Objective: Anemia remains a major public health concern among pregnant women, significantly contributing to maternal and infant morbidity and mortality. With advances in digital technology, particularly machine learning (ML), there is potential to enhance early detection and prevention strategies. This scoping review is aimed at synthesizing the existing literature on the application of ML-based digital tools for predicting and preventing anemia in pregnant women. Methods: Following the PRISMA-ScR guidelines, this review included articles from PubMed, Scopus, and Google Scholar published between 2015 and 2024. Eligibility criteria included studies using ML methods for anemia prediction in pregnant women. Extracted data included study population, ML algorithms used, and performance metrics. Due to the scoping nature of this review, risk of bias assessment was not conducted. Results: A total of 11 studies met the inclusion criteria, utilizing various ML algorithms such as decision trees, random forest, support vector machines, naive Bayes, K-nearest neighbors, PART, fuzzy Tsukamoto, and boosting algorithms. Comparative analysis based on performance metrics (accuracy, precision, recall, F1-score, and AUC) identified boosting and random forest as the most effective models in resource-limited settings. However, heterogeneity in data sources, evaluation metrics, and populations limits generalizability. Conclusions: ML-based models demonstrate considerable promise in predicting anemia among pregnant women. However, further validation across diverse datasets, clearer articulation of methodological strengths and limitations, and attention to implementation feasibility in low-resource settings are needed. Copyright © 2025 Husnul Khotimah et al. International Journal of Telemedicine and Applications published by John Wiley & Sons Ltd.