M-TabNet: A Multi-Encoder Transformer Model for Predicting Neonatal Birth Weight from Multimodal Data

2025-04-20

AI Summary

This study addresses the challenge of accurately predicting newborn birth weight during early pregnancy (<12 weeks), overcoming limitations of ultrasound—namely narrow temporal windows, suboptimal accuracy, and operator dependency. We propose the first multi-encoder Transformer architecture tailored for structured clinical data, integrating multimodal features including maternal physiology, lifestyle, nutrition, and genetics to jointly support birth weight regression and low birth weight (LBW) risk classification. A novel cross-domain feature interaction mechanism is introduced, enabling the first systematic integration of nutritional and genetic factors; SHAP-based interpretability further supports clinically actionable risk attribution. Evaluated on a private cohort, our model achieves MAE = 122 g (R² = 0.94); independent validation on the IEEE Children’s Dataset yields MAE = 105 g (R² = 0.95), with LBW classification sensitivity of 97.55% and specificity of 94.48%.

Technology Category

• Machine Learning: Feature Construction/Reformulation
• Computer Vision: Multi-modal Vision
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• Web Mining and Content Analysis: Large pretrained models with web data
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI

Abstract

Birth weight (BW) is a key indicator of neonatal health, with low birth weight (LBW) linked to increased mortality and morbidity. Early prediction of BW enables timely interventions; however, current methods like ultrasonography have limitations, including reduced accuracy before 20 weeks and operator dependent variability. Existing models often neglect nutritional and genetic influences, focusing mainly on physiological and lifestyle factors. This study presents an attention-based transformer model with a multi-encoder architecture for early (less than 12 weeks of gestation) BW prediction. Our model effectively integrates diverse maternal data such as physiological, lifestyle, nutritional, and genetic, addressing limitations seen in prior attention-based models such as TabNet. The model achieves a Mean Absolute Error (MAE) of 122 grams and an R-squared value of 0.94, demonstrating high predictive accuracy and interoperability with our in-house private dataset. Independent validation confirms generalizability (MAE: 105 grams, R-squared: 0.95) with the IEEE children dataset. To enhance clinical utility, predicted BW is classified into low and normal categories, achieving a sensitivity of 97.55% and a specificity of 94.48%, facilitating early risk stratification. Model interpretability is reinforced through feature importance and SHAP analyses, highlighting significant influences of maternal age, tobacco exposure, and vitamin B12 status, with genetic factors playing a secondary role. Our results emphasize the potential of advanced deep-learning models to improve early BW prediction, offering clinicians a robust, interpretable, and personalized tool for identifying pregnancies at risk and optimizing neonatal outcomes.

Problem

• Predict neonatal birth weight early using multimodal data
• Overcome limitations of current methods like ultrasonography
• Integrate diverse maternal factors for accurate risk stratification

Innovation

• Multi-encoder transformer model for early prediction
• Integrates physiological, lifestyle, nutritional, genetic data
• Achieves high accuracy with interpretable SHAP analysis