An artificial intelligence (AI)-assisted dietary recording application (app) demonstrates its potential as an alternative to expert evaluation for nutritional management in young patients with anorexia nervosa (AN), according to a study.
“The overall level of agreement suggests that the app has potential clinical utility when used with appropriate attention to portion size inputs and dish selection,” the investigators said.
Thirty female inpatients with AN (mean age 14.8 years) and their mothers participated in the study. During hospital leave prior to discharge, the parents recorded 1 day of their child’s dietary intake using the app based on meal photographs. The energy and nutrient intakes estimated by the app were then compared with that of a registered dietitian via visual estimation of the photographs.
The investigators examined the differences using the Wilcoxon signed-rank test, explored associations using Spearman’s correlation coefficients, and assessed agreement using Bland‒Altman analysis. They also performed sensitivity analyses excluding extreme outliers.
No significant difference was noted in the median total energy intake between the AI-assisted app and the reference method (2,462 vs 2,439 kcal/day). [Nutrients 2026;18:708]
On the other hand, moderate to high correlations were seen for total energy (ρ=0.62) and major nutrient intakes. The app appeared to overestimate such intakes, but no systematic bias was found in Bland‒Altman analyses. Furthermore, two outliers were excluded, strengthening the associations for total energy intake (ρ=0.74) and narrowing the limits of agreement.
“Although the app tended to overestimate energy and nutrient intakes, sensitivity analyses excluding outliers strengthened the validity of results,” the investigators said.
“These findings suggest that the app can estimate the total energy and major nutrient intake with an accuracy comparable to that of a trained dietician,” they added.
Accommodating behaviours
The overestimated energy intake may indicate the parents’ limited experience with tablet-based data entry or their low confidence in using the app. Family dynamics may also contribute to the observed overestimation of energy intake, specifically through parental behaviour, according to the investigators.
“One hypothesis is that a subset of parents is engaged in accommodating eating disorders by modifying their behaviour to reduce their child’s distress,” they said. [J Eat Disord 2024;12:143]
A previous study found that family caregivers’ anxiety correlated with accommodating behaviours (eg, bending rules to avoid conflict) in patients with eating disorders. [Eat Disord 2021;29:327-343]
“In our study, such accommodating behaviours could partly explain the overreporting of food intake out of sympathy, particularly with the intention of hastening hospital discharge,” the investigators said.
Another possible explanation is that careless dietary logging may stem from the parents’ indifference toward their child’s care. Caregiver burdens and burnout can result in emotional disengagement as a coping mechanism, according to the investigators.
An earlier study, for instance, found that mothers who described their caregiving experiences negatively tended to adopt avoidance-based coping styles. [Psychiatry Res 2018;260:241-247]
“In our study, some parents may have entered the data inaccurately or without vigilance, potentially contributing to an unintentional overestimation of food intake,” the investigators said.
“Further validation studies in broader clinical settings as well as refinement of the assessment system are needed,” they said.