Browsing by Author "Bannerman, B."
Now showing 1 - 2 of 2
Results Per Page
Sort Options
Item Household food insecurity is associated with child’s dietary diversity score among primary school children in two districts in Ghana(Food and Nutrition, 2022) Antwi, J.; Quaidoo, E.; Ohemeng, A.; Bannerman, B.Background: Dietary diversity is generally considered as a good indicator of nutrient adequacy and is influenced by various factors at the national, household, and individual levels. Objective: The present study sought to determine the relationships between household food insecurity, primary caregivers’ nutrition knowledge, and dietary diversity of school-aged children in Ghana. Methods: This forms part of a longitudinal study conducted in the Ayawaso West Municipal district in Accra (urban setting) and the Upper Manya Krobo district (rural setting) in Ghana. Data were collected from a total of 116 caregiver-child dyads using 24-h dietary recall and a short version of the US 12-month Household Food Security Survey Module. Nutrition knowledge and sociodemographic data were obtained using a structured questionnaire. Multivariable logistic regression was used to check for factors associated with children’s dietary diversity. Results: Majority of households reported food insecurity, with a higher percentage of insecure households located in the rural area (88.9% vs. 46.5%, P ≤ 0.0001), compared to the urban setting. Diet diversity among the study children was low, with a mean (standard deviation [SD]) of 5.8 (2.1) out of 14 food groups. Children living in food insecure households were three times more likely to have received low diverse diet compared to those from food secure households (adjusted odds ratio [OR] =3.3, 95% confidence interval [CI]: 1.4–8.0). Caregivers’ nutrition knowledge was, however, not related to children’s dietary diversity. Discussion and conclusion: Household food insecurity was a main predictor of dietary diversity among school-age children in this study. Thus, caregiver knowledge in nutrition may not be enough, particularly in the presence of food insecurity to guarantee adequate nutrition for school-aged children.Item Validation of Mobile Artificial Intelligence Technology–Assisted Dietary Assessment Tool Against Weighed Records and 24-Hour Recall in Adolescent Females in Ghana(The Journal of Nutrition, 2023) Folson, G.K.; Bannerman, B.; Atadze, V.; et al.Background: Important gaps exist in the dietary intake of adolescents in low- and middle-income countries (LMICs), partly due to expensive assessment methods and inaccuracy in portion-size estimation. Dietary assessment tools leveraging mobile technologies exist but only a few have been validated in LMICs. Objective: We validated Food Recognition Assistance and Nudging Insights (FRANI), a mobile artificial intelligence (AI) dietary assessment application in adolescent females aged 12–18 y (n ¼ 36) in Ghana, against weighed records (WR), and multipass 24-hour recalls (24HR). Methods: Dietary intake was assessed during 3 nonconsecutive days using FRANI, WRs, and 24HRs. Equivalence of nutrient intake was tested using mixed-effect models adjusted for repeated measures, by comparing ratios (FRANI/WR and 24HR/WR) with equivalence margins at 10%, 15%, and 20% error bounds. Agreement between methods was assessed using the concordance correlation coefficient (CCC). Results: Equivalence for FRANI and WR was determined at the 10% bound for energy intake, 15% for 5 nutrients (iron, zinc, folate, niacin, and vitamin B6), and 20% for protein, calcium, riboflavin, and thiamine intakes. Comparisons between 24HR and WR estimated equivalence at the 20% bound for energy, carbohydrate, fiber, calcium, thiamine, and vitamin A intakes. The CCCs by nutrient between FRANI and WR ranged between 0.30 and 0.68, which was similar for CCC between 24HR and WR (ranging between 0.38 and 0.67). Comparisons of food consumption episodes from FRANI and WR found 31% omission and 16% intrusion errors. Omission and intrusion errors were lower when comparing 24HR with WR (21% and 13%, respectively). Conclusions: FRANI AI–assisted dietary assessment could accurately estimate nutrient intake in adolescent females compared with WR in urban Ghana. FRANI estimates were at least as accurate as those provided through 24HR. Further improvements in food recognition and portion estimation in FRANI could reduce errors and improve overall nutrient intake estimations.