Identifying biomarkers of endometriosis using serum protein fingerprinting and artificial neural networks

Abstract

Objectives: To use surface-enhanced laser desorption/ionization time-of-flight mass spectrometry (SELDI-TOF-MS) protein chip array technology to detect proteomic patterns in the serum of women with endometriosis; build diagnostic models; and evaluate their clinical significance.

Methods: Serum samples from women with endometriosis and healthy women were studied using SELDI-TOF-MS protein chip technology. For every matched pair, two-thirds of the samples were used to look for different patterns and one-third was used for cross-validation.

Results: Five potential biomarkers were found and the diagnostic system distinguished endometriosis from validation samples with a sensitivity of 91.7% and a specificity of 90.0%.

Conclusion: This method shows great potential in identifying biomarkers to be used for endometriosis screening.