Relative validity of a mobile AI-technology–assisted dietary assessment in adolescent females in Vietnam

Abstract

Background There is a gap in data on dietary intake of adolescents in low- and middle-income countries. Traditional methods for dietary assessment are resource intensive and lack accuracy with regards to portion size estimation. Technology assisted dietary assessment tools have been proposed but few have been validated for feasibility of use in LMICs. Objectives We assess the relative validity of FRANI (Food Recognition Assistance and Nudging Insights), a mobile Artificial Intelligence (AI) application for dietary assessment in adolescent females (n = 36) aged 12–18y in Vietnam, against weighed records (WR) standard, and compared FRANI performance to a multi-pass 24-hour recall (24HR). Methods Dietary intake was assessed using 3 methods: FRANI, WRs and 24HRs undertaken on three non-consecutive days. Equivalence of nutrient intakes was tested using mixed effect models adjusting for repeated measures, using 10%, 15% and 20% bounds. The concordance correlation coefficient (CCC) was used to assess the agreement between methods. Sources of errors were identified for memory and portion size estimation bias. Results Equivalence between FRANI app and WR was determined at the 10% bound for energy, protein and fat and four nutrients (iron, riboflavin, vitamin B6 and zinc), and at 15% and 20% bounds for carbohydrate, calcium, vitamin C, thiamin, niacin, and folate. Similar results were observed for differences between 24HR and WR with 20% equivalent bound for all nutrients except for vitamin A. The CCCs between FRANI and WR (0.60,0.81) were slightly lower CCCs between 24HR and WR (0.70,0.89) for energy and most nutrients. Memory error (food omissions or intrusions) was ∼21% with no clear pattern apparent on portion size estimation bias for foods. Conclusions AI assisted dietary assessment and 24HR accurately estimate nutrient intake in adolescent females when compared to WR. Errors could be reduced with further improvements of AI-assisted food recognition and portion estimation.

Precision Nutrition and Artificial Intelligence Mobile Apps: A Narrative Review

“…After searching for relevant articles in PubMed, 198 results were found and 7 clinical studies were considered relevant for inclusion [6][7][8][9][10][11][12]. Table 1 provides a brief overview of the studies included in this analysis (five randomized controlled trials, two crossover studies, and a pilot trial).…”

The use of machine learning in paediatric nutrition

“…The second study used mobile phone photos taken by participants to classify foodstuffs and estimate nutrient intakes [17 ▪ ]. The same system was validated in Vietnam [18 ▪ ]. Another group focused on food labels, demonstrating that natural language processing models could accurately determine nutrient contents of food from images of their packaging [19].…”

Mobile Apps for Dietary and Food Timing Assessment: Evaluation for Use in Clinical Research

“…When evaluating dietary assessment apps, participant and researcher efficiencies vary based on the input method [32], with food photography and automated image scoring leading to the greatest gains in efficiency. Martin et al [50] demonstrated that food photography could result in a smaller error than self-report, and automated image scoring using AI was comparable with or more accurate than trained dieticians in calculating nutrients [51][52][53]. Keeney et al [34] showed increased efficiency for photo-based versus database entry caloric analysis (35 min/wk vs 85-90 min/wk).…”