Search

ObjectiveTo provide an overview of the status of monitoring and evaluation (M&E) of school feeding across sub-Saharan Africa and to reflect on the experience on strengthening M&E systems to influence policy making in low-income countries.DesignLiterature review on the M&E of school feeding programmes as well as data from World Food Programme surveys.SettingSub-Saharan Africa.SubjectsCountries implementing school feeding.ResultsOnly two randomized controlled impact evaluations have been implemented in sub-Saharan Africa. Where M&E data collection is underway, the focus is on process and service delivery and not on child outcomes. M&E systems generally operate under the Ministry of Education, with other Ministries represented within technical steering groups supporting implementation. There is no internationally accepted standardized framework for the M&E of school feeding. There have been examples where evidence of programme performance has influenced policy: considering the popularity of school feeding these cases though are anecdotal, highlighting the opportunity for systemic changes.ConclusionsThere is strong buy-in on school feeding from governments in sub-Saharan Africa. In response to this demand, development partners have been harmonizing their support to strengthen national programmes, with a focus on M&E. However, policy processes are complex and can be influenced by a number of factors. A comprehensive but simple approach is needed where the first step is to ensure a valid mandate to intervene, legitimizing the interaction with key stakeholders, involving them in the problem definition and problem solving. This process has been facilitated through the provision of technical assistance and exposure to successful experiences through South–South cooperation and knowledge exchange. [ABSTRACT FROM PUBLISHER]

Background. The provision of food in and through schools has been used to support the education, health, and nutrition of school-aged children. The monitoring of financial inputs into school health and nutrition programs is critical for a number of reasons, including accountability, transparency, and equity. Furthermore, there is a gap in the evidence on the costs, cost-efficiency, and cost-effectiveness of providing food through schools, particularly in areas of high food insecurity, Objective. To estimate the programmatic costs and cost-efficiency associated with providing food through schools in food-insecure, developing-country contexts, by analyzing global project data from the World Food Programme (WFP). Methods. Project data, including expenditures and number of schoolchildren covered, were collected through project reports and validated through WFP Country Office records. Yearly project costs per schoolchild were standardized over a set number of feeding days and the amount of energy provided by the average ration. Output metrics, such as tonnage, calories, and micronutrient content, were used to assess the cost-efficiency of the different delivery mechanisms. Results. The average yearly expenditure per child, standardized over a 200-day on-site feeding period and an average ration, excluding school-level costs, was US$21.59. The costs varied substantially according to choice of food modality, with fortified biscuits providing the least costly option of about US$11 per year and take-home rations providing the most expensive option at approximately US$52 per year. Comparisons across the different food modalities suggested that fortified biscuits provide the most cost-efficient option in terms of micronutrient delivery (particularly vitamin A and iodine), whereas on-site meals appear to be more efficient in terms of calories delivered. Transportation and logistics costs were the main drivers for the high costs. Conclusions. The choice of program objectives will to a large degree dictate the food modality (biscuits, cooked meals, or take-home rations) and associated implementation costs. Fortified biscuits can provide substantial nutritional inputs at a fraction of the cost of school meals, making them an appealing option for service delivery in food-insecure contexts. Both costs and effects should be considered carefully when designing the appropriate school-based intervention. The costs estimates in this analysis do not include all school-level costs and are therefore lower-bound estimates of full implementation costs. [ABSTRACT FROM AUTHOR]

This study examined modifiable caregiver factors influencing child development in Malawi using baseline data from 1,021 mothers and their children <2 years of age participating in a cluster‐randomized controlled trial implemented in rural Malawi (2022–2025). We fit an evidence‐based theoretical model using structural equation modelling examining four caregiver factors: (1) diet diversity (sum of food groups consumed in the past 24 h), (2) empowerment (assessed using the project‐level Women's Empowerment in Agriculture Index), (3) mental health (assessed using the Self‐Reported Questionnaire, SRQ‐20), and (4) stimulation (number of stimulation activities the mother engaged in the past 3 days). Child development was assessed using the Malawi Development Assessment Tool (norm‐referenced aggregate Z‐score). The model controlled for child, caregiver, and household socioeconomic characteristics. Results showed that caregiver dietary diversity was directly associated with higher child development scores (standardized coefficient 0.091 [95% CI 0.027, 0.153]) and lower SRQ‐20 scores −0.058 (−0.111, −0.006). Empowerment was directly associated with higher child development scores (0.071 [0.007, 0.133]), higher stimulation score (0.074 [0.013, 0.140]), higher dietary diversity (0.085 [0.016, 0.145]), and lower SRQ‐20 scores (−0.068 [−0.137, −0.002]). Further, higher empowerment was indirectly associated with improved child development through enhancement of caregiver dietary diversity, with an indirect effect of 0.008 (0.002, 0.018). These findings highlight the important role that caregiver diet and empowerment play in directly influencing child development and other aspects of caregiver well‐being. Interventions aimed at enhancing child development should consider these factors as potential targets to improve outcomes for children and caregivers. [ABSTRACT FROM AUTHOR]

Background: The Minimum Dietary Diversity for Women of Reproductive Age (MDD-W) indicator was validated as a proxy of micronutrient adequacy among nonpregnant women in low- and middle-income countries (LMICs). At that time, indeed, there was insufficient data to validate the indicator among pregnant women, who face higher micronutrient requirements. Objective: This study aimed to validate a minimum food group consumption threshold, out of the 10 food groups used to construct MDD-W, to be used as a population-level indicator of higher micronutrient adequacy among pregnant women aged 15-49 y in LMICs. Methods: We used secondary quantitative 24-h recall data from 6 surveys in 4 LMICs (Bangladesh, Burkina Faso, India, and Nepal, total n = 4909). We computed the 10-food group Women's Dietary Diversity Score (WDDS-10) and calculated the mean probability of adequacy (MPA) of 11 micronutrients. Linear regression models were fitted to assess the associations between WDDS-10 and MPA. Sensitivity, specificity, and proportion of individuals correctly classified were used to assess the performance of MDD-W in predicting an MPA of >0.60. Results: In the pooled sample, median values (interquartile range) of WDDS-10 and MPA were 3 (1) and 0.20 (0.34), respectively, whereas the proportion of pregnant women with an MPA of >0.60 was 9.6%. The WDDS-10 was significantly positively associated with MPA in each survey. Although the acceptable food group consumption threshold varied between 4 and 6 food groups across surveys, the threshold of 5 showed the highest performance in the pooled sample with good sensitivity (62%), very good specificity (81%), and percentage of correctly classified individuals (79%). Conclusions: The WDDS-10 is a good predictor of dietary micronutrient adequacy among pregnant women aged 15-49 y in LMICs. Moreover, the threshold of 5 or more food groups for the MDD-W indicator may be extended to all women of reproductive age, regardless of their physiologic status. [ABSTRACT FROM AUTHOR]

Objective: We examined the trends over time and the factors associated with malnutrition among adolescent girls in Ghana. Design: Cross-sectional analysis from 3 nationwide Ghana Demographic and Health Surveys conducted in 2003 (n 983), 2008 (n 955) and 2014 (n 857). We used Cox proportional hazard models with sample weighting to model the prevalence ratio (PR) of malnutrition. Setting: Countrywide, covering rural and urban areas in Ghana. Participants: Non-pregnant adolescent girls aged 15–19 years. Results: Compared with 2003, thinness declined marginally (PR 0·88 (95 % CI 0·45, 1·73)) in 2008 and in 2014 (PR 0·71 (95 % CI 0·38, 1·56)). Stunting declined marginally by 19 % in 2008 (PR 0·81 (95 % CI 0·59, 1·12)), flattening out in 2014 (PR 0·81 (95 % CI 0·57, 1·17)). We found an increasing trend of overweight/obesity with the PR peaking in 2014 (PR 1·39 (95 % CI 1·02, 1·88)) compared to 2003. The anaemia prevalence remained severe without a clear trend. A low level of education of the adolescent girl was positively associated with stunting. Increasing age was positively associated with stunting but inversely associated with thinness and anaemia. Girls who ever bore a child were more likely to be anaemic compared to those who never did. A lower level of household wealth and a unit increase in household size was negatively associated with overweight/obesity. Urban dwelling girls were less likely to be stunted. Conclusions: The stagnant burden of under-nutrition and rising over-nutrition emphasise the need for double-duty actions to tackle malnutrition in all its forms in Ghanaian adolescent girls. [ABSTRACT FROM AUTHOR]

Background: Soutenir l'Exploitation Familiale pour Lancer l'Élevage des Volailles et Valoriser l'Économie Rurale (SELEVER) is a nutrition- and gender-sensitive poultry value chain project designed and implemented by international nongovernmental organization Tanager, which consists of poultry market facilitation and behavior change activities aiming at increasing poultry production and improving diets without free inputs transfer.Objectives: The study aimed at assessing the impact of SELEVER on diets of women and children during the lean season.Methods: Within a cluster randomized controlled trial, 45 communes were assigned to 1 of 3 arms, including 1) SELEVER interventions, 2) SELEVER with an intensive hygiene and sanitation component (SELEVER + WASH), and 3) a control group without intervention. Two rounds of survey were conducted 2 y apart during the lean season. Primary dietary outcomes were the probability of adequacy (PA) of iron, zinc, and vitamin A intakes; mean PA of 11 micronutrients and individual dietary diversity score collected through quantitative 24-h recall in longitudinal samples of women and index children (2-4 y old) in 1054 households; and minimum acceptable diet in the repeated cross-sectional sample of their younger sibling aged 6-23 mo. Impacts were assessed by intention-to-treat ANCOVA.Results: Relative to control, SELEVER interventions (groups 1 + 2) increased the PA of iron intakes in women by 1.8 percentage points (pp) (P = 0.030). We found no further impact on primary outcomes, although egg consumption increased in index children (+0.73 pp, P = 0.010; +0.69 kcal/d, P = 0.036). Across the 3 groups, we observed negative effects of SELEVER on the PA of zinc intakes in women relative to SELEVER + WASH (-4.1 pp, P = 0.038) and on a variety of secondary dietary outcomes relative to both other groups. The study was registered on the ISCRCTN registry (ISRCTN16686478).Conclusions: Information-only-based value chain interventions may not have meaningful positive effects on diets of women and children in the lean season in settings with largely inadequate diets. We found suggestive evidence that synergies between intervention components may have introduced heterogeneity in effects on diet. [ABSTRACT FROM AUTHOR]

• Nutrition and agriculture-based programs often rely on women's participation; little evidence if programs burden women. • We investigate how a nutrition-sensitive agriculture program delivered through preschools in Malawi affected women's time. • The program modestly increased lean season time in caregiving, but investments were considered important to child development. • Mixed-method evaluations of women's program participation can improve interpretation of time tradeoffs and help avoid harm. Development programs often rely on women's participation. However, there is little evidence of whether development programs that engage women's unpaid labor – particularly in care work – add to their time burdens. We tested this hypothesis on a nutrition-sensitive agriculture program delivered through community-based preschools in Malawi. The mixed-methods study was conducted over one year using data from 1,168 female caregivers from a cluster-randomized control trial. A longitudinal binomial logistic regression model was used to estimate the proportion of time spent caregiving in a 24-hour period (expressed as minutes) at baseline and then separately for each treatment group at 6-months and 1-year post-randomization. In addition, two rounds of 38 qualitative in-depth interviews (n = 76) were conducted with women, men and adolescent girls to explore their perceptions of program activities, time use and gender attitudes. We found that the program quantitatively increased daily caregiving time for participating women by approximately 30 min. However, this effect occurred only during the lean season when preschool scale-up investments increased. Qualitatively, program-related tasks were not considered burdensome. Moreover, participants saw contributions as important investments in their children's development. These findings add to limited evidence of the impacts of nutrition-sensitive agricultural programs and early childhood interventions on women's time use. Measuring women's participation through mixed-method evaluations can aid interpretation to avoid harm and to better understand the tradeoffs of women's time. [ABSTRACT FROM AUTHOR]

School feeding programs can support children's nutrition, health, and education in emergencies. This study assessed the feasibility, trade-offs, cost efficiency, and perceived benefits of school feeding modalities operating in urban Yemen. It draws on primary data from a qualitative evaluation with 21 school feeding implementers and 88 beneficiaries conducted in Feb-Mar 2023, and secondary data from a desk review of published and program literature on school feeding operations. Results showed that school feeding provided students with on average 18%, 40%, and 66% of daily energy, protein, and micronutrient requirements, respectively. Models including fortified snacks were 3-11 times more cost-efficient in terms of nutrient delivery. The most prominent strength of the models examined were the perceived benefits on child, family, and financial outcomes. Among the main weaknesses was the poor nutritional quality of the meal, which in turn emerged as a primary opportunity to improve school feeding through hybrid models providing a combination of fortified snacks and healthy meals. Other weaknesses such as poor water, sanitation, and hygiene infrastructure, and desired improvements such as the school kitchen and canteen, require considerable investments. Hybrid models are cost-efficient, acceptable, and feasible in Yemen and can serve the diet and nutrition needs of school-aged children., (© 2024 The Author(s). Annals of the New York Academy of Sciences published by Wiley Periodicals LLC on behalf of The New York Academy of Sciences.)

Background: Adolescent nutrition has faced a policy neglect, partly owing to the gaps in dietary intake data for this age group. The Food Recognition Assistance and Nudging Insights (FRANI) is a smartphone application validated for dietary assessment and to influence users toward healthy food choices., Objectives: This study aimed to assess the feasibility (adherence, acceptability, and usability) of FRANI and its effects on food choices and diet quality in female adolescents in Vietnam., Methods: Adolescents ( N = 36) were randomly selected from a public school and allocated into 2 groups. The control group received smartphones with a version of FRANI limited to dietary assessment, whereas the intervention received smartphones with gamified FRANI. After the first 4 wk, both groups used gamified FRANI for further 2 wk. The primary outcome was the feasibility of using FRANI as measured by adherence (the proportion of completed food records), acceptability and usability (the proportion of participants who considered FRANI acceptable and usable according to answers of a Likert questionnaire). Secondary outcomes included the percentage of meals recorded, the Minimum Dietary Diversity for Women (MDDW) and the Eat-Lancet Diet Score (ELDS). Dietary diversity is important for dietary quality, and sustainable healthy diets are important to reduce carbon emissions. Poisson regression models were used to estimate the effect of gamified FRANI on the MDDW and ELDS., Results: Adherence to the application was 82% and the percentage of meals recorded was 97%. Acceptability and usability were 97%. MDDW in the intervention group was 1.07 points (95% CI: 0.98, 1.18; P = 0.13) greater than that in the control (constant = 4.68); however, the difference was not statistically significant. Moreover, ELDS in the intervention was 1.09 (95% CI: 1.01, 1.18; P = 0.03) points greater than in the control (constant = 3.67)., Conclusions: FRANI was feasible and may be effective to influence users toward healthy food choices. Research is needed for FRANI in different contexts and at scale.The trial was registered at the International Standard Randomized Controlled Trial Number as ISRCTN 10681553., (© 2023 The Authors.)

Background: The Minimum Dietary Diversity for Women of Reproductive Age (MDD-W) indicator was validated as a proxy of micronutrient adequacy among nonpregnant women in low- and middle-income countries (LMICs). At that time, indeed, there was insufficient data to validate the indicator among pregnant women, who face higher micronutrient requirements., Objective: This study aimed to validate a minimum food group consumption threshold, out of the 10 food groups used to construct MDD-W, to be used as a population-level indicator of higher micronutrient adequacy among pregnant women aged 15-49 y in LMICs., Methods: We used secondary quantitative 24-h recall data from 6 surveys in 4 LMICs (Bangladesh, Burkina Faso, India, and Nepal, total n  = 4909). We computed the 10-food group Women's Dietary Diversity Score (WDDS-10) and calculated the mean probability of adequacy (MPA) of 11 micronutrients. Linear regression models were fitted to assess the associations between WDDS-10 and MPA. Sensitivity, specificity, and proportion of individuals correctly classified were used to assess the performance of MDD-W in predicting an MPA of >0.60., Results: In the pooled sample, median values (interquartile range) of WDDS-10 and MPA were 3 (1) and 0.20 (0.34), respectively, whereas the proportion of pregnant women with an MPA of >0.60 was 9.6%. The WDDS-10 was significantly positively associated with MPA in each survey. Although the acceptable food group consumption threshold varied between 4 and 6 food groups across surveys, the threshold of 5 showed the highest performance in the pooled sample with good sensitivity (62%), very good specificity (81%), and percentage of correctly classified individuals (79%)., Conclusions: The WDDS-10 is a good predictor of dietary micronutrient adequacy among pregnant women aged 15-49 y in LMICs. Moreover, the threshold of 5 or more food groups for the MDD-W indicator may be extended to all women of reproductive age, regardless of their physiologic status., (© 2023 The Authors.)

Nutrition-sensitive agriculture programmes have the potential to improve child nutrition outcomes, but livestock intensification may pose risks related to water, sanitation and hygiene (WASH) conditions. We assessed the impact of SELEVER, a nutrition- and gender-sensitive poultry intervention, with and without added WASH focus, on hygiene practices, morbidity and anthropometric indices of nutrition in children aged 2-4 years in Burkina Faso. A 3-year cluster randomised controlled trial was implemented in 120 villages in 60 communes (districts) supported by the SELEVER project. Communes were randomly assigned using restricted randomisation to one of three groups: (1) SELEVER intervention (n = 446 households); (2) SELEVER plus WASH intervention (n = 432 households); and (3) control without intervention (n = 899 households). The study population included women aged 15-49 years with an index child aged 2-4 years. We assessed the effects 1.5-years (WASH substudy) and 3-years (endline) post-intervention on child morbidity and child anthropometry secondary trial outcomes using mixed effects regression models. Participation in intervention activities was low in the SELEVER groups, ranging from 25% at 1.5 years and 10% at endline. At endline, households in the SELEVER groups had higher caregiver knowledge of WASH-livestock risks (∆ = 0.10, 95% confidence interval [CI] [0.04-0.16]) and were more likely to keep children separated from poultry (∆ = 0.09, 95% CI [0.03-0.15]) than in the control group. No differences were found for other hygiene practices, child morbidity symptoms or anthropometry indicators. Integrating livestock WASH interventions alongside poultry and nutrition interventions can increase knowledge of livestock-related risks and improve livestock-hygiene-related practices, yet may not be sufficient to improve the morbidity and nutritional status of young children., (© 2023 The Authors. Maternal & Child Nutrition published by John Wiley & Sons Ltd.)

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 = 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., (Copyright © 2023 The Authors. Published by Elsevier Inc. All rights reserved.)

Background: Bolstering farm-level crop diversity is one strategy to strengthen food system resilience and achieve global food security. Women who live in rural areas play an essential role in food production; therefore, we aimed to assess the associations between women's empowerment and crop diversity., Methods: In this secondary analysis of cross-sectional data, we used data from four cluster-randomised controlled trials done in Burkina Faso, India, Malawi, and Tanzania. We assessed women's empowerment using indicators from the Women's Empowerment in Agriculture Index. Farm-level crop diversity measures were the number of food crops grown, number of food groups grown, and if nutrient-dense crops were grown. We used a two-stage modelling approach. First, we analysed covariate-adjusted country-specific associations between women's empowerment and crop diversity indicators using multivariable generalised linear models. Second, we pooled country-specific associations using random-effects models., Findings: The final analytic sample included 1735 women from Burkina Faso, 4450 women from India, 547 women from Malawi, and 574 women from Tanzania. Across all countries, compared with households in which women provided input into fewer productive decisions, households of women with greater input into productive decisions produced more food crops (mean difference 0·36 [95% CI 0·16-0·55]), a higher number of food groups (mean difference 0·16 [0·06-0·25]), and more nutrient-dense crops (percentage point difference 3 [95% CI 3-4]). Across all countries, each additional community group a woman actively participated in was associated with cultivating a higher number of food crops (mean difference 0·20 [0·04-0·35]) and a higher number of food groups (mean difference 0·11 [0·03-0·18]), but not more nutrient-dense crops. In pooled associations from Burkina Faso and India, asset ownership was associated with cultivating a higher number of food crops (mean difference 0·08 [0·04-0·12]) and a higher number of food groups (mean difference 0·05 [0·04-0·07]), but not more nutrient-dense crops., Interpretation: Greater women's empowerment was associated with higher farm-level crop diversity among low-income agricultural households, suggesting that it could help enhance efforts to strengthen food system resilience., Funding: Bill & Melinda Gates Foundation., Competing Interests: Declaration of interests We declare no competing interests., (Copyright © 2023 The Author(s). Published by Elsevier Ltd. This is an Open Access article under the CC BY 4.0 license. Published by Elsevier Ltd.. All rights reserved.)

Understanding the types of food systems interventions that foster women's empowerment and the types of women that are able to benefit from different interventions is important for development policy. SELEVER was a gender- and nutrition-sensitive poultry production intervention implemented in western Burkina Faso from 2017 to 2020 that aimed to empower women. We evaluated SELEVER using a mixed-methods cluster-randomized controlled trial, which included survey data from 1763 households at baseline and endline and a sub-sample for two interim lean season surveys. We used the multidimensional project-level Women's Empowerment in Agriculture Index (pro-WEAI), which consists of 12 binary indicators, underlying count versions of 10 of these, an aggregate empowerment score (continuous) and a binary aggregate empowerment indicator, all for women and men. Women's and men's scores were compared to assess gender parity. We also assessed impacts on health and nutrition agency using the pro-WEAI health and nutrition module. We estimated program impact using analysis of covariance (ANCOVA) models and examined whether there were differential impacts by flock size or among those who participated in program activities (treatment on the treated). Program impacts on empowerment and gender parity were null, despite the program's multipronged and gender-sensitive approach. Meanwhile, results of the in-depth gender-focused qualitative work conducted near the project mid-point found there was greater awareness in the community of women's time burden and their economic contributions, but it did not seem that awareness led to increased empowerment of women. We reflect on possible explanations for the null findings. One notable explanation may be the lack of a productive asset transfer, which have previously been shown to be essential, but not sufficient, for the empowerment of women in agricultural development programs. We consider these findings in light of current debates on asset transfers. Unfortunately, null impacts on women's empowerment are not uncommon, and it is important to learn from such findings to strengthen future program design and delivery., Competing Interests: All authors declare that they have no conflicts of interest., (© 2023 The Authors.)

Bangladesh struggles with undernutrition in women and young children. Nutrition-sensitive agriculture programmes can help address rural undernutrition. However, questions remain on the costs of multisectoral programmes. This study estimates the economic costs of the Targeting and Re-aligning Agriculture to Improve Nutrition (TRAIN) programme, which integrated nutrition behaviour change and agricultural extension with a credit platform to support women's income generation. We used the Strengthening Economic Evaluation for Multisectoral Strategies for Nutrition (SEEMS-Nutrition) approach. The approach aligns costs with a multisectoral nutrition typology, identifying inputs and costs along programme impact pathways. We measure and allocate costs for activities and inputs, combining expenditures and micro-costing. Quantitative and qualitative data were collected retrospectively from implementers and beneficiaries. Expenditure data and economic costs were combined to calculate incremental economic costs. The intervention was designed around a randomised control trial. Incremental costs are presented by treatment arm. The total incremental cost was $795,040.34 for a 3.5-year period. The annual incremental costs per household were US$65.37 (Arm 2), USD$114.15 (Arm 3) and $157.11 (Arm 4). Total costs were led by nutrition counselling (37%), agriculture extension (12%), supervision (12%), training (12%), monitoring and evaluation (9%) and community events (5%). Total input costs were led by personnel (68%), travel (12%) and supplies (7%). This study presents the total incremental costs of an agriculture-nutrition intervention implemented through a microcredit platform. Costs per household compare favourably with similar interventions. Our results illustrate the value of a standardised costing approach for comparison with other multisectoral nutrition interventions., (© 2022 The Authors. Maternal & Child Nutrition published by John Wiley & Sons Ltd.)

Unhealthy diets are a critical global concern while dietary measure methods are time consuming and expensive. There is limited evidence that phone-based interventions can improve nutrition data collection and dietary quality, especially for adolescents in developing countries. We developed an artificial-intelligence-based phone application called Food Recognition Assistance and Nudging Insights (FRANI) to address these problems. FRANI can recognize foods in images, track food consumption, display statistics and use gamified nudges to give positive feedback on healthy food choice. This study protocol describes the design of new pilot studies aimed at measuring the feasibility (acceptability, adherence, and usability) of FRANI and its effects on the quality of food choice of adolescents in Ghana and Vietnam. In each country, 36 adolescents (12-18 years) will be randomly allocated into two groups: The intervention group with the full version of FRANI and the control group with the functionality limited to image recognition and dietary assessment. Participants in both groups will have their food choices tracked for four weeks. The control groups will then switch to the full version of FRANI and both groups will be tracked for a further 2 weeks to assess acceptability, adherence, and usability. Analysis of outcomes will be by intent to treat and differences in outcomes between intervention and control group will use Poisson and odds ratio regression models, accounting for repeated measures at individual levels. If deemed feasible, acceptable and usable, FRANI will address gaps in the literature and advance the nutrition field by potentially improving the quality of food choices of adolescent girls in developing countries. This pilot study will also provide insights on the design of a large randomized controlled trial. The functioning and dissemination of FRANI can be an important step towards highly scalable nutrition data collection and healthier food choices for a population at risk of malnutrition. The study protocol and the methods and materials were approved by the Institutional Review Board (IRB) of the IFPRI on April 29th, 2020 (registration number #00007490), the Thai Nguyen National Hospital on April 14th, 2020 (protocol code 274/ĐĐĐ-BVTWTN) and the University of Ghana on August 10th, 2020 (Federalwide Assurance FWA 00001824; NMIMR-IRB CPN 078-19/20). The study protocol was registered in the International Standard Randomized Controlled Trial Number (ISRCTN 10681553; https://doi.org/10.1186/ISRCTN10681553) on November 12, 2021., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (© 2022 Braga, Arrieta, Bannerman, Doyle, Folson, Gangupantulu, Hoang, Huynh, Koch, McCloskey, Tran, Tran, Truong, Nguyen, Hughes and Gelli.)