The Metabolomic Approach for the Screening of Endometrial Cancer: Validation from a Large Cohort of Women Scheduled for Gynecological Surgery
Jacopo Troisi,
Antonio Mollo,
Martina Lombardi,
Giovanni Scala,
Sean M. Richards,
Steven J. K. Symes,
Antonio Travaglino,
Daniele Neola,
Umberto de Laurentiis,
Luigi Insabato,
Attilio Di Spiezio Sardo,
Antonio Raffone,
Maurizio Guida
Affiliations
Jacopo Troisi
Department of Medicine, Surgery and Dentistry, “Scuola Medica Salernitana”, University of Salerno, 84081 Baronissi, Italy
Antonio Mollo
Department of Medicine, Surgery and Dentistry, “Scuola Medica Salernitana”, University of Salerno, 84081 Baronissi, Italy
Martina Lombardi
Theoreo Srl, Via Degli Ulivi 3, 84090 Montecorvino Pugliano, Italy
Giovanni Scala
Theoreo Srl, Via Degli Ulivi 3, 84090 Montecorvino Pugliano, Italy
Sean M. Richards
Section on Maternal-Fetal Medicine, Department of Obstetrics and Gynecology, University of Tennessee College of Medicine, Chattanooga, TN 37403, USA
Steven J. K. Symes
Department of Biology, Geology and Environmental Sciences, University of Tennessee College of Medicine, Chattanooga, TN 37403, USA
Antonio Travaglino
Anatomic Pathology Unit, Department of Advanced Biomedical Sciences, University of Naples Federico II, 80138 Naples, Italy
Daniele Neola
Gynecology and Obstetrics Unit, Department of Public Health, University of Naples Federico II, 80138 Naples, Italy
Umberto de Laurentiis
Department of Medicine, Surgery and Dentistry, “Scuola Medica Salernitana”, University of Salerno, 84081 Baronissi, Italy
Luigi Insabato
Gynecology and Obstetrics Unit, Department of Public Health, University of Naples Federico II, 80138 Naples, Italy
Attilio Di Spiezio Sardo
Gynecology and Obstetrics Unit, Department of Public Health, University of Naples Federico II, 80138 Naples, Italy
Antonio Raffone
Division of Gynaecology and Human Reproduction Physiopathology, Department of Medical and Surgical Sciences (DIMEC), IRCCS Azienda Ospedaliero-Univeristaria di Bologna. S. Orsola Hospital, University of Bologna, Via Massarenti 13, 40138 Bologna, Italy
Maurizio Guida
Gynecology and Obstetrics Unit, Department of Neuroscience, Reproductive Sciences and Dentistry, University of Naples Federico II, 80138 Naples, Italy
Endometrial cancer (EC) is the most common gynecological neoplasm in high-income countries. Five-year survival rates are related to stage at diagnosis, but currently, no validated screening tests are available in clinical practice. The metabolome offers an unprecedented overview of the molecules underlying EC. In this study, we aimed to validate a metabolomics signature as a screening test for EC on a large study population of symptomatic women. Serum samples collected from women scheduled for gynecological surgery (n = 691) were separated into training (n = 90), test (n = 38), and validation (n = 563) sets. The training set was used to train seven classification models. The best classification performance during the training phase was the PLS-DA model (96% accuracy). The subsequent screening test was based on an ensemble machine learning algorithm that summed all the voting results of the seven classification models, statistically weighted by each models’ classification accuracy and confidence. The efficiency and accuracy of these models were evaluated using serum samples taken from 871 women who underwent endometrial biopsies. The EC serum metabolomes were characterized by lower levels of serine, glutamic acid, phenylalanine, and glyceraldehyde 3-phosphate. Our results illustrate that the serum metabolome can be an inexpensive, non-invasive, and accurate EC screening test.
