Role of Inflammatory Markers and Doppler Parameters in Late-Onset Fetal Growth Restriction: A Machine Learning Approach

Objectives This study evaluates the association of novel inflammatory markers and Doppler parameters in late-onset FGR, utilizing a machine learning approach to enhance predictive accuracy. Materials and methods A retrospective case-control study was conducted at the Department of Perinatology, Ministry of Health Etlik City Hospital, Ankara, from 2023 to 2024. The study included 240 patients between 32–37 weeks of gestation, divided equally between patients diagnosed with late-onset FGR and a control group. We focused on novel inflammatory markers—systemic immune-inflammation index (SII), systemic inflammatory response index (SIRI), and neutrophil-percentage-to-albumin ratio (NPAR)—and their correlation with Doppler parameters of umbilical and uterine arteries. Machine learning algorithms were employed to analyze data collected, including demographic, neonatal, and clinical parameters, to develop a predictive model for FGR. Results The machine learning model, specifically the Random Forest algorithm, effectively integrated the inflammatory markers with Doppler parameters to predict FGR. NPAR showed a significant correlation with FGR presence, providing a robust tool in the predictive model. In contrast, SII and SIRI, while useful, did not achieve the same level of predictive accuracy. The model highlighted the potential of combining ultrasound measurements with inflammatory markers to improve diagnostic accuracy for late-onset FGR. Conclusions This study illustrates the efficacy of integrating machine learning with traditional diagnostic methods to enhance the prediction of late-onset FGR. Further research with a larger cohort is recommended to validate these findings and refine the predictive model, which could lead to improved clinical outcomes for affected pregnancies. The take-home message: This study demonstrates that combining novel inflammatory markers, particularly the neutrophil-percentage-to-albumin ratio (NPAR) and the systemic immune-inflammation index (SII), with Doppler ultrasound parameters can significantly improve the prediction accuracy of late-onset fetal growth restriction (FGR) using a machine learning approach. This integration of machine learning with traditional diagnostic methods provides a more robust and cost-effective tool for the early diagnosis and management of FGR in clinical settings.