Weight Loss Following Use of a Smartphone Food Photo Feature: Retrospective Cohort Study
Bibliographic record
Abstract
BACKGROUND: Tracking of dietary intake is key to enhancing weight loss. Mobile apps may be useful for tracking food intake and can provide feedback about calories and nutritional value. Recent technological developments have enabled image recognition to identify foods and track food intake. OBJECTIVE: We aimed to determine the effectiveness of using photography as a feature of a smartphone weight loss app to track food intake in adults who were overweight or obese. METHODS: ; ≥4 days of logged food intake; and ≥2 weigh-ins) who used a mobile-based weight loss app. In a retrospective study, we compared those who used the photo feature (n=9871) and those who did not use the feature (n=113,916). Linear regression analyses were used to assess use of the photo feature in relation to percent weight loss. RESULTS: Weight loss was greater in the group using the photo feature (Δ=0.14%; 95% CI 0.06-0.22; P<.001). The photo feature group used the weight loss app for a longer duration (+3.5 days; 95% CI 2.61-4.37; P<.001) and logged their food intake on more days (+6.1 days; 95% CI 5.40-6.77; P<.001) than the nonusers. Mediation analysis showed that the weight loss effect was absent when controlling for either duration or number of logged days in the program. CONCLUSIONS: This study was the first to examine the effect of a food photo feature to track food intake on weight loss in a free-living setting. Use of photo recognition was associated with greater weight loss, which was mediated by the duration of app use and number of logged days in the program.
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 imitationNot 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.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.000 | 0.001 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
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".