Clinical utility assessment framework for machine learning-based fetal health classification in cardiotocography: an observational study

Key Points

• Evaluate the clinical utility of AI-based systems for fetal health classification in cardiotocography.
• Observational study design
• Analysis of machine learning algorithms for fetal health
• Assessment of false negative rates in pathological cases
• Multicenter clinical data utilization
• Significant false negative rate observed for pathological cases
• Machine learning systems require external validation before clinical use
• Study highlights importance of multicenter data for reliability