Multiplexed Serum Biomarkers to Discriminate Nonviable and Ectopic Pregnancy

Kurt T Barnhart; Kassie J Bollig; Suneeta Senapati; Peter Takacs; Jared C Robins; Daniel J Haisenleder; Lynn A Beer; Ricardo F Savaris; Nathanael C Koelper; David W Speicher; Jesse Chittams; Jingxuan Bao; Zixuan Wen; Yanbo Feng; Mansu Kim; Sunni Mumford; Li Shen; Phyllis Gimotty

doi:10.1016/j.fertnstert.2024.04.028

Multiplexed Serum Biomarkers to Discriminate Nonviable and Ectopic Pregnancy

Fertil Steril. 2024 Apr 25:S0015-0282(24)00262-0. doi: 10.1016/j.fertnstert.2024.04.028. Online ahead of print.

Authors

Kurt T Barnhart¹, Kassie J Bollig², Suneeta Senapati², Peter Takacs³, Jared C Robins⁴, Daniel J Haisenleder⁵, Lynn A Beer⁶, Ricardo F Savaris⁷, Nathanael C Koelper², David W Speicher⁶, Jesse Chittams⁸, Jingxuan Bao⁹, Zixuan Wen⁹, Yanbo Feng⁹, Mansu Kim⁹, Sunni Mumford¹⁰, Li Shen¹¹, Phyllis Gimotty¹²

Affiliations

¹ Department of Obstetrics and Gynecology, University of Pennsylvania, 3701 Market Street Suite 800, Philadelphia, PA 19104, USA; Biostatistics Consulting Unit, University of Pennsylvania School of Nursing, Claire M. Fagin Hall, 418 Curie Boulevard, Philadelphia, PA 19104, USA. Electronic address: kbarnhart@pennmedicine.upenn.edu.
² Department of Obstetrics and Gynecology, University of Pennsylvania, 3701 Market Street Suite 800, Philadelphia, PA 19104, USA.
³ Department of Obstetrics and Gynecology, Eastern Virginia Medical School, 825 Fairfax Avenue, Suite 310, Norfolk, VA 23507, USA.
⁴ Department of Obstetrics and Gynecology, Northwestern University, 250 East Superior Street, Suite 03-2303, Chicago, IL 60611, USA.
⁵ Department of Internal Medicine and the Center for Research in Reproduction, University of Virginia, PO Box 800391, OMS Suhling Building Room 6921, Hospital Drive, Charlottesville, VA 22908, USA.
⁶ Center for Systems & Computational Biology, The Wistar Institute, 3601 Spruce Street, Philadelphia, PA 19104, USA.
⁷ Department of Gynecology and Obstetrics, School of Medicine, Universidade Federal do Rio Grande do Sul, Porto Alegre, Brazil.
⁸ Biostatistics Consulting Unit, University of Pennsylvania School of Nursing, Claire M. Fagin Hall, 418 Curie Boulevard, Philadelphia, PA 19104, USA.
⁹ Department of Biostatistics, Epidemiology and Informatics, University of Pennsylvania Perelman School of Medicine, Philadelphia, PA 19104, USA.
¹⁰ Department of Obstetrics and Gynecology, University of Pennsylvania, 3701 Market Street Suite 800, Philadelphia, PA 19104, USA; Department of Biostatistics, Epidemiology and Informatics, University of Pennsylvania Perelman School of Medicine, Philadelphia, PA 19104, USA.
¹¹ Department of Biostatistics, Epidemiology and Informatics, University of Pennsylvania Perelman School of Medicine, B306 Richards Building, 3700 Hamilton Walk, Philadelphia, PA 19104, USA.
¹² Department of Biostatistics, Epidemiology and Informatics, University of Pennsylvania Perelman School of Medicine, 631 Blockley Hall, 423 Guardian Drive, Philadelphia, PA 19140, USA.

PMID: 38677710
DOI: 10.1016/j.fertnstert.2024.04.028

Abstract

Objective: The use of multiplexed biomarkers may improve the diagnosis of normal and abnormal early pregnancies. In this study we assessed 24 markers with multiple machine learning-based methodologies to evaluate combinations of top candidates to develop a multiplexed prediction model for identification of 1) viability and 2) location of an early pregnancy.

Design: A nested case-control design evaluating the predictive ability and discrimination of biomarkers in patients at risk of early pregnancy failure in the first trimester to classify viability and location SUBJECTS: 218 individuals with a symptomatic (pain and/or bleeding) early pregnancy: 75 with an ongoing intrauterine gestation, 68 ectopic pregnancies, and 75 miscarriages.

Interventions: Serum values 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 identification of 1) a nonviable pregnancy (ongoing intrauterine pregnancy vs miscarriage or ectopic pregnancy) and 2) an ectopic pregnancy (ectopic pregnancy vs ongoing intrauterine pregnancy or miscarriage).

Main outcome measures: The predicted classification by each model was compared to actual diagnosis and sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), conclusive classification, and accuracy were calculated.

Results: Models using classification regression tree analysis using three markers (PSG3, CG-Alpha and PAPPA) were able to predict a maximum sensitivity 93.3%, a maximum specificity 98.6%. The model with the highest accuracy was 97.4% (with 70.2% receiving classification). Models using an overlapping group of three markers (sFLT, PSG3 and TFP12) 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 95.9%. The predictive ability of the biomarkers random forest produced similar test characteristics when using 11 predictive markers.

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 CG-Alpha, PAPPA and PSG3 can be used to predict viability and sFLT, TPFI2 and PSG3 can be used to predict pregnancy location.

Keywords: biomarker; ectopic pregnancy; machine learning; multiple marker.