Validity of nutrient and food group contents estimated automatically by an image recognition system: A smartphone application for health promotion (Preprint)

2021 ◽  
Author(s):  
Yuki Sasaki ◽  
Koryu Sato ◽  
Satomi Kobayashi ◽  
Keiko Asakura
Keyword(s):  
Food Intake ◽  
Image Recognition ◽  
Smartphone Application ◽  
Recognition System ◽  
Food Group ◽  
Automatic Identification ◽  
Dietary Intakes ◽  
Food Groups ◽  
System A ◽  
Nutritional Recommendations

BACKGROUND A smartphone image recognition application is expected to be a novel tool to measure nutrients and food intake, but its performance has not been well evaluated. OBJECTIVE We assessed the performance of an image recognition application called CALO mama in terms of the nutrient and food group contents automatically estimated by the application. METHODS We prepared 120 sample meals for which the nutrients and food groups were already calculated. Next, we predicted the nutrients and food groups included in the meals from their photographs using 1) automated image recognition only and 2) manual modification after automatic identification. RESULTS Predictions using only image recognition were similar to the actual data in weight of meals, 11 out of 30 nutrients, and 4 out of 15 food groups; it underestimated energy, 19 nutrients, and 9 food groups; it overestimated dairy products and confectioneries. After manual modification, predictions were similar in energy, 29 out of 30 nutrients, and 10 out of 15 food groups; it underestimated pulses, fruits, and meats; it overestimated weight, vitamin C, vegetables, and confectioneries. CONCLUSIONS The results of this study suggest that manual modification after prediction using image recognition improves the performance of the assessment of nutrients and food intake. Our findings suggest the potential of image recognition to achieve a description of the dietary intakes of populations using “precision nutrition” (a comprehensive and dynamic approach to develop tailored nutritional recommendations) for individuals.

Inadequate Dietary Intakes: Among Pregnant Women

2012 ◽  
Vol 73 (2) ◽  
pp. 72-77 ◽  
Author(s):  
Jennifer K. Fowler ◽  
Susan E. Evers ◽  
M. Karen Campbell
Keyword(s):  
Pregnant Women ◽  
Food Group ◽  
Reproductive Age ◽  
Dietary Intakes ◽  
Food Groups ◽  
Eating Behaviours ◽  
Prenatal Health ◽  
Canadian City ◽  
Minimum Number ◽  
Health Project

Purpose: Eating behaviours were assessed among pregnant women in a mid-sized Canadian city. Methods: As part of the Prenatal Health Project, we interviewed 2313 pregnant women in London, Ontario. Subjects also completed a food frequency questionnaire. Recruitment took place in ultrasound clinics at 10 to 22 weeks of gestation. The main outcome measures were number of daily servings for each food group, measured against the minimum number recommended by the 2007 Eating Well with Canada’s Food Guide (CFG), the proportion of women consuming the recommended number of servings for each and all of the four food groups, and factors associated with adequate consumption. We also determined the number of servings of “other foods.” Analysis included descriptive statistics and logistic regression, all at p<0.05. Results: A total of 3.5% of women consumed the recommended number of servings for all four food groups; 15.3% did not consume the minimum number of servings of foods for any of the four food groups. Women for whom this was their first pregnancy were less likely to consume the recommended number of servings from all four food groups (odds ratio=0.41; confidence interval=0.23, 0.74). Conclusions: Very few pregnant women consumed food group servings consistent with the 2007 recommendations. Strategies to improve dietary behaviours must focus on the establishment of healthy eating behaviours among women of reproductive age.

scholarly journals Food consumption of sugarcane workers' families in the Brazilian Northeast

2015 ◽  
Vol 28 (2) ◽  
pp. 175-184
Author(s):  
Vanessa Messias Muniz ◽  
Débora Silva Cavalcanti ◽  
Nayalla Morais de Lima ◽  
Mônica Maria Osório
Keyword(s):  
Food Intake ◽  
Total Energy ◽  
Energy Intake ◽  
Family Members ◽  
Age Groups ◽  
Total Energy Intake ◽  
Dietary Intakes ◽  
Food Groups ◽  
Micronutrient Intake ◽  
Brazilian Northeast

OBJECTIVE: To analyze the food intake of sugarcane workers' family members. METHODS: The food intake of 159 family members of sugarcane workers from Gameleira, Pernambuco, Brazilian Northeast, was investigated by directly weighing the foods on three non-consecutive days. The percent risk of inadequate macro- and micronutrient intakes was analyzed according to the Reference Dietary Intakes. The macronutrients were analyzed in relation to acceptable distribution intervals. The energy consumed from the various food groups was expressed as a ratio of the total energy intake. RESULTS: The median intake of carbohydrates and proteins remained above the Estimated Average Requirement, and all age groups presented a low risk of inadequate carbohydrate and protein intakes. The median intakes of riboflavin, niacin, thiamin, and iron remained above the Estimated Average Requirement for all age groups, but children aged 1-3 years presented a high percent risk of inadequate iron intake. All age groups presented high percent risk of inadequate zinc, calcium, vitamin A, and vitamin C intakes. Grains and derivatives had a greater participation in the total energy intake, especially in men aged 19-30 years. The group "milk and dairy products" had a greater participation in the diet of children aged 1-3 years. CONCLUSION: The low percent risk of inadequate carbohydrate and protein intakes in all age groups was opposed to the high risk of inadequate mineral and vitamin intakes, making the population vulnerable to nutritional disorders caused by excess macronutrient intake and inadequate micronutrient intake.

scholarly journals Underreporting of energy intake among Japanese women aged 18–20 years and its association with reported nutrient and food group intakes

2004 ◽  
Vol 7 (7) ◽  
pp. 911-917 ◽  
Author(s):  
Hitomi Okubo ◽  
Satoshi Sasaki
Keyword(s):  
Metabolic Rate ◽  
Energy Intake ◽  
Basal Metabolic Rate ◽  
Food Group ◽  
Young Female ◽  
Dietary Intakes ◽  
Food Groups ◽  
Female Population ◽  
Reporting Accuracy ◽  
Diet History Questionnaire

AbstractObjectives:To evaluate the ratio of energy intake to basal metabolic rate (EI/BMR) among young female Japanese adults, and to compare the lifestyle and dietary characteristics between relatively low and high reporters.Design:Dietary intakes were assessed over a 1-month period with a validated, self-administered, diet history questionnaire, and lifestyle variables were assessed by a second questionnaire designed for this survey. The ratio of EI/BMR was calculated from reported energy intake and estimated basal metabolic rate.Subjects:In total, 1889 female Japanese university students aged 18–20 years who were enrolled in dietetics courses.Results:Ninety-five per cent of the subjects were classified into a non-obese group (body mass index (BMI) <25 kg m−2; mean±standard deviation (SD): 20.8±2.6 kg m−2). EI/BMR was 1.43±0.40 (mean±SD). Sixty-eight per cent of the subjects showed an EI/BMR level below the possibly balanced value of 1.56, 37% showed EI/BMR below the minimum survival value of 1.27 and 2% of the subjects showed EI/BMR exceeding the maximum value for a sustainable lifestyle of 2.4. BMI, body weight and BMR decreased significantly with the increase in EI/BMR (P<0.001). The percentage of energy from carbohydrate was significantly higher, whereas those from fat and protein were significantly lower, among the lower EI/BMR groups. As for food groups, a significantly declining trend from the lowest to the highest EI/BMR groups was observed for cereals.Conclusion:Underreporting, rather than overreporting, of energy intake was predominant in this relatively lean Japanese female population. BMI was the most important factor affecting the reporting accuracy of energy intake.

scholarly journals Energy, Nutrient and Food Intakes of Male Shift Workers Vary According to the Schedule Type but Not the Number of Nights Worked

Nutrients ◽  
2020 ◽  
Vol 12 (4) ◽  
pp. 919
Author(s):  
Sophie Bucher Della Torre ◽  
Pascal Wild ◽  
Victor Dorribo ◽  
Brigitta Danuser ◽  
Francesca Amati
Keyword(s):  
Eating Habits ◽  
Night Shift ◽  
Food Group ◽  
Pooled Analysis ◽  
Dietary Intakes ◽  
Food Groups ◽  
Shift Workers ◽  
Increased Risk ◽  
Schedule Type ◽  
Night Shifts

Shift work is associated with increased risk of chronic diseases due to circadian rhythm disruptions and behavioral changes such as in eating habits. Impact of type of shifts and number of night shifts on energy, nutrient and food intake is as yet unknown. Our goal was to analyze shift workers’ dietary intake, eating behavior and eating structure, with respect to frequency of nights worked in a given week and seven schedule types. Eating habits and dietary intakes of 65 male shift workers were analyzed in three steps based on 365 24-h food records: (1) according to the number of nights, (2) in a pooled analysis according to schedule type, and (3) in search of an interaction of the schedule and the timing of intake. Mean nutrient and food group intake during the study period did not depend on the number of nights worked. Amount and distribution of energy intake as well as quality of food, in terms of nutrient and food groups, differed depending on the type of schedule, split night shifts and recovery day (day after night shift) being the most impacted. Shift workers’ qualitative and quantitative dietary intakes varied between different schedules, indicating the need for tailored preventive interventions.

scholarly journals Changes in children's food group intake from age 3 to 7 years: comparison of a FFQ with an online food record

2014 ◽  
Vol 112 (2) ◽  
pp. 269-276 ◽  
Author(s):  
Carine Vereecken ◽  
Marc Covents ◽  
Inge Huybrechts ◽  
Colette Kelly ◽  
Lea Maes
Keyword(s):  
Food Intake ◽  
Young Children ◽  
Dietary Intake ◽  
Food Group ◽  
Food Groups ◽  
Food Record ◽  
Online Tool ◽  
Relative Validity ◽  
Signed Rank

Few studies have investigated the relative validity of FFQ in young children and no study has investigated the relative validity of changes in children's food intake in a longitudinal context. The aim of the present study was to compare the FFQ of the longitudinal Family Influences on Food Intake study, assessing children's food intake in the previous 3 months, with a 3 d online food record when children were 3 and 7 years old, as well as to investigate the relative validity of changes in food group intake over a 4-year period. Parents (n 89) completed the FFQ and an online food record over three non-consecutive days on two separate occasions (January–April 2008 and 2012). Wilcoxon signed-rank tests and Spearman's correlations were used to compare food group intake and changes in intake assessed using both methods. In 2008, the intake of eleven of the twenty-two food groups was overestimated and that of four food groups underestimated in the FFQ in comparison with the online tool; in 2012, the intake of four food groups was overestimated and that of seven food groups underestimated. Nevertheless, changes in intake did not differ significantly between the two methods for eighteen food groups. Correlations in 2008 and 2012 were, on average, 0·47; correlations between the changes in dietary intake were, on average, 0·26. The results suggest that despite the significant differences between the two methods for a number of food groups at both baseline and/or follow-up, the FFQ can be used to monitor changes in dietary intake for groups of young children.

scholarly journals Canadians’ Dietary Intake from 2007 to 2011 and across Different Sociodemographic/Lifestyle Factors Using the Canadian Health Measures Survey Cycles 1 and 2

2019 ◽  
Vol 2019 ◽  
pp. 1-8 ◽  
Author(s):  
Zeinab Hosseini ◽  
Susan J. Whiting ◽  
Hassan Vatanparast
Keyword(s):  
Dietary Intake ◽  
Food Group ◽  
Dietary Intakes ◽  
Food Groups ◽  
Milk Products ◽  
Objective Health ◽  
Health Measures ◽  
Canadian Health ◽  
Vegetables And Fruits ◽  
Canadian Health Measures Survey

Background. Nutrition is an important factor that impacts health, yet in Canada, there have been only a few surveys reflecting dietary intakes. The Canadian Health Measures Survey (CHMS) is a national survey that includes both food intake data as targeted questions and objective health measures. The aim of this research was to determine how food group intake data reported in CHMS is related to food group intakes from Canadian Community Health Survey (CCHS) (2004). A secondary objective was to examine the dietary status of Canadians across sociodemographic levels. Methods. The CHMS Cycles 1 and 2 food group intake data (meat and alternatives; milk products; grains; vegetables and fruits; dietary fat consumption; and beverages) of Canadians (6–79 years, n=11,387) were descriptively compared to previously reported intake of Canadians from CCHS 2.2 in 2004. Further, Canadians’ food intakes were assessed across sociodemographic characteristics. Results. The CHMS dietary intake data from vegetables and fruits and from milk products groups were similar to the dietary intake reported from CCHS 2.2. For the other food groups, the difference in intakes suggested CHMS data by FFQ were not complete. However, similar patterns in food intakes with regards to age/sex and income were observed in both surveys. Conclusion. Not all food groups measured in CHMS provide complete dietary intake data as compared to CCHS 2.2, yet CHMS food group intakes provide valuable information when it comes to evaluating dietary intake across different population groups.

scholarly journals A systematic review to identify biomarkers of intake for fermented food products

2021 ◽  
Vol 16 (1) ◽  
Author(s):  
Katherine J. Li ◽  
Elske M. Brouwer-Brolsma ◽  
Kathryn J. Burton-Pimentel ◽  
Guy Vergères ◽  
Edith J. M. Feskens
Keyword(s):  
Systematic Review ◽  
Food Intake ◽  
Fermentation Process ◽  
Food Group ◽  
Fermented Food ◽  
Assessment Tools ◽  
Fermented Foods ◽  
Food Groups ◽  
Phenyllactic Acid ◽  
Fermentation Processes

Abstract Background Fermented foods are ubiquitous in human diets and often lauded for their sensory, nutritious, and health-promoting qualities. However, precise associations between the intake of fermented foods and health have not been well-established. This is in part due to the limitations of current dietary assessment tools that rely on subjective reporting, making them prone to memory-related errors and reporting bias. The identification of food intake biomarkers (FIBs) bypasses this challenge by providing an objective measure of intake. Despite numerous studies reporting on FIBs for various types of fermented foods and drinks, unique biomarkers associated with the fermentation process (“fermentation-dependent” biomarkers) have not been well documented. We therefore conducted a comprehensive, systematic review of the literature to identify biomarkers of fermented foods commonly consumed in diets across the world. Results After title, abstract, and full-text screening, extraction of data from 301 articles resulted in an extensive list of compounds that were detected in human biofluids following the consumption of various fermented foods, with the majority of articles focusing on coffee (69), wine (69 articles), cocoa (62), beer (34), and bread (29). The identified compounds from all included papers were consolidated and sorted into FIBs proposed for a specific food, for a food group, or for the fermentation process. Alongside food-specific markers (e.g., trigonelline for coffee), and food-group markers (e.g., pentadecanoic acid for dairy intake), several fermentation-dependent markers were revealed. These comprised compounds related to the fermentation process of a particular food, such as mannitol (wine), 2-ethylmalate (beer), methionine (sourdough bread, cheese), theabrownins (tea), and gallic acid (tea, wine), while others were indicative of more general fermentation processes (e.g., ethanol from alcoholic fermentation, 3-phenyllactic acid from lactic fermentation). Conclusions Fermented foods comprise a heterogeneous group of foods. While many of the candidate FIBs identified were found to be non-specific, greater specificity may be observed when considering a combination of compounds identified for individual fermented foods, food groups, and from fermentation processes. Future studies that focus on how fermentation impacts the composition and nutritional quality of food substrates could help to identify novel biomarkers of fermented food intake.

scholarly journals Lunch on School Days in Canada: Examining Contributions to Nutrient and Food Group Intakes and Differences Across Eating Locations

2020 ◽  
Vol 4 (Supplement_2) ◽  
pp. 1497-1497
Author(s):  
Claire Tugault-Lafleur ◽  
Jennifer Black
Keyword(s):  
Canadian Community Health Survey ◽  
Food Group ◽  
Whole Grains ◽  
Dietary Intakes ◽  
Food Groups ◽  
Linear Regression Models ◽  
Dietary Recall ◽  
Dark Green ◽  
Sugary Beverages ◽  
Fluid Milk

Abstract Objectives Recent federal proposals in Canada have called for changes in the delivery and funding of school lunches. Yet little evidence has documented the nutritional quality of meals eaten by school children needed to inform school lunch reforms. This study assessed the dietary contributions of lunch foods to daily food and nutrient intakes on school days and compared dietary intakes across eating locations (school, home, and off-campus). Methods Nationally representative 24-hour dietary recall data were obtained from the 2015 Canadian Community Health Survey-Nutrition (n = 2540 children aged 6–17 years). Descriptive statistics were used to assess the % of daily energy, nutrients and food groups contributed by lunch foods. Multivariable age-stratified linear regression models examined differences in lunch-time consumption of energy, food groups and nutrients across eating locations. Results On average, foods reported at lunch provided ∼26% of daily calories. Relative to energy, lunch foods provided lower contributions of: dark green and orange vegetables, whole fruit, fruit juice, whole grains, milk and alternatives, fluid milk, minimally nutritious foods including sugary beverages, and several related nutrients including total sugars, vitamins A, D, B6, and B12, riboflavin, calcium, magnesium and potassium. Yet, lunch foods provided proportionally higher contributions of grain products, non-whole grains, meat and alternatives and sodium. Children aged 14–17 years who ate lunch at school reported higher intakes of total vegetables and fruit, whole fruit, whole grains, fiber, vitamin C, and magnesium but reported fewer calories from sugary beverages compared to their peers who ate lunch off-campus. Conclusions Relative to its contribution to energy, lunch on school days contributed to proportionally lower intakes of many healthful foods (dark green and orange vegetables, whole fruit, whole grains and fluid milk), but also proportionally lower intakes of sugary beverages. This study adds to the growing body of evidence on dietary concerns during school-time for Canadian children and highlights particular challenges for adolescents consuming lunch off-campus. Funding Sources Canadian Institutes of Health Research (FRN 151,549).

scholarly journals Food sources and correlates of sodium and potassium intakes in Flemish pre-school children

2011 ◽  
Vol 15 (6) ◽  
pp. 1039-1046 ◽  
Author(s):  
Inge Huybrechts ◽  
Willem De Keyzer ◽  
Yi Lin ◽  
Stefanie Vandevijvere ◽  
Carine Vereecken ◽  
...  
Keyword(s):  
School Children ◽  
Meat Products ◽  
Food Group ◽  
Food Sources ◽  
Cluster Sampling ◽  
Dietary Intakes ◽  
Food Groups ◽  
Diet Records ◽  
Fried Potatoes ◽  
Low K

AbstractObjectiveThe aim of the present study was to investigate dietary sources of Na and K intakes among Flemish pre-school children using multiple linear regression analyses.DesignThree-day estimated diet records were used to assess dietary intakes. The contribution to Na and K intakes of fifty-seven food groups was computed by summing the amount provided by the food group for all individuals divided by the total intake for all individuals.SettingA random cluster sampling design at the level of schools, stratified by province and age, was used.SubjectsA representative sample of 696 Flemish pre-school children aged 2·5–6·5 years was recruited.ResultsMean Na intake was above and mean K intake was largely below the recommendation for children. Bread (22 %) and soup (13 %) were main contributors to Na intake followed by cold meat cuts and other meat products (12 % and 11 %, respectively). Sugared milk drinks, fried potatoes, milk and fruit juices were the main K sources (13 %, 12 %, 11 % and 11 %, respectively). Although Na and K intakes were positively correlated, several food categories showed Na:K intake ratio well above one (water, cheeses, soup, butter/margarine, fast foods and light beverages) whereas others presented a ratio well below one (oil & fat, fruits & juices, potatoes, vegetables and hot beverages).ConclusionsFlemish pre-school children had too high Na and too low K intakes. The finding that main dietary sources of Na and K are clearly different indicates the feasibility of simultaneously decreasing Na and increasing K intake among children.

Sign in / Sign up

Export Citation Format

Share Document