OBJECTIVES: Preterm delivery contributes to an increased risk of fetal and maternal death and several health deficiencies. Diagnosis of preterm delivery in advance is important to avoid or minimize its undesirable consequences to the baby and the mother. Data-driven decision-making using AI algorithms has been increasingly common in the obstetrics field by providing improved diagnostic accuracy and automated, standardized interpretation and inference processes. CADXpert OB-GYN uses clinically validated models that can efficiently predict Pre-term birth using data from standard clinical practice. The study evaluated the economic and clinical performance of the AI-web based predictive model on the accurate detection of preterm births.

METHODS: A micro-costing analysis, based on costs of the Greek healthcare system, was performed to identify the costs of development of the new AI technology and an array of the most important indicators to enable performance identification. The most important KPIs were clinical performance, and user satisfaction. The analysis of costs and consequences was performed incrementally between the current practice and the new AI technology.

RESULTS: Although the new AI technology imposes extra costs of €12.142 annually, this cost is counterbalanced by the clinical performance with a ROC-AUC of 83% and recall of 94%, indicating that almost all positive cases are correctly identified, and the possibility of earlier detection of premature birth by 6 weeks in favor of the new AI technology vs. current practice (28 weeks vs. 34 weeks). A conservative estimation of potential savings of €155.794 on an annual basis could be considered the baseline. The system usability score of the new technology was 71.50%. The new AI technology required fewer human resources for the review of the examination.

CONCLUSIONS: AI could automate parts of the process providing improved accuracy, with less human resources, resulting in savings for the healthcare systems.