this work, we propose RelapsePredNet, a Long Short-Term Memory (LSTM) neural network-based model for relapse prediction. The model is personalized for a particular patient by training using data from patients most similar to the given patient. Several demographics and baseline mental health scores were considered as personalization metrics to define patient similarity. We investigated the effect of personalization on training dataset characteristics, learned embeddings, and relapse prediction performance. We compared RelapsePredNet with a deep learning-based anomaly detection model for relapse prediction. Further, we investigated if RelapsePredNet could complement ClusterRFModel (a random forest model leveraging clustering and template features proposed in prior work) in a fusion model, by identifying latent behavioral features relevant to relapse prediction. The CrossCheck dataset consisting of continuous mobile sensing data obtained from 63 schizophrenia patients, each monitored for up to a year, was used for our evaluations. The proposed RelapsePredNet outperformed the deep learning-based anomaly detection model for relapse prediction. The F2 score for prediction were 0.21 and 0.52 in the full test set and the Relapse Test Set (consisting of data from patients who have had relapse only), respectively. These corresponded to a 29.4% and 38.8% improvement compared to the existing deep learning-based model for relapse prediction. Patients' SFS score was the best personalization metric to define patient similarity. RelapsePredNet complemented the ClusterRFModel as it improved the F2 score by 26.1% with a fusion model, resulting in an F2 score of 0.30 in the full test set.

Clinical characteristics and outcomes of pheochromocytoma crisis: a literature review of 200 cases

PURPOSE

Pheochromocytoma crisis is a life-threatening endocrine emergency that requires prompt diagnosis and treatment. Because of its rarity, sudden onset, and lack of internationally uniform and validated diagnostic criteria, pheochromocytoma crisis remains to be fully clarified. Therefore, we aimed to describe the clinical characteristics and outcomes of pheochromocytoma crisis through a literature review.

METHODS

We performed a systematic literature search of PubMed/MEDLINE database, Igaku-Chuo-Zasshi (Japanese database), and Google Scholar to identify case reports of pheochromocytoma crisis published until February 5, 2021. Information was extracted and analyzed from the literature that reported adequate individual patient data of pheochromocytoma crisis in English or Japanese. Cases were also termed as pheochromocytoma multisystem crisis (PMC) if patients had signs of hyperthermia, multiple organ failure, encephalopathy, and labile blood pressure.

RESULTS

In the 200 cases of pheochromocytoma crisis identified from 187 articles, the mean patient age was 43.8 ± 15.5 years. The most common symptom was headache (39.5%). The heart was the most commonly damaged organ resulting from a complication of a pheochromocytoma crisis (99.0%), followed by the lungs (44.0%) and the kidney (21.5%). PMC accounted for 19.0% of all pheochromocytoma crisis cases. After excluding 12 cases with unknown survival statuses, the mortality rate was 13.8% (26/188 cases). Multivariable logistic regression analysis revealed that nausea and vomiting were significantly associated with a higher mortality rate.

CONCLUSION

Pheochromocytoma can present with different symptomatology, affecting different organ systems. Clinicians should be aware that patients with nausea or vomiting are at a higher risk of death because of pheochromocytoma crisis.

Turning data into better mental health: Past, present, and future

In this mini-review, we discuss the fundamentals of using technology in mental health diagnosis and tracking. We highlight those principles using two clinical concepts: (1) cravings and relapse in the context of addictive disorders and (2) anhedonia in the context of depression. This manuscript is useful for both clinicians wanting to understand the scope of technology use in psychiatry and for computer scientists and engineers wishing to assess psychiatric frameworks useful for diagnosis and treatment. The increase in smartphone ownership and internet connectivity, as well as the accelerated development of wearable devices, have made the observation and analysis of human behavior patterns possible. This has, in turn, paved the way to understand mental health conditions better. These technologies have immense potential in facilitating the diagnosis and tracking of mental health conditions; they also allow the implementation of existing behavioral treatments in new contexts (e.g., remotely, online, and in rural/underserved areas), and the possibility to develop new treatments based on new understanding of behavior patterns. The path to understand how to best use technology in mental health includes the need to match interdisciplinary frameworks from engineering/computer sciences and psychiatry. Thus, we start our review by introducing bio-behavioral sensing, the types of information available, and what behavioral patterns they may reflect and be related to in psychiatric diagnostic frameworks. This information is linked to the use of functional imaging, highlighting how imaging modalities can be considered "ground truth" for mental health/psychiatric dimensions, given the heterogeneity of clinical presentations, and the difficulty of determining what symptom corresponds to what disease. We then discuss how mental health/psychiatric dimensions overlap, yet differ from, psychiatric diagnoses. Using two clinical examples, we highlight the potential agreement areas in assessment/management of anhedonia and cravings. These two dimensions were chosen because of their link to two very prevalent diseases worldwide: depression and addiction. Anhedonia is a core symptom of depression, which is one of the leading causes of disability worldwide. Cravings, the urge to use a substance or perform an action (e.g., shopping, internet), is the leading step before relapse. Lastly, through the manuscript, we discuss potential mental health dimensions.

More to Less (M2L): Enhanced Health Recognition in the Wild with Reduced Modality of Wearable Sensors

Accurately recognizing health-related conditions from wearable data is crucial for improved healthcare outcomes. To improve the recognition accuracy, various approaches have focused on how to effectively fuse information from multiple sensors. Fusing multiple sensors is a common choice in many applications, but may not always be feasible in real-world scenarios. For example, although combining biosignals from multiple sensors (i.e., a chest pad sensor and a wrist wearable sensor) has been proved effective for improved performance, wearing multiple devices might be impractical in the free-living context. To solve the challenges, we propose an effective more to less (M2L) learning framework to improve testing performance with reduced sensors through leveraging the complementary information of multiple modalities during training. More specifically, different sensors may carry different but complementary information, and our model is designed to enforce collaborations among different modalities, where positive knowledge transfer is encouraged and negative knowledge transfer is suppressed, so that better representation is learned for individual modalities. Our experimental results show that our framework achieves comparable performance when compared with the full modalities. Our code and results will be available at https://github.com/comp-well-org/More2Less.git.

Measuring Health-Related Quality of Life With Multimodal Data: Viewpoint

The ability to objectively measure aspects of performance and behavior is a fundamental pillar of digital health, enabling digital wellness products, decentralized trial concepts, evidence generation, digital therapeutics, and more. Emerging multimodal technologies capable of measuring several modalities simultaneously and efforts to integrate inputs across several sources are further expanding the limits of what digital measures can assess. Experts from the field of digital health were convened as part of a multi-stakeholder workshop to examine the progress of multimodal digital measures in two key areas: detection of disease and the measurement of meaningful aspects of health relevant to the quality of life. Here we present a meeting report, summarizing key discussion points, relevant literature, and finally a vision for the immediate future, including how multimodal measures can provide value to stakeholders across drug development and care delivery, as well as three key areas where headway will need to be made if we are to continue to build on the encouraging progress so far: collaboration and data sharing, removal of barriers to data integration, and alignment around robust modular evaluation of new measurement capabilities.

Predicting Psychotic Relapse in Schizophrenia With Mobile Sensor Data: Routine Cluster Analysis

BACKGROUND

Behavioral representations obtained from mobile sensing data can be helpful for the prediction of an oncoming psychotic relapse in patients with schizophrenia and the delivery of timely interventions to mitigate such relapse.

OBJECTIVE

In this study, we aim to develop clustering models to obtain behavioral representations from continuous multimodal mobile sensing data for relapse prediction tasks. The identified clusters can represent different routine behavioral trends related to daily living of patients and atypical behavioral trends associated with impending relapse.

METHODS

We used the mobile sensing data obtained from the CrossCheck project for our analysis. Continuous data from six different mobile sensing-based modalities (ambient light, sound, conversation, acceleration, etc) obtained from 63 patients with schizophrenia, each monitored for up to a year, were used for the clustering models and relapse prediction evaluation. Two clustering models, Gaussian mixture model (GMM) and partition around medoids (PAM), were used to obtain behavioral representations from the mobile sensing data. These models have different notions of similarity between behaviors as represented by the mobile sensing data, and thus, provide different behavioral characterizations. The features obtained from the clustering models were used to train and evaluate a personalized relapse prediction model using balanced random forest. The personalization was performed by identifying optimal features for a given patient based on a personalization subset consisting of other patients of similar age.

RESULTS

The clusters identified using the GMM and PAM models were found to represent different behavioral patterns (such as clusters representing sedentary days, active days but with low communication, etc). Although GMM-based models better characterized routine behaviors by discovering dense clusters with low cluster spread, some other identified clusters had a larger cluster spread, likely indicating heterogeneous behavioral characterizations. On the other hand, PAM model-based clusters had lower variability of cluster spread, indicating more homogeneous behavioral characterization in the obtained clusters. Significant changes near the relapse periods were observed in the obtained behavioral representation features from the clustering models. The clustering model-based features, together with other features characterizing the mobile sensing data, resulted in an F2 score of 0.23 for the relapse prediction task in a leave-one-patient-out evaluation setting. The obtained F2 score was significantly higher than that of a random classification baseline with an average F2 score of 0.042.

CONCLUSIONS

Mobile sensing can capture behavioral trends using different sensing modalities. Clustering of the daily mobile sensing data may help discover routine and atypical behavioral trends. In this study, we used GMM-based and PAM-based cluster models to obtain behavioral trends in patients with schizophrenia. The features derived from the cluster models were found to be predictive for detecting an oncoming psychotic relapse. Such relapse prediction models can be helpful in enabling timely interventions.

Health Label and Behavioral Feature Prediction Using Bayesian Hierarchical Vector Autoregression Models

The rising availability and accessibility of data from wearable devices and ubiquitous sensors allow the leveraging of computational methods to address human health and behavioral challenges. In particular, recent works have created time series, interpretable, and generalizable models for predicting patient healthcare outcomes from multidimensional data including expensive self-reported patient data, clinical data, and data from mobile and wearable devices. In this work, we used a Bayesian Hierarchical Vector Autoregression (BHVAR) model to predict behavioral and self-reported health outcomes on college student participants from passively collected data from their smartphones, wearable devices, and environment, as well as their self-reports. We also evaluated how the model performed being trained on 3, 7, 11, and 13 different features including some actionable and modifiable behavioral features. Then, we showed the value of augmenting self-reported datasets with many different types of data by demonstrating that additional inferences can be made with no significant toll on accuracy in comparison to using only self-reported features. Our models proved to be robust despite the greatly increased variable count as the reduced mean squared error (RMSE) of BHVAR over the patient-specific, maximum likelihood estimate (MLE) model was 10.5%, 14.9%, 26.6%, 39.6% in the 3, 7, 11, and 13 variable models respectively. We also obtained patient-level insights from clustering analysis of patient-level coefficients.

A classification approach to estimating human circadian phase under circadian alignment from actigraphy and photometry data

The time of dim light melatonin onset (DLMO) is the gold standard for circadian phase assessment in humans, but collection of samples for DLMO is time and resource-intensive. Numerous studies have attempted to estimate circadian phase from actigraphy data, but most of these studies have involved individuals on controlled and stable sleep-wake schedules, with mean errors reported between 0.5 and 1 hour. We found that such algorithms are less successful in estimating DLMO in a population of college students with more irregular schedules: Mean errors in estimating the time of DLMO are approximately 1.5-1.6 hours. We reframed the problem as a classification problem and estimated whether an individual's current phase was before or after DLMO. Using a neural network, we found high classification accuracy of about 90%, which decreased the mean error in DLMO estimation-identifying the time at which the switch in classification occurs-to approximately 1.3 hours. To test whether this classification approach was valid when activity and circadian rhythms are decoupled, we applied the same neural network to data from inpatient forced desynchrony studies in which participants are scheduled to sleep and wake at all circadian phases (rather than their habitual schedules). In participants on forced desynchrony protocols, overall classification accuracy dropped to 55%-65% with a range of 20%-80% for a given day; this accuracy was highly dependent upon the phase angle (ie, time) between DLMO and sleep onset, with the highest accuracy at phase angles associated with nighttime sleep. Circadian patterns in activity, therefore, should be included when developing and testing actigraphy-based approaches to circadian phase estimation. Our novel algorithm may be a promising approach for estimating the onset of melatonin in some conditions and could be generalized to other hormones.

[11C]K-2 image with positron emission tomography represents cell surface AMPA receptors

The glutamate α-amino-3-hydroxy-5-methyl-4-isoxazole propionic acid receptors (AMPARs) is an important molecule in neurotransmission. We have recently developed the first positron emission tomography (PET) tracer [¹¹C]K-2 to visualize and quantify AMPARs in the living human brain. After injection, [¹¹C]K-2 is hydrolyzed at the terminal amide (and is thus metabolized to a major metabolite, [¹¹C]K-2_OH) within 10 min, representing the PET image in rodents and humans. Here, we found that K-2_OH did not penetrate the cell membrane but slowly passed through the blood brain barrier (BBB) with paracellular transport. Furthermore, major efflux transporters in the BBB did not carry K-2_OH. Logan graphical analysis exhibited reversible binding kinetics of this radiotracer in healthy individuals; these results demonstrated that the PET image of this tracer represents cell surface AMPARs with passive penetration of [¹¹C]K-2_OH through the BBB, resulting in reversible binding kinetics. Thus, PET images with this tracer depict the physiologically crucial fraction of AMPARs.

Robust stability of melatonin circadian phase, sleep metrics, and chronotype across months in young adults living in real-world settings

Appropriate synchronization of the timing of behaviors with the circadian clock and adequate sleep are both important for almost every physiological process. The timing of the circadian clock relative to social (ie, local) clock time and the timing of sleep can vary greatly among individuals. Whether the timing of these processes is stable within an individual is not well-understood. We examined the stability of circadian-controlled melatonin timing, sleep timing, and their interaction across ~ 100 days in 15 students at a single university. At three time points ~ 35-days apart, circadian timing was determined from the dim-light melatonin onset (DLMO). Sleep behaviors (timing and duration) and chronotype (ie, mid-sleep time on free days corrected for sleep loss on school/work days) were determined via actigraphy and analyzed in ~ 1-month bins. Melatonin timing was stable, with an almost perfect relationship strength as determined via intraclass correlation coefficients ([ICC]=0.85); average DLMO timing across all participants only changed from the first month by 21 minutes in month 2 and 5 minutes in month 3. Sleep behaviors also demonstrated high stability, with ICC relationship strengths ranging from substantial to almost perfect (ICCs = 0.65-0.85). Average DLMO was significantly associated with average chronotype (r²  = 0.53, P <.01), with chronotype displaying substantial stability across months (ICC = 0.61). These findings of a robust stability in melatonin timing and sleep behaviors in young adults living in real-world settings holds promise for a better understanding of the reliability of previous cross-sectional reports and for the future individualized strategies to combat circadian-associated disease and impaired safety (ie, "chronomedicine").

Activity-induced secretion of semaphorin 3A mediates learning

The semaphorin family is a well‐characterized family of secreted or membrane‐bound proteins that are involved in activity‐independent neurodevelopmental processes, such as axon guidance, cell migration, and immune functions. Although semaphorins have recently been demonstrated to regulate activity‐dependent synaptic scaling, their roles in Hebbian synaptic plasticity as well as learning and memory remain poorly understood. Here, using a rodent model, we found that an inhibitory avoidance task, a hippocampus‐dependent contextual learning paradigm, increased secretion of semaphorin 3A in the hippocampus. Furthermore, the secreted semaphorin 3A in the hippocampus mediated contextual memory formation likely by driving AMPA receptors into hippocampal synapses via the neuropilin1–plexin A4–semaphorin receptor complex. This signaling process involves alteration of the phosphorylation status of collapsin response mediator protein 2, which has been characterized as a downstream molecule in semaphorin signaling. These findings implicate semaphorin family as a regulator of Hebbian synaptic plasticity and learning.

Internet-Based Individualized Cognitive Behavioral Therapy for Shift Work Sleep Disorder Empowered by Well-Being Prediction: Protocol for a Pilot Study

Background

Shift work sleep disorders (SWSDs) are associated with the high turnover rates of nurses, and are considered a major medical safety issue. However, initial management can be hampered by insufficient awareness. In recent years, it has become possible to visualize, collect, and analyze the work-life balance of health care workers with irregular sleeping and working habits using wearable sensors that can continuously monitor biometric data under real-life settings. In addition, internet-based cognitive behavioral therapy for psychiatric disorders has been shown to be effective. Application of wearable sensors and machine learning may potentially enhance the beneficial effects of internet-based cognitive behavioral therapy.

Objective

In this study, we aim to develop and evaluate the effect of a new internet-based cognitive behavioral therapy for SWSD (iCBTS). This system includes current methods such as medical sleep advice, as well as machine learning well-being prediction to improve the sleep durations of shift workers and prevent declines in their well-being.

Methods

This study consists of two phases: (1) preliminary data collection and machine learning for well-being prediction; (2) intervention and evaluation of iCBTS for SWSD. Shift workers in the intensive care unit at Mie University Hospital will wear a wearable sensor that collects biometric data and answer daily questionnaires regarding their well-being. They will subsequently be provided with an iCBTS app for 4 weeks. Sleep and well-being measurements between baseline and the intervention period will be compared.

Results

Recruitment for phase 1 ended in October 2019. Recruitment for phase 2 has started in October 2020. Preliminary results are expected to be available by summer 2021.

Conclusions

iCBTS empowered with well-being prediction is expected to improve the sleep durations of shift workers, thereby enhancing their overall well-being. Findings of this study will reveal the potential of this system for improving sleep disorders among shift workers.

Trial Registration

UMIN Clinical Trials Registry UMIN000036122 (phase 1), UMIN000040547 (phase 2); https://tinyurl.com/dkfmmmje, https://upload.umin.ac.jp/cgi-open-bin/ctr_e/ctr_view.cgi?recptno=R000046284

International Registered Report Identifier (IRRID)

DERR1-10.2196/24799

Using Mobile Sensors to Study Personality Dynamics

Abstract. Research interest in personality dynamics over time is rapidly growing. Passive personality assessment via mobile sensors offers an intriguing new approach for measuring a wide variety of personality dynamics. In this paper, we address the possibility of integrating sensor-based assessments to enhance personality dynamics research. We consider a variety of research designs that can incorporate sensor-based measures and address pitfalls and limitations in terms of psychometrics and practical implementation. We also consider analytic challenges related to data quality and model evaluation that researchers must address when applying machine learning methods to translate sensor data into composite personality assessments.

Passive Sensor Data Based Future Mood, Health, and Stress Prediction: User Adaptation Using Deep Learning

Predicting one's mood, health, and stress in the future may provide useful feedback before wellbeing related problems become severe. Previously, researchers developed participant-dependent wellbeing prediction models using mobile and wearable sensors, where the models were trained and tested with the same group of people. However, in real-world applications, it is essential to consider the adaptability of the developed models to new users for predicting new users' wellbeing immediately and accurately. In this paper, we built wellbeing prediction models using passively sensed data from wearable sensors, mobile phones, and weather API, and deep learning methods, and evaluated the models with the data from new users. We compared deep long short-term memory (LSTM) network and the combination of convolutional neural network (CNN) and the LSTM model. We found that our deep LSTM model provided performances, in mean absolute error (MAE), as 15.7, 15.6, and 16.8 out of 100 in predicting self-reported mood, health, and stress respectively for new users. Furthermore, we applied a fine-tuning transfer learning method based on our deep LSTM model, which provided new participants with more accurate predictions, especially when the volume of new participants' data was limited. The transfer learning model improved the MAE performances to 13.5, 13.2, and 14.4 out of 100 for mood, health, and stress, respectively.

Frequency-Dependent Light Stimulation Effects on Performance During Vigilance Tasks on a Laptop

Students, office workers, or other computer and mobile device users can suffer from decrements in alertness or productivity, but many intervention methods on these can be too distracting or even affect daily routines. Using heart rate (HR) to determine a fast and slow target frequency at which to oscillate light brightness stimulation on a laptop, thirty-six participants joined a cognitive task where we hypothesized that fast frequency stimulation would increase alertness and decrease relaxation, while slow frequency stimulation would have the opposite effects. We found that slow frequency stimulation produces a statistically significant delay in response time, users react more slowly (3.8e2 ± 5.5e1 ms), when compared to the no stimulation (3.7e2 ± 4.1e1 ms) (p = 9.0e-3) conditions. The (Slow - No Stimulation) response time (1.7e1 ± 2.7e2 ms) produced a statistically significant delay in response time versus the (Fast - No Stimulation) response time (-0.74 ± 2.4e1 ms) (p = .016). These delays due to slow stimulation occurred without influencing accuracy or subjective sleepiness ratings. We observed that frequency-dependent light stimulation can potentially influence HRV metrics such as the mean normal-to-normal intervals and mean HR. Future work will target breathing rate to determine light stimulation oscillations as we further investigate the potential of using the slow-frequency domain to unobtrusively influence user performance and physiology.

Forecasting stress, mood, and health from daytime physiology in office workers and students

We examine the problem of forecasting tomorrow morning's three self-reported levels (on scales from 0 to 100) of stressed-calm, sad-happy, and sick-healthy based on physiological data (skin conductance, skin temperature, and acceleration) from a sensor worn on the wrist from 10am-5pm today. We train automated forecasting regression algorithms using Random Forests and compare their performance over two sets of data: "workers" consisting of 490 days of weekday data from 39 employees at a high-tech company in Japan and "students" consisting of 3,841 days of weekday data from 201 New England USA college students. Mean absolute errors on held-out test data achieved 10.8, 13.5, and 14.4 for the estimated levels of mood, stress, and health respectively of office workers, and 17.8, 20.3, and 20.4 for the mood, stress, and health respectively of students. Overall the two groups reported comparable stress and mood scores, while employees reported slightly poorer health, and engaged in significantly lower levels of physical activity as measured by accelerometers. We further examine differences in population features and how systems trained on each population performed when tested on the other.

Using behavioral rhythms and multi-task learning to predict fine-grained symptoms of schizophrenia

Schizophrenia is a severe and complex psychiatric disorder with heterogeneous and dynamic multi-dimensional symptoms. Behavioral rhythms, such as sleep rhythm, are usually disrupted in people with schizophrenia. As such, behavioral rhythm sensing with smartphones and machine learning can help better understand and predict their symptoms. Our goal is to predict fine-grained symptom changes with interpretable models. We computed rhythm-based features from 61 participants with 6,132 days of data and used multi-task learning to predict their ecological momentary assessment scores for 10 different symptom items. By taking into account both the similarities and differences between different participants and symptoms, our multi-task learning models perform statistically significantly better than the models trained with single-task learning for predicting patients' individual symptom trajectories, such as feeling depressed, social, and calm and hearing voices. We also found different subtypes for each of the symptoms by applying unsupervised clustering to the feature weights in the models. Taken together, compared to the features used in the previous studies, our rhythm features not only improved models' prediction accuracy but also provided better interpretability for how patients' behavioral rhythms and the rhythms of their environments influence their symptom conditions. This will enable both the patients and clinicians to monitor how these factors affect a patient's condition and how to mitigate the influence of these factors. As such, we envision that our solution allows early detection and early intervention before a patient's condition starts deteriorating without requiring extra effort from patients and clinicians.

Early versus Late Modality Fusion of Deep Wearable Sensor Features for Personalized Prediction of Tomorrow's Mood, Health, and Stress. Annu Int Conf IEEE Eng Med Biol Soc 2020;2020:5896-5899. [PMID: 33019316 DOI: 10.1109/embc44109.2020.9175463] [Citation(s) in RCA: 0] [Impact Index Per Article: 0]

Predicting mood, health, and stress can sound an early alarm against mental illness. Multi-modal data from wearable sensors provide rigorous and rich insights into one's internal states. Recently, deep learning-based features on continuous high-resolution sensor data have outperformed statistical features in several ubiquitous and affective computing applications including sleep detection and depression diagnosis. Motivated by this, we investigate multi-modal data fusion strategies featuring deep representation learning of skin conductance, skin temperature, and acceleration data to predict self-reported mood, health, and stress scores (0 - 100) of college students (N = 239). Our cross-validated results from the early fusion framework exhibit a significantly higher (p <; 0.05) prediction precision over the late fusion for unseen users. Therefore, our findings call attention to the benefits of fusing physiological data modalities at a low level and corroborate the predictive efficacy of the deeply learned features.

Irregular sleep and event schedules are associated with poorer self-reported well-being in US college students

STUDY OBJECTIVES

Sleep regularity, in addition to duration and timing, is predictive of daily variations in well-being. One possible contributor to changes in these sleep dimensions are early morning scheduled events. We applied a composite metric-the Composite Phase Deviation (CPD)-to assess mistiming and irregularity of both sleep and event schedules to examine their relationship with self-reported well-being in US college students.

METHODS

Daily well-being, actigraphy, and timing of sleep and first scheduled events (academic/exercise/other) were collected for approximately 30 days from 223 US college students (37% females) between 2013 and 2016. Participants rated well-being daily upon awakening on five scales: Sleepy-Alert, Sad-Happy, Sluggish-Energetic, Sick-Healthy, and Stressed-Calm. A longitudinal growth model with time-varying covariates was used to assess relationships between sleep variables (i.e. CPDSleep, sleep duration, and midsleep time) and daily and average well-being. Cluster analysis was used to examine relationships between CPD for sleep vs. event schedules.

RESULTS

CPD for sleep was a significant predictor of average well-being (e.g. Stressed-Calm: b = -6.3, p < 0.01), whereas sleep duration was a significant predictor of daily well-being (Stressed-Calm, b = 1.0, p < 0.001). Although cluster analysis revealed no systematic relationship between CPD for sleep vs. event schedules (i.e. more mistimed/irregular events were not associated with more mistimed/irregular sleep), they interacted upon well-being: the poorest well-being was reported by students for whom both sleep and event schedules were mistimed and irregular.

CONCLUSIONS

Sleep regularity and duration may be risk factors for lower well-being in college students. Stabilizing sleep and/or event schedules may help improve well-being.

CLINICAL TRIAL REGISTRATION

NCT02846077.

Extraction and Interpretation of Deep Autoencoder-based Temporal Features from Wearables for Forecasting Personalized Mood, Health, and Stress

Continuous wearable sensor data in high resolution contain physiological and behavioral information that can be utilized to predict human health and wellbeing, establishing the foundation for developing early warning systems to eventually improve human health and wellbeing. We propose a deep neural network framework, the Locally Connected Long Short-Term Memory Denoising AutoEncoder (LC-LSTM-DAE), to automatically extract features from passively collected raw sensor data and perform personalized prediction of self-reported mood, health, and stress scores with high precision. We enabled personalized learning of features by finetuning the general representation model with participant-specific data. The framework was evaluated using wearable sensor data and wellbeing labels collected from college students (total 6391 days from N=239). Sensor data include skin temperature, skin conductance, and acceleration; wellbeing labels include self-reported mood, health and stress scored 0 - 100. Compared to the prediction performance based on hand-crafted features, the proposed framework achieved higher precision with a smaller number of features. We also provide statistical interpretation and visual explanation to the automatically learned features and the prediction models. Our results show the possibility of predicting self-reported mood, health, and stress accurately using an interpretable deep learning framework, ultimately for developing real-time health and wellbeing monitoring and intervention systems that can benefit various populations.

Personalized Multitask Learning for Predicting Tomorrow's Mood, Stress, and Health

While accurately predicting mood and wellbeing could have a number of important clinical benefits, traditional machine learning (ML) methods frequently yield low performance in this domain. We posit that this is because a one-size-fits-all machine learning model is inherently ill-suited to predicting outcomes like mood and stress, which vary greatly due to individual differences. Therefore, we employ Multitask Learning (MTL) techniques to train personalized ML models which are customized to the needs of each individual, but still leverage data from across the population. Three formulations of MTL are compared: i) MTL deep neural networks, which share several hidden layers but have final layers unique to each task; ii) Multi-task Multi-Kernel learning, which feeds information across tasks through kernel weights on feature types; and iii) a Hierarchical Bayesian model in which tasks share a common Dirichlet Process prior. We offer the code for this work in open source. These techniques are investigated in the context of predicting future mood, stress, and health using data collected from surveys, wearable sensors, smartphone logs, and the weather. Empirical results demonstrate that using MTL to account for individual differences provides large performance improvements over traditional machine learning methods and provides personalized, actionable insights.

Mobile Sensing of Alertness, Sleep and Circadian Rhythm

Human biology is deeply rooted in the daily 24-hour temporal period. Our biochemistry varies significantly and idiosyncratically over the course of a day. Staying out of sync with one's circadian rhythm can lead to many complications over time, including a higher likelihood for cardiovascular disease, cancer, obesity, and mental health problems [1]. Constant changes in daily rhythm due to shift work has been shown to increase risk factors for cancer, obesity, and Type 2 diabetes. Moreover, the advent of technology and the resultant always-on ethos can cause rhythm disruption on personal and societal levels for about 70% of the population [2].

Circadian disruption can also cause a serious deficit in cognitive performance. In particular, alertness - a key biological process underlying our cognitive performance - reflects circadian rhythms [3]. Sleep deprivation and circadian disruption can result in poor alertness and reaction time [3]. The decline in cognitive performance after 20 to 25 hours of wakefulness is equivalent to a Blood Alcohol Concentration (BAC) of 0.10% [4]. To compare, in New York State, a BAC of more than 0.05% is considered "impaired" and 0.08% is considered "intoxicated" [5]. In other words, the effects of sustained sleep deprivation and circadian disruption on cognitive performance is similar (or worse) to being intoxicated.

Daytime Data and LSTM can Forecast Tomorrow's Stress, Health, and Happiness

Accurately forecasting well-being may enable people to make desirable behavioral changes that could improve their future well-being. In this paper, we evaluate how well an automated model can forecast the next-day's well-being (specifically focusing on stress, health, and happiness) from static models (support vector machine and logistic regression) and time-series models (long short-term memory neural network models (LSTM)) using the previous seven days of physiological, mobile phone, and behavioral survey data. We especially examine how using only a portion of the day's data (e.g. just night-time, or just daytime) influences the forecasting accuracy. The results show that accuracy is improved, across every condition tested, by using an LSTM instead of using static models. We find that daytime-only physiology data from wearable sensors, using an LSTM, can provide an accurate forecast of tomorrow's well-being using students' daily life data (stress: 80.4%, health: 86.0%, and happiness: 79.1%), achieving the same accuracy as using data collected from around the clock. These findings are valuable steps toward developing a practical and convenient well-being forecasting system.

Multimodal Ambulatory Sleep Detection Using LSTM Recurrent Neural Networks

Unobtrusive and accurate ambulatory methods are needed to monitor long-term sleep patterns for improving health. Previously developed ambulatory sleep detection methods rely either in whole or in part on self-reported diary data as ground truth, which is a problem, since people often do not fill them out accurately. This paper presents an algorithm that uses multimodal data from smartphones and wearable technologies to detect sleep/wake state and sleep onset/offset using a type of recurrent neural network with long-short-term memory (LSTM) cells for synthesizing temporal information. We collected 5580 days of multimodal data from 186 participants and compared the new method for sleep/wake classification and sleep onset/offset detection to, first, nontemporal machine learning methods and, second, a state-of-the-art actigraphy software. The new LSTM method achieved a sleep/wake classification accuracy of 96.5%, and sleep onset/offset detection F₁ scores of 0.86 and 0.84, respectively, with mean absolute errors of 5.0 and 5.5 min, res-pectively, when compared with sleep/wake state and sleep onset/offset assessed using actigraphy and sleep diaries. The LSTM results were statistically superior to those from nontemporal machine learning algorithms and the actigraphy software. We show good generalization of the new algorithm by comparing participant-dependent and participant-independent models, and we show how to make the model nearly realtime with slightly reduced performance.

Identifying Objective Physiological Markers and Modifiable Behaviors for Self-Reported Stress and Mental Health Status Using Wearable Sensors and Mobile Phones: Observational Study

Background

Wearable and mobile devices that capture multimodal data have the potential to identify risk factors for high stress and poor mental health and to provide information to improve health and well-being.

Objective

We developed new tools that provide objective physiological and behavioral measures using wearable sensors and mobile phones, together with methods that improve their data integrity. The aim of this study was to examine, using machine learning, how accurately these measures could identify conditions of self-reported high stress and poor mental health and which of the underlying modalities and measures were most accurate in identifying those conditions.

Methods

We designed and conducted the 1-month SNAPSHOT study that investigated how daily behaviors and social networks influence self-reported stress, mood, and other health or well-being-related factors. We collected over 145,000 hours of data from 201 college students (age: 18-25 years, male:female=1.8:1) at one university, all recruited within self-identified social groups. Each student filled out standardized pre- and postquestionnaires on stress and mental health; during the month, each student completed twice-daily electronic diaries (e-diaries), wore two wrist-based sensors that recorded continuous physical activity and autonomic physiology, and installed an app on their mobile phone that recorded phone usage and geolocation patterns. We developed tools to make data collection more efficient, including data-check systems for sensor and mobile phone data and an e-diary administrative module for study investigators to locate possible errors in the e-diaries and communicate with participants to correct their entries promptly, which reduced the time taken to clean e-diary data by 69%. We constructed features and applied machine learning to the multimodal data to identify factors associated with self-reported poststudy stress and mental health, including behaviors that can be possibly modified by the individual to improve these measures.

Results

We identified the physiological sensor, phone, mobility, and modifiable behavior features that were best predictors for stress and mental health classification. In general, wearable sensor features showed better classification performance than mobile phone or modifiable behavior features. Wearable sensor features, including skin conductance and temperature, reached 78.3% (148/189) accuracy for classifying students into high or low stress groups and 87% (41/47) accuracy for classifying high or low mental health groups. Modifiable behavior features, including number of naps, studying duration, calls, mobility patterns, and phone-screen-on time, reached 73.5% (139/189) accuracy for stress classification and 79% (37/47) accuracy for mental health classification.

Conclusions

New semiautomated tools improved the efficiency of long-term ambulatory data collection from wearable and mobile devices. Applying machine learning to the resulting data revealed a set of both objective features and modifiable behavioral features that could classify self-reported high or low stress and mental health groups in a college student population better than previous studies and showed new insights into digital phenotyping.

CRMP2-binding compound, edonerpic maleate, accelerates motor function recovery from brain damage

Brain damage such as stroke is a devastating neurological condition that may severely compromise patient quality of life. No effective medication-mediated intervention to accelerate rehabilitation has been established. We found that a small compound, edonerpic maleate, facilitated experience-driven synaptic glutamate AMPA (α-amino-3-hydroxy-5-methyl-4-isoxazole-propionic-acid) receptor delivery and resulted in the acceleration of motor function recovery after motor cortex cryoinjury in mice in a training-dependent manner through cortical reorganization. Edonerpic bound to collapsin-response-mediator-protein 2 (CRMP2) and failed to augment recovery in CRMP2-deficient mice. Edonerpic maleate enhanced motor function recovery from internal capsule hemorrhage in nonhuman primates. Thus, edonerpic maleate, a neural plasticity enhancer, could be a clinically potent small compound with which to accelerate rehabilitation after brain damage.

QuantifyMe: An Open-Source Automated Single-Case Experimental Design Platform

Smartphones and wearable sensors have enabled unprecedented data collection, with many products now providing feedback to users about recommended step counts or sleep durations. However, these recommendations do not provide personalized insights that have been shown to be best suited for a specific individual. A scientific way to find individualized recommendations and causal links is to conduct experiments using single-case experimental design; however, properly designed single-case experiments are not easy to conduct on oneself. We designed, developed, and evaluated a novel platform, QuantifyMe, for novice self-experimenters to conduct proper-methodology single-case self-experiments in an automated and scientific manner using their smartphones. We provide software for the platform that we used (available for free on GitHub), which provides the methodological elements to run many kinds of customized studies. In this work, we evaluate its use with four different kinds of personalized investigations, examining how variables such as sleep duration and regularity, activity, and leisure time affect personal happiness, stress, productivity, and sleep efficiency. We conducted a six-week pilot study (N = 13) to evaluate QuantifyMe. We describe the lessons learned developing the platform and recommendations for its improvement, as well as its potential for enabling personalized insights to be scientifically evaluated in many individuals, reducing the high administrative cost for advancing human health and wellbeing.

Irregular sleep/wake patterns are associated with poorer academic performance and delayed circadian and sleep/wake timing

The association of irregular sleep schedules with circadian timing and academic performance has not been systematically examined. We studied 61 undergraduates for 30 days using sleep diaries, and quantified sleep regularity using a novel metric, the sleep regularity index (SRI). In the most and least regular quintiles, circadian phase and light exposure were assessed using salivary dim-light melatonin onset (DLMO) and wrist-worn photometry, respectively. DLMO occurred later (00:08 ± 1:54 vs. 21:32 ± 1:48; p < 0.003); the daily sleep propensity rhythm peaked later (06:33 ± 0:19 vs. 04:45 ± 0:11; p < 0.005); and light rhythms had lower amplitude (102 ± 19 lux vs. 179 ± 29 lux; p < 0.005) in Irregular compared to Regular sleepers. A mathematical model of the circadian pacemaker and its response to light was used to demonstrate that Irregular vs. Regular group differences in circadian timing were likely primarily due to their different patterns of light exposure. A positive correlation (r = 0.37; p < 0.004) between academic performance and SRI was observed. These findings show that irregular sleep and light exposure patterns in college students are associated with delayed circadian rhythms and lower academic performance. Moreover, the modeling results reveal that light-based interventions may be therapeutically effective in improving sleep regularity in this population.

Multimodal Ambulatory Sleep Detection

Inadequate sleep affects health in multiple ways. Unobtrusive ambulatory methods to monitor long-term sleep patterns in large populations could be useful for health and policy decisions. This paper presents an algorithm that uses multimodal data from smartphones and wearable technologies to detect sleep/wake state and sleep episode on/offset. We collected 5580 days of multimodal data and applied recurrent neural networks for sleep/wake classification, followed by cross-correlation-based template matching for sleep episode on/offset detection. The method achieved a sleep/wake classification accuracy of 96.5%, and sleep episode on/offset detection F1 scores of 0.85 and 0.82, respectively, with mean errors of 5.3 and 5.5 min, respectively, when compared with sleep/wake state and sleep episode on/offset assessed using actigraphy and sleep diaries.

Neonatal isolation augments social dominance by altering actin dynamics in the medial prefrontal cortex

Social separation early in life can lead to the development of impaired interpersonal relationships and profound social disorders. However, the underlying cellular and molecular mechanisms involved are largely unknown. Here, we found that isolation of neonatal rats induced glucocorticoid-dependent social dominance over nonisolated control rats in juveniles from the same litter. Furthermore, neonatal isolation inactivated the actin-depolymerizing factor (ADF)/cofilin in the juvenile medial prefrontal cortex (mPFC). Isolation-induced inactivation of ADF/cofilin increased stable actin fractions at dendritic spines in the juvenile mPFC, decreasing glutamate synaptic AMPA receptors. Expression of constitutively active ADF/cofilin in the mPFC rescued the effect of isolation on social dominance. Thus, neonatal isolation affects spines in the mPFC by reducing actin dynamics, leading to altered social behavior later in life.

Preoperative prediction for regaining ambulatory ability in paretic non-ambulatory patients with metastatic spinal cord compression

STUDY DESIGN

Retrospective multicenter study.

OBJECTIVES

To analyze the predictive factors for postoperative ambulatory recovery in paretic non-ambulatory patients with metastatic spinal cord compression (MSCC).

SETTING

Japan.

METHODS

Eighty-two consecutive patients (74.4% men; mean age, 66.2 years) who could not walk before surgery due to cervical or thoracic MSCC and underwent posterior decompressive surgery between 2003 and 2014 were included. Patients were divided into two groups according to ambulatory status at 6 weeks after surgery: recovery (group R) and non-recovery (group NR). To evaluate the speed of progression of motor deficits, we assessed the period from onset of neurological symptoms to gait inability (T1).

RESULTS

Fifty patients (61.0%) regained the ability to walk (group R). The period of T1 demonstrated a positive correlation with probability of ambulatory recovery (P=0.00; Kendall's tau-b=0.38), and a receiver operating characteristic curve analysis showed that the cutoff value of T1 was 5 days (area under the curve=0.72; P=0.001). In multivariate analysis, <6 days of T1 was one of the independent risk factors for failing to regain ambulatory ability (odds ratio, 8.74; P=0.00).

CONCLUSIONS

The speed of progression of motor deficits can independently and powerfully predict the chance of postoperative ambulatory recovery as well as previously identified predictors. Since information about the speed of progression can be obtained easily by interviewing patients or family members, even if the patient is in an urgent state, our results will be helpful in clinical decision-making.

Comparison of sleep-wake classification using electroencephalogram and wrist-worn multi-modal sensor data

This paper presents the comparison of sleep-wake classification using electroencephalogram (EEG) and multi-modal data from a wrist wearable sensor. We collected physiological data while participants were in bed: EEG, skin conductance (SC), skin temperature (ST), and acceleration (ACC) data, from 15 college students, computed the features and compared the intra-/inter-subject classification results. As results, EEG features showed 83% while features from a wrist wearable sensor showed 74% and the combination of ACC and ST played more important roles in sleep/wake classification.