Objective:

To develop and validate a machine-learning model for predicting preterm birth in pregnant women with gestational diabetes mellitus and hypertensive disorders.

Approach:

Key Findings:

• The Naive Bayes model showed the best balance of discrimination, interpretability, and robustness among evaluated algorithms.
• Five significant predictors were identified: alanine transaminase, aspartate transaminase, albumin, lactate dehydrogenase, and systolic blood pressure.
• The Naive Bayes model maintained strong generalization in the external validation cohort with an AUC of 0.777.

Interpretation:

The Naive Bayes model may assist clinicians in early identification and personalized risk management of high-risk pregnancies, representing a step towards evidence-based decision support in obstetrics.

Limitations:

• The study was limited to two centers and a relatively small sample size.
• Further validation in larger, multicenter cohorts is needed.

Conclusion:

The Naive Bayes model is a promising tool for predicting preterm birth in high-risk pregnancies, warranting further research for real-time clinical application.

Sources:

• Frontiers in Endocrinology
Attribution Notice

This content is an AI-generated, fully rewritten summary based on a published scholarly article. It does not reproduce the original text and is not a substitute for the original publication. Readers are encouraged to consult the source for full context, data, and methodology.