AI-Augmented Prenatal Care: A Dual-Modal Fetal Health Assessment System Integrating Cardiotocography and Uterine Contraction Synergy

Tianxin Qiu^1,2Xinghe Zhou²Jun Zhou^1*Chunxia Lin^1*Shiling Jiang¹Hui Cheng¹Xinhao Wang²Qingshan You²

• ¹The First People's Hospital of Longquanyi District Chengdu, Chengdu, China
• ²Civil Aviation Flight University of China, Guanghan, China

This study explores the importance of artificial intelligence technology and bimodal coanalysis in obstetrics clinical decision making from the technical implementation of clinical practice guidelines. The research team developed an intelligent monitoring system based on the DenseNet121-SK architecture by constructing the first fetal heart-contraction bimodal clinical dataset (n=326) using deep learning methods. The study reveals three core findings: (1) at the technology standardization level, the bimodal data input significantly improves the classification performance (AUC 0.944 vs. 0.812) over the traditional unimodal analysis, validating the scientific validity of the clinical guidelines that emphasize the synergistic multi-parameter interpretation; (2) at the human-computer collaboration dimension, the model simulates obstetrician's multi-scalar cognitive features through the Selective Attention mechanism (SK module), while achieving 95.88% accuracy while maintaining clinical interpretability; (3) medical practice dimension, the system demonstrates the potential to reduce subjective interpretation discrepancies with a 100% recall rate of abnormal cases, providing a technological solution for mitigating excessive medical interventions. This study is based on lightweight AI design (e.g., optimizing contraction curve visualization) can effectively enhance physicians' willingness to adopt, demonstrates high practical value in resource-constrained healthcare scenarios, and provides a feasible path for primary care intelligence. The research results have important policy implications for optimizing perinatal medical resource allocation and balancing technical rationality and clinical experience.