Differential diagnosis of early-stage ovarian cancer based on the bioinformatic analysis of the blood metabolome

The early diagnosis of ovarian cancer (OC) represents an important step in reducing the number of fatal outcomes associated with the disease. Timely treatment initiation, minimizing the risk of recurrence and side effects of therapy, largely depend on early diagnosis.

Objective: To create stable panels of blood metabolites for differentiating healthy patients, patients with early-stage high-grade OC from other ovarian tumors.

Materials and methods. A search for markers for clustering of blood samples obtained from patients with verified stage I–II high-grade OC (n=10) and other proliferative processes (cystadenoma (n=30), endometrioid cyst (n=56), teratoma (n=21), borderline tumor (n=28), low-grade OC (n=16), stage III–IV high-grade (n=49)) and control volunteers (n=19) was performed. The study was carried out at the V.I. Kulakov National Medical Research Centre for Obstetrics, Gynecology and Perinatology, Moscow, Russia. The data were analyzed using recursive variable removal from the support vector machine and other statistical tools. There was a search for markers of malignant neoplasms (MNPs), followed by the analysis of their involvement in metabolic pathways. Models based on neural networks were built.

Results: The panels of metabolite-markers of early stages of MNPs were identified. The overlap of the obtained panels with metabolic pathway databases was studied. Artificial neural network models were developed to differentiate blood samples from I–II stage OC from controls with sensitivity and specificity of 90% and 89%, and from I–II stage OC from other ovarian neoplasms with sensitivity and specificity of 80% and 71%, respectively.

Conclusion: The introduction of post-genomic research has the potential to increase the diagnostic value of the methods used to detect ovarian MNPs at an earlier stage and also to expand the available data on the processes of carcinogenesis in the ovaries.