MétaCan
Menu
← Back to cohort
Record W4402281383 · doi:10.2196/58682

An Image-Recognition Dietary Assessment App for Adolescents With Obesity: Pilot Randomized Controlled Trial

2024· article· en· W4402281383 on OpenAlexafffundvenue
Krista Oei, Elizabeth Choi, Alisa Bar-Dayan, Jennifer Stinson, Mark R. Palmert, Jeffrey Alfonsi, Jill Hamilton

Bibliographic record

VenueJMIR Formative Research · 2024
Typearticle
Languageen
FieldHealth Professions
TopicMobile Health and mHealth Applications
Canadian institutionsHospital for Sick ChildrenUniversity of Toronto
FundersHospital for Sick Children
KeywordsUsabilityMedicineObesityRandomized controlled trialPercentilePhysical therapyComputer scienceInternal medicine

Abstract

fetched live from OpenAlex

BACKGROUND: Adolescence is a period of increased susceptibility to developing obesity-related health issues due to poor eating patterns and increased sedentary behaviors. Recommendations for pediatric obesity management include dietary assessments. However, adolescents often avoid food logging through traditional methods. The use of image-recognition dietary assessment apps in adolescents with obesity is not well studied. Eating for Wellness (E4W) is a mobile app that determines the nutritional content of meals from photos and incorporates nutritional goal setting. Nutritional data can be displayed for health care providers (HCPs) via the Clinician Portal, while the data are presented to the user in a manner that minimizes the focus on calorie counting. OBJECTIVE: This study aims to evaluate the usability and feasibility of E4W, a mobile health app designed to improve dietary intake in adolescents with obesity attending an obesity clinic, using a phased approach. METHODS: The overall study was conducted in 2 phases to refine and evaluate E4W. In Phase 1, usability was tested through 3 iterative cycles of patient interviews. A total of 14 patient participants, aged 12-18 years with a BMI≥97th percentile, were included. Participants performed standardized scenario-based tasks in E4W and provided feedback on the app. Two iterative cycles were conducted for HCPs (n=4). Refinements were made during each cycle based on issues encountered and feedback provided. In Phase 2, a pilot randomized controlled trial of 32 adolescents (16 adolescents enrolled in the experimental group for 1 month, and 16 controls enrolled for 1 month) was completed. Both groups met with their dietitian at baseline, midstudy, and 1 month following their baseline visit to discuss goals and eating patterns. The control group was instructed to take photos of all intake using their default phone camera, without access to E4W, while those in the experimental group received full access to E4W. The primary outcome was the feasibility of implementation. Secondary outcomes examined overall change in dietary intake and achievement of nutritional goals. RESULTS: Usability testing demonstrated that E4W and the Clinician Portal were easy to use, efficient, and well-liked by patients and HCPs. Feasibility testing revealed high patient acceptability scores. However, significant technical challenges were encountered. Although the use of E4W did not significantly impact patient engagement (control: mean 0.9, SD 0.7; experimental: mean 1.7, SD 1.9; P=.14), there were outliers in the experimental group with very high engagement and improved self-reported efficacy. Overall, there was no improvement in dietary intake, although assessment was hindered by poor adherence to traditional methods of food logging. CONCLUSIONS: E4W and the Clinician Portal were well-received by patients and HCPs. Further research is warranted and planned to determine if E4W can improve dietary intake and achievement of nutritional goals in adolescents with obesity. TRIAL REGISTRATION: ClinicalTrials.gov NCT05548868; https://clinicaltrials.gov/study/NCT05548868.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.006
metaresearch head score (Gemma)0.007
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Randomized trial · Consensus signal: Randomized trial
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.010
Threshold uncertainty score0.032

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0060.007
Meta-epidemiology (narrow)0.0020.001
Meta-epidemiology (broad)0.0040.003
Bibliometrics0.0010.001
Science and technology studies0.0010.002
Scholarly communication0.0010.002
Open science0.0020.001
Research integrity0.0030.003
Insufficient payload (model declined to judge)0.0100.001

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.121
GPT teacher head0.545
Teacher spread0.424 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designRandomized trial
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations5
Published2024
Admission routes3
Has abstractyes

Explore more

Same venueJMIR Formative Research→Same topicMobile Health and mHealth Applications→French-language works237,207→