Behavior vs. introspection: refining prediction of clinical depression via smartphone sensing data

Farhan, Asma Ahmad; Yue, Chaoqun; Morillo, Reynaldo; Ware, Shweta; Lü, Jin; Bi, Jinbo; Kamath, Jayesh; Russell, Alexander; Bamis, Athanasios; Wang, Bing

doi:10.1109/wh.2016.7764553

Cited by 96 publications

(109 citation statements)

References 24 publications

Supporting

Mentioning

101

Contrasting

Order By: Relevance

“…Several recent studies [6,13,14,17,18,38,44] have explored using smartphone sensing data for depression screening and have identified several sensor-based features as depression indicators. The present paper represents our ongoing effort in building an automatic depression diagnosis system.…”

Section: Introductionmentioning

confidence: 99%

“…For the first time, Android and iPhone features are merged in a joint analysis, and complementary Fitbit features are used in conjunction with smartphone variables. In addition, unlike many other works, including our own prior works [12,13,52], that use the 9-item Patient Health Questionniare (PHQ-9) [23], we use a more comprehensive questionniare, a 16-item QIDS-SR 16 survey. Furthermore, beyond self-reports, we examine the depression prediction using clinical ground truth.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Joint Modeling of Heterogeneous Sensing Data for Depression Assessment via Multi-task Learning

Lü

Chen

Yue

et al. 2018

Proc. ACM Interact. Mob. Wearable Ubiquitous Technol.

Self Cite

View full text Add to dashboard Cite

Depression is a common mood disorder that causes severe medical problems and interferes negatively with daily life. Identifying human behavior patterns that are predictive or indicative of depressive disorder is important. Clinical diagnosis of depression relies on costly clinician assessment using survey instruments which may not objectively reflect the fluctuation of daily behavior. Self-administered surveys, such as the Quick Inventory of Depressive Symptomatology (QIDS) commonly used to monitor depression, may show disparities from clinical decision. Smartphones provide easy access to many behavioral parameters, and Fitbit wrist bands are becoming another important tool to assess variables such as heart rates and sleep efficiency that are complementary to smartphone sensors. However, data used to identify depression indicators have been limited to a single platform either iPhone, or Android, or Fitbit alone due to the variation in their methods of data collection. The present work represents a large-scale effort to collect and integrate data from mobile phones, wearable devices, and self reports in depression analysis by designing a new machine learning approach. This approach constructs sparse mappings from sensing variables collected by various tools to two separate targets: self-reported QIDS scores and clinical assessment of depression severity. We propose a so-called heterogeneous multi-task feature learning method that jointly builds inference models for related tasks but of different types including classification and regression tasks. The proposed method was evaluated using data collected from 103 college students and could predict the QIDS score with an R 2 reaching 0.44 and depression severity with an F1-score as high as 0.77. By imposing appropriate regularizers, our approach identified strong depression indicators such as time staying at home and total time asleep.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Joint Modeling of Heterogeneous Sensing Data for Depression Assessment via Multi-task Learning

Lü

Chen

Yue

et al. 2018

Proc. ACM Interact. Mob. Wearable Ubiquitous Technol.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Studies have shown statistically significant differences that needs to be accommodated within the study design [71]. For example, Farhan et al [17] developed a smartphone based sensing application with PHQ-9 assessment on both iOS and Android. The study showed that the feature movement duration changed from a correlation of r = .06 (p = .36) on Android to r = -.13 (p = .07) on iOS.…”

Section: Limitations Data Collection and Analysis Methodsmentioning

confidence: 99%

“…A digital marker has been defined as a consumer generated physiological and behavioral measure collected from digital tool that can be used to explain, influence and/or predict health related outcomes [13]. Many studies have found statistically significant correlations between objective behavioral features collected from mobile and wearable technology and mood symptoms in non-clinical samples of participants without psychiatric illness (e.g., [14][15][16][17]) as well as in clinical samples of patients diagnosed with psychiatric disorders (e.g., [11,[18][19][20]), and this has raised great enthusiasm in terms of using mobile and wearable technology in the treatment and monitoring of depression and other affective disorders. It has been argued that such an approach may provide an easy and objective way to monitor illness activity and could serve as a digital marker of mood symptoms in affective disorders [18].…”

Section: Introductionmentioning

confidence: 99%

Correlations between objective behavioral features collected from mobile and wearable devices, and depressive mood symptoms in affective disorders: A systematic review (Preprint)

Rohani¹,

Faurholt‐Jepsen²,

Kessing³

et al. 2017

Preprint

View full text Add to dashboard Cite

Background: A number of studies have recently reported on the correlation between objective behavioral features collected via mobile and wearable technologies and mood symptoms in affective disorders (unipolar disorder and bipolar disorder). However, individual studies have reported on different and sometimes contradicting results and no quantitative systematic review of the correlation between objective behavioral features and mood symptoms has been published. Objective: The objectives of this systematic review were to 1) provide an overview of correlations between objective behavioral features and mood symptoms reported in the literature, and 2) investigate the strength and statistical significance of these correlations across studies. The answers to these questions could potentially help in the identification on which objective features have shown most promising results across studies. Methods: A systematic review of the scientific literature, reported according to the Preferred Reporting items for Systematic Reviews and Meta-Analysis (PRISMA) guidelines was conducted. IEEE Xplore, ACM Digital Library, Web of Sciences, PsychINFO, Pubmed, DBLP computer science bibliography, HTA, DARE, Scopus and Science Direct were searched and supplemented by hand examination of reference lists. The search was limited to studies published 2007-2017. Results: A total of 34 studies were eligible for the present review. They investigated 71 unique objective features divided into six different types covering 16 various sensor data inputs. Several objective features were found to have consistent correlation directionality with mood assessment (e.g., the amount of home stay, sleep duration, vigorous activity), while others showed directionality discrepancies across the studies (e.g., amount of SMS sent, time you spend between locations, frequency of smartphone screen activity).

show abstract

“…Sensor data is generally sampled at regular intervals on Android devices (e.g. every 5 minutes [6,24]), but iOS geolocation collection can be event-based depending on a significant location change [30], meaning location data is often collected intermittently on iPhones [31]. Missing data may limit the number of participant for which features can be reliably estimated.…”

Section: Data Completenessmentioning

confidence: 99%

Using Mobile Phone Sensor Technology for Mental Health Research: Integrated Analysis to Identify Hidden Challenges and Potential Solutions (Preprint)

Boonstra¹,

Nicholas²,

Wong³

et al. 2018

Preprint

View full text Add to dashboard Cite

show abstract

Behavior vs. introspection: refining prediction of clinical depression via smartphone sensing data

Cited by 96 publications

References 24 publications

Joint Modeling of Heterogeneous Sensing Data for Depression Assessment via Multi-task Learning

Joint Modeling of Heterogeneous Sensing Data for Depression Assessment via Multi-task Learning

Correlations between objective behavioral features collected from mobile and wearable devices, and depressive mood symptoms in affective disorders: A systematic review (Preprint)

Using Mobile Phone Sensor Technology for Mental Health Research: Integrated Analysis to Identify Hidden Challenges and Potential Solutions (Preprint)

Contact Info

Product

Resources

About