Research on Prediction of Preterm Birth Risk Based on Digital Twin Technology

Background: Preterm birth remains a major cause of perinatal morbidity and long-term developmental complications. Existing prediction methods often lack individualized assessment and have limited capability to integrate multi-source maternal–fetal information. This study aims to develop a personalized preterm birth risk prediction model and to construct a visual, interactive digital twin platform that enhances clinical communication and supports early risk identification. Methods: A total of 1157 structured clinical records collected from 2020 to 2024 were preprocessed through automated feature typing, missing-value handling, and normalization. Two complementary machine-learning models—FT-Transformer and Light Gradient Boosting Machine (LightGBM)—were trained and calibrated to produce probabilities. Their outputs were fused using a Stacking Logistic Regression framework to improve prediction stability and calibration. A 3D visualization module was developed using 3ds Max, PyQt6, and PyVista to generate personalized uterine–fetal models based on fetal position, placental location, and Biparietal Diameter (BPD), enabling synchronized display of prediction results. Results: The fused model achieved an AUC of 0.820, PR-AUC of 0.405, a Brier score of 0.040, and an expected calibration error (ECE) of 3.39 × 10−3, demonstrating superior discrimination and probability reliability compared with single models. The interactive platform supports real-time data input, risk prediction, and adaptive 3D rendering, providing clear and intuitive visual feedback for clinical interpretation. Conclusions: The integration of machine learning fusion and digital twin visualization enables individualized assessment of preterm birth risk. The system improves model accuracy, enhances interpretability, and offers a practical tool for clinical follow-up, risk counseling, and maternal health education.

• Publication year

  2026

• Venue

  Diagnostics

• Publication date

  2026-02-01

• Fields of study

  Medicine, Computer Science

• Identifiers
  DOI 10.3390/diagnostics16030499PMID 41681816PMCID 12897373
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Predicting and preventing preterm birth in Europe: current challenges and gaps

  2025cited by this paper
• Evaluating ensemble models for fair and interpretable prediction in higher education using multimodal data

  2025cited by this paper
• Predicting learning achievement using ensemble learning with result explanation

  2025cited by this paper
• Large-scale IoT attack detection scheme based on LightGBM and feature selection using an improved salp swarm algorithm

  2024cited by this paper
• Gegen Qinlian Decoction treatment of asymptomatic hyperuricemia by targeting circadian immune function

  2023cited by this paper
• Predictive value of quantitative fetal fibronectin for spontaneous preterm birth in asymptomatic pregnancies: a systematic literature review and meta-analysis

  2023cited by this paper
• Prediction of preterm birth using artificial intelligence: a systematic review

  2022cited by this paper
• Computational Methods for Fluid-Structure Interaction Simulation of Heart Valves in Patient-Specific Left Heart Anatomies

  2022cited by this paper
• Gradient boosting decision tree becomes more reliable than logistic regression in predicting probability for diabetes with big data

  2022cited by this paper
• Why do tree-based models still outperform deep learning on tabular data?

  2022cited by this paper
• An individualized digital twin of a patient for transdermal fentanyl therapy for chronic pain management

  2022cited by this paper
• A Review of Roles of Uterine Artery Doppler in Pregnancy Complications

  2022cited by this paper
• Development of Digital Twins to Optimize Trauma Surgery and Postoperative Management. A Case Study Focusing on Tibial Plateau Fracture

  2021cited by this paper
• Optimal Treatment Selection in Sequential Systemic and Locoregional Therapy of Oropharyngeal Squamous Carcinomas: Deep Q-Learning With a Patient-Physician Digital Twin Dyad

  2021cited by this paper
• Machine Learning Methods for Preterm Birth Prediction: A Review

  2021cited by this paper
• Revisiting Deep Learning Models for Tabular Data

  2021cited by this paper
• Development and Verification of a Digital Twin Patient Model to Predict Specific Treatment Response During the First 24 Hours of Sepsis

  2020cited by this paper
• TabTransformer: Tabular Data Modeling Using Contextual Embeddings

  2020cited by this paper
• Women's Obstetric History and Midtrimester Cervical Length Measurements by 2D/3D and Doppler Ultrasound

  2020cited by this paper
• Flexible Imputation of Missing Data, 2nd ed.

  2019cited by this paper
• High-performance medicine: the convergence of human and artificial intelligence

  2019cited by this paper
• An artificial intelligence-enabled ECG algorithm for the identification of patients with atrial fibrillation during sinus rhythm: a retrospective analysis of outcome prediction.

  2019cited by this paper
• Epigenetic signature of preterm birth in adult twins

  2018cited by this paper
• Flexible Imputation of Missing Data, Second Edition

  2018cited by this paper
• Super learning in the SAS system

  2018cited by this paper
• Scalable and accurate deep learning with electronic health records

  2018cited by this paper
• Ensemble learning: A survey

  2018cited by this paper
• Deep EHR: A Survey of Recent Advances in Deep Learning Techniques for Electronic Health Record (EHR) Analysis

  2017cited by this paper
• Dermatologist-level classification of skin cancer with deep neural networks

  2017cited by this paper
• Can machine-learning improve cardiovascular risk prediction using routine clinical data?

  2017cited by this paper
• Reproducibility in critical care: a mortality prediction case study

  2017cited by this paper
• XGBoost: A Scalable Tree Boosting System

  2016cited by this paper
• Applied Predictive Modeling

  2013cited by this paper
• Challenges in defining and classifying the preterm birth syndrome.

  2012cited by this paper
• The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd Edition

  2009cited by this paper
• Feature-Weighted Linear Stacking

  2009cited by this paper
• Pattern Recognition and Machine Learning

  2006cited by this paper
• Predicting good probabilities with supervised learning

  2005cited by this paper
• The Elements of Statistical Learning: Data Mining, Inference, and Prediction

  2001cited by this paper
• Stacked generalization

  1992cited by this paper

• No citing papers are available for this paper.