1. Multiplexed serum biomarkers to discriminate nonviable and ectopic pregnancy.
- Author
-
Barnhart KT, Bollig KJ, Senapati S, Takacs P, Robins JC, Haisenleder DJ, Beer LA, Savaris RF, Koelper NC, Speicher DW, Chittams J, Bao J, Wen Z, Feng Y, Kim M, Mumford S, Shen L, and Gimotty P
- Subjects
- Humans, Female, Pregnancy, Case-Control Studies, Adult, Diagnosis, Differential, Pregnancy Trimester, First blood, Reproducibility of Results, Pregnancy, Ectopic blood, Pregnancy, Ectopic diagnosis, Biomarkers blood, Abortion, Spontaneous blood, Abortion, Spontaneous diagnosis, Predictive Value of Tests, Machine Learning
- Abstract
Objective: To evaluate combinations of candidate biomarkers to develop a multiplexed prediction model for identifying the viability and location of an early pregnancy. In this study, we assessed 24 biomarkers with multiple machine learning-based methodologies to assess if multiplexed biomarkers may improve the diagnosis of normal and abnormal early pregnancies., Design: A nested case-control design evaluated the predictive ability and discrimination of biomarkers in patients at risk of early pregnancy failure in the first trimester to classify viability and location., Setting: Three university hospitals., Patients: A total of 218 individuals with pain and/or bleeding in early pregnancy: 75 had an ongoing intrauterine gestation; 68 had ectopic pregnancies (EPs); and 75 had miscarriages., Interventions: Serum levels of 24 biomarkers were assessed in the same patients. Multiple machine learning-based methodologies to evaluate combinations of these top candidates to develop a multiplexed prediction model for the identification of a nonviable pregnancy (ongoing intrauterine pregnancy vs. miscarriage or EP) and an EP (EP vs. ongoing intrauterine pregnancy or miscarriage)., Main Outcome Measures: The predicted classification using each model was compared with the actual diagnosis, and sensitivity, specificity, positive predictive value, negative predictive value, conclusive classification, and accuracy were calculated., Results: Models using classification regression tree analysis using 3 (pregnancy-specific beta-1-glycoprotein 3 [PSG3], chorionic gonadotropin-alpha subunit, and pregnancy-associated plasma protein-A) biomarkers were able to predict a maximum sensitivity of 93.3% and a maximum specificity of 98.6%. The model with the highest accuracy was 97.4% (with 70.2% receiving classification). Models using an overlapping group of 3 (soluble fms-like tyrosine kinase-1, PSG3, and tissue factor pathway inhibitor 2) biomarkers achieved a maximum sensitivity of 98.5% and a maximum specificity of 95.3%. The model with the highest accuracy was 94.4% (with 65.6% receiving classification). When the models were used simultaneously, the conclusive classification increased to 72.7% with an accuracy of 95.9%. The predictive ability of the biomarkers in the random forest produced similar test characteristics when using 11 predictive biomarkers., Conclusion: We have demonstrated a pool of biomarkers from divergent biological pathways that can be used to classify individuals with potential early pregnancy loss. The biomarkers choriogonadotropin alpha, pregnancy-associated plasma protein-A, and PSG3 can be used to predict viability, and soluble fms-like tyrosine kinase-1, tissue factor pathway inhibitor 2, and PSG3 can be used to predict pregnancy location., Competing Interests: Declaration of Interests K.T.B. reports funding from NIH R01HD076279 and NIH ROI HD 110448 for the submitted work; funding from NIH ROI HD 110448 and NIH R01HD076279; patent pending outside the submitted work. K.J.B. has nothing to disclose. S.S. reports funding from National Institutes of Health, AbbVie, and Burroughs Wellcome Fund; Society for Assisted Reproductive Technology Research Committee Chair; Oncofertility Consortium Practice Committee outside the submitted work. P.T. reports funding from NIH ROI HD 110448 for the submitted work. J.C.R. has nothing to disclose. D.J.H. has nothing to disclose. L.A.B. has nothing to disclose. R.F.S. has nothing to disclose. N.C.K. has nothing to disclose. D.W.S. has nothing to disclose. J.C. has nothing to disclose. J.B. has nothing to disclose. Z.W. has nothing to disclose. Y.F. has nothing to disclose. M.K. reports funding from National research foundation of Korea; honorarium from Catholic university of Korea. S.M. reports funding from National Institutes of Health (UG3-OD035537) and PCORI (BPS-2022C3-30268); travel support from Society for Epidemiologic Research; Society for Epidemiologic Research Member at Large of the Executive Committee outside the submitted work. L.S. reports funding from R01 HD110448 for the submitted work; funding from IIS 1837964 RF1 AG063481 R01 LM013463 U01 AG068057 R01 AG058854 R01 AG071470 RF1 AG068191 U01 AG066833 R01 AG066833 P30 AG073105 R01 LM011176 - 09 R01 LM011176 - 09S1 R01 LM011176 - 09S2 R00 HG010905 R01 HD110448 U19 AG074879 LillyLRAP P30AG073105-03S2 outside the submitted work. P.G. has nothing to disclose., (Copyright © 2024. Published by Elsevier Inc.)
- Published
- 2024
- Full Text
- View/download PDF