A Brief Tool to Assess Image-Based Dietary Records and Guide Nutrition Counselling Among Pregnant Women: An Evaluation
Bibliographic record
Abstract
BACKGROUND: Dietitians ideally should provide personally tailored nutrition advice to pregnant women. Provision is hampered by a lack of appropriate tools for nutrition assessment and counselling in practice settings. Smartphone technology, through the use of image-based dietary records, can address limitations of traditional methods of recording dietary intake. Feedback on these records can then be provided by the dietitian via smartphone. Efficacy and validity of these methods requires examination. OBJECTIVE: The aims of the Australian Diet Bytes and Baby Bumps study, which used image-based dietary records and a purpose-built brief Selected Nutrient and Diet Quality (SNaQ) tool to provide tailored nutrition advice to pregnant women, were to assess relative validity of the SNaQ tool for analyzing dietary intake compared with nutrient analysis software, to describe the nutritional intake adequacy of pregnant participants, and to assess acceptability of dietary feedback via smartphone. METHODS: Eligible women used a smartphone app to record everything they consumed over 3 nonconsecutive days. Records consisted of an image of the food or drink item placed next to a fiducial marker, with a voice or text description, or both, providing additional detail. We used the SNaQ tool to analyze participants' intake of daily food group servings and selected key micronutrients for pregnancy relative to Australian guideline recommendations. A visual reference guide consisting of images of foods and drinks in standard serving sizes assisted the dietitian with quantification. Feedback on participants' diets was provided via 2 methods: (1) a short video summary sent to participants' smartphones, and (2) a follow-up telephone consultation with a dietitian. Agreement between dietary intake assessment using the SNaQ tool and nutrient analysis software was evaluated using Spearman rank correlation and Cohen kappa. RESULTS: We enrolled 27 women (median age 28.8 years, 8 Indigenous Australians, 15 primiparas), of whom 25 completed the image-based dietary record. Median intakes of grains, vegetables, fruit, meat, and dairy were below recommendations. Median (interquartile range) intake of energy-dense, nutrient-poor foods was 3.5 (2.4-3.9) servings/day and exceeded recommendations (0-2.5 servings/day). Positive correlations between the SNaQ tool and nutrient analysis software were observed for energy (ρ=.898, P<.001) and all selected micronutrients (iron, calcium, zinc, folate, and iodine, ρ range .510-.955, all P<.05), both with and without vitamin and mineral supplements included in the analysis. Cohen kappa showed moderate to substantial agreement for selected micronutrients when supplements were included (kappa range .488-.803, all P ≤.001) and for calcium, iodine, and zinc when excluded (kappa range .554-.632, all P<.001). A total of 17 women reported changing their diet as a result of the personalized nutrition advice. CONCLUSIONS: The SNaQ tool demonstrated acceptable validity for assessing adequacy of key pregnancy nutrient intakes and preliminary evidence of utility to support dietitians in providing women with personalized advice to optimize nutrition during pregnancy.
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 | 0.015 | 0.034 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 0.001 |
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.
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".