Nutritools

Log in Register

Tool Library Tool Information Best Practice Guidelines – Evaluation Checklist (opens new tab)

Validation Information: Keenoa

Ji 2020

Validity and Usability of a Smartphone Image-Based Dietary Assessment App Compared to 3-Day Food Diaries in Assessing Dietary Intake Among Canadian Adults: Randomized Controlled Trial

Background: Accurate dietary assessment is needed in studies that include analysis of nutritional intake. Image-based dietary assessment apps have gained in popularity for assessing diet, which may ease researcher and participant burden compared to traditional pen-to-paper methods. However, few studies report the validity of these apps for use in research. Keenoa is a smartphone image-based dietary assessment app that recognizes and identifies food items using artificial intelligence and permits real-time editing of food journals.

Objective: This study aimed to assess the relative validity of an image-based dietary assessment app — Keenoa — against a 3-day food diary (3DFD) and to test its usability in a sample of healthy Canadian adults.

Methods: We recruited 102 participants to complete two 3-day food records. For 2 weeks, on 2 non-consecutive days and 1 weekend day, in random order, participants completed a traditional pen-to-paper 3DFD and the Keenoa app. At the end of the study, participants completed the System Usability Scale. The nutrient analyses of the 3DFD and Keenoa data before (Keenoa-participant) and after they were reviewed by dietitians (Keenoa-dietitian) were analyzed using analysis of variance. Multiple tests, including the Pearson coefficient, cross-classification, kappa score, % difference, paired t test, and Bland-Altman test, were performed to analyze the validity of Keenoa (Keenoa-dietitian).

Results: The study was completed by 72 subjects. Most variables were significantly different between Keenoa-participant and Keenoa-dietitian (P<.05) except for energy, protein, carbohydrates, fiber, vitamin B1, vitamin B12, vitamin C, vitamin D, and potassium. Significant differences in total energy, protein, carbohydrates, % fat, saturated fatty acids, iron, and potassium were found between the 3DFD and Keenoa-dietitian data (P<.05). The Pearson correlation coefficients between the Keenoa-dietitian and 3DFD ranged from .04 to .51. Differences between the mean intakes assessed by the 3DFD and Keenoa-dietitian were within 10% except for vitamin D (misclassification rate=33.8%). The majority of nutrients were within an acceptable range of agreement in the Bland-Altman analysis; no agreements were seen for total energy, protein, carbohydrates, fat (%), saturated fatty acids, iron, potassium, and sodium (P<.05). According to the System Usability Scale, 34.2% of the participants preferred using Keenoa, while 9.6% preferred the 3DFD.

Conclusions: The Keenoa app provides acceptable relative validity for some nutrients compared to the 3DFD. However, the average intake of some nutrients, including energy, protein, carbohydrates, % fat, saturated fatty acids, and iron, differed from the average obtained using the 3DFD. These findings highlight the importance of verifying data entries of participants before proceeding with nutrient analysis. Overall, Keenoa showed better validity at the group level than the individual level, suggesting it can be used when focusing on the dietary intake of the general population. Further research is recommended with larger sample sizes and objective dietary assessment approaches.

Web Link

Validation Information

Author
Ji
Year of Publication
2020

Tool Information

Dietary Exposure Measured
Full Nutrient
Tool Type
Food Diary Estimated
Timeframe Tool Measures info
3 Days
Portion Size Measures info
Using visual aids , the participant scrolled to the correct unit and identified a number corresponding to the unit.
Reporting Method info
Prospective
Format info
Online
Supplements Measured
Not Reported
Administration Method info
Self-administered

Study Information

Study Location
Quebec, Canada
Associated Nutrient Database
Canadian Nutrient File (2015) dataset
Comparator Validated Against
Food Diary Estimated

Participants

Sample Size
72
Lifestage
Adults and Elderly
Age of Population

Mean: 38.5years

Sex
Both
Other Notable Characteristics
Adults (>18 years of age) who owned a smartphone (Android or Apple) and would be able to download the Keenoa app without assistance.

Total number of nutrients validated: 18 info

Not all of the nutrients validated in the validation studies are included in the table below, as statistical data was only selected to be displayed for a number of nutrients, this included:

  • Energy
  • Fat
  • Saturated Fat
  • Mono-unsaturated Fat
  • Poly-unsaturated Fat
  • Carbohydrates
  • Protein
  • Sugar
  • Non‐starch polysaccharides(NSP)
  • Sodium
  • Calcium
  • Iron
  • Zinc
  • Retinol
  • Folate
  • Folic Acid
  • Vitamin B12
  • Vitamin C
  • Fruit & Vegetables
  • Urinary Nitrogen

To find information on the other validated nutrients please read the validation study.

  • Energy
  • Macronutrients: 6
  • Micronutrients: 12
Comparator Lifestage Sex Nutrient Measured info Mean Difference Standard Deviation info Correlation Coefficient info Cohen's Kappa Coefficient Percentage Agreement Percentage Agreement Categories info Lower Limits of Agreement Upper Limits of Agreement
3-day food diary Adults and Elderly Both Energy (kcal) -391 1204 0.20-0.49 (P) <0.20 -2799 2017
Protein (g) -21 34 >0.05 (P) <0.20 -88.6 47.4
Fat (g) -32.3 29 0.20-0.49 (P) <0.20 -90 26
Saturated Fat (g) -10.2 11 0.20-0.49 (P) <0.20 -32 12
Carbohydrates (g) 0.90 268 0.20-0.49 (P) <0.20 -535 536
Sodium (mg) -1240 1369 <0.20 (P) <0.20 -3978 1498
Calcium (mg) -97 1147 <0.20 (P) <0.20 -2393 2199
Iron(mg) -3.1 4.6 0.20-0.49 (P) <0.20 -12 6
Vitamin B12 (μg) -1 2.4 <0.20 (P) <0.20 -5.8 3.8
Vitamin C (mg) 131.5 639 <0.20 (P) <0.20 -1146 1410

Some results have been calculated using statistical techniques based on the published data.

For further information on statistical terms click on Statistical tests used in validation studies

All correlations coefficients in the table are unadjusted unless stated otherwise. For adjusted correlation coefficients and other statistical methods used in the study e.g. paired t-tests, please read the validation articles.

  • # Adjusted
  • † Energy adjusted.
  • ‡ For loge-transformed, energy-adjusted nutrient intakes.
  • ^ Adjacent included.
  • ᵟ Participants provided identical responses.
  • (w) = Weighted.

Ji Y, Plourde H, Bouzo V, Kilgour RD, Cohen TR. Validity and Usability of a Smartphone Image-Based Dietary Assessment App Compared to 3-Day Food Diaries in Assessing Dietary Intake Among Canadian Adults: Randomized Controlled Trial. JMIR Mhealth and Uhealth. 2020;8(9):e16953.