Your new experience awaits. Try the new design now and help us make it even better

ORIGINAL RESEARCH article

Front. Physiol.

Sec. Computational Physiology and Medicine

Volume 16 - 2025 | doi: 10.3389/fphys.2025.1638788

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

Provisionally accepted
Tianxin  QiuTianxin Qiu1,2Xinghe  ZhouXinghe Zhou2Jun  ZhouJun Zhou1*Chunxia  LinChunxia Lin1*Shiling  JiangShiling Jiang1Hui  ChengHui Cheng1Xinhao  WangXinhao Wang2Qingshan  YouQingshan You2
  • 1The First People's Hospital of Longquanyi District Chengdu, Chengdu, China
  • 2Civil Aviation Flight University of China, Guanghan, China

The final, formatted version of the article will be published soon.

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.

Keywords: Medical artificial intelligence, Obstetric decision-making, DenseNet121-SK, Clinical cognition, Human-machine collaboration

Received: 05 Jun 2025; Accepted: 03 Sep 2025.

Copyright: © 2025 Qiu, Zhou, Zhou, Lin, Jiang, Cheng, Wang and You. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

* Correspondence:
Jun Zhou, The First People's Hospital of Longquanyi District Chengdu, Chengdu, China
Chunxia Lin, The First People's Hospital of Longquanyi District Chengdu, Chengdu, China

Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.