Cardiogenic control of affective behavioural state.

Emotional states influence bodily physiology, as exemplified in the top-down process by which anxiety causes faster beating of the heart1-3. However, whether an increased heart rate might itself induce anxiety or fear responses is unclear3-8. Physiological theories of emotion, proposed over a century ago, have considered that in general, there could be an important and even dominant flow of information from the body to the brain9. Here, to formally test this idea, we developed a noninvasive optogenetic pacemaker for precise, cell-type-specific control of cardiac rhythms of up to 900 beats per minute in freely moving mice, enabled by a wearable micro-LED harness and the systemic viral delivery of a potent pump-like channelrhodopsin. We found that optically evoked tachycardia potently enhanced anxiety-like behaviour, but crucially only in risky contexts, indicating that both central (brain) and peripheral (body) processes may be involved in the development of emotional states. To identify potential mechanisms, we used whole-brain activity screening and electrophysiology to find brain regions that were activated by imposed cardiac rhythms. We identified the posterior insular cortex as a potential mediator of bottom-up cardiac interoceptive processing, and found that optogenetic inhibition of this brain region attenuated the anxiety-like behaviour that was induced by optical cardiac pacing. Together, these findings reveal that cells of both the body and the brain must be considered together to understand the origins of emotional or affective states. More broadly, our results define a generalizable approach for noninvasive, temporally precise functional investigations of joint organism-wide interactions among targeted cells during behaviour.

Prospective associations of text-message-based sentiment with symptoms of depression, generalized anxiety, and social anxiety.

OBJECTIVE: Language patterns may elucidate mechanisms of mental health conditions. To inform underlying theory and risk models, we evaluated prospective associations between in vivo text messaging language and differential symptoms of depression, generalized anxiety, and social anxiety. METHODS: Over 16 weeks, we collected outgoing text messages from 335 adults. Using Linguistic Inquiry and Word Count (LIWC), NRC Emotion Lexicon, and previously established depression and stress dictionaries, we evaluated the degree to which language features predict symptoms of depression, generalized anxiety, or social anxiety the following week using hierarchical linear models. To isolate the specificity of language effects, we also controlled for the effects of the two other symptom types. RESULTS: We found significant relationships of language features, including personal pronouns, negative emotion, cognitive and biological processes, and informal language, with common mental health conditions, including depression, generalized anxiety, and social anxiety (ps < .05). There was substantial overlap between language features and the three mental health outcomes. However, after controlling for other symptoms in the models, depressive symptoms were uniquely negatively associated with language about anticipation, trust, social processes, and affiliation (ßs: -.10 to -.09, ps < .05), whereas generalized anxiety symptoms were positively linked with these same language features (ßs: .12-.13, ps < .001). Social anxiety symptoms were uniquely associated with anger, sexual language, and swearing (ßs: .12-.13, ps < .05). CONCLUSION: Language that confers both common (e.g., personal pronouns and negative emotion) and specific (e.g., affiliation, anticipation, trust, and anger) risk for affective disorders is perceptible in prior week text messages, holding promise for understanding cognitive-behavioral mechanisms and tailoring digital interventions.

Machine Learning and Surgical Outcomes Prediction: A Systematic Review.

BACKGROUND: Machine learning (ML) has garnered increasing attention as a means to quantitatively analyze the growing and complex medical data to improve individualized patient care. We herein aim to critically examine the current state of ML in predicting surgical outcomes, evaluate the quality of currently available research, and propose areas of improvement for future uses of ML in surgery. METHODS: A systematic review was conducted in accordance with the Preferred Reporting Items for a Systematic Review and Meta-Analysis (PRISMA) checklist. PubMed, MEDLINE, and Embase databases were reviewed under search syntax "machine learning" and "surgery" for papers published between 2015 and 2020. RESULTS: Of the initial 2677 studies, 45 papers met inclusion and exclusion criteria. Fourteen different subspecialties were represented with neurosurgery being most common. The most frequently used ML algorithms were random forest (n = 19), artificial neural network (n = 17), and logistic regression (n = 17). Common outcomes included postoperative mortality, complications, patient reported quality of life and pain improvement. All studies which compared ML algorithms to conventional studies which used area under the curve (AUC) to measure accuracy found improved outcome prediction with ML models. CONCLUSIONS: While still in its early stages, ML models offer surgeons an opportunity to capitalize on the myriad of clinical data available and improve individualized patient care. Limitations included heterogeneous outcome and imperfect quality of some of the papers. We therefore urge future research to agree upon methods of outcome reporting and require basic quality standards.

Evaluation of Changes in Depression, Anxiety, and Social Anxiety Using Smartphone Sensor Features: Longitudinal Cohort Study.

BACKGROUND: The assessment of behaviors related to mental health typically relies on self-report data. Networked sensors embedded in smartphones can measure some behaviors objectively and continuously, with no ongoing effort. OBJECTIVE: This study aims to evaluate whether changes in phone sensor-derived behavioral features were associated with subsequent changes in mental health symptoms. METHODS: This longitudinal cohort study examined continuously collected phone sensor data and symptom severity data, collected every 3 weeks, over 16 weeks. The participants were recruited through national research registries. Primary outcomes included depression (8-item Patient Health Questionnaire), generalized anxiety (Generalized Anxiety Disorder 7-item scale), and social anxiety (Social Phobia Inventory) severity. Participants were adults who owned Android smartphones. Participants clustered into 4 groups: multiple comorbidities, depression and generalized anxiety, depression and social anxiety, and minimal symptoms. RESULTS: A total of 282 participants were aged 19-69 years (mean 38.9, SD 11.9 years), and the majority were female (223/282, 79.1%) and White participants (226/282, 80.1%). Among the multiple comorbidities group, depression changes were preceded by changes in GPS features (Time: r=-0.23, P=.02; Locations: r=-0.36, P<.001), exercise duration (r=0.39; P=.03) and use of active apps (r=-0.31; P<.001). Among the depression and anxiety groups, changes in depression were preceded by changes in GPS features for Locations (r=-0.20; P=.03) and Transitions (r=-0.21; P=.03). Depression changes were not related to subsequent sensor-derived features. The minimal symptoms group showed no significant relationships. There were no associations between sensor-based features and anxiety and minimal associations between sensor-based features and social anxiety. CONCLUSIONS: Changes in sensor-derived behavioral features are associated with subsequent depression changes, but not vice versa, suggesting a directional relationship in which changes in sensed behaviors are associated with subsequent changes in symptoms.

Examining a Novel Legacy Activity for Elders: Oral Histories as Produced Stories.

Background: Many African American elders who participated in The Great Migration are in the latter years of their lives. One way to maintain their memories and those of elders at large is through legacy activities, projects that initiate a life review process resulting in a product surviving after an individual's death. However, literature on culturally attuned legacy activities as well as measurement of impact are limited. Objectives: This project sought to introduce a novel legacy activity for elders-the oral history as produced aural self-story-detailing its creation and examining its therapeutic efficacy. Design Setting and Subjects: Nine African American elders who experienced The Great Migration receiving care from an urban, geriatric clinic were recruited. Oral histories were conducted, produced into aural self-stories, and examined with follow-up interviews and a project evaluation survey. Qualitative analysis of the follow-up interview and a project evaluation survey were used to ascertain therapeutic outcomes. Results: : All participants recommended the project and found self-story listening meaningful or beneficial. Qualitative interviews produced 13 codes; the five most frequent were reflection/contemplation (n = 18), sentimentality/positive affect and affirmation/enlightenment (n = 10), as well as empathy/gratitude and curiosity/intrigue/peculiarity (n = 7). Conclusion: : Our project suggests that aural self-stories produced from oral histories enhance the current elder legacy activity landscape by facilitating meaning and existential affirmation, additionally leaving a product for subsequent generations. Future studies include comparison to existing legacy interventions and project examination in additional elder populations.

Computational kinematics of dance: distinguishing hip hop genres.

Dance plays a vital role in human societies across time and culture, with different communities having invented different systems for artistic expression through movement (genres). Differences between genres can be described by experts in words and movements, but these descriptions can only be appreciated by people with certain background abilities. Existing dance notation schemes could be applied to describe genre-differences, however they fall substantially short of being able to capture the important details of movement across a wide spectrum of genres. Our knowledge and practice around dance would benefit from a general, quantitative and human-understandable method of characterizing meaningful differences between aspects of any dance style; a computational kinematics of dance. Here we introduce and apply a novel system for encoding bodily movement as 17 macroscopic, interpretable features, such as expandedness of the body or the frequency of sharp movements. We use this encoding to analyze Hip Hop Dance genres, in part by building a low-cost machine-learning classifier that distinguishes genre with high accuracy. Our study relies on an open dataset (AIST++) of pose-sequences from dancers instructed to perform one of ten Hip Hop genres, such as Breakdance, Popping, or Krump. For comparison we evaluate moderately experienced human observers at discerning these sequence's genres from movements alone (38% where chance = 10%). The performance of a baseline, Ridge classifier model was fair (48%) and that of the model resulting from our automated machine learning pipeline was strong (76%). This indicates that the selected features represent important dimensions of movement for the expression of the attitudes, stories, and aesthetic values manifested in these dance forms. Our study offers a new window into significant relations of similarity and difference between the genres studied. Given the rich, complex, and culturally shaped nature of these genres, the interpretability of our features, and the lightweight techniques used, our approach has significant potential for generalization to other movement domains and movement-related applications.

Differential temporal utility of passively sensed smartphone features for depression and anxiety symptom prediction: a longitudinal cohort study.

While studies show links between smartphone data and affective symptoms, we lack clarity on the temporal scale, specificity (e.g., to depression vs. anxiety), and person-specific (vs. group-level) nature of these associations. We conducted a large-scale (n = 1013) smartphone-based passive sensing study to identify within- and between-person digital markers of depression and anxiety symptoms over time. Participants (74.6% female; M age = 40.9) downloaded the LifeSense app, which facilitated continuous passive data collection (e.g., GPS, app and device use, communication) across 16 weeks. Hierarchical linear regression models tested the within- and between-person associations of 2-week windows of passively sensed data with depression (PHQ-8) or generalized anxiety (GAD-7). We used a shifting window to understand the time scale at which sensed features relate to mental health symptoms, predicting symptoms 2 weeks in the future (distal prediction), 1 week in the future (medial prediction), and 0 weeks in the future (proximal prediction). Spending more time at home relative to one's average was an early signal of PHQ-8 severity (distal ß = 0.219, p = 0.012) and continued to relate to PHQ-8 at medial (ß = 0.198, p = 0.022) and proximal (ß = 0.183, p = 0.045) windows. In contrast, circadian movement was proximally related to (ß = -0.131, p = 0.035) but did not predict (distal ß = 0.034, p = 0.577; medial ß = -0.089, p = 0.138) PHQ-8. Distinct communication features (i.e., call/text or app-based messaging) related to PHQ-8 and GAD-7. Findings have implications for identifying novel treatment targets, personalizing digital mental health interventions, and enhancing traditional patient-provider interactions. Certain features (e.g., circadian movement) may represent correlates but not true prospective indicators of affective symptoms. Conversely, other features like home duration may be such early signals of intra-individual symptom change, indicating the potential utility of prophylactic intervention (e.g., behavioral activation) in response to person-specific increases in these signals.

Analyzing text message linguistic features: Do people with depression communicate differently with their close and non-close contacts?

BACKGROUND: Relatively little is known about how communication changes as a function of depression severity and interpersonal closeness. We examined the linguistic features of outgoing text messages among individuals with depression and their close- and non-close contacts. METHODS: 419 participants were included in this 16-week-long observational study. Participants regularly completed the PHQ-8 and rated subjective closeness to their contacts. Text messages were processed to count frequencies of word usage in the LIWC 2015 libraries. A linear mixed modeling approach was used to estimate linguistic feature scores of outgoing text messages. RESULTS: Regardless of closeness, people with higher PHQ-8 scores tended to use more differentiation words. When texting with close contacts, individuals with higher PHQ-8 scores used more first-person singular, filler, sexual, anger, and negative emotion words. When texting with non-close contacts these participants used more conjunctions, tentative, and sadness-related words and fewer first-person plural words. CONCLUSION: Word classes used in text messages, when combined with symptom severity and subjective social closeness data, may be indicative of underlying interpersonal processes. These data may hold promise as potential treatment targets to address interpersonal drivers of depression.

Intracranial electrical stimulation of corticolimbic sites modulates arousal in humans.

BACKGROUND: Humans routinely shift their sleepiness and wakefulness levels in response to emotional factors. The diversity of emotional factors that modulates sleep-wake levels suggests that the ascending arousal network may be intimately linked with networks that mediate mood. Indeed, while animal studies have identified select limbic structures that play a role in sleep-wake regulation, the breadth of corticolimbic structures that directly modulates arousal in humans remains unknown. OBJECTIVE: We investigated whether select regional activation of the corticolimbic network through direct electrical stimulation can modulate sleep-wake levels in humans, as measured by subjective experience and behavior. METHODS: We performed intensive inpatient stimulation mapping in two human participants with treatment resistant depression, who underwent intracranial implantation with multi-site, bilateral depth electrodes. Stimulation responses of sleep-wake levels were measured by subjective surveys (i.e. Stanford Sleepiness Scale and visual-analog scale of energy) and a behavioral arousal score. Biomarker analyses of sleep-wake levels were performed by assessing spectral power features of resting-state electrophysiology. RESULTS: Our findings demonstrated three regions whereby direct stimulation modulated arousal, including the orbitofrontal cortex (OFC), subgenual cingulate (SGC), and, most robustly, ventral capsule (VC). Modulation of sleep-wake levels was frequency-specific: 100Hz OFC, SGC, and VC stimulation promoted wakefulness, whereas 1Hz OFC stimulation increased sleepiness. Sleep-wake levels were correlated with gamma activity across broad brain regions. CONCLUSIONS: Our findings provide evidence for the overlapping circuitry between arousal and mood regulation in humans. Furthermore, our findings open the door to new treatment targets and the consideration of therapeutic neurostimulation for sleep-wake disorders.

Demographic Features and Clinical Course of Patients With Pediatric-Onset Multiple Sclerosis on Newer Disease-Modifying Treatments.

BACKGROUND: Treatment of pediatric-onset multiple sclerosis (POMS) is challenging given the lack of safety and efficacy data in the pediatric population for many of the disease-modifying treatments (DMTs) approved for use in adults with MS. Our objective was to describe the demographic features and clinical and radiologic course of patients with POMS treated with the commonly used newer DMTs within the US Network of Pediatric MS Centers (NPMSC). METHODS: This is an analysis of prospectively collected data from patients who initiated treatment before age 18 with the DMTs listed below at the 12 regional pediatric MS referral centers participating in the NPMSC. RESULTS: One hundred sixty-eight patients on dimethyl fumarate, 96 on fingolimod, 151 on natalizumab, 166 on rituximab, and 37 on ocrelizumab met criteria for analysis. Mean age at DMT initiation ranged from 15.2 to 16.5 years. Disease duration at the time of initiation of index DMT ranged from 1.1 to 1.6 years with treatment duration of 0.9-2.0 years. Mean annualized relapse rate (ARR) in the year prior to initiating index DMT ranged from 0.4 to 1.0. Mean ARR while on index DMT ranged from 0.05 to 0.20. New T2 and enhancing lesions occurred in 75%-88% and 55%-73% of the patients, respectively, during the year prior to initiating index DMT. After initiating index DMT, new T2 and enhancing lesions occurred in 0%-46% and 11%-34% patients, respectively. Rates of NEDA-2 (no evidence of disease activity) ranged from 76% to 91% at 6 months of treatment with index DMTs and 66% to 84% at 12 months of treatment with index DMTs. CONCLUSIONS: Though limited by relatively short treatment duration with the index DMTs, our data suggest clinical and MRI benefit, as well as high rates of NEDA-2, in a large number of POMS patients, which can be used to guide future studies in this population.

Connectomic features underlying diverse synaptic connection strengths and subcellular computation.

Connectomes generated from electron microscopy images of neural tissue unveil the complex morphology of every neuron and the locations of every synapse interconnecting them. These wiring diagrams may also enable inference of synaptic and neuronal biophysics, such as the functional weights of synaptic connections, but this requires integration with physiological data to properly parameterize. Working with a stereotyped olfactory network in the Drosophila brain, we make direct comparisons of the anatomy and physiology of diverse neurons and synapses with subcellular and subthreshold resolution. We find that synapse density and location jointly predict the amplitude of the somatic postsynaptic potential evoked by a single presynaptic spike. Biophysical models fit to data predict that electrical compartmentalization allows axon and dendrite arbors to balance independent and interacting computations. These findings begin to fill the gap between connectivity maps and activity maps, which should enable new hypotheses about how network structure constrains network function.

Sleep after burn injuries: A systematic review and meta-analysis.

Burn injuries are a complex medical condition associated with negative physical and emotional consequences including disturbances in sleep. The goals of this systematic review were to examine the prevalence of sleep disturbances in adult burn survivors and evaluate the effects of intervention to improve sleep. Eight electronic databases were systematically searched and yielded 49 studies (13 interventional and 36 non-interventional). Results from the systematic review demonstrate that a variety of sleep disturbances are common in burn survivors, persisting years after the injury and are associated with pain, itch, emotional distress and reduction in quality of life. Sleep assessment was primarily based on subjective measures and the available data did not allow for assessing the prevalence of sleep disorders in burn survivors. Results of the meta-analysis of four studies demonstrated that a variety of interventions improved sleep quality. These findings provide further evidence that sleep is compromised in burn survivors and highlight the need for ongoing assessment using a combination of validated self-reports and objective measures of sleep. More research is needed to determine the most effective treatments for sleep disorders in burn survivors and if early intervention will serve to improve long term outcomes.

Metagenome-Assembled Genomes for "Candidatus Phormidium sp. Strain AB48" and Co-occurring Microorganisms from an Industrial Photobioreactor Environment.

Here, we report metagenome-assembled genomes for "Candidatus Phormidium sp. strain AB48" and three cooccurring microorganisms from a biofilm-forming industrial photobioreactor environment, using the PacBio sequencing platform. Several mobile genetic elements, including a double-stranded DNA phage and plasmids, were also recovered, with the potential to mediate gene transfer within the biofilm community.

The relationship between text message sentiment and self-reported depression.

BACKGROUND: Personal sensing has shown promise for detecting behavioral correlates of depression, but there is little work examining personal sensing of cognitive and affective states. Digital language, particularly through personal text messages, is one source that can measure these markers. METHODS: We correlated privacy-preserving sentiment analysis of text messages with self-reported depression symptom severity. We enrolled 219 U.S. adults in a 16 week longitudinal observational study. Participants installed a personal sensing app on their phones, which administered self-report PHQ-8 assessments of their depression severity, collected phone sensor data, and computed anonymized language sentiment scores from their text messages. We also trained machine learning models for predicting end-of-study self-reported depression status using on blocks of phone sensor and text features. RESULTS: In correlation analyses, we find that degrees of depression, emotional, and personal pronoun language categories correlate most strongly with self-reported depression, validating prior literature. Our classification models which predict binary depression status achieve a leave-one-out AUC of 0.72 when only considering text features and 0.76 when combining text with other networked smartphone sensors. LIMITATIONS: Participants were recruited from a panel that over-represented women, caucasians, and individuals with self-reported depression at baseline. As language use differs across demographic factors, generalizability beyond this population may be limited. The study period also coincided with the initial COVID-19 outbreak in the United States, which may have affected smartphone sensor data quality. CONCLUSIONS: Effective depression prediction through text message sentiment, especially when combined with other personal sensors, could enable comprehensive mental health monitoring and intervention.

Medical Assistance in Dying in Oncology Patients: A Canadian Academic Hospital's Experience.

BACKGROUND: Medical assistance in dying (MAID) was legislatively enacted in Canada in June 2016. Most studies of patients who received MAID grouped patients with cancer and non-cancer diagnoses. Our goal was to analyze the characteristics of oncology patients who received MAID in a Canadian tertiary care hospital. METHODS: We conducted a retrospective review of all patients with cancer who received MAID between June 2016 and July 2020 at London Health Sciences Centre (LHSC). We describe patients' demographics, oncologic characteristics, symptoms, treatments, and palliative care involvement. RESULTS: Ninety-two oncology patients received MAID. The median age was 72. The leading cancer diagnoses among these patients were lung, colorectal, and pancreatic. At the time of MAID request, 68% of patients had metastatic disease. Most patients (90%) had ECOG performance status of 3 or 4 before receiving MAID. Ninety-nine percent of patients had distressing symptoms at time of MAID request, most commonly pain. One-third of patients with metastatic or recurrent cancer received early palliative care. The median time interval between the first MAID assessment and receipt of MAID was 7 days. INTERPRETATION: Most oncology patients who received MAID at LHSC had poor performance status and almost all had distressing symptoms. The median time interval between first MAID assessment and receipt of MAID was shorter than expected. Only one-third of patients with metastatic or recurrent cancer received early palliative care. Improving access to early palliative care is a priority in patients with advanced cancer. STUDY REGISTRATION: We received research approval from Western University's Research Ethics Board (REB) with project ID number 115367, and from Lawson's Research Database Application (ReDA) with study ID number 9579.

Quantifying causality in data science with quasi-experiments.

Estimating causality from observational data is essential in many data science questions but can be a challenging task. Here we review approaches to causality that are popular in econometrics and that exploit (quasi) random variation in existing data, called quasi-experiments, and show how they can be combined with machine learning to answer causal questions within typical data science settings. We also highlight how data scientists can help advance these methods to bring causal estimation to high-dimensional data from medicine, industry and society.

Closed-loop neuromodulation in an individual with treatment-resistant depression.

Deep brain stimulation is a promising treatment for neuropsychiatric conditions such as major depression. It could be optimized by identifying neural biomarkers that trigger therapy selectively when symptom severity is elevated. We developed an approach that first used multi-day intracranial electrophysiology and focal electrical stimulation to identify a personalized symptom-specific biomarker and a treatment location where stimulation improved symptoms. We then implanted a chronic deep brain sensing and stimulation device and implemented a biomarker-driven closed-loop therapy in an individual with depression. Closed-loop therapy resulted in a rapid and sustained improvement in depression. Future work is required to determine if the results and approach of this n-of-1 study generalize to a broader population.

A web-based automated machine learning platform to analyze liquid biopsy data.

Liquid biopsy (LB) technologies continue to improve in sensitivity, specificity, and multiplexing and can measure an ever growing library of disease biomarkers. However, clinical interpretation of the increasingly large sets of data these technologies generate remains a challenge. Machine learning is a popular approach to discover and detect signatures of disease. However, limited machine learning expertise in the LB field has kept the discipline from fully leveraging these tools and risks improper analyses and irreproducible results. In this paper, we develop a web-based automated machine learning tool tailored specifically for LB, where machine learning models can be built without the user's input. We also incorporate a differential privacy algorithm, designed to limit the effects of overfitting that can arise from users iteratively developing a panel with feedback from our platform. We validate our approach by performing a meta-analysis on 11 published LB datasets, and found that we had similar or better performance compared to those reported in the literature. Moreover, we show that our platform's performance improved when incorporating information from prior LB datasets, suggesting that this approach can continue to improve with increased access to LB data. Finally, we show that by using our platform the results achieved in the literature can be matched using 40% of the number of subjects in the training set, potentially reducing study cost and time. This self-improving and overfitting-resistant automatic machine learning platform provides a new standard that can be used to validate machine learning works in the LB field.

COVID-19 pandemic: every day feels like a weekday to most.

The COVID-19 outbreak has clear clinical and economic impacts, but also affects behaviors e.g. through social distancing, and may increase stress and anxiety. However, while case numbers are tracked daily, we know little about the psychological effects of the outbreak on individuals in the moment. Here we examine the psychological and behavioral shifts over the initial stages of the outbreak in the United States in an observational longitudinal study. Through GPS phone data we find that homestay is increasing, while being at work dropped precipitously. Using regular real-time experiential surveys we observe an overall increase in stress and mood levels which is similar in size to the weekend vs. weekday differences. As there is a significant difference between weekday and weekend mood and stress levels, this is an important decrease in wellbeing. For some, especially those affected by job loss, the mental health impact is severe.

Machine Learning for Phone-Based Relationship Estimation: The Need to Consider Population Heterogeneity.

Estimating the category and quality of interpersonal relationships from ubiquitous phone sensor data matters for studying mental well-being and social support. Prior work focused on using communication volume to estimate broad relationship categories, often with small samples. Here we contextualize communications by combining phone logs with demographic and location data to predict interpersonal relationship roles on a varied sample population using automated machine learning methods, producing better performance (F1 = 0.68) than using communication features alone (F1 = 0.62). We also explore the effect of age variation in the underlying training sample on interpersonal relationship prediction and find that models trained on younger subgroups, which is popular in the field via student participation and recruitment, generalize poorly to the wider population. Our results not only illustrate the value of using data across demographics, communication patterns and semantic locations for relationship prediction, but also underscore the importance of considering population heterogeneity in phone-based personal sensing studies.