Machine Learning Models for the Prediction of Preterm Birth at Mid-Gestation Using Individual Characteristics and Biophysical Markers: A Cohort Study
Models using routine mid-gestation data demonstrate effective prediction for iatrogenic PTB, with accuracy improving for earlier, more severe cases. In contrast, performance for spontaneous PTB was modest. Traditional Logistic Regression performed comparably to complex machine learning algorithms, highlighting that the clinical value is rooted in the subtype-specific modeling approach rather than in algorithmic complexity.
Authors
- Ιoannis Tsakiridis (ORCID: https://orcid.org/0000-0003-4337-7871)
- Dimitra Kappou (ORCID: https://orcid.org/0000-0003-1141-4738)
- Ioannis Papastefanou (ORCID: https://orcid.org/0000-0002-7969-1435)
- Themistoklis Dagklis (ORCID: https://orcid.org/0000-0002-2863-5839)
- Apostolos Mamopoulos (ORCID: https://orcid.org/0000-0002-2605-0765)
- Antonios Siargkas (ORCID: https://orcid.org/0000-0003-3066-9963)
Institutions
- King's College London (GB)
- Aristotle University of Thessaloniki (GR)
- IASO General Hospital (GR)
Publication Details
- Journal
- Children
- Published
- 2025-10-25
- DOI
- https://doi.org/10.3390/children12111451
- Primary Topic
- Preterm Birth and Chorioamnionitis
- Type
- article
- Field-Weighted Citation Impact
- 0.00