A First-Trimester Serum Proteomic Signature for Early Prediction of Preeclampsia: Integrated Untargeted and Targeted Mass Spectrometry with Machine Learning

First-trimester prediction of preeclampsia (PE) remains a major clinical challenge, particularly outside specialized fetal medicine centers. This study aimed to identify and validate serum protein biomarkers for early PE prediction using an integrated proteomic approach. A prospective cohort of 64 first-trimester singleton pregnancies (32 future PE cases, 32 matched controls) was analyzed. Untargeted proteomics was performed using DIA-PASEF-MS, followed by targeted cross-platform verification with MRM-MS. Machine learning classifiers (support vector machines, SVM, and random forest) were trained on differentially abundant proteins (FDR 1.5). DIA-MS identified 33 protein markers associated with complement activation, IGF transport regulation, and platelet degranulation. An SVM model with a linear kernel achieved 95% accuracy (AUC = 0.95, sensitivity = 95%, specificity = 97%). Four markers (AFM, AHSG, C8A, IGHG1) were confirmed across platforms, confirming the discovery findings. Cross-platform correlation was high: 71% of overlapping proteins showed r > 0.5 (p 0.5, p < 0.05), linking the proteomic signature to clinical severity. Integrated DIA-MS and MRM-MS proteomics yields a reproducible, high-performance serum signature for first-trimester PE prediction. The identified markers reflect core pathophysiological pathways and offer potential to augment current FMF-based screening algorithms.