<![CDATA[Background: The increasing use of digital applications to analyze nutritional status of children under five years offers significant progress in public health. However, the accuracy and precision of these tools continue to be a concern due to variations in data quality and user proficiency. Objectives: This study aimed to systematically evaluate the accuracy and precision of digital applications in calculating and assessing nutritional status of children under five years. Methods: A comprehensive systematic review was conducted by searching PubMed, ScienceDirect, and Google Scholar databases for relevant studies published between 2010 and 2024. The study followed the PRISMA 2020 guidelines for article selection. Risk of bias was assessed using QUADAS-2 for diagnostic studies, then data were analyzed descriptively through a narrative synthesis of results on accuracy, data input methods, and user proficiency. Discussions: The results showed that out of 925 initially identified articles, 13 met the inclusion criteria and were further analyzed. Advanced algorithms, particularly K-Nearest Neighbor (K-NN) and other machine learning models had high accuracy when supported by quality data and adequate user training. Moreover, real-time IoT-based tools showed high precision in nutritional assessments. Challenges remain in ensuring accurate data entry and algorithm updates to meet the needs of diverse populations. Conclusions: Digital applications present promising accuracy and precision in evaluating nutritional status of children under five. However, continuous improvement in data quality and user training is essential for the optimal implementation in public health interventions.]]>
Copyrights © 2025
