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
  1. Home
  3. Using Digital Phenotyping For Depression Screening In Community-dwelling Older Adults: Bayesian Multilevel Hurdle Model Machine Learning Approach.
  1. Home
  3. Using Digital Phenotyping For Depression Screening In Community-dwelling Older Adults: Bayesian Multilevel Hurdle Model Machine Learning Approach.

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

Association of Conventional and Electronic Cigarette Use with Obesity and Central Obesity Among Korean Adults: A Cross-Sectional Analysis of the 2016-2018 KNHANES (2016-2018).

Medicina (Kaunas, Lithuania)·2026
Same author

Scalable and Privacy-Conscious End-to-End Processing of Large-Scale Clinical Data for Precision Medicine: Empirical Evaluation Study.

JMIR medical informatics·2026
Same author

Association Between Types of Shift Work and Physical Health Symptoms, Including Musculoskeletal Symptoms and Sleep Disturbance: Evidence From the Seventh Korean Working Conditions Survey.

Journal of occupational and environmental medicine·2025
Same author

Exploring the relationship between lifestyle factors and depressive symptoms in Korean adolescents amid the COVID-19 pandemic.

BMC psychiatry·2025
Same author

Longitudinal Examination of Stress and Depression in Older Adults Over a 2-Year Period: Moderation Effect of Varied Social Support Measures.

Depression and anxiety·2025
Same author

Explainable Artificial Intelligence Models for Predicting Depression Based on Polysomnographic Phenotypes.

Bioengineering (Basel, Switzerland)·2025
Same journal

Supporting Radiology Resident Education and Clinical Decision-Making With Large Language Models: Comparative Study of Reasoning Models DeepSeek-R1 and ChatGPT-o1.

JMIR AI·2026
Same journal

Patient Perceptions on the Use of Artificial Intelligence in Creating Clinical Research Documents: Survey Study.

JMIR AI·2026
Same journal

Application of Language Models for the Analysis of Adverse Drug Events in Pharmaceutical Research and Development: Scoping Review.

JMIR AI·2026
Same journal

Correction: Deep Learning for Age Estimation and Sex Prediction Using Mandibular-Cropped Cephalometric Images: Comparative Model Development and Validation Study.

JMIR AI·2026
Same journal

AI-Assisted Systematic Literature Review of the Economic Burden of Pneumococcal Disease: Development and Validation Study.

JMIR AI·2026
Same journal

Knowledge-Augmented Large Language Model for Multimodal Electronic Health Record-Based Risk Prediction: Development and Validation Study.

JMIR AI·2026
See all related articles

Related Experiment Video

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
12:18

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

Using Digital Phenotyping for Depression Screening in Community-Dwelling Older Adults: Bayesian Multilevel Hurdle

Moo-Kwon Chung1, Hyo-Sang Lim2, Sang Yup Lee3

  • 1Department of Global Public Administration, Yonsei University Mirae Campus, Wonju, Republic of Korea.

JMIR AI
|May 15, 2026

View abstract on PubMed

Summary
This summary is machine-generated.

Digital phenotyping using wearable devices helps identify depression in older adults. A machine learning model effectively screens for depressive symptom severity and presence, accounting for individual differences.

Keywords:
Bayesian modelingdepressiondigital phenotypingmachine learningmultilevel modelingolder adults

More Related Videos

Closed-Loop Neurostimulation for Biomarker-Driven, Personalized Treatment of Major Depressive Disorder
05:19

Closed-Loop Neurostimulation for Biomarker-Driven, Personalized Treatment of Major Depressive Disorder

Published on: July 7, 2023

Related Experiment Videos

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
12:18

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

Closed-Loop Neurostimulation for Biomarker-Driven, Personalized Treatment of Major Depressive Disorder
05:19

Closed-Loop Neurostimulation for Biomarker-Driven, Personalized Treatment of Major Depressive Disorder

Published on: July 7, 2023

Area of Science:

  • Gerontology
  • Digital Health
  • Machine Learning

Background:

  • Aging populations face increased depression risk, yet stigma deters clinical visits.
  • Digital phenotyping offers a promising solution for early detection via wearable devices.
  • Machine learning approaches are needed to analyze complex individual data for depression monitoring.

Purpose of the Study:

  • To assess active and passive digital phenotyping data for monitoring depression probability and severity.
  • To apply multilevel hurdle modeling within a machine learning framework for efficient depression screening in older adults.

Main Methods:

  • Analysis of 1011 cases from 147 older Korean adults over 2 years.
  • Collection of active/passive sensing data via smartphones and smartwatches, alongside monthly PHQ-9.
  • Application of parallel analysis, principal component analysis, and a Bayesian multilevel hurdle model.

Main Results:

  • Weekly stress and sleep features were key components in principal components (PCs).
  • A PC of low distress and high social support correlated significantly with depression.
  • The model achieved high accuracy in screening severity (R2=0.53) and detection (AUC=0.88, F1=0.75).

Conclusions:

  • Digital phenotyping data, combined with clinical tools, can monitor depression in older adults.
  • Dimensionality reduction and Bayesian multilevel models aid in identifying risk and screening.
  • Digital phenotyping enables personalized health tracking, even with significant between-person variance.