Development and validation of a smartphone image-based app for dietary intake assessment among Palestinian undergraduates

Abstract

Accurate dietary assessment is required in a variety of research fields and clinical settings. Image-based dietary assessment using smartphones applications offer the opportunity to reduce both researcher and participant burden compared to traditional dietary assessment methods. The current study, conducted in Palestine, aimed to design an image-based dietary assessment application, to assess the relative validity of the application as a dietary assessment tool for energy and macronutrient intake using the 3-Day Food Record (3-DFR) as a reference method, and to test its usability among a sample of Palestinian university students. The development of a smartphone application (Ghithaona) designed to assess energy and macronutrient intake is reported. The application validity was tested among a sample of Palestinian undergraduates from An-Najah National University. Participants recorded their dietary intake using the Ghithaona application over 2 consecutive days and 1 weekend day. Intake from the Ghithaona application were compared to intake collected from 3-DFR, taken on 2 consecutive weekdays and 1 weekend day, in the second week following the Ghithaona application. At the end of the study, participants completed an exit survey to test assess application usability and to identify barriers to its use. Mean differences in energy, and macronutrients intake were evaluated between the methods using paired t-tests or Wilcoxon signed-rank tests. Agreement between methods was ascertained using Pearson correlations and Bland-Altman plots. The Ghithaona application took 6 months to develop. The validation test was completed by 70 participants with a mean age of 21.0 ± 2.1 years. No significant differences were found between the two methods for mean intakes of energy or macronutrients (p > 0.05). Significant correlations between the two methods were observed for energy, and all macronutrients (r = 0.261-0.58, p ≤ 0.05). Bland-Altman plots confirmed wide limits of agreement between the methods with no systematic bias. According to the exit survey, it was found that majority of participants strongly agreed and agreed that the application saves time (94.2%), helps the participant to pay attention to their dietary habits (87.2%), and is easy to use (78.6%). The Ghithaona application showed relative validity for assessment of nutrient intake of Palestinian undergraduates.

Figure 1

Screenshots taken on Samsung device.

Figure 1

Screenshots taken on Samsung device.

Figure 2

Bland–Altman plots showing mean difference (3-DFR—Ghithaona app, solid line) vs. mean intakes ((3-DFR + Ghithaona app)/2) for (a) energy; (b) carbohydrate; (c) protein; (d) fat. The dotted lines indicate the 95% limits of agreement (SD 1.96).