Fibronectin Molecular Status in Plasma of Women with Endometriosis and Fertility Disorders

A stacked machine learning-based classification model for endometriosis and adenomyosis: a retrospective cohort study utilizing peripheral blood and coagulation markers

Introduction

Endometriosis (EMs) and adenomyosis (AD) are common gynecological diseases that impact women's health, and they share symptoms such as dysmenorrhea, chronic pain, and infertility, which adversely affect women's quality of life. Current diagnostic approaches for EMs and AD involve invasive surgical procedures, and thus, methods of noninvasive differentiation between EMs and AD are needed. This retrospective cohort study introduces a novel, noninvasive classification methodology employing a stacked ensemble machine learning (ML) model that utilizes peripheral blood and coagulation markers to distinguish between EMs and AD.

Methods

The study included a total of 558 patients (329 with EMs and 229 with AD), in whom key hematological and coagulation markers were analyzed to identify distinctive profiles. Feature selection was conducted through ML (logistic regression, support vector machine, and K-nearest neighbors) to determine significant hematological markers.

Results

Red cell distribution width, mean corpuscular hemoglobin concentration, activated partial thromboplastin time, international normalized ratio, and antithrombin III were proved to be the key distinguishing indexes for disease differentiation. Among all the ML classification models developed, the stacked ensemble model demonstrated superior performance (area under the curve = 0.803, 95% credibility interval = 0.701-0.904). Our findings demonstrate the effectiveness of the stacked ensemble ML model for classifying EMs and AD.

Discussion

Integrating biomarkers into this multi-algorithm framework offers a novel approach to noninvasive diagnosis. These results advocate for the application of stacked ensemble ML utilizing cost-effective and readily available peripheral blood and coagulation indicators for the early, rapid, and noninvasive differential diagnosis of EMs and AD, offering a potentially transformative approach for clinical decision-making and personalized treatment strategies.

Vitamin D and reproductive disorders: a comprehensive review with a focus on endometriosis

Vitamin D is a fat-soluble steroid hormone that was initially known only for regulating calcium and phosphorus levels and maintaining bone health. However, it was later discovered that many organs express vitamin D metabolizing enzymes and have a ligand for vitamin D, which regulates the expression of an extensive assortment of genes. As a result, vitamin D is indispensable for the proper function of organs, and its deficiency is believed to be a critical factor in symptoms and disorders such as cardiovascular diseases, autoimmune diseases, and cancers. The significance of vitamin D in reproductive tissues was recognized later, and studies have revealed its crucial role in male and female fertility, as well as proper reproductive function during pregnancy. Vitamin D deficiency has been identified as a risk factor for infertility, gonadal cancers, pregnancy complications, polycystic ovary syndrome, and endometriosis. However, data investigating the association between vitamin D levels and reproductive disorders, including endometriosis, have encountered inconsistencies. Therefore, the present study aims to review existing research on the effect of vitamin D on proper reproductive function, and the role of deficiency in reproductive diseases and specifically focuses on endometriosis.

Role of Molecular Biomarkers in Endometriosis-Related Infertility: A Narrative Review of the Literature

Endometriosis is a chronic benign inflammatory disease that affects women of reproductive age. The clinical presentations of endometriosis include dysmenorrhea, dyspareunia, chronic pelvic pain, and infertility. There is a well-established association between endometriosis and infertility. Therefore, there is a need for an early diagnosis of endometriosis-related infertility. In this study, we aim to identify the role of biomarkers as predictive factors of the presence of the disease and its severity and their correlation with the pregnancy outcome. We performed an electronic database search of all published studies in PubMed and EMBASE from January 2018 to May 2023. Numerous innovative biomarkers identified in cases of endometriosis and infertility have been studied over the past years, including micro-RNAs, BCL6 endometrial expression, cytotoxic T-lymphocyte antigen 4, human leukocyte antigen G, programmed cell death protein 1, programmed cell death ligand 1 immune checkpoint molecules, plasma fibronectin-fibrin complexes, homeobox A10 gene, systemic inflammatory response markers, uterine natural killer cells, and the eutopic endometrium proteome. Considerable research has been done to identify diagnostic biomarkers for the early detection and prevention of endometriosis-associated infertility. However, none of these biomarkers displayed enough diagnostic accuracy to be used in daily clinical practice. Future research is valuable to establish them as reliable diagnostic tools.

Relaxed fibronectin: a potential novel target for imaging endometriotic lesions

BACKGROUND

Endometriosis is characterized by the ectopic occurrence of endometrial tissue. Though considered benign, endometriotic lesions possess tumor-like properties such as tissue invasion and remodeling of the extracellular matrix. One major clinical hurdle concerning endometriosis is its diagnosis. The diagnostic modalities ultrasound and MRI are often unable to detect all lesions, and a clear correlation between imaging and clinical symptoms is still controversial. Therefore, it was our aim to identify a potential target to image active endometriotic lesions.

RESULTS

For our studies, we employed the preclinical radiotracer [111In]In-FnBPA5, which specifically binds to relaxed fibronectin-an extracellular matrix protein with key functions in homeostasis that has been implicated in the pathogenesis of diseases such as cancer and fibrosis. We employed this tracer in biodistribution as well as SPECT/CT studies in mice and conducted immunohistochemical stainings on mouse uterine tissue as well as on patient-derived endometriosis tissue. In biodistribution and SPECT/CT studies using the radiotracer [111In]In-FnBPA5, we found that radiotracer uptake in the myometrium varies with the estrous cycle of the mouse, leading to higher uptake of [111In]In-FnBPA5 during estrogen-dependent phases, which indicates an increased abundance of relaxed fibronectin when estrogen levels are high. Finally, immunohistochemical analysis of patient samples demonstrated that there is preferential relaxation of fibronectin in the proximity of the endometriotic stroma.

CONCLUSION

Estrous cycle stages characterized by high estrogen levels result in a higher abundance of relaxed fibronectin in the murine myometrium. This finding together with a first proof-of-concept study employing human endometriosis tissues suggests that relaxed fibronectin could be a potential target for the development of a diagnostic radiotracer targeting endometriotic lesions. With [111In]In-FnBPA5, the matching targeting molecule is in preclinical development.

Drug repurposing for targeting fibronectin in treatment of endometriosis and cancers

Increased concentrations of the fibronectin glycoprotein can cause ectopic tissue growth patients with endometriosis and the formation of various cancerous tumors. Furthermore, fibronectin binding to its receptors from the EDA (Extra Domain A) region contributes to promote tumorigenesis, metastasis and vasculogenesis. Thus, the EDA region can be considered a unique target for therapeutic intervention. Therefore, the present study used computational methods to identify the best fibronectin inhibitor(s) among FDA-approved drugs. First, docking-based virtual screening was performed using PyRx 0.8. Next, FDA-approved drugs that obtained favorable results in the docking phase were selected for further studies and analysis using molecular dynamics (MD) simulation. The preliminary findings of the virtual screening showed that 17 FDA-approved drugs (from 2471) had more favorable energy with their binding energy less than -9 kcal/mol. The MD simulation results of these 17 drugs showed that Avapritinib had a lower RMSD value and higher binding energy and hydrogen bonding than the other complexes in the EDA domain. Also, analyses related to the second structure changes displayed that Avapritinib in the EDA domain led to more changes in the second structure. According to the results, the anticancer drug Avapritinib forms a more stable complex with fibronectin than other FDA-approved drugs. Furthermore, this drug leads to more changes in the second EDA structure, which may have more serious potential for inhibiting EDA fibronectin.Communicated by Ramaswamy H. Sarma.

Plasma and Peritoneal Fluid Fibronectin and Collagen IV Levels as Potential Biomarkers of Endometriosis

Laparoscopy as a diagnostic tool for patients with suspected endometriosis is associated with several potentially life-threatening complications. Therefore, it is imperative to identify reliable, non-invasive biomarkers of the disease. The aim of this study was to analyse the concentrations of fibronectin and type IV collagen in peritoneal fluid and plasma to assess their role as potential biomarkers in the diagnosis of endometriosis. Fibronectin and collagen IV protein levels were assessed by surface plasmon resonance imaging (SPRi) biosensors with the usage of monoclonal antibodies. All patients enrolled in the study were referred for laparoscopy for the diagnosis of infertility or chronic pelvic pain (n = 84). The study group included patients with endometriosis confirmed during surgery (n = 49). The concentration of fibronectin in the plasma (329.3 ± 98.5 mg/L) and peritoneal fluid (26.8 ± 11.1 μg/L) in women with endometriosis was significantly higher than in the control group (251.2 ± 84.0 mg/L, 7.0 ± 5.9 μg/L). Fibronectin levels were independent of endometriosis stage (p = 0.874, p = 0.469). No significant differences were observed in collagen IV levels (p = 0.385, p = 0.465). The presence of elevated levels of fibronectin may indicate abnormalities in cell-ECM signalling during the course of endometriosis, and may be a potential biomarker for early detection.