Maintenance Notice

Due to necessary scheduled maintenance, the JMIR Publications website will be unavailable from Wednesday, July 01, 2020 at 8:00 PM to 10:00 PM EST. We apologize in advance for any inconvenience this may cause you.

Who will be affected?

Accepted for/Published in: JMIR Pediatrics and Parenting

Date Submitted: Sep 13, 2021
Date Accepted: Jan 11, 2022

The final, peer-reviewed published version of this preprint can be found here:

An Objective System for Quantitative Assessment of Television Viewing Among Children (Family Level Assessment of Screen Use in the Home-Television): System Development Study

Kumar Vadathya A, Musaad S, Beltran A, Perez O, Meister L, Baranowski T, Hughes SO, Mendoza JA, Sabharwal A, Veeraraghavan A, O'Connor T

An Objective System for Quantitative Assessment of Television Viewing Among Children (Family Level Assessment of Screen Use in the Home-Television): System Development Study

JMIR Pediatr Parent 2022;5(1):e33569

DOI: 10.2196/33569

PMID: 35323113

PMCID: 8990369

An objective system for quantitative assessment of TV viewing among children: FLASH-TV

  • Anil Kumar Vadathya; 
  • Salma Musaad; 
  • Alicia Beltran; 
  • Oriana Perez; 
  • Leo Meister; 
  • Tom Baranowski; 
  • Sheryl O. Hughes; 
  • Jason A. Mendoza; 
  • Ashutosh Sabharwal; 
  • Ashok Veeraraghavan; 
  • Teresia O'Connor

ABSTRACT

Background:

TV viewing among children is associated with developmental and health outcomes, yet measurement techniques for TV viewing are prone to errors/biases.

Objective:

To develop a system to objectively and passively measure children’s TV viewing time.

Methods:

The Family Level Assessment of Screen use in the Home-TV (FLASH-TV) system includes three sequential algorithms applied to video data collected in front of a TV screen: face detection, face verification, and gaze estimation. Twenty-one families of diverse race/ethnicity were enrolled in one of four design studies to train the algorithms and provide proof of concept testing for the integrated FLASH-TV system. Video data were collected of each family in a laboratory mimicking a living room, or in the child’s home. Staff coded the video data for the target child as the gold standard. The accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were calculated for each algorithm, as compared to the gold standard. Prevalence and biased adjusted Kappa scores and an intraclass correlation (ICC) using a generalized linear mixed model compared FLASH-TV’s estimation of TV viewing duration to the gold standard.

Results:

FLASH-TV demonstrated high sensitivity for detecting faces (95.5%-97.9%) and performed well on face verification when the child’s gaze was on the TV. Each of the metrics for estimating the child’s gaze on the screen was moderate to good (range: 55.1% NPV to 91.2% specificity). When combining the three sequential steps, FLASH-TV estimation of the child’s screen viewing was overall good, with an ICC for overall time watched TV of 0.725 across conditions.

Conclusions:

FLASH-TV offers a critical step forward in improving the assessment of children’s TV viewing. Clinical Trial: Not applicable


 Citation

Please cite as:

Kumar Vadathya A, Musaad S, Beltran A, Perez O, Meister L, Baranowski T, Hughes SO, Mendoza JA, Sabharwal A, Veeraraghavan A, O'Connor T

An Objective System for Quantitative Assessment of Television Viewing Among Children (Family Level Assessment of Screen Use in the Home-Television): System Development Study

JMIR Pediatr Parent 2022;5(1):e33569

DOI: 10.2196/33569

PMID: 35323113

PMCID: 8990369

Download PDF


Request queued. Please wait while the file is being generated. It may take some time.

© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.