A holistic approach for suppression of COVID-19 spread in workplaces and universities.

As society has moved past the initial phase of the COVID-19 crisis that relied on broad-spectrum shutdowns as a stopgap method, industries and institutions have faced the daunting question of how to return to a stabilized state of activities and more fully reopen the economy. A core problem is how to return people to their workplaces and educational institutions in a manner that is safe, ethical, grounded in science, and takes into account the unique factors and needs of each organization and community. In this paper, we introduce an epidemiological model (the "Community-Workplace" model) that accounts for SARS-CoV-2 transmission within the workplace, within the surrounding community, and between them. We use this multi-group deterministic compartmental model to consider various testing strategies that, together with symptom screening, exposure tracking, and nonpharmaceutical interventions (NPI) such as mask wearing and physical distancing, aim to reduce disease spread in the workplace. Our framework is designed to be adaptable to a variety of specific workplace environments to support planning efforts as reopenings continue. Using this model, we consider a number of case studies, including an office workplace, a factory floor, and a university campus. Analysis of these cases illustrates that continuous testing can help a workplace avoid an outbreak by reducing undetected infectiousness even in high-contact environments. We find that a university setting, where individuals spend more time on campus and have a higher contact load, requires more testing to remain safe, compared to a factory or office setting. Under the modeling assumptions, we find that maintaining a prevalence below 3% can be achieved in an office setting by testing its workforce every two weeks, whereas achieving this same goal for a university could require as much as fourfold more testing (i.e., testing the entire campus population twice a week). Our model also simulates the dynamics of reduced spread that result from the introduction of mitigation measures when test results reveal the early stages of a workplace outbreak. We use this to show that a vigilant university that has the ability to quickly react to outbreaks can be justified in implementing testing at the same rate as a lower-risk office workplace. Finally, we quantify the devastating impact that an outbreak in a small-town college could have on the surrounding community, which supports the notion that communities can be better protected by supporting their local places of business in preventing onsite spread of disease.

Relationship Between Sleep Quality and Mood: Ecological Momentary Assessment Study.

BACKGROUND: Sleep disturbances play an important role in everyday affect and vice versa. However, the causal day-to-day interaction between sleep and mood has not been thoroughly explored, partly because of the lack of daily assessment data. Mobile phones enable us to collect ecological momentary assessment data on a daily basis in a noninvasive manner. OBJECTIVE: This study aimed to investigate the relationship between self-reported daily mood and sleep quality. METHODS: A total of 208 adult participants were recruited to report mood and sleep patterns daily via their mobile phones for 6 consecutive weeks. Participants were recruited in 4 roughly equal groups: depressed and anxious, depressed only, anxious only, and controls. The effect of daily mood on sleep quality and vice versa were assessed using mixed effects models and propensity score matching. RESULTS: All methods showed a significant effect of sleep quality on mood and vice versa. However, within individuals, the effect of sleep quality on next-day mood was much larger than the effect of previous-day mood on sleep quality. We did not find these effects to be confounded by the participants' past mood and sleep quality or other variables such as stress, physical activity, and weather conditions. CONCLUSIONS: We found that daily sleep quality and mood are related, with the effect of sleep quality on mood being significantly larger than the reverse. Correcting for participant fixed effects dramatically affected results. Causal analysis suggests that environmental factors included in the study and sleep and mood history do not mediate the relationship.

Mobile Phone Detection of Semantic Location and Its Relationship to Depression and Anxiety.

BACKGROUND: Is someone at home, at their friend's place, at a restaurant, or enjoying the outdoors? Knowing the semantic location of an individual matters for delivering medical interventions, recommendations, and other context-aware services. This knowledge is particularly useful in mental health care for monitoring relevant behavioral indicators to improve treatment delivery. Local search-and-discovery services such as Foursquare can be used to detect semantic locations based on the global positioning system (GPS) coordinates, but GPS alone is often inaccurate. Mobile phones can also sense other signals (such as movement, light, and sound), and the use of these signals promises to lead to a better estimation of an individual's semantic location. OBJECTIVE: We aimed to examine the ability of mobile phone sensors to estimate semantic locations, and to evaluate the relationship between semantic location visit patterns and depression and anxiety. METHODS: A total of 208 participants across the United States were asked to log the type of locations they visited daily, using their mobile phones for a period of 6 weeks, while their phone sensor data was recorded. Using the sensor data and Foursquare queries based on GPS coordinates, we trained models to predict these logged locations, and evaluated their prediction accuracy on participants that models had not seen during training. We also evaluated the relationship between the amount of time spent in each semantic location and depression and anxiety assessed at baseline, in the middle, and at the end of the study. RESULTS: While Foursquare queries detected true semantic locations with an average area under the curve (AUC) of 0.62, using phone sensor data alone increased the AUC to 0.84. When we used Foursquare and sensor data together, the AUC further increased to 0.88. We found some significant relationships between the time spent in certain locations and depression and anxiety, although these relationships were not consistent. CONCLUSIONS: The accuracy of location services such as Foursquare can significantly benefit from using phone sensor data. However, our results suggest that the nature of the places people visit explains only a small part of the variation in their anxiety and depression symptoms.

Scalable Passive Sleep Monitoring Using Mobile Phones: Opportunities and Obstacles.

BACKGROUND: Sleep is a critical aspect of people's well-being and as such assessing sleep is an important indicator of a person's health. Traditional methods of sleep assessment are either time- and resource-intensive or suffer from self-reporting biases. Recently, researchers have started to use mobile phones to passively assess sleep in individuals' daily lives. However, this work remains in its early stages, having only examined relatively small and homogeneous populations in carefully controlled contexts. Thus, it remains an open question as to how well mobile device-based sleep monitoring generalizes to larger populations in typical use cases. OBJECTIVE: The aim of this study was to assess the ability of machine learning algorithms to detect the sleep start and end times for the main sleep period in a 24-h cycle using mobile devices in a diverse sample. METHODS: We collected mobile phone sensor data as well as daily self-reported sleep start and end times from 208 individuals (171 females; 37 males), diverse in age (18-66 years; mean 39.3), education, and employment status, across the United States over 6 weeks. Sensor data consisted of geographic location, motion, light, sound, and in-phone activities. No specific instructions were given to the participants regarding phone placement. We used random forest classifiers to develop both personalized and global predictors of sleep state from the phone sensor data. RESULTS: Using all available sensor features, the average accuracy of classifying whether a 10-min segment was reported as sleep was 88.8%. This is somewhat better than using the time of day alone, which gives an average accuracy of 86.9%. The accuracy of the model considerably varied across the participants, ranging from 65.1% to 97.3%. We found that low accuracy in some participants was due to two main factors: missing sensor data and misreports. After correcting for these, the average accuracy increased to 91.8%, corresponding to an average median absolute deviation (MAD) of 38 min for sleep start time detection and 36 min for sleep end time. These numbers are close to the range reported by previous research in more controlled situations. CONCLUSIONS: We find that mobile phones provide adequate sleep monitoring in typical use cases, and that our methods generalize well to a broader population than has previously been studied. However, we also observe several types of data artifacts when collecting data in uncontrolled settings. Some of these can be resolved through corrections, but others likely impose a ceiling on the accuracy of sleep prediction for certain subjects. Future research will need to focus more on the understanding of people's behavior in their natural settings in order to develop sleep monitoring tools that work reliably in all cases for all people.

The need to approximate the use-case in clinical machine learning.

The availability of smartphone and wearable sensor technology is leading to a rapid accumulation of human subject data, and machine learning is emerging as a technique to map those data into clinical predictions. As machine learning algorithms are increasingly used to support clinical decision making, it is vital to reliably quantify their prediction accuracy. Cross-validation (CV) is the standard approach where the accuracy of such algorithms is evaluated on part of the data the algorithm has not seen during training. However, for this procedure to be meaningful, the relationship between the training and the validation set should mimic the relationship between the training set and the dataset expected for the clinical use. Here we compared two popular CV methods: record-wise and subject-wise. While the subject-wise method mirrors the clinically relevant use-case scenario of diagnosis in newly recruited subjects, the record-wise strategy has no such interpretation. Using both a publicly available dataset and a simulation, we found that record-wise CV often massively overestimates the prediction accuracy of the algorithms. We also conducted a systematic review of the relevant literature, and found that this overly optimistic method was used by almost half of the retrieved studies that used accelerometers, wearable sensors, or smartphones to predict clinical outcomes. As we move towards an era of machine learning-based diagnosis and treatment, using proper methods to evaluate their accuracy is crucial, as inaccurate results can mislead both clinicians and data scientists.

Using and understanding cross-validation strategies. Perspectives on Saeb et al.

This three-part review takes a detailed look at the complexities of cross-validation, fostered by the peer review of Saeb et al.'s paper entitled "The need to approximate the use-case in clinical machine learning." It contains perspectives by reviewers and by the original authors that touch upon cross-validation: the suitability of different strategies and their interpretation.

Authorship Correction: Scalable Passive Sleep Monitoring Using Mobile Phones: Opportunities and Obstacles.

[This corrects the article DOI: 10.2196/jmir.6821.].

The relationship between mobile phone location sensor data and depressive symptom severity.

BACKGROUND: Smartphones offer the hope that depression can be detected using passively collected data from the phone sensors. The aim of this study was to replicate and extend previous work using geographic location (GPS) sensors to identify depressive symptom severity. METHODS: We used a dataset collected from 48 college students over a 10-week period, which included GPS phone sensor data and the Patient Health Questionnaire 9-item (PHQ-9) to evaluate depressive symptom severity at baseline and end-of-study. GPS features were calculated over the entire study, for weekdays and weekends, and in 2-week blocks. RESULTS: The results of this study replicated our previous findings that a number of GPS features, including location variance, entropy, and circadian movement, were significantly correlated with PHQ-9 scores (r's ranging from -0.43 to -0.46, p-values <  .05). We also found that these relationships were stronger when GPS features were calculated from weekend, compared to weekday, data. Although the correlation between baseline PHQ-9 scores with 2-week GPS features diminished as we moved further from baseline, correlations with the end-of-study scores remained significant regardless of the time point used to calculate the features. DISCUSSION: Our findings were consistent with past research demonstrating that GPS features may be an important and reliable predictor of depressive symptom severity. The varying strength of these relationships on weekends and weekdays suggests the role of weekend/weekday as a moderating variable. The finding that GPS features predict depressive symptom severity up to 10 weeks prior to assessment suggests that GPS features may have the potential as early warning signals of depression.

Making Activity Recognition Robust against Deceptive Behavior.

Healthcare services increasingly use the activity recognition technology to track the daily activities of individuals. In some cases, this is used to provide incentives. For example, some health insurance companies offer discount to customers who are physically active, based on the data collected from their activity tracking devices. Therefore, there is an increasing motivation for individuals to cheat, by making activity trackers detect activities that increase their benefits rather than the ones they actually do. In this study, we used a novel method to make activity recognition robust against deceptive behavior. We asked 14 subjects to attempt to trick our smartphone-based activity classifier by making it detect an activity other than the one they actually performed, for example by shaking the phone while seated to make the classifier detect walking. If they succeeded, we used their motion data to retrain the classifier, and asked them to try to trick it again. The experiment ended when subjects could no longer cheat. We found that some subjects were not able to trick the classifier at all, while others required five rounds of retraining. While classifiers trained on normal activity data predicted true activity with ~38% accuracy, training on the data gathered during the deceptive behavior increased their accuracy to ~84%. We conclude that learning the deceptive behavior of one individual helps to detect the deceptive behavior of others. Thus, we can make current activity recognition robust to deception by including deceptive activity data from a few individuals.

The Relationship between Clinical, Momentary, and Sensor-based Assessment of Depression.

The clinical assessment of severity of depressive symptoms is commonly performed with standardized self-report questionnaires, most notably the patient health questionnaire (PHQ-9), which are usually administered in a clinic. These questionnaires evaluate symptoms that are stable over time. Ecological momentary assessment (EMA) methods, on the other hand, acquire patient ratings of symptoms in the context of their lives. Today's smartphones allow us to also obtain objective contextual information, such as the GPS location, that may also be related to depression. Considering clinical PHQ-9 scores as ground truth, an interesting question is to what extent the EMA ratings and contextual sensor data can be used as potential predictors of depression. To answer this question, we obtained PHQ-9 scores from 18 participants with a variety of depressive symptoms in our lab, and then collected their EMA and GPS sensor data using their smartphones over a period of two weeks. We analyzed the relationship between GPS sensor features, EMA ratings, and the PHQ-9 scores. While we found a strong correlation between a number of sensor features extracted from the two-week period and the PHQ-9 scores, the other relationships remained non-significant. Our results suggest that depression is better evaluated using long-term sensor-based measurements than the momentary ratings of mental state or short-term sensor information.

Mobile Phone Sensor Correlates of Depressive Symptom Severity in Daily-Life Behavior: An Exploratory Study.

BACKGROUND: Depression is a common, burdensome, often recurring mental health disorder that frequently goes undetected and untreated. Mobile phones are ubiquitous and have an increasingly large complement of sensors that can potentially be useful in monitoring behavioral patterns that might be indicative of depressive symptoms. OBJECTIVE: The objective of this study was to explore the detection of daily-life behavioral markers using mobile phone global positioning systems (GPS) and usage sensors, and their use in identifying depressive symptom severity. METHODS: A total of 40 adult participants were recruited from the general community to carry a mobile phone with a sensor data acquisition app (Purple Robot) for 2 weeks. Of these participants, 28 had sufficient sensor data received to conduct analysis. At the beginning of the 2-week period, participants completed a self-reported depression survey (PHQ-9). Behavioral features were developed and extracted from GPS location and phone usage data. RESULTS: A number of features from GPS data were related to depressive symptom severity, including circadian movement (regularity in 24-hour rhythm; r=-.63, P=.005), normalized entropy (mobility between favorite locations; r=-.58, P=.012), and location variance (GPS mobility independent of location; r=-.58, P=.012). Phone usage features, usage duration, and usage frequency were also correlated (r=.54, P=.011, and r=.52, P=.015, respectively). Using the normalized entropy feature and a classifier that distinguished participants with depressive symptoms (PHQ-9 score ≥5) from those without (PHQ-9 score <5), we achieved an accuracy of 86.5%. Furthermore, a regression model that used the same feature to estimate the participants' PHQ-9 scores obtained an average error of 23.5%. CONCLUSIONS: Features extracted from mobile phone sensor data, including GPS and phone usage, provided behavioral markers that were strongly related to depressive symptom severity. While these findings must be replicated in a larger study among participants with confirmed clinical symptoms, they suggest that phone sensors offer numerous clinical opportunities, including continuous monitoring of at-risk populations with little patient burden and interventions that can provide just-in-time outreach.

Learning the optimal control of coordinated eye and head movements.

Various optimality principles have been proposed to explain the characteristics of coordinated eye and head movements during visual orienting behavior. At the same time, researchers have suggested several neural models to underly the generation of saccades, but these do not include online learning as a mechanism of optimization. Here, we suggest an open-loop neural controller with a local adaptation mechanism that minimizes a proposed cost function. Simulations show that the characteristics of coordinated eye and head movements generated by this model match the experimental data in many aspects, including the relationship between amplitude, duration and peak velocity in head-restrained and the relative contribution of eye and head to the total gaze shift in head-free conditions. Our model is a first step towards bringing together an optimality principle and an incremental local learning mechanism into a unified control scheme for coordinated eye and head movements.

Goal-directed learning of features and forward models.

The brain is able to perform actions based on an adequate internal representation of the world, where task-irrelevant features are ignored and incomplete sensory data are estimated. Traditionally, it is assumed that such abstract state representations are obtained purely from the statistics of sensory input for example by unsupervised learning methods. However, more recent findings suggest an influence of the dopaminergic system, which can be modeled by a reinforcement learning approach. Standard reinforcement learning algorithms act on a single layer network connecting the state space to the action space. Here, we involve in a feature detection stage and a memory layer, which together, construct the state space for a learning agent. The memory layer consists of the state activation at the previous time step as well as the previously chosen action. We present a temporal difference based learning rule for training the weights from these additional inputs to the state layer. As a result, the performance of the network is maintained both, in the presence of task-irrelevant features, and at randomly occurring time steps during which the input is invisible. Interestingly, a goal-directed forward model emerges from the memory weights, which only covers the state-action pairs that are relevant to the task. The model presents a link between reinforcement learning, feature detection and forward models and may help to explain how reward systems recruit cortical circuits for goal-directed feature detection and prediction.

Incorporating synaptic time-dependent plasticity and dynamic synapse into a computational model of wind-up.

"Wind-up", a condition related to chronic pain, is a form of plasticity in spinal dorsal horn that can be observed during electrical stimulation of pain receptors at low frequencies (0.3-3 Hz). In this paper, we present a computational model to explain several aspects of wind-up. The core of this model is the interplay of spike-time-dependent plasticity (STDP), short-term synaptic plasticity (STP), and different propagation velocities of the three afferent fibers (C, Adelta, and Abeta). We utilize Izhikevich's simple spiking neuron to model a dorsal horn neuron (DHN) of the spinal cord. To achieve the expected results, the model parameters need to adapt to the frequency response which is motivated by biological results. The adaptation is performed by a genetic algorithm (GA), and the resulting optimized values interestingly lie in biological ranges. Based on the proposed model, we suggest that STP may be the origin of the band-pass behavior of wind-up between 0.3 and 3 Hz; while the STDP-based long-term plasticity can be responsible for the synaptic potentiation leading to wind-up, or similar phenomena such as central sensitization. Understanding the mechanisms underlying wind-up generation might allow clarification of the molecular mechanisms of pain signaling and development of strategies, such as transcutaneous electrical nerve stimulation (TENS), for pain treatment.

Modeling the primary auditory cortex using dynamic synapses: can synaptic plasticity explain the temporal tuning?

The molecular mechanisms underlying the temporal plasticity (temporal tuning) of cortical cells remain controversial. Experimental observations indicate that the neuronal responses at the primary auditory cortex are affected by behavioral learning. In this paper, we present a minimal feed-forward model of the primary auditory cortex, based on the dynamic synapse and the leaky integrate-and-fire neuron models, in order to search for the origin of the observed plasticity. We demonstrate that the frequency response of the model is markedly modified by regulating the contribution of synaptic facilitation to the short-term dynamics of synapses (U(1)). Consequently, we propose that the variation of this parameter may be responsible for primary auditory cortex enhancement achieved by behavioral training. Based on our model, we assume that the contribution of facilitation arises from the amount of Ca(2+) influx each time an action potential arrives at the nerve terminal. Regardless of what really leads to the long-term variation of Ca(2+) influx, we suggest that this process is responsible for the temporal tuning of responses observed in experimental studies. We believe that measurement of the long-term variation of Ca(2+) influx at the pre-synaptic area of the cortical cells in auditory learning trials would be the first step to validate our hypothesis.

A cybernetic view on wind-up.

Wind-up is described traditionally as a frequency dependent increase in the excitability of spinal cord neurons, evoked by electrical stimulation of afferent C-fibers. Different kinds of wind-up have been reported, but wind-up of Abeta fibers in hyperalgesic states has gained little attention. In this paper, we present a cybernetic view on Abeta fiber wind-up and consider the involved molecular mechanisms as feedback and feedforward processes. Furthermore, our previous hypothesis, the sprouting phenomenon, is included in this view. Considering the proposed model, wind-up in hyperalgesic states might leave out in three different ways: (1) blocking the NMDA receptors by increasing extracellular Mg2+, 2) blocking the receptors and channels that contribute to Ca2+ inward current, and 3) blocking the Abeta fibers by local anesthetics. It seems that wind-up may be inhibited more effectively by using these three blocking mechanisms simultaneously, because in this case, the feedback process (main controller), the feedforward process (trigger), and Abeta stimulation (trigger) would be inhibited concurrently. Wind up may aggravate the pain in clinical hyperalgesic situations such as post-surgical states, some neuropathic pains, fibromyalgia syndrome, and post-herpetic neuralgia. Surely, clinical studies are needed to validate the effectiveness of our abovementioned suggestions in relieving such clinical pains.