Related Experiment Video
Updated: Jan 4, 2026
Anesthesia-free Heartbeat Measurements in Freely Moving Zebrafish
Published on: April 18, 2025
Integrating machine learning techniques and physiology based heart rate features for antepartum fetal monitoring
Maria G Signorini1, Nicolò Pini1, Alberto Malovini2
1Department of Electronics, Information and Bioengineering (DEIB), Politecnico Milano, Piazza Leonardo da Vinci 32, 20133 Milano, Italy.
Insights
Early identification of Intrauterine Growth Restriction (IUGR) is crucial for fetal wellbeing. Machine learning models accurately diagnosed IUGR using antepartum CardioTocographic (CTG) recordings, improving pregnancy management.
Area of Science:
- Perinatal Medicine
- Biomedical Engineering
- Artificial Intelligence in Healthcare
Background:
- Intrauterine Growth Restriction (IUGR) is a critical fetal condition associated with significant morbidity and mortality.
- Current diagnosis of IUGR is typically confirmed postnatally, highlighting the need for improved antepartum detection.
- Early and accurate identification of IUGR during pregnancy is essential for effective management and improved fetal outcomes.
Purpose of the Study:
- To develop and validate an accurate machine learning framework for early antepartum diagnosis of IUGR.
- To assess the performance of various machine learning techniques in discriminating between healthy and IUGR fetuses.
- To identify key fetal heart rate features predictive of IUGR.
Main Methods:
- Utilized 15 distinct machine learning algorithms to classify fetuses as healthy or affected by IUGR.
- Extracted 12 physiology-based heart rate features from antepartum CardioTocographic (CTG) recordings.
- Employed time, frequency, and nonlinear indices for their established ability to reflect fetal physiological states.
Main Results:
- The Random Forests model achieved the highest classification accuracy of 0.911 (95% CI: 0.860-0.961) in discriminating between healthy and IUGR fetuses.
- Classification Trees, Logistic Regression, and Support Vector Machines also demonstrated strong performance.
- Nonlinear indices were identified as highly discriminative, with their combination further enhancing classification accuracy.
Conclusions:
- An accurate artificial intelligence framework for antepartum IUGR diagnosis has been validated.
- Physiology-based heart rate features provide an interpretable link between machine learning outputs and fetal wellbeing.
- This AI framework holds promise for improving antepartum surveillance and management of IUGR pregnancies.
Background And Objectives:
Intrauterine Growth Restriction (IUGR) is a fetal condition defined as the abnormal rate of fetal growth. The pathology is a documented cause of fetal and neonatal morbidity and mortality. In clinical practice, diagnosis is confirmed at birth and may only be suspected during pregnancy. Therefore, designing an accurate model for the early and prompt identification of pathology in the antepartum period is crucial in view of pregnancy management.
Methods:
We tested the performance of 15 machine learning techniques in discriminating healthy versus IUGR fetuses. The various models were trained with a set of 12 physiology based heart rate features extracted from a single antepartum CardioTocographic (CTG) recording. The reason for the utilization of time, frequency, and nonlinear indices is based on their standalone documented ability to describe several physiological and pathological fetal conditions.
Results:
We validated our approach on a database of 60 healthy and 60 IUGR fetuses. The machine learning methodology achieving the best performance was Random Forests. Specifically, we obtained a mean classification accuracy of 0.911 [0.860, 0.961 (0.95 confidence interval)] averaged over 10 test sets (10 Fold Cross Validation). Similar results were provided by Classification Trees, Logistic Regression, and Support Vector Machines. A features ranking procedure highlighted that nonlinear indices showed the highest capability to discriminate between the considered fetal conditions. Nevertheless, is the combination of features investigating CTG signal in different domains, that contributes to an increase in classification accuracy.
Conclusions:
We provided validation of an accurate artificially intelligence framework for the diagnosis of IUGR condition in the antepartum period. The employed physiology based heart rate features constitute an interpretable link between the machine learning results and the quantitative estimators of fetal wellbeing.
More Related Videos
Related Concept Videos
01:30Pulse rhythm
Conversely, an irregular pulse pattern is termed dysrhythmia, stemming from disruptions in cardiac...
01:14Fetal Circulation
Two umbilical arteries transport blood from the fetus to the placenta. At the placenta, the blood absorbs oxygen and nutrients while simultaneously eliminating waste products. This oxygen-enriched and nutrient-rich blood then returns to the fetus through one...
01:23Holter Monitor: 24-Hour Monitoring