International Food Policy Research Institute, Washington, DC, USA.
Thai Nguyen University of Pharmacy and Medicine, Thai Nguyen, Vietnam.
Am J Clin Nutr. 2022 Oct 6;116(4):992-1001. doi: 10.1093/ajcn/nqac216.
There is a gap in data on dietary intake of adolescents in low- and middle-income countries (LMICs). Traditional methods for dietary assessment are resource intensive and lack accuracy with regard to portion-size estimation. Technology-assisted dietary assessment tools have been proposed but few have been validated for feasibility of use in LMICs.
We assessed 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 12-18 y in Vietnam, against a weighed records (WR) standard and compared FRANI performance with a multi-pass 24-h recall (24HR).
Dietary intake was assessed using 3 methods: FRANI, WR, and 24HRs undertaken on 3 nonconsecutive days. Equivalence of nutrient intakes was tested using mixed-effects 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.
Equivalence between the FRANI app and WR was determined at the 10% bound for energy, protein, and fat and 4 nutrients (iron, riboflavin, vitamin B-6, and zinc), and at 15% and 20% bounds for carbohydrate, calcium, vitamin C, thiamin, niacin, and folate. Similar results were observed for differences between 24HRs and WR with a 20% equivalent bound for all nutrients except for vitamin A. The CCCs between FRANI and WR (0.60, 0.81) were slightly lower between 24HRs 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.
AI-assisted dietary assessment and 24HRs accurately estimate nutrient intake in adolescent females when compared with WR. Errors could be reduced with further improvements in AI-assisted food recognition and portion estimation.
在中低收入国家（LMICs），青少年饮食摄入数据存在缺口。传统的饮食评估方法资源密集且在估计份量方面准确性不足。已经提出了技术辅助饮食评估工具，但很少有针对在 LMICs 中使用的可行性进行验证的工具。
我们评估了 FRANI（食物识别辅助和推知洞察）在越南 12-18 岁少女（n=36）中的相对有效性，该工具是一种移动人工智能（AI）应用程序，用于饮食评估，与称重记录（WR）标准进行了比较，并比较了 FRANI 与多次 24 小时回顾（24HR）的性能。
使用 3 种方法评估饮食摄入：FRANI、WR 和 3 天内进行的 24HR。使用混合效应模型调整重复测量，使用 10%、15%和 20%的界限测试营养素摄入量的等效性。使用一致性相关系数（CCC）评估方法之间的一致性。确定了记忆和份量估计偏差的误差源。
FRANI 应用程序与 WR 在能量、蛋白质和脂肪以及 4 种营养素（铁、核黄素、维生素 B-6 和锌）的 10%界限以及碳水化合物、钙、维生素 C、硫胺素、烟酸和叶酸的 15%和 20%界限上确定了等效性。24HR 与 WR 之间的差异也观察到类似的结果，除了维生素 A 之外，所有营养素的等效性都在 20%。FRANI 与 WR 之间的 CCC（0.60、0.81）略低于 24HR 与 WR 之间的 CCC（0.70、0.89），对于能量和大多数营养素而言。记忆错误（食物遗漏或干扰）约为 21%，对于食物的份量估计偏差没有明显的模式。
与 WR 相比，人工智能辅助饮食评估和 24HR 可以准确估计少女的营养素摄入量。通过进一步改进人工智能辅助食物识别和份量估计，可以减少错误。
