Assessing engagement features in an observational study of mental health apps in college students

Melcher, Jennifer R.; Patel, Suraj K.; Scheuer, Luke; Hays, Ryan; Torous, John

doi:10.1016/j.psychres.2022.114470

Cited by 12 publications

(14 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The prompt could alternatively be delayed to a more optimal moment where a response is more likely. Similarly, previous research has suggested that feedback can help respondents remain engaged with mental health smartphone applications (Melcher et al, 2022) and data on moments in Note. Higher scores here represent lower levels of the state.…”

Section: Discussionmentioning

confidence: 87%

Prompt-level predictors of compliance in an ecological momentary assessment study of young adults' mental health

Murray

Brown

Zhu

et al. 2023

Journal of Affective Disorders

View full text Add to dashboard Cite

Section: Discussionmentioning

confidence: 87%

Prompt-level predictors of compliance in an ecological momentary assessment study of young adults' mental health

Murray

Brown

Zhu

et al. 2023

Journal of Affective Disorders

View full text Add to dashboard Cite

“…Another useful approach is to employ tools and procedures that make it easy to monitor passive data quality in near real time. As an example, we have created interactive visualizations on the Data Portal of our researcher dashboard 20 to allow study staff or clinicians a simple way to track participant data. These graphs are automatically updated each day and contain information about data coverage (as shown in Fig.…”

Section: Resultsmentioning

confidence: 99%

“…While the studies differed in their clinical populations (patients with schizophrenia; college students with stress, anxiety, and depression; patients with depression using mindLAMP to augment therapy), they all collected two common digital phenotyping data streams: geolocation and accelerometer data. Each study presented participants with a symptom survey at least every three days [13][14][15][16] . For completeness, all participants in each study (including those that were discontinued because of non-adherence to protocol) were included in this analysis.…”

Section: Data Setsmentioning

confidence: 99%

Increasing the Value of Digital Phenotyping Through Reducing Missingness: A Retrospective Analysis

Currey¹,

Torous²

2022

Preprint

Self Cite

View full text Add to dashboard Cite

ObjectivesDigital phenotyping methods present a scalable tool to realize the potential of personalized medicine. But underlying this potential is the need for digital phenotyping data to represent accurate and precise health measurements. This requires a focus on the data quality of digital phenotyping and assessing the nature of the smartphone data used to derive clinical and health-related features.DesignRetrospective cohorts. Representing the largest combined dataset of smartphone digital phenotyping, we report on the impact of sampling frequency, active engagement with the app, phone type (Android vs Apple), gender, and study protocol features may have on missingness / data quality.SettingmindLAMP smartphone app digital phenotyping studies run at BIDMC between May 2019 and March 2022Participants1178 people who partook in mindLAMP studiesMain outcome measuresRates of missing digital phenotyping data.ResultsMissingness from sensors in digital phenotyping is related to active user engagement with the app. There are small but notable differences in missingness between phone models and genders. Datasets with high degrees of missingness can generate incorrect behavioral features that may lead to faulty clinical interpretations.ConclusionsDigital phenotyping data quality is a moving target that requires ongoing technical and protocol efforts to minimize missingness. Adding run-in periods, education with hands-on support, and tools to easily monitor data coverage are all productive strategies studies can utilize today.Strengths and Limitations of this Study○Methods are informed by a large sample of participants in digital phenotyping studies.○Methods can be replicated by others given the open-source nature of the app and code.○Methods are informed by only mindLAMP studies from one team which is a limitation.

show abstract

“…While the studies differed in their clinical populations (patients with schizophrenia or depression/anxiety; college students with stress/anxiety), they all collected two common digital phenotyping data streams: geolocation (GPS) and accelerometer data. Each study presented participants with a symptom survey at least every 3 days 12–16. All participants in each study (including those who were discontinued for non-adherence to protocol) were included in this analysis.…”

Section: Methodsmentioning

confidence: 99%

Increasing the value of digital phenotyping through reducing missingness: a retrospective review and analysis of prior studies

Currey

Torous

2023

BMJ Ment Health

Self Cite

View full text Add to dashboard Cite

BackgroundDigital phenotyping methods present a scalable tool to realise the potential of personalised medicine. But underlying this potential is the need for digital phenotyping data to represent accurate and precise health measurements.ObjectiveTo assess the impact of population, clinical, research and technological factors on the digital phenotyping data quality as measured by rates of missing digital phenotyping data.MethodsThis study analyses retrospective cohorts of mindLAMP smartphone application digital phenotyping studies run at Beth Israel Deaconess Medical Center between May 2019 and March 2022 involving 1178 participants (studies of college students, people with schizophrenia and people with depression/anxiety). With this large combined data set, we report on the impact of sampling frequency, active engagement with the application, phone type (Android vs Apple), gender and study protocol features on missingness/data quality.FindingsMissingness from sensors in digital phenotyping is related to active user engagement with the application. After 3 days of no engagement, there was a 19% decrease in average data coverage for both Global Positioning System and accelerometer. Data sets with high degrees of missingness can generate incorrect behavioural features that may lead to faulty clinical interpretations.ConclusionsDigital phenotyping data quality requires ongoing technical and protocol efforts to minimise missingness. Adding run-in periods, education with hands-on support and tools to easily monitor data coverage are all productive strategies studies can use today.Clinical implicationsWhile it is feasible to capture digital phenotyping data from diverse populations, clinicians should consider the degree of missingness in the data before using them for clinical decision-making.

show abstract

Assessing engagement features in an observational study of mental health apps in college students

Cited by 12 publications

References 25 publications

Prompt-level predictors of compliance in an ecological momentary assessment study of young adults' mental health

Prompt-level predictors of compliance in an ecological momentary assessment study of young adults' mental health

Increasing the Value of Digital Phenotyping Through Reducing Missingness: A Retrospective Analysis

Increasing the value of digital phenotyping through reducing missingness: a retrospective review and analysis of prior studies

Contact Info

Product

Resources

About