Validating Accuracy of a Mobile Application against Food Frequency Questionnaire on Key Nutrients with Modern Diets for mHealth Era

Abstract

In preparation for personalized nutrition, an accurate assessment of dietary intakes on key essential nutrients using smartphones can help promote health and reduce health risks across vulnerable populations. We, therefore, validated the accuracy of a mobile application (app) against Food Frequency Questionnaire (FFQ) using artificial intelligence (AI) machine-learning-based analytics, assessing key macro- and micro-nutrients across various modern diets. We first used Bland and Altman analysis to identify and visualize the differences between the two measures. We then applied AI-based analytics to enhance prediction accuracy, including generalized regression to identify factors that contributed to the differences between the two measures. The mobile app underestimated most macro- and micro-nutrients compared to FFQ (ranges: −5% for total calories, −19% for cobalamin, −33% for vitamin E). The average correlations between the two measures were 0.87 for macro-nutrients and 0.84 for micro-nutrients. Factors that contributed to the differences between the two measures using total calories as an example, included caloric range (1000–2000 versus others), carbohydrate, and protein; for cobalamin, included caloric range, protein, and Chinese diet. Future studies are needed to validate actual intakes and reporting of various diets, and to examine the accuracy of mobile App. Thus, a mobile app can be used to support personalized nutrition in the mHealth era, considering adjustments with sources that could contribute to the inaccurate estimates of nutrients.

Validating Accuracy of an Internet-Based Application against USDA Computerized Nutrition Data System for Research on Essential Nutrients among Social-Ethnic Diets for the E-Health Era

“…We evaluated the essential nutrients from 131 social-ethnic diets taken by various vulnerable populations, continued from our series of studies [ 7 , 12 , 42 ]. Under-reporting is a common human behavior in human studies in recording dietary intake [ 13 , 43 , 44 ]; thus, validation of dietary intake with model social-ethnic diets as recipes or menus can offer precise and controlled nutrient intake for individuals to follow and consume [ 12 , 45 ].…”

“…Methyl donors including micro-nutrients such as vitamins (folate B9, cobalamin B12) and amino acids are crucial for DNA methylation in nutrigenomics pathways for personalized precision nutrition [ 7 , 8 , 9 , 10 , 11 ]. Various internet-based applications (apps) are rapidly developing in the e-Health era [ 12 , 13 , 14 ], that are accessible and convenient for assessing nutrient intake in real-time [ 15 , 16 , 17 , 18 ]. However, compared to established dietary measures, the accuracy of apps is yet to be examined for essential micro-nutrients in addition to macro-nutrients, with records of 1–3 day diaries and longer durations including a food frequency questionnaire (FFQ) [ 12 , 13 , 19 ].…”

“…The Bland-Altman analysis is a commonly used method to examine the validity of a new measure against another measure [ 13 , 19 , 38 , 39 , 40 , 41 ]. Additionally, machine-learning-based, artificial-intelligence (AI), generalized regression (GR) models could be employed to identify the source factors that could contribute to the differences between measures [ 7 , 42 ], with enhanced prediction accuracy [ 7 , 12 ]. A previous study noted that the source factors that could contribute to the differences between the two measures of an app and FFQ included caloric ranges; the difference between two measures for carbohydrates, protein, fat; and diet types [ 12 ].…”

“…Additionally, machine-learning-based, artificial-intelligence (AI), generalized regression (GR) models could be employed to identify the source factors that could contribute to the differences between measures [ 7 , 42 ], with enhanced prediction accuracy [ 7 , 12 ]. A previous study noted that the source factors that could contribute to the differences between the two measures of an app and FFQ included caloric ranges; the difference between two measures for carbohydrates, protein, fat; and diet types [ 12 ]. Therefore, in this study, we further validated the app against NDSR, to identify factors that could contribute to the differences between two measures for essential nutrients including various diet types, integrating AI method to confirm the source factors to the differences between the two measures.…”

Prediction Tool to Estimate Potassium Diet in Chronic Kidney Disease Patients Developed Using a Machine Learning Tool: The UniverSel Study

“…Most popular dietary surveys use 24-h dietary recalls, dietary records based on dietary databases and the food frequency questionnaires (FFQ) [23,24]. However, these surveybased methods suffer from lack of reliability [23].…”