Explore the vast range of titles available.

Physical activity helps people maintain a healthy weight and reduces the risk for several chronic diseases. Although this knowledge is widely recognized, adults and children in many countries around the world do not get recommended amounts of physical activity. Although many interventions are found to be ineffective at increasing physical activity or reaching inactive populations, there have been anecdotal reports of increased physical activity due to novel mobile games that embed game play in the physical world. The most recent and salient example of such a game is Pokémon Go, which has reportedly reached tens of millions of users in the United States and worldwide. The objective of this study was to quantify the impact of Pokémon Go on physical activity. We study the effect of Pokémon Go on physical activity through a combination of signals from large-scale corpora of wearable sensor data and search engine logs for 32,000 Microsoft Band users over a period of 3 months. Pokémon Go players are identified through search engine queries and physical activity is measured through accelerometers. We find that Pokémon Go leads to significant increases in physical activity over a period of 30 days, with particularly engaged users (ie, those making multiple search queries for details about game usage) increasing their activity by 1473 steps a day on average, a more than 25% increase compared with their prior activity level (P<.001). In the short time span of the study, we estimate that Pokémon Go has added a total of 144 billion steps to US physical activity. Furthermore, Pokémon Go has been able to increase physical activity across men and women of all ages, weight status, and prior activity levels showing this form of game leads to increases in physical activity with significant implications for public health. In particular, we find that Pokémon Go is able to reach low activity populations, whereas all 4 leading mobile health apps studied in this work largely draw from an already very active population. Mobile apps combining game play with physical activity lead to substantial short-term activity increases and, in contrast to many existing interventions and mobile health apps, have the potential to reach activity-poor populations. Future studies are needed to investigate potential long-term effects of these applications.

Neuropsychiatric disorders pose a high societal cost, but their treatment is hindered by lack of objective outcomes and fidelity metrics. AI technologies and specifically Natural Language Processing (NLP) have emerged as tools to study mental health interventions (MHI) at the level of their constituent conversations. However, NLP’s potential to address clinical and research challenges remains unclear. We therefore conducted a pre-registered systematic review of NLP-MHI studies using PRISMA guidelines (osf.io/s52jh) to evaluate their models, clinical applications, and to identify biases and gaps. Candidate studies (n = 19,756), including peer-reviewed AI conference manuscripts, were collected up to January 2023 through PubMed, PsycINFO, Scopus, Google Scholar, and ArXiv. A total of 102 articles were included to investigate their computational characteristics (NLP algorithms, audio features, machine learning pipelines, outcome metrics), clinical characteristics (clinical ground truths, study samples, clinical focus), and limitations. Results indicate a rapid growth of NLP MHI studies since 2019, characterized by increased sample sizes and use of large language models. Digital health platforms were the largest providers of MHI data. Ground truth for supervised learning models was based on clinician ratings (n = 31), patient self-report (n = 29) and annotations by raters (n = 26). Text-based features contributed more to model accuracy than audio markers. Patients’ clinical presentation (n = 34), response to intervention (n = 11), intervention monitoring (n = 20), providers’ characteristics (n = 12), relational dynamics (n = 14), and data preparation (n = 4) were commonly investigated clinical categories. Limitations of reviewed studies included lack of linguistic diversity, limited reproducibility, and population bias. A research framework is developed and validated (NLPxMHI) to assist computational and clinical researchers in addressing the remaining gaps in applying NLP to MHI, with the goal of improving clinical utility, data access, and fairness.

An unhealthy diet is a major risk factor for chronic diseases including cardiovascular disease, type 2 diabetes, and cancer 1 – 4 . Limited access to healthy food options may contribute to unhealthy diets 5 , 6 . Studying diets is challenging, typically restricted to small sample sizes, single locations, and non-uniform design across studies, and has led to mixed results on the impact of the food environment 7 – 23 . Here we leverage smartphones to track diet health, operationalized through the self-reported consumption of fresh fruits and vegetables, fast food and soda, as well as body-mass index status in a country-wide observational study of 1,164,926 U.S. participants (MyFitnessPal app users) and 2.3 billion food entries to study the independent contributions of fast food and grocery store access, income and education to diet health outcomes. This study constitutes the largest nationwide study examining the relationship between the food environment and diet to date. We find that higher access to grocery stores, lower access to fast food, higher income and college education are independently associated with higher consumption of fresh fruits and vegetables, lower consumption of fast food and soda, and lower likelihood of being affected by overweight and obesity. However, these associations vary significantly across zip codes with predominantly Black, Hispanic or white populations. For instance, high grocery store access has a significantly larger association with higher fruit and vegetable consumption in zip codes with predominantly Hispanic populations (7.4% difference) and Black populations (10.2% difference) in contrast to zip codes with predominantly white populations (1.7% difference). Policy targeted at improving food access, income and education may increase healthy eating, but intervention allocation may need to be optimized for specific subpopulations and locations. Studying diets is challenging, typically restricted to small sample sizes, single locations, and non-uniform design across studies. Here, the authors leverage food entry data of a popular diet tracking app to observe diet health and weight status, studying the associations of fast food and grocery access, income and education with diet health outcomes.

A huge smartphone dataset of physical activity yields global insights, revealing that activity inequality predicts obesity better than does volume of activity and that much of the inequality is a result of reduced activity in females. Obesity signals activity inequalities Globally, millions of deaths each year are associated with physical inactivity but our understanding of activity patterns in different populations remains limited owing to a lack of large-scale measurements. Jure Leskovec and colleagues analysed smartphone sensor-based activity patterns from over 600,000 people in 46 countries. They find a large range of distributions of activity levels across populations, which are primarily driven by the activity level of women. The inequality between the least and most active segments of populations is more predictive of obesity prevalence in each population than the mean activity levels. Additionally, inequality is reduced in the more walkable cities where the greatest gains in activity are observed in females. These findings suggest the potential benefits of focusing urban planning and public health policy on increasing activity on the most activity-poor subgroups. To be able to curb the global pandemic of physical inactivity 1 , 2 , 3 , 4 , 5 , 6 , 7 and the associated 5.3 million deaths per year 2 , we need to understand the basic principles that govern physical activity. However, there is a lack of large-scale measurements of physical activity patterns across free-living populations worldwide 1 , 6 . Here we leverage the wide usage of smartphones with built-in accelerometry to measure physical activity at the global scale. We study a dataset consisting of 68 million days of physical activity for 717,527 people, giving us a window into activity in 111 countries across the globe. We find inequality in how activity is distributed within countries and that this inequality is a better predictor of obesity prevalence in the population than average activity volume. Reduced activity in females contributes to a large portion of the observed activity inequality. Aspects of the built environment, such as the walkability of a city, are associated with a smaller gender gap in activity and lower activity inequality. In more walkable cities, activity is greater throughout the day and throughout the week, across age, gender, and body mass index (BMI) groups, with the greatest increases in activity found for females. Our findings have implications for global public health policy and urban planning and highlight the role of activity inequality and the built environment in improving physical activity and health.

The COVID-19 pandemic has stimulated important changes in online information access as digital engagement became necessary to meet the demand for health, economic, and educational resources. Our analysis of 55 billion everyday web search interactions during the pandemic across 25,150 US ZIP codes reveals that the extent to which different communities of internet users enlist digital resources varies based on socioeconomic and environmental factors. For example, we find that ZIP codes with lower income intensified their access to health information to a smaller extent than ZIP codes with higher income. We show that ZIP codes with higher proportions of Black or Hispanic residents intensified their access to unemployment resources to a greater extent, while revealing patterns of unemployment site visits unseen by the claims data. Such differences frame important questions on the relationship between differential information search behaviors and the downstream real-world implications on more and less advantaged populations. The COVID-19 pandemic has stimulated an important changes in online information access. Here, the authors analyse everyday web search interactions across 25,150 US ZIP codes revealing significant differences in how digital informational resources are mobilized by different communities.

Deriving personalized insights from popular wearable trackers requires complex numerical reasoning that challenges standard LLMs, necessitating tool-based approaches like code generation. Large language model (LLM) agents present a promising yet largely untapped solution for this analysis at scale. We introduce the Personal Health Insights Agent (PHIA), a system leveraging multistep reasoning with code generation and information retrieval to analyze and interpret behavioral health data. To test its capabilities, we create and share two benchmark datasets with over 4000 health insights questions. A 650-hour human expert evaluation shows that PHIA significantly outperforms a strong code generation baseline, achieving 84% accuracy on objective, numerical questions and, for open-ended ones, earning 83% favorable ratings while being twice as likely to achieve the highest quality rating. This work can advance behavioral health by empowering individuals to understand their data, enabling a new era of accessible, personalized, and data-driven wellness for the wider population. Wearable devices generate vast streams of health data, but making sense of these measurements requires complex numerical reasoning beyond the reach of conventional language models. This study introduces a large language model agent that interprets wearable data to deliver accurate, personalized health insights.

Integrating stress-reduction interventions into the workplace may improve the health and well-being of employees, and there is an opportunity to leverage ubiquitous everyday work technologies to understand dynamic work contexts and facilitate stress reduction wherever work happens. Sensing-powered just-in-time adaptive intervention (JITAI) systems have the potential to adapt and deliver tailored interventions, but such adaptation requires a comprehensive analysis of contextual and individual-level variables that may influence intervention outcomes and be leveraged to drive the system's decision-making. This study aims to identify key tailoring variables that influence momentary engagement in digital stress reduction microinterventions to inform the design of similar JITAI systems. To inform the design of such dynamic adaptation, we analyzed data from the implementation and deployment of a system that incorporates passively sensed data across everyday work devices to send just-in-time stress reduction microinterventions in the workplace to 43 participants during a 4-week deployment. We evaluated 27 trait-based factors (ie, individual characteristics), state-based factors (ie, workplace contextual and behavioral signals and momentary stress), and intervention-related factors (ie, location and function) across 1585 system-initiated interventions. We built logistical regression models to identify the factors contributing to momentary engagement, the choice of interventions, the engagement given an intervention choice, the user rating of interventions engaged, and the stress reduction from the engagement. We found that women (odds ratio [OR] 0.41, 95% CI 0.21-0.77; P=.03), those with higher neuroticism (OR 0.57, 95% CI 0.39-0.81; P=.01), those with higher cognitive reappraisal skills (OR 0.69, 95% CI 0.52-0.91; P=.04), and those that chose calm interventions (OR 0.43, 95% CI 0.23-0.78; P=.03) were significantly less likely to experience stress reduction, while those with higher agreeableness (OR 1.73, 95% CI 1.10-2.76; P=.06) and those that chose prompt-based (OR 6.65, 95% CI 1.53-36.45; P=.06) or video-based (OR 5.62, 95% CI 1.12-34.10; P=.12) interventions were substantially more likely to experience stress reduction. We also found that work-related contextual signals such as higher meeting counts (OR 0.62, 95% CI 0.49-0.78; P<.001) and higher engagement skewness (OR 0.64, 95% CI 0.51-0.79; P<.001) were associated with a lower likelihood of engagement, indicating that state-based contextual factors such as being in a meeting or the time of the day may matter more for engagement than efficacy. In addition, a just-in-time intervention that was explicitly rescheduled to a later time was more likely to be engaged with (OR 1.77, 95% CI 1.32-2.38; P<.001). JITAI systems have the potential to integrate timely support into the workplace. On the basis of our findings, we recommend that individual, contextual, and content-based factors be incorporated into the system for tailoring as well as for monitoring ineffective engagements across subgroups and contexts.

Large scale analysis of source code, and in particular scientific source code, holds the promise of better understanding the data science process, identifying analytical best practices, and providing insights to the builders of scientific toolkits. However, large corpora have remained unanalyzed in depth, as descriptive labels are absent and require expert domain knowledge to generate. We propose a novel weakly supervised transformer-based architecture for computing joint representations of code from both abstract syntax trees and surrounding natural language comments. We then evaluate the model on a new classification task for labeling computational notebook cells as stages in the data analysis process from data import to wrangling, exploration, modeling, and evaluation. We show that our model, leveraging only easily-available weak supervision, achieves a 38% increase in accuracy over expert-supplied heuristics and outperforms a suite of baselines. Our model enables us to examine a set of 118,000 Jupyter Notebooks to uncover common data analysis patterns. Focusing on notebooks with relationships to academic articles, we conduct the largest study of scientific code to date and find that notebooks which devote an higher fraction of code to the typically labor-intensive process of wrangling data in expectation exhibit decreased citation counts for corresponding papers. We also show significant differences between academic and non-academic notebooks, including that academic notebooks devote substantially more code to wrangling and exploring data, and less on modeling.

Although web-based mental health resources have the potential to assist millions, particularly those who face barriers to treatment, most mental health website visitors disengage before accessing resources that can help improve their mental health. We used a sequential multiple assignment randomized trial to test whether personalized tailoring improved engagement on a self-guided mental health website. Data were collected via voluntary response sampling on the Mental Health America website. Inclusion criteria included residing in the United States and viewing a postscreening survey after completing the Patient Health Questionnaire-9 (PHQ-9). Participants were randomized to 1 of 2 postscreening survey conditions: the demographics survey or the Next Steps survey, which included additional tailoring questions assessing perceived need and participants' intended next steps. Participants who viewed the following screening results page were subsequently randomized to 1 of 5 conditions that displayed nontailored or tailored messages and featured resources, as well as persistent general resources that did not vary by condition. Data were analyzed using logistic regressions predicting disengagement and clicks on featured resources (versus persistent general resources) by condition. Adding questions to inform tailoring significantly increased the odds of disengaging by 14% (demographics survey: 25%; Next Steps survey: 27.5%; odds ratio [OR] 1.14, 95% CI 1.11-1.16; P<.001). Among participants who viewed a postscreening survey (n=169,647), 87,712 participants were randomized to the demographics survey condition, and 81,935 participants were randomized to the Next Steps survey condition. Among participants who submitted the demographics survey (n=38,490), tailoring resources to demographics reduced the odds of disengaging by 10% (OR 0.90, 95% CI 0.87-0.94; P<.001) and, among those who engaged, increased the odds of clicking a featured resource versus a persistent general resource by 90% (OR 1.90, 95% CI 1.79-2.01; P<.001). Among participants who submitted the Next Steps survey (n=34,204), tailoring messages to perceived need (P=.33), tailoring resources to intended next steps (P=.51), and a combination of both (P=.52) did not significantly reduce the odds of disengaging compared with the nontailored condition. However, tailoring resources to intended next steps and combining a tailored message to perceived need with tailored resources to intended next steps increased the odds of clicking a featured resource by 25% (OR 1.25, 95% CI 1.14-1.37; P<.001) and 34% (OR 1.34, 95% CI 1.23-1.47; P<.001), respectively. Tailoring resources to demographics was significantly more effective in improving engagement than tailoring to perceived need or intended next steps (P≤.004). There was a small but statistically significant cost to engagement from adding tailoring questions assessing perceived need and intended next steps. Among the strategies tested in this study, tailoring resources to demographics was the most effective strategy for increasing engagement among visitors who viewed their screening results. This study demonstrates how personalization may increase engagement with mental health websites and provides design implications for future research.

Gender minority populations experience an increased risk of depression and report significant barriers to accessing mental health services. While digital mental health (DMH) technologies may address barriers, it remains unclear how gender minority clients engage with DMH services and if DMH improves their clinical outcomes. This naturalistic study explored gender differences in 15-week clinical outcomes of clients receiving technology-mediated psychotherapy from a large DMH provider. This study used observational data of clients who signed up for Talkspace (Talkspace, Inc) between February 2017 and July 2021. The analytic sample included Talkspace clients (N=20,156) with a baseline 8-item Patient Health Questionnaire (PHQ-8) score ≥10. Participants completed at least 2 PHQ-8 assessments over 15 weeks of treatment. Multilevel linear models tested gender differences in depressive symptom trajectories over the course of treatment (model 1) while also controlling for baseline PHQ-8 scores (model 2) and treatment engagement indicators (model 3). Sensitivity analyses reestimated model 2 among clients who submitted a PHQ-8 survey during the week 15 assessment period and among those who discontinued treatment beforehand. Reasons for service cancellation were also described for the latter group. Gender differences in secondary clinical outcomes were examined via chi-square and Fisher exact tests. In all models, there were significant week-by-gender interactions. When controlling for baseline PHQ-8 scores, rates of symptom change were significantly slower for gender-diverse participants (b=0.60; P<.001), nonbinary participants (b=0.81; P<.001), and transgender women (b=0.87; P=.007), but not for women (P=.98) or transgender men (P=.38) compared to men. By week 15, adjusted PHQ-8 scores declined 8.7 points for both men and women, versus 4.4-7.4 points for gender minority clients. Sensitivity analyses indicated attenuated symptom improvement among week-15 completers, with transgender women showing the slowest changes (b=0.76; P=.02). Among earlier dropouts, weekly symptom reductions were steep overall (eg, week 3: b=-4.06, P<.001; week 6: b=-2.31, P<.001) while certain gender minority subgroups worsened (eg, adjusted scores for transgender women increased from 15.41 at baseline to 16.08 at final week 3 PHQ-8 survey submissions). Cancellation data (3450/20,156, 17.12%) confirmed discontinuation reasons related to both symptom improvement (928/3691 reasons, 25.14%) and potential barriers to treatment engagement (eg, cost: 1431/3691, 38.77%; poor service fit or poor perceived effectiveness: 677/3691, 18.34%). Gender differences were observed in rates of treatment response (weeks 3-12; all P≤.02), symptom remission (weeks 3, 6, 9, and 15; all P≤.047), and clinically significant symptom reduction (all time points, all P≤.03). Symptom deterioration did not differ by gender (all P>.05). While clinical outcomes generally improved over time among clients engaged in technology-mediated psychotherapy, some gender minority populations experienced slower improvements. Future research may explore strategies to adapt DMH interventions to better meet the needs of diverse gender identities.