Intelligent Nutrition Technologies in Prenatal Support: Digital Nutrition Personalization for Metabolic and Fetal Health in Pregnant Women

Citation: Anastasiia Shapovalova, "Intelligent Nutrition Technologies in Prenatal Support: Digital Nutrition Personalization for Metabolic and Fetal Health in Pregnant Women", Universal Library of Medical and Health Sciences, Volume 02, Issue 03.

Copyright: This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Abstract

Against the background of a sustained increase in the incidence of gestational diabetes mellitus (GDM) and excessive gestational weight gain (EGWG), the effectiveness of standard population-based dietary recommendations appears to be limited. According to estimates by the International Diabetes Federation (IDF), the global prevalence of hyperglycemia in the prenatal period has reached a critical level, affecting 15,6% of all live births in 2024. A substantial methodological and technological gap is evident, driven by the fragmentation of existing digital solutions: despite compelling results from point solutions, such as the use of artificial intelligence methods for predicting GDM risk and Internet of Things (IoT) systems for continuous monitoring of the condition of pregnant women, these tools are generally not integrated into a single system for supporting clinical and nutrition-related decision-making. In this context, a scientific and practical objective emerges: to develop a holistic concept of digital infrastructure aimed at personalized pregnancy management under increased metabolic risks. Within this objective, the conceptual architecture of an Intelligent Nutrition Platform (INP) is substantiated, intended for comprehensive, dynamic digital personalization of diet and physical activity in pregnant women. A three-level organization of the INP is envisaged, based on multimodal phenotyping, including: real-time recording of physiological parameters using IoT devices, detailed analysis of dietary intake employing computer vision technologies and semantic data processing, and integration of omics information, in particular microbiome profiles. The intelligent core of the platform is built on adaptive ensemble machine learning algorithms operating in an environment protected by a blockchain architecture, which ensures interoperability, integrity, and confidentiality of data at all stages of their lifecycle. It is expected that the implementation of the INP will substantially increase the accuracy of early prediction of metabolic risks during gestation, strengthen pregnant women’s adherence to personalized nutritional and behavioral interventions and, consequently, improve key indicators of maternal metabolic status as well as fetal growth and development.

Keywords: Intelligent Nutrition Science, Prenatal Support, Digital Personalization, Gestational Diabetes, Artificial Intelligence, Fetal Health, IoT, Blockchain, Multimodal Phenotyping.

https://doi.org/10.70315/uloap.ulmhs.2024.0203006