A novel screening tool to predict severe acute malnutrition through automated monitoring of weight-for-age growth curves.

Weight-for-age (WFA) growth faltering often precedes severe acute malnutrition (SAM) in children, yet it is often missed during routine growth monitoring. Automated interpretation of WFA growth within electronic health records could expedite the identification of children at risk of SAM. This study aimed to develop an automated screening tool to predict SAM risk from WFA growth, and to determine its predictive ability compared with simple changes in weight or WFA z-score. To develop the screening tool, South African child growth experts (n = 30) rated SAM risk on 100 WFA growth curves, which were then used to train an artificial neural network (ANN) to assess SAM risk from consecutive WFA z-scores. The ANN was validated in 185 children under five (63 SAM cases; 122 controls) using diagnostic accuracy methodology. The ANN's performance was compared with that of changes in weight or WFA z-score. Even though experts' SAM risk ratings of the WFA growth curves differed considerably, the ANN achieved a sensitivity of 73.0% (95% confidence interval [CI]: 60.3; 83.4), specificity of 86.1% (95% CI: 78.6; 91.7) and receiver-operating characteristic curve area of 0.795 (95% CI: 0.732; 0.859) during validation with real cases, outperforming changes in weight or WFA z-scores. The ANN, as an automated screening tool, could markedly improve the identification of children at risk of SAM using routinely collected WFA growth information.

Agreement between parent-report and EMR height, weight, and BMI among rural children.

Introduction: Remote anthropometric surveillance has emerged as a strategy to accommodate lapses in growth monitoring for pediatricians during coronavirus disease 2019 (COVID-19). The purpose of this investigation was to validate parent-reported anthropometry and inform acceptable remote measurement practices among rural, preschool-aged children. Methods: Parent-reported height, weight, body mass index (BMI), BMI z-score, and BMI percentile for their child were collected through surveys with the assessment of their source of home measure. Objective measures were collected by clinic staff at the child's well-child visit (WCV). Agreement was assessed using correlations, alongside an exploration of the time gap (TG) between parent-report and WCV to moderate agreement. Using parent- and objectively reported BMI z-scores, weight classification agreement was evaluated. Correction equations were applied to parent-reported anthropometrics. Results: A total of 55 subjects were included in this study. Significant differences were observed between parent- and objectively reported weight in the overall group (-0.24 kg; p = 0.05), as well as height (-1.8 cm; p = 0.01) and BMI (0.4 kg/m2; p = 0.02) in the ≤7d TG + Direct group. Parental reporting of child anthropometry ≤7d from their WCV with direct measurements yielded the strongest correlations [r = 0.99 (weight), r = 0.95 (height), r = 0.82 (BMI), r = 0.71 (BMIz), and r = 0.68 (BMI percentile)] and greatest classification agreement among all metrics [91.67% (weight), 54.17% (height), 83.33% (BMI), 91.67% (BMIz), and 33.33% (BMI percentile)]. Corrections did not remarkably improve correlations. Discussion: Remote pediatric anthropometry is a valid supplement for clinical assessment, conditional on direct measurement within 7 days. In rural populations where socioenvironmental barriers exist to care and surveillance, we highlight the utility of telemedicine for providers and researchers.

How Is Context Addressed in Growth Monitoring? A Comparison of the Tanzanian, Indian, and Dutch Manuals.

Background: To address malnutrition in all its forms, context should be taken into account in growth-monitoring (GM) practices. Objectives: The aim was to compare GM manuals of countries with different nutrition problems, and to assess how these manuals are adapted to the different biological, socioeconomic, and cultural contexts. Methods: GM manuals from Tanzania, India, and the Netherlands were compared with each other, and with the materials for the WHO training course on child growth assessment. First, the aims of GM, growth measurements, interpretation of these measurements, and counseling approaches are compared. Second, contextual determinants of malnutrition are identified using the UNICEF framework for malnutrition as an analytical model. Results: Our results show that the GM manuals differ in their descriptions of the aim of GM, growth measurements, their interpretation, and counseling approaches. Assessing normal growth and detecting growth problems are among the aims of GM in all of the analyzed countries. In Tanzania and India, the focus is mainly on undernutrition, whereas the Dutch manuals focus on overweight and on underlying pathologies that contribute to poor linear growth. The findings of our analysis of contextual factors within the UNICEF framework show that the Tanzanian protocol is only minimally adapted to the local context. Of the manuals examined in our study, the Indian manual is most focused on the contextual determinants of malnutrition, and stresses the importance of taking customs and beliefs into account. The Dutch protocol, by contrast, emphasizes the importance of the biological environment, including parental height and ethnicity, as determinants of child growth. Conclusions: The country manuals we analyzed only partly reflect the contexts in which children live. To address malnutrition in all its forms, the GM manuals should take children's biological, socioeconomic, and cultural contexts into account, as this would help health professionals to tailor counseling messages for parents.