Application of adjusted-receiver operating characteristic curve analysis in combination of biomarkers for early detection of gestational diabetes mellitus

Introduction: In medical diagnostic field, evaluation of diagnostic accuracy of biomarkers or tests has always been a matter of concern. In some situations, one biomarker alone may not be sufficiently sensitive and specific for prediction of a disease. However, combining multiple biomarkers may lead to better diagnostic.  The aim of this study was to assess the performance of combination of biomarkers to early detection of gestational diabetes. Materials and Methods: In the present study, the information of 523 pregnant women referring to Mahdieh and Taleghani hospitals located in Tehran city was used. Relatively, Unconjugated Estriol (uE3), Alfa-Fetoprotein (AFP), and Beta- Human Chorionic Gonadotropin (β-HCG) were measured in the early second trimester of pregnancy. The accuracy of these biomarkers and also finding optimal linear combination of them was evaluated by area under receiver operating characteristic (ROC) curve (AUC), sensitivity, and specificity. Choosing of the best cut-point was based on Youden index. Data were statistically analyzed applying R 3.5.1 software package. Results: In the combination of two biomarkers, the largest AUC, sensitivity, and specificity values were 0.593, 61.90%, and 58.30%, respectively with optimal cut-point value 0.11. In the combination of the three biomarkers by adjusting for age and BMI effects simultaneously, the largest AUC, sensitivity, and specificity values were 0.751, 82.95%, and 74.62%, respectively with optimal cut-point value 0.10. Conclusion: Based on the findings of this research, the linear combination of the three biomarkers by considering covariate effects improved the diagnostic performance.