Multiplex analysis of 40 cytokines do not allow separation between endometriosis patients and controls

Tamara Knifc, Dmytro Fishman, Andrej Vogler, Manuela Gstöttner, René Wenzl, Hedi Peterson, Tea Lanišnik Rižner

Abstract:

Endometriosis is a common gynaecological condition characterized by severe pelvic pain and/or
infertility. The combination of nonspecifc symptoms and invasive laparoscopic diagnostics have
prompted researchers to evaluate potential biomarkers that would enable a non-invasive diagnosis of
endometriosis. Endometriosis is an infammatory disease thus diferent cytokines represent potential
diagnostic biomarkers. As panels of biomarkers are expected to enable better separation between
patients and controls we evaluated 40 diferent cytokines in plasma samples of 210 patients (116
patients with endometriosis; 94 controls) from two medical centres (Slovenian, Austrian). Results of
the univariate statistical analysis showed no diferences in concentrations of the measured cytokines
between patients and controls, confrmed by principal component analysis showing no clear separation
amongst these two groups. In order to validate the hypothesis of a more profound (non-linear)
diferentiating dependency between features, machine learning methods were used. We trained four
common machine learning algorithms (decision tree, linear model, k-nearest neighbour, random forest)
on data from plasma levels of proteins and patients’ clinical data. The constructed models, however, did
not separate patients with endometriosis from the controls with sufcient sensitivity and specifcity.
This study thus indicates that plasma levels of the selected cytokines have limited potential for
diagnosis of endometriosis.