Validation of Mobile Artificial Intelligence Technology–Assisted Dietary Assessment Tool Against Weighed Records and 24-Hour Recall in Adolescent Females in Ghana

Background Important gaps exist on dietary intake of adolescents in low- and middle-income countries (LMICs), partly due to expensive assessment methods and inaccuracy in portion size estimation. Dietary assessment tools leveraging mobile technologies exist but few have been validated in LMICs. Objective We validated FRANI (Food Recognition Assistance and Nudging Insights), a mobile Artificial Intelligence (AI) dietary assessment application in adolescent females aged 12–18y (n = 36) in Ghana, against weighed records (WR), and multi-pass 24-hour recalls (24HR). Methods Dietary intake was assessed during three non-consecutive days using FRANI, WRs and 24HRs. Equivalence of nutrient intake was tested using mixed effect models adjusted for repeated measures, by comparing ratios (FRANI/WR and 24HR/WR) with equivalence margins at 10%, 15% and 20% error bounds. Agreement between methods was assessed using the concordance correlation coefficient (CCC). Results Equivalence for FRANI and WR was determined at the 10% bound for energy intake, 15% for five nutrients (iron, zinc, folate, niacin, and vitamin B6), and 20% for protein, calcium, riboflavin, and thiamine intakes. Comparisons between 24HR and WR estimated equivalence at the 20% bound for energy, carbohydrate, fibre, calcium, thiamine and vitamin A intakes. The CCCs by nutrient between FRANI and WR ranged between 0.30 and 0.68, which was similar for CCC between 24HR and WR (ranging between 0.38 and 0.67). Comparisons of food consumption episodes from FRANI and WR found 31% omission and 16% intrusion errors. Omission and intrusion errors were lower when comparing 24HR to WR (21% and 13% respectively). Conclusions FRANI AI-assisted dietary assessment could accurately estimate nutrient intake in adolescent females compared to WR in urban Ghana. FRANI estimates were at least as accurate as those provided through 24HR. Further improvements in food-recognition and portion estimation in FRANI could reduce errors and improve overall nutrient intake estimations.

Bibliographic Details

Main Authors:	Folson, Gloria, Bannerman, Boateng, Atadze, Vicentia, Ador, Gabriel, Kolt, Bastien, McCloske, Peter, Gangupantulu, Rohit, Arrieta, Alejandra, Braga, Bianca C., Arsenault, Joanne, Kehs, Annalyse, Doyle, Frank, Tran, Lan Mai, Hoang, Nga Thu, Hughes, David, Nguyen, Phuong Hong, Gelli, Aulo
Format:	Journal Article biblioteca
Language:	English
Published:	Elsevier 2023-08
Subjects:	adolescence (human), artificial intelligence, diet, nutrient intake, women,
Online Access:	https://hdl.handle.net/10568/130688 https://doi.org/10.1016/j.tjnut.2023.06.001
Tags:	Add Tag No Tags, Be the first to tag this record!