Characteristic Latent Features for Analyzing Digital Mental Health Interaction and Improved Explainability (Preprint)

2021 ◽  
Author(s):  
Max-Marcel Theilig ◽  
Ashley A Knapp ◽  
Jennifer M Nicholas ◽  
Rüdiger Zarnekow ◽  
David C Mohr
Keyword(s):  
Mental Health ◽  
Data Science ◽  
Digital Health ◽  
A Priori ◽  
User Interaction ◽  
User Engagement ◽  
Behavioral Strategies ◽  
Data Set ◽  
Public Data ◽  
Latent Features

BACKGROUND Using mobile health technology has sparked a broad engagement of data science and machine learning methods to leverage the complex, assorted amount of data for mental health purposes. Despite many studies, there is a reported underdevelopment of user engagement concepts, and the desire for high accuracy or significance has shown to lead to low explicability and irreproducibility. OBJECTIVE To overcome such reasons of poor analysis input and facilitate the reproducibility and credibility of artificial intelligence applications, we aim to explore principal characteristics of user interaction with digital mental health. METHODS We generated five latent features based on previous research, expert opinions from digital mental health, and informed by data. The features were analyzed with descriptive statistics and data visualization. We carried out two rounds of evaluations with data from 12,400 users of IntelliCare, a mental health platform with 12 apps. First, we focused to proof concept and second, we assessed reproducibility by drawing conclusion from distribution differences. User data was drawn from both research trials and public deployment on Google Play. RESULTS Our algorithms showed advantages over commonly used concepts and reproduce in our public data set with different underlying behavioral strategies. These measures relate to the distribution of a user’s allocated attention, users’ circadian behavior, their consecutive commitment to a specific strategy, and users’ interaction trajectory. Because distributions between research trial and public deployment were similar, consistency was implied regarding the underlying behavioral strategies: psychoeducation and goal setting are used as a catalyst to overcome the users’ primary obstacles, sleep hygiene is addressed most regularly, while regular self-reflective thinking is avoided. Relaxation as well as cognitive reframing have increased variance in commitment among public users, indicating the challenging nature of these apps. The relative course of users’ engagement is similar in research and public data. CONCLUSIONS We argue that deliberate, a-priori feature engineering is essential for reproducible, tangible, and explainable study analyses. Our features enable improved results as well as interpretability, providing an increased understanding of how people engage with multiple mental health apps over time. Since we based the generation of features on generic interaction, these methods are applicable to further methods of study analysis and digital health.

scholarly journals Characteristic Latent Features for Analyzing Digital Mental Health Interaction and Improved Explainability

2020 ◽  
Author(s):  
Max-Marcel Theilig ◽  
Ashley Arehart Knapp ◽  
Jennifer Nicholas ◽  
Rüdiger Zarnekow ◽  
David Curtis Mohr
Keyword(s):  
Mental Health ◽  
Data Science ◽  
Digital Health ◽  
A Priori ◽  
Sensor Technology ◽  
User Engagement ◽  
Behavioral Strategies ◽  
Data Set ◽  
Public Data ◽  
Latent Features

Abstract Background: Using smartphones and wearable sensor technology has sparked a broad engagement of data science and machine learning methods to leverage the complex, assorted amount of data. Despite verified processes, there is a reported underdevelopment of user engagement concepts, and the desire for high accuracy or significance has shown to lead to low explicability and irreproducibility. To overcome these issues, we aim to analyze principal characteristics of everyday behavior in digital mental health. Methods: We generated five latent features based on previous research, expert opinions from digital mental health, and informed by data. The features were analyzed with descriptive statistics and data visualization. We carried out two rounds of evaluations with data from 12,400 users of IntelliCare, a mental health platform with 12 apps. First, we focused to proof concept and second, we assessed reproducibility by drawing conclusion from distribution differences. User data was drawn from both research trials and public deployment on Google Play. Results: Our algorithms showed increased rationale for the basic usage of apps with different underlying behavioral strategies. Measures of the distribution of user’s allocated attention, the user’s circadian behavior, their consecutive commitment to a specific strategy, and users’ interaction trajectory are perceived as transferable to the public data set. Because distributions between research trial and public deployment were similar, consistency was shown regarding the underlying behavioral strategies: psychoeducation and goal setting are used as a catalyst to overcome the users’ primary obstacles, sleep hygiene is addressed most regularly, while regular self-reflective thinking is avoided. Relaxation as well as cognitive reframing have increased variance in commitment among public users, indicating the challenging nature of these apps. The relative course of the engagement (learning curve) is similar in research and public data. Conclusions: The deliberate, a-priori engineered features were reproducible across app users from both data sets. These features led to improved results as well as increased interpretability, providing an increased understanding of how people engage with multiple mental health apps over time. Since we based the generation of features on generic interaction proxies, these methods are applicable to other cases in artificial intelligence and digital health.

scholarly journals Characteristic Latent Features for Analyzing Digital Mental Health Interaction and Improved Explainability

2020 ◽  
Author(s):  
Max-Marcel Theilig ◽  
Ashley Arehart Knapp ◽  
Jennifer Nicholas ◽  
Rüdiger Zarnekow ◽  
David Curtis Mohr
Keyword(s):  
Mental Health ◽  
Data Science ◽  
Digital Health ◽  
A Priori ◽  
Sensor Technology ◽  
User Engagement ◽  
Behavioral Strategies ◽  
Data Set ◽  
Public Data ◽  
Latent Features

Abstract Background: Using smartphones and wearable sensor technology has sparked a broad engagement of data science and machine learning methods to leverage the complex, assorted amount of data. Despite verified processes, there is a reported underdevelopment of user engagement concepts, and the desire for high accuracy or significance has shown to lead to low explicability and irreproducibility. To overcome these issues, we aim to analyze principal characteristics of everyday behavior in digital mental health. Methods: We generated five latent features based on previous research, expert opinions from digital mental health, and informed by data. The features were analyzed with descriptive statistics and data visualization. We carried out two rounds of evaluations with data from 12,400 users of IntelliCare, a mental health platform with 12 apps. First, we focused to proof concept and second, we assessed reproducibility by drawing conclusion from distribution differences. User data was drawn from both research trials and public deployment on Google Play. Results: Our algorithms showed increased rationale for the basic usage of apps with different underlying behavioral strategies. Measures of the distribution of user’s allocated attention, the user’s circadian behavior, their consecutive commitment to a specific strategy, and users’ interaction trajectory curve are perceived as transferable to the public data set. Because distributions between research trial and public deployment were similar, consistency was shown regarding the underlying behavioral strategies: psychoeducation and goal setting are used as a catalyst to overcome the users’ primary obstacles, sleep hygiene is addressed most regularly, while regular emotional exposure is avoided. Relaxation as well as cognitive reframing have increased variance in commitment among public users, indicating the challenging nature of these apps. The relative course of the engagement (learning curve) is similar in research and public data. Conclusions: The deliberate, a-priori engineered features were reproducible across app users from both data sets. These features led to improved results as well as increased interpretability, providing an increased understanding of how people engage with multiple mental health apps over time. Since we based the generation of features on generic interaction proxies, these methods are applicable to other cases in artificial intelligence and digital health.

scholarly journals A public data set of spatio-temporal match events in soccer competitions

2019 ◽  
Vol 6 (1) ◽  
Author(s):  
Luca Pappalardo ◽  
Paolo Cintia ◽  
Alessio Rossi ◽  
Emanuele Massucco ◽  
Paolo Ferragina ◽  
...  
Keyword(s):  
Data Science ◽  
Social Systems ◽  
Team Sports ◽  
Data Set ◽  
Evaluation Of Performance ◽  
Public Data ◽  
Wide Range ◽  
Spatio Temporal ◽  
Measurement And Evaluation ◽  
Temporal Events

Abstract Soccer analytics is attracting increasing interest in academia and industry, thanks to the availability of sensing technologies that provide high-fidelity data streams for every match. Unfortunately, these detailed data are owned by specialized companies and hence are rarely publicly available for scientific research. To fill this gap, this paper describes the largest open collection of soccer-logs ever released, containing all the spatio-temporal events (passes, shots, fouls, etc.) that occured during each match for an entire season of seven prominent soccer competitions. Each match event contains information about its position, time, outcome, player and characteristics. The nature of team sports like soccer, halfway between the abstraction of a game and the reality of complex social systems, combined with the unique size and composition of this dataset, provide an ideal ground for tackling a wide range of data science problems, including the measurement and evaluation of performance, both at individual and at collective level, and the determinants of success and failure.

scholarly journals GAMIFICATION AND NUDGING TECHNIQUES FOR IMPROVING USER ENGAGEMENT IN MENTAL HEALTH AND WELL-BEING APPS

2021 ◽  
Vol 1 ◽  
pp. 1647-1656
Author(s):  
Hassan Auf ◽  
Jessica Dagman ◽  
Sara Renström ◽  
John Chaplin
Keyword(s):  
Mental Health ◽  
User Interaction ◽  
Well Being ◽  
Retention Rates ◽  
User Engagement ◽  
Age Group ◽  
Interaction Techniques ◽  
Health Apps ◽  
Google Play ◽  
Health And Well Being

AbstractIn the last decades, mental health disorders have been a growing source of the global burden of disease. Thousands of mental health apps are available nowadays addressing this problem, but studies show that the effectiveness of these apps is jeopardized by the low user engagement.This study investigates the most potentially effective gamification and nudging techniques in design for improving engagement in mental health apps for young people, by carrying out app-reviews for top installed mental health apps on Google play store and connecting it with engagement data, in addition to conducting expert-interviews with professionals from gamification and design background.From the findings, techniques that participated in improving retention rates included using app character for creating app narrative and user interaction, in addition to adopting a non-forcible language. While to improve app daily duration of use, simplification nudge, and stating the recommended minutes of use found to be useful. Personalization and social interaction techniques were potentially effective for improving the frequency of app daily use. For the young age group, using juicy feedback and high-quality gamification were recommended

Measurement in an on-demand virtual mental health system: a review and viewpoint (Preprint)

2020 ◽  
Author(s):  
Sarah Kunkle ◽  
John A Naslund ◽  
Justin Hunt ◽  
Dana Udall ◽  
Erica Hayes ◽  
...  
Keyword(s):  
Mental Health ◽  
Data Science ◽  
New Technologies ◽  
Digital Health ◽  
Clinical Care ◽  
The United States ◽  
On Demand ◽  
Measurement Based Care ◽  
Multidisciplinary Perspective ◽  
Development And Management

UNSTRUCTURED Mental health is a growing public health priority in the United States and globally. Measurement-based care (MBC) has been shown to improve outcomes in clinical care, yet there are significant challenges to implementation. New technologies offer opportunities to address these obstacles and to measure new and existing constructs at a scale that was previously not possible. This paper aims to summarize existing literature on MBC, focusing on mental health and digital health. Specifically, we describe a case example called Ginger, a novel on-demand virtual system for delivering mental health services, and demonstrate how this platform aligns with core principles of MBC in mental health based on existing frameworks and findings from the literature. Additionally, we integrate feedback from multidisciplinary stakeholders (clinical practitioners, data science, product development and management, and research) to develop a perspective on key tenets of measurement in this system. To navigate the challenges of translating traditional measurement tools into new technologies in addition to developing new measurements, this multidisciplinary perspective is required. Ultimately, this will enhance our understanding of mental health and ability to develop interventions to improve outcomes.

scholarly journals A Convenient and Low-Cost Model of Depression Screening and Early Warning Based on Voice Data Using for Public Mental Health

2021 ◽  
Vol 18 (12) ◽  
pp. 6441
Author(s):  
Xin Chen ◽  
Zhigeng Pan
Keyword(s):  
Mental Health ◽  
Early Warning ◽  
Cost Model ◽  
Low Cost ◽  
Ethical Review ◽  
Algorithm Selection ◽  
Data Set ◽  
Public Data ◽  
Voice Data ◽  
The Voice

Depression is a common mental health disease, which has great harm to public health. At present, the diagnosis of depression mainly depends on the interviews between doctors and patients, which is subjective, slow and expensive. Voice data are a kind of data that are easy to obtain and have the advantage of low cost. It has been proved that it can be used in the diagnosis of depression. The voice data used for modeling in this study adopted the authoritative public data set, which had passed the ethical review. The features of voice data were extracted by Python programming, and the voice features were stored in the format of CSV files. Through data processing, a big database, containing 1479 voice feature samples, was generated for modeling. Then, the decision tree screening model of depression was established by 10-fold cross validation and algorithm selection. The experiment achieved 83.4% prediction accuracy on voice data set. According to the prediction results of the model, the patients can be given early warning and intervention in time, so as to realize the health management of personal depression.

scholarly journals Ecological Momentary Assessment Within a Digital Health Intervention for Reminiscence in Persons With Dementia and Caregivers: User Engagement Study (Preprint)

2019 ◽  
Author(s):  
Courtney Potts ◽  
Raymond Bond ◽  
Assumpta Ryan ◽  
Maurice Mulvenna ◽  
Claire McCauley ◽  
...  
Keyword(s):  
Ecological Momentary Assessment ◽  
Digital Health ◽  
User Interaction ◽  
Large Data ◽  
Feasibility Trial ◽  
User Engagement ◽  
Time Data ◽  
Quasi Experimental ◽  
Ecological Momentary ◽  
Momentary Assessment

BACKGROUND User-interaction event logs provide rich and large data sets that can provide valuable insights into how people engage with technology. Approaches such as ecological momentary assessment (EMA) can be used to gather accurate real-time data in an individual’s natural environment by asking questions at any given instant. OBJECTIVE The purpose of this study was to evaluate user engagement and responses to EMA questions using InspireD, an app used for reminiscence by persons with dementia and their caregivers. Research findings can be used to inform EMA use within digital health interventions. METHODS A feasibility trial was conducted in which participants (n=56) used the InspireD app over a 12-week period. Participants were a mean age of 73 (SD 13) and were either persons with dementia (n=28) or their caregivers (n=28). Questions, which they could either answer or choose to dismiss, were presented to participants at various instants after reminiscence with personal or generic photos, videos, and music. Presentation and dismissal rates for questions were compared by hour of the day and by trial week to investigate user engagement. RESULTS Overall engagement was high, with 69.1% of questions answered when presented. Questions that were presented in the evening had the lowest dismissal rate; the dismissal rate for questions presented at 9 PM was significantly lower than the dismissal rate for questions presented at 11 AM (9 PM: 10%; 11 AM: 50%; χ<sup>2</sup><sub>1</sub>=21.4, <i>P</i>&lt;.001). Questions asked following reminiscence with personal media, especially those asked after personal photos, were less likely to be answered compared to those asked after other media. In contrast, questions asked after the user had listened to generic media, in particular those asked after generic music, were much more likely to be answered. CONCLUSIONS The main limitation of our study was the lack of generalizability of results to a larger population given the quasi-experimental design and older demographic where half of participants were persons with dementia; however, this study shows that older people are willing to participate and engage in EMA. Based on this study, we propose a series of recommendations for app design to increase user engagement with EMA. These include presenting questions no more than once per day, after 8 PM in the evening, and only if the user is not trying to complete a task within the app.

scholarly journals Ecological Momentary Assessment Within a Digital Health Intervention for Reminiscence in Persons With Dementia and Caregivers: User Engagement Study

10.2196/17120 ◽  
2020 ◽  
Vol 8 (7) ◽  
pp. e17120
Author(s):  
Courtney Potts ◽  
Raymond Bond ◽  
Assumpta Ryan ◽  
Maurice Mulvenna ◽  
Claire McCauley ◽  
...  
Keyword(s):  
Ecological Momentary Assessment ◽  
Digital Health ◽  
User Interaction ◽  
Large Data ◽  
Feasibility Trial ◽  
User Engagement ◽  
Time Data ◽  
Quasi Experimental ◽  
Ecological Momentary ◽  
Momentary Assessment

Background User-interaction event logs provide rich and large data sets that can provide valuable insights into how people engage with technology. Approaches such as ecological momentary assessment (EMA) can be used to gather accurate real-time data in an individual’s natural environment by asking questions at any given instant. Objective The purpose of this study was to evaluate user engagement and responses to EMA questions using InspireD, an app used for reminiscence by persons with dementia and their caregivers. Research findings can be used to inform EMA use within digital health interventions. Methods A feasibility trial was conducted in which participants (n=56) used the InspireD app over a 12-week period. Participants were a mean age of 73 (SD 13) and were either persons with dementia (n=28) or their caregivers (n=28). Questions, which they could either answer or choose to dismiss, were presented to participants at various instants after reminiscence with personal or generic photos, videos, and music. Presentation and dismissal rates for questions were compared by hour of the day and by trial week to investigate user engagement. Results Overall engagement was high, with 69.1% of questions answered when presented. Questions that were presented in the evening had the lowest dismissal rate; the dismissal rate for questions presented at 9 PM was significantly lower than the dismissal rate for questions presented at 11 AM (9 PM: 10%; 11 AM: 50%; χ21=21.4, P<.001). Questions asked following reminiscence with personal media, especially those asked after personal photos, were less likely to be answered compared to those asked after other media. In contrast, questions asked after the user had listened to generic media, in particular those asked after generic music, were much more likely to be answered. Conclusions The main limitation of our study was the lack of generalizability of results to a larger population given the quasi-experimental design and older demographic where half of participants were persons with dementia; however, this study shows that older people are willing to participate and engage in EMA. Based on this study, we propose a series of recommendations for app design to increase user engagement with EMA. These include presenting questions no more than once per day, after 8 PM in the evening, and only if the user is not trying to complete a task within the app.

scholarly journals Plant PhysioSpace: a robust tool to compare stress response across plant species

2020 ◽  
Author(s):  
Ali Hadizadeh Esfahani ◽  
Janina Maß ◽  
Asis Hallab ◽  
Bernhard M. Schuldt ◽  
David Nevarez ◽  
...  
Keyword(s):  
Stress Response ◽  
A Priori ◽  
Plant Stress ◽  
Marker Genes ◽  
Specific Gene ◽  
Data Sets ◽  
Data Set ◽  
Plant Stress Response ◽  
Gene Sets ◽  
Public Data

AbstractGeneralization of transcriptomics results can be achieved by comparison across experiments, which is based on integration of interrelated transcriptomics studies into a compendium. Both characterization of the fate of the organism under study as well as distinguishing between generic and specific responses can be gained in such a broader context. We have built such a compendium for plant stress response, which is based on integrating publicly available data sets for plant stress response to generalize results across studies and extract the most robust and meaningful information possible from them.There are numerous methods and tools to analyze such data sets, most focusing on gene-wise dimension reduction of data to obtain marker genes and gene sets, e.g. for pathway analysis. Relying only on isolated biological modules might lead to missing of important confounders and relevant context. Therefore, we have chosen a different approach: Our novel tool, which we called Plant PhysioSpace, provides the ability to compute experimental conditions across species and platforms without a priori reducing the reference information to specific gene-sets. It extracts physiologically relevant signatures from a reference data set, a collection of public data sets, by integrating and transforming heterogeneous reference gene expression data into a set of physiology-specific patterns, called PhysioSpace. New experimental data can be mapped to these PhysioSpaces, resulting in similarity scores, providing quantitative similarity of the new experiment to an a priori compendium.Here we report the implementation of two R packages, one software and one data package, and a shiny web application, which provides plant biologists convenient ways to access the method and a precomputed compendium of more than 900 PhysioSpace basis vectors from 4 different species (Arabidopsis thaliana, Oryza sativa, Glycine max, and Triticum aestivum).The tool reduces the dimensionality of data sample-wise (and not gene-wise), which results in a vector containing all genes. This method is very robust against noise and change of platform while still being sensitive. Plant PhysioSpace can therefore be used as an inter-species or cross-platform similarity measure. We demonstrate that Plant PhysioSpace can successfully translate stress responses between different species and platforms (including single cell technologies).

Prevalence of Self-Reported Depression Symptoms and Perceived Anxiety Among Community-Dwelling U.S. Adults Reporting Tinnitus

2020 ◽  
Vol 5 (4) ◽  
pp. 959-970
Author(s):  
Kelly M. Reavis ◽  
James A. Henry ◽  
Lynn M. Marshall ◽  
Kathleen F. Carlson
Keyword(s):  
Mental Health ◽  
Fold Increase ◽  
Community Dwelling ◽  
Self Report ◽  
Depression Symptoms ◽  
Community Based Interventions ◽  
Data Set ◽  
Health Distress ◽  
Validated Questionnaire ◽  
Mental Health Distress

Purpose The aim of this study was to examine the relationship between tinnitus and self-reported mental health distress, namely, depression symptoms and perceived anxiety, in adults who participated in the National Health and Nutrition Examinations Survey between 2009 and 2012. A secondary aim was to determine if a history of serving in the military modified the associations between tinnitus and mental health distress. Method This was a cross-sectional study design of a national data set that included 5,550 U.S. community-dwelling adults ages 20 years and older, 12.7% of whom were military Veterans. Bivariable and multivariable logistic regression was used to estimate the association between tinnitus and mental health distress. All measures were based on self-report. Tinnitus and perceived anxiety were each assessed using a single question. Depression symptoms were assessed using the Patient Health Questionnaire, a validated questionnaire. Multivariable regression models were adjusted for key demographic and health factors, including self-reported hearing ability. Results Prevalence of tinnitus was 15%. Compared to adults without tinnitus, adults with tinnitus had a 1.8-fold increase in depression symptoms and a 1.5-fold increase in perceived anxiety after adjusting for potential confounders. Military Veteran status did not modify these observed associations. Conclusions Findings revealed an association between tinnitus and both depression symptoms and perceived anxiety, independent of potential confounders, among both Veterans and non-Veterans. These results suggest, on a population level, that individuals with tinnitus have a greater burden of perceived mental health distress and may benefit from interdisciplinary health care, self-help, and community-based interventions. Supplemental Material https://doi.org/10.23641/asha.12568475

Sign in / Sign up

Export Citation Format

Share Document