Background: Central nervous system anomalies represent a wide range of congenital birth defects, with an incidence of approximately 1% of all births. They are currently diagnosed using ultrasound evaluation. However, there is strong need for a more accurate and less operator-dependent screening method.
Objectives: To perform a characterization of maternal serum in order to build a metabolomic fingerprint resulting from congenital anomalies of the central nervous system.
Methods: This is a case-control pilot study. Metabolomic profiles were obtained from serum of 168 mothers (98 controls and 70 cases), using gas chromatography coupled to mass spectrometry. Nine machine learning and classification models were built and optimized. An ensemble model was built based on results from the individual models. All samples were randomly divided into two groups. One was used as training set, the other one for diagnostic performance assessment.
Results: Ensemble machine learning model correctly classified all cases and controls. Propanoic, lactic, gluconic, benzoic, oxalic, 2-hydroxy-3-methylbutyric, acetic, lauric, myristic and stearic acid and myo-inositol and mannose were selected as the most relevant metabolites in class separation.
Conclusion: The metabolomic signature of second trimester maternal serum from pregnancies affected by a fetal central nervous system anomaly is quantifiably different from that of a normal pregnancy. Maternal serum metabolomics is therefore a promising tool for the accurate and sensitive screening of such congenital defects. Moreover, the details of the most relevant metabolites and their respective biochemical pathways allow better understanding of the overall pathophysiology of affected pregnancies.
Keywords: Central nervous system abnormalities; Gas chromatography mass spectrometry; Machine learning; Metabolomics; Screening test.