A5079905799- Mental Health Research Topics
- Digital Mental Health Interventions
- COVID-19 and Mental Health
- Functional Brain Connectivity Studies
- Impact of Technology on Adolescents
- Human Mobility and Location-Based Analysis
- Mental Health via Writing
- Innovative Human-Technology Interaction
- Context-Aware Activity Recognition Systems
- Mobile Crowdsensing and Crowdsourcing
- Consumer Retail Behavior Studies
- Emotion and Mood Recognition
- Neuroscience and Music Perception
- Schizophrenia research and treatment
- Health, Environment, Cognitive Aging
- Health disparities and outcomes
- Anxiety, Depression, Psychometrics, Treatment, Cognitive Processes
- Psychosomatic Disorders and Their Treatments
- Personal Information Management and User Behavior
- Mental Health Treatment and Access
- Psychological and Temporal Perspectives Research
- Behavioral Health and Interventions
- Green IT and Sustainability
- Evacuation and Crowd Dynamics
- Job Satisfaction and Organizational Behavior
Dartmouth College
2019-2024
Microsoft (United States)
2024
Dartmouth Hospital
2020-2021
Background The vast majority of people worldwide have been impacted by coronavirus disease (COVID-19). In addition to the millions individuals who infected with disease, billions asked or required local and national governments change their behavioral patterns. Previous research on epidemics traumatic events suggests that this can lead profound mental health changes; however, researchers are rarely able track these changes frequent, near-real-time sampling compare findings previous years...
There is a growing body of research revealing that longitudinal passive sensing data from smartphones and wearable devices can capture daily behavior signals for human modeling, such as depression detection. Most prior studies build evaluate machine learning models using collected single population. However, to ensure model work larger group users, its generalizability needs be verified on multiple datasets different populations. We present the first evaluating cross-dataset models,...
Major depressive disorder (MDD) is conceptualized by individual symptoms occurring most of the day for at least two weeks. Despite this operationalization, MDD highly variable with persons showing greater variation within and across days. Moreover, heterogeneous, varying considerably people in both function form. Recent efforts have examined heterogeneity byinvestigating how influence one another over time individuals a system; however, these assumed that symptom dynamics are static do not...
Assessing performance in the workplace typically relies on subjective evaluations, such as, peer ratings, supervisor ratings and self assessments, which are manual, burdensome potentially biased. We use objective mobile sensing data from phones, wearables beacons to study offer new insights into behavioral patterns that distinguish higher lower performers when considering roles companies (i.e., supervisors non-supervisors) different types of high tech consultancy). present initial results an...
Since late 2019, the lives of people across globe have been disrupted by COVID-19. Millions become infected with disease, while billions continually asked or required local and national governments to change their behavioral patterns. Previous research on COVID-19 pandemic suggests that it is associated large-scale mental health changes; however, few studies able track these changes frequent, near real-time sampling compare previous years data for same individuals.
MindScape aims to study the benefits of integrating time series behavioral patterns (e.g., conversational engagement, sleep, location) with Large Language Models (LLMs) create a new form contextual AI journaling, promoting self-reflection and well-being. We argue that sensing in LLMs will likely lead frontier AI. In this Late-Breaking Work paper, we discuss journal App design uses generate personalized journaling prompts crafted encourage emotional development. also college students based on...
Understanding the dynamics of mental health among undergraduate students across college years is critical importance, particularly during a global pandemic. In our study, we track two cohorts first-year at Dartmouth College for four years, both on and off campus, creating longest longitudinal mobile sensing study to date. Using passive sensor data, surveys, interviews, capture changing behaviors before, during, after COVID-19 pandemic subsides. Our findings reveal pandemic's impact students'...
Impaired social functioning is a symptom of mental illness (e.g., depression, schizophrenia) and wide range other conditions cognitive decline in the elderly, dementia). Today, assessing relies on subjective evaluations self assessments. We propose different approach collect detailed measures objective mobile sensing data from N=55 outpatients living with schizophrenia to study new methods passively accessing functioning. identify number behavioral patterns data, discuss important...
Background People with serious mental illness (SMI) have significant unmet health needs. Development and testing of digital interventions that can alleviate the suffering people SMI is a public priority. Objective The aim this study to conduct fully remote randomized waitlist-controlled trial CORE, smartphone intervention comprises daily exercises designed promote reassessment dysfunctional beliefs in multiple domains. Methods Individuals were recruited via web using Google Facebook...
The transition from high school to college is a taxing time for young adults. New students arriving on campus navigate myriad of challenges centered around adapting new living situations, financial needs, academic pressures and social demands. First-year need gain skills strategies cope with these demands in order make good decisions, ease their independent ultimately succeed. In general, first-generation are less prepared when they enter comparison non-first-generation students. This...
Abstract Background and Hypothesis Loneliness, the subjective experience of feeling alone, is associated with physical psychological impairments. While there an extensive literature linking loneliness to psychopathology, limited work has examined in daily life those serious mental illness. We hypothesized that trait momentary would be transdiagnostic relate symptoms measures functioning. Study Design The current study utilized ecological assessment passive sensing examine schizophrenia (N =...
MoodCapture presents a novel approach that assesses depression based on images automatically captured from the front-facing camera of smartphones as people go about their daily lives. We collect over 125,000 photos in wild N=177 participants diagnosed with major depressive disorder for 90 days. Images are naturalistically while respond to PHQ-8 survey question: \textit{``I have felt down, depressed, or hopeless''}. Our analysis explores important image attributes, such angle, dominant...
Large language models (LLMs) show promise for health applications when combined with behavioral sensing data. Traditional approaches convert sensor data into text prompts, but this process is prone to errors, computationally expensive, and requires domain expertise. These challenges are particularly acute processing extended time series While foundation (TFMs) have recently emerged as powerful tools learning representations from temporal data, bridging TFMs LLMs remains challenging. Here, we...
Major Depressive Disorder (MDD) is a prevalent mental health disorder often identified by persistentlow mood, and lack of motivation energy. Persons with MDD experience largefluctuations in their symptoms over hours days, which can offer valuable clinical insights,highlighting potential targets for treatment intervention strategies. However, there remains gapin our understanding how feasible it to accurately predict fluctuations depressive symptoms. Inthis preregistered study, we aim explore...
Several psychologists posit that performance is not only a function of personality but also situational contexts, such as day-level activities. Yet in practice, since assessments are used to infer job performance, they provide limited perspective by ignoring activity. However, multi-modal sensing has the potential characterize these daily This paper illustrates how empirically measured activity data complements traditional effects explain worker's performance. We leverage sensors commodity...
BackgroundWorldwide, the vast majority of people have been impacted by COVID-19. While millions individuals become infected, billions asked or required local and national governments to change their behavioral patterns. Previous research on epidemics traumatic events suggest this can lead profound mental health changes, but rarely are researchers able track these changes with frequent, near real-time sampling compare previous years data same individuals.ObjectivesWe seek answer two...
The COVID-19 pandemic continues to affect the daily life of college students, impacting their social life, education, stress levels and overall mental well-being. We study assess behavioral changes N=180 undergraduate students one year prior as a baseline then during first using mobile phone sensing inference. observe that certain groups experience very differently. Furthermore, we explore association self-reported concern with students' behavior health. find heightened is correlated...
Speech-based diaries from mobile phones can capture paralinguistic patterns that help detect mental illness symptoms such as suicidal ideation. However, previous studies have primarily evaluated machine learning models on a single dataset, making their performance unknown under distribution shifts. In this paper, we investigate the generalizability of speech-based ideation detection using through cross-dataset experiments four datasets with N=786 individuals experiencing major depressive...
As concerns about employee burnout and skilled staff shortages in cybersecurity grow, our study aims to better understand the contributing factors this field. Utilizing a mixed-methods approach, we analyze self-reported job personal characteristics, along with digital activity data from 35 incident responders, identifying several such as high workload, time pressure, lack of support management. Our findings reveal that over half participants experience (N=19), which is linked increased...
Ubiquitous computing, the seamless integration of sensing, analytics, and feedback into daily life envisioned by Weiser [12], has come closer to reality with broad adoption smartphones wearable devices. These devices, integral users' routines, passively collect massive amounts data on human behavior, offering unprecedented insights personal health well-being [7]. For example, passive sensing can continuously monitor subtle changes in behavior indicative depression or other shifts mental...
Social isolation is a common problem faced by individuals with serious mental illness (SMI), and current intervention approaches have limited effectiveness. This article presents blended approach, called mobile Interaction Therapy Exposure, to address social in SMI. The approach combines brief in-person cognitive-behavioral therapy (CBT) context-triggered CBT interventions that are personalized using sensing data. Our targets behavior the first context-aware for improving outcomes
Most people desire promotions in the workplace. Typically, rising through ranks comes with increased demands, better salary and higher status among peers. However, promoted workers have to deal new challenges, such as, adjusting roles responsibilities, which can turn impact their physical mental wellbeing. In this year long study, we use mobile sensing track physiological behavioral patterns of N=141 information who are promoted. We show that experience a change after promotion captured by...
Commercial grade activity trackers and phone agents are increasingly being deployed as sensors for sleep in large scale, longitudinal designs. In general, wearables detect through diminished movement decreased heart rate (HR), while look lack of user input, movement, sound or light. However, recent literature suggests that commercial-grade apps vary greatly the accuracy predictions. Constant innovation proprietary algorithms further make it difficult to evaluate their efficacy scientific...