Measuring Diet Intake in Adolescents: Relative Validation of an Artificial Intelligence Enhanced, Image Assisted Mobile Application in the CHILD Cohort Study
Bibliographic record
Abstract
Objectives: Retinopathy of prematurity (ROP) is an eye condition in newborns caused by oxidative stress leading to the abnormal growth of the retinal blood vessels.Rodent models are commonly used to study ROP, but the retina must be analyzed in vitro, leaving no opportunity to monitor its progression.Fundus imaging is used in clinical ophthalmology and could provide a method for in vivo imaging in rodents with ROP.Lutein is a dietary antioxidant that serves as the main component of the macular pigment, making it vital for infant ocular health.Lutein has been shown to promote revascularization in neonatal rats with ROP.The aim of this study was to develop a smartphone-based fundus imaging system and a computer vision-based method to monitor the in vivo changes caused by lutein in neonatal rats with ROP.Methods: KRN 633 was used to induce ROP, and lutein was administered orally to rats with ROP from postnatal day 9 (P9) until P21.Rat pups with ROP receiving olive oil served as a negative control.Fundus imaging was conducted using a condensing lens and a smartphone.At P22, rats were euthanized, and in vitro analysis of the retina was conducted for comparison using immunohistochemistry.The arterial tortuosity was analyzed from fundus images manually using ImageJ and by the computer vision-based method developed from the OpenCV module in Python.Results: ROP induced tortuous arteries in the fundus and microscopy images of the retina.Lutein improved arterial tortuosity in rats with ROP, which was successfully visualized by both the microscopy and fundus images.The two imaging techniques exhibited a significantly positive correlation.Additionally, the analysis of the fundus images with the computer vision-based method was significantly correlated with ImageJ analysis.Conclusions: The smartphone-based fundus camera system could be used to supplement traditional histological analysis by providing a cheap and accessible method for in vivo imaging and monitoring the effect of nutritional interventions on retinal diseases in rodent models.With future research, the computer vision-based image processing technique can be enhanced to evaluate other measures of visual function.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".