Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

SPI1 Promotes Intracranial Aneurysm Formation by Inhibiting Wnt5a Transcription.

Frontiers in bioscience (Landmark edition)·2026
Same author

Medical Appointments are Associated With Same-Day Worry and Sleep Difficulties Among Cancer Survivors.

Psycho-oncology·2026
Same author

Parental Autonomy Support and Psychological Resilience in College Students: The Longitudinal Sequential Mediating Roles of Basic Psychological Need Satisfaction and Autonomous Motivation.

Psychological reports·2026
Same author

Mood in the moment: a study protocol for embedding ecological momentary assessments into established longitudinal cohorts to examine depression in real time.

BMJ open·2026
Same author

Feasibility and Acceptability of a Smartphone and Wearable Assessment Protocol for Adolescents with Depression.

Research on child and adolescent psychopathology·2026
Same author

Multisite Assessment of Methods for Cell Preservation Upstream of Single-Cell RNA Sequencing.

Journal of biomolecular techniques : JBT·2026

Related Experiment Video

Updated: Jun 18, 2025

Smartphone Fundus Photography
05:51

Smartphone Fundus Photography

Published on: July 6, 2017

38.9K

MoodCapture: Depression Detection Using In-the-Wild Smartphone Images.

Subigya Nepal1, Arvind Pillai1, Weichen Wang1

  • 1Dartmouth College, Hanover, New Hampshire, USA.

Proceedings of the SIGCHI Conference on Human Factors in Computing Systems. CHI Conference
|August 5, 2024
PubMed
Summary
This summary is machine-generated.

MoodCapture uses smartphone photos to assess depression, analyzing image attributes to detect mood changes. This novel approach offers insights into digital mental health assessment and user privacy concerns.

Keywords:
DepressionFaceFacial ExpressionsIn-the-wildMachine LearningMental HealthMoodPHQPassive SensingSmartphones

More Related Videos

Author Spotlight: Therapeutic Benefit of Closed-Loop Deep Brain Stimulation in Depression Treatment
05:19

Author Spotlight: Therapeutic Benefit of Closed-Loop Deep Brain Stimulation in Depression Treatment

Published on: July 7, 2023

2.2K
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

2.7K

Related Experiment Videos

Last Updated: Jun 18, 2025

Smartphone Fundus Photography
05:51

Smartphone Fundus Photography

Published on: July 6, 2017

38.9K
Author Spotlight: Therapeutic Benefit of Closed-Loop Deep Brain Stimulation in Depression Treatment
05:19

Author Spotlight: Therapeutic Benefit of Closed-Loop Deep Brain Stimulation in Depression Treatment

Published on: July 7, 2023

2.2K
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

2.7K

Area of Science:

  • Digital mental health
  • Computational psychiatry
  • Computer vision for healthcare

Background:

  • Major depressive disorder (MDD) diagnosis often relies on subjective self-reports.
  • Objective, continuous monitoring of depression symptoms is challenging.
  • Mobile sensing offers potential for ecological momentary assessment of mental health.

Purpose of the Study:

  • To introduce MoodCapture, a system for assessing depression using passively captured smartphone images.
  • To investigate the relationship between visual image attributes and depression severity.
  • To evaluate the feasibility and user perceptions of image-based depression detection.

Main Methods:

  • Collected over 125,000 images from 177 participants with MDD over 90 days.
  • Images were captured naturally during daily life, concurrent with PHQ-8 depression surveys.
  • Utilized a random forest model trained on facial landmarks and image attributes to classify depression and predict PHQ-8 scores.

Main Results:

  • The random forest model effectively classified depressed versus non-depressed states and predicted PHQ-8 scores.
  • Analysis revealed significant image attributes correlating with depression, including angle, color, location, objects, and lighting.
  • Post-hoc analysis provided insights into feature importance and potential biases.

Conclusions:

  • Smartphone-captured images contain quantifiable visual information relevant to depression assessment.
  • MoodCapture demonstrates potential as a novel, in-the-wild tool for monitoring depression.
  • User privacy concerns are critical and must inform the design of future digital mental health technologies.