Identification biomarkers of eutopic endometrium in endometriosis using artificial neural networks and protein fingerprinting

Horizons in Endometriosis: Proceedings of the Montreux Reproductive Summit, 14-15 July 2023

Endometriosis is a complex and chronic gynaecological disorder that affects millions of women worldwide, leading to significant morbidity and impacting reproductive health. This condition affects up to 10% of women of reproductive age and is characterised by the presence of endometrial-like tissue outside the uterus, potentially leading to symptoms such as chronic pelvic pain, dysmenorrhoea, dyspareunia, and infertility. The Montreux summit brought a number of experts in this field together to provide a platform for discussion and exchange of ideas. These proceedings summarise the six main topics that were discussed at this summit to shed light on future directions of endometriosis classification, diagnosis, and therapeutical management. The first question addressed the possibility of preventing endometriosis in the future by identifying risk factors, genetic predispositions, and further understanding of the pathophysiology of the condition to develop targeted interventions. The clinical presentation of endometriosis is varied, and the correlation between symptoms severity and disease extent is unclear. While there is currently no universally accepted optimal classification system for endometriosis, several attempts striving towards its optimisation - each with its own advantages and limitations - were discussed. The ideal classification should be able to reconcile disease status based on the various diagnostic tools, and prognosis to guide proper patient tailored management. Regarding diagnosis, we focused on future tools and critically discussed emerging approaches aimed at reducing diagnostic delay. Preserving fertility in endometriosis patients was another debatable aspect of management that was reviewed. Moreover, besides current treatment modalities, potential novel medical therapies that can target underlying mechanisms, provide effective symptom relief, and minimise side effects in endometriotic patients were considered, including hormonal therapies, immunomodulation, and regenerative medicine. Finally, the question of hormonal substitution therapy after radical treatment for endometriosis was debated, weighing the benefits of hormone replacement.

Clinical use of artificial intelligence in endometriosis: a scoping review

Endometriosis is a chronic, debilitating, gynecologic condition with a non-specific clinical presentation. Globally, patients can experience diagnostic delays of ~6 to 12 years, which significantly hinders adequate management and places a significant financial burden on patients and the healthcare system. Through artificial intelligence (AI), it is possible to create models that can extract data patterns to act as inputs for developing interventions with predictive and diagnostic accuracies that are superior to conventional methods and current tools used in standards of care. This literature review explored the use of AI methods to address different clinical problems in endometriosis. Approximately 1309 unique records were found across four databases; among those, 36 studies met the inclusion criteria. Studies were eligible if they involved an AI approach or model to explore endometriosis pathology, diagnostics, prediction, or management and if they reported evaluation metrics (sensitivity and specificity) after validating their models. Only articles accessible in English were included in this review. Logistic regression was the most popular machine learning method, followed by decision tree algorithms, random forest, and support vector machines. Approximately 44.4% (n = 16) of the studies analyzed the predictive capabilities of AI approaches in patients with endometriosis, while 47.2% (n = 17) explored diagnostic capabilities, and 8.33% (n = 3) used AI to improve disease understanding. Models were built using different data types, including biomarkers, clinical variables, metabolite spectra, genetic variables, imaging data, mixed methods, and lesion characteristics. Regardless of the AI-based endometriosis application (either diagnostic or predictive), pooled sensitivities ranged from 81.7 to 96.7%, and pooled specificities ranged between 70.7 and 91.6%. Overall, AI models displayed good diagnostic and predictive capacity in detecting endometriosis using simple classification scenarios (i.e., differentiating between cases and controls), showing promising directions for AI in assessing endometriosis in the near future. This timely review highlighted an emerging area of interest in endometriosis and AI. It also provided recommendations for future research in this field to improve the reproducibility of results and comparability between models, and further test the capacity of these models to enhance diagnosis, prediction, and management in endometriosis patients.

Clinical effectiveness and potential long-term benefits of high-intensity focused ultrasound therapy for patients with adenomyosis

OBJECTIVES

Adenomyosis is a common and refractory disease in gynecology. Preserving the uterus during treatment for adenomyosis remains a problem. High-intensity focused ultrasound (HIFU) is widely used in treatment of solid tumors. This study aimed to analyze patients with adenomyosis who were treated by HIFU and to preliminarily examine the characteristics of patients who are more suitable for HIFU to treat adenomyosis with reliable efficacy.

METHODS

Over 2 years, 67 women who were diagnosed with adenomyosis and treated with HIFU at our gynecology department were included in this study. We investigated outcomes of their symptoms (dysmenorrhea and hypermenorrhea) and the volume of their uterine lesions. We also compared the patients' clinical profiles.

RESULTS

The women had a mean follow-up duration of 11.6 ± 0.46 months. In the numerical rating scale, used to assess the degree of dysmenorrhea, the score was significantly lower (mean difference: -1.94, 95% confidence interval: -2.704 to -1.176) 3 months after HIFU treatment compared with before treatment, then it remained stable for 3 to 12 months. Hypermenorrhea was reduced to a certain degree, with a mean difference of -0.54 (-1.01-0.02).

CONCLUSIONS

HIFU is a new noninvasive treatment method for adenomyosis that may help relieve dysmenorrhea.

Endometrial biomarkers for the non-invasive diagnosis of endometriosis

BACKGROUND

About 10% of reproductive-aged women suffer from endometriosis, which is a costly, chronic disease that causes pelvic pain and subfertility. Laparoscopy is the gold standard diagnostic test for endometriosis, but it is expensive and carries surgical risks. Currently, there are no non-invasive tests available in clinical practice that accurately diagnose endometriosis. This is the first diagnostic test accuracy review of endometrial biomarkers for endometriosis that utilises Cochrane methodologies, providing an update on the rapidly expanding literature in this field.

OBJECTIVES

To determine the diagnostic accuracy of the endometrial biomarkers for pelvic endometriosis, using a surgical diagnosis as the reference standard. We evaluated the tests as replacement tests for diagnostic surgery and as triage tests to inform decisions to undertake surgery for endometriosis.

SEARCH METHODS

We did not restrict the searches to particular study designs, language or publication dates. To identify trials, we searched the following databases: CENTRAL (2015, July), MEDLINE (inception to May 2015), EMBASE (inception to May 2015), CINAHL (inception to April 2015), PsycINFO (inception to April 2015), Web of Science (inception to April 2015), LILACS (inception to April 2015), OAIster (inception to April 2015), TRIP (inception to April 2015) and ClinicalTrials.gov (inception to April 2015). We searched DARE and PubMed databases up to April 2015 to identify reviews and guidelines as sources of references to potentially relevant studies. We also performed searches for papers recently published and not yet indexed in the major databases. The search strategies incorporated words in the title, abstract, text words across the record and the medical subject headings (MeSH).

SELECTION CRITERIA

We considered published peer-reviewed, randomised controlled or cross-sectional studies of any size that included prospectively collected samples from any population of reproductive-aged women suspected of having one or more of the following target conditions: ovarian, peritoneal or deep infiltrating endometriosis (DIE).

DATA COLLECTION AND ANALYSIS

Two authors independently extracted data from each study and performed a quality assessment. For each endometrial diagnostic test, we classified the data as positive or negative for the surgical detection of endometriosis and calculated the estimates of sensitivity and specificity. We considered two or more tests evaluated in the same cohort as separate data sets. We used the bivariate model to obtain pooled estimates of sensitivity and specificity whenever sufficient data were available. The predetermined criteria for a clinically useful test to replace diagnostic surgery was one with a sensitivity of 94% and a specificity of 79%. The criteria for triage tests were set at sensitivity at or above 95% and specificity at or above 50%, which in case of negative results rules out the diagnosis (SnOUT test) or sensitivity at or above 50% with specificity at or above 95%, which in case of positive result rules in the diagnosis (SpIN test).

MAIN RESULTS

We included 54 studies involving 2729 participants, most of which were of poor methodological quality. The studies evaluated endometrial biomarkers either in specific phases of the menstrual cycle or outside of it, and the studies tested the biomarkers either in menstrual fluid, in whole endometrial tissue or in separate endometrial components. Twenty-seven studies evaluated the diagnostic performance of 22 endometrial biomarkers for endometriosis. These were angiogenesis and growth factors (PROK-1), cell-adhesion molecules (integrins α3β1, α4β1, β1 and α6), DNA-repair molecules (hTERT), endometrial and mitochondrial proteome, hormonal markers (CYP19, 17βHSD2, ER-α, ER-β), inflammatory markers (IL-1R2), myogenic markers (caldesmon, CALD-1), neural markers (PGP 9.5, VIP, CGRP, SP, NPY, NF) and tumour markers (CA-125). Most of these biomarkers were assessed in single studies, whilst only data for PGP 9.5 and CYP19 were available for meta-analysis. These two biomarkers demonstrated significant diversity for the diagnostic estimates between the studies; however, the data were too limited to reliably determine the sources of heterogeneity. The mean sensitivities and specificities of PGP 9.5 (7 studies, 361 women) were 0.96 (95% confidence interval (CI) 0.91 to 1.00) and 0.86 (95% CI 0.70 to 1.00), after excluding one outlier study, and for CYP19 (8 studies, 444 women), they were were 0.77 (95% CI 0.70 to 0.85) and 0.74 (95% CI 0.65 to 84), respectively. We could not statistically evaluate other biomarkers in a meaningful way. An additional 31 studies evaluated 77 biomarkers that showed no evidence of differences in expression levels between the groups of women with and without endometriosis.

AUTHORS' CONCLUSIONS

We could not statistically evaluate most of the biomarkers assessed in this review in a meaningful way. In view of the low quality of most of the included studies, the findings of this review should be interpreted with caution. Although PGP 9.5 met the criteria for a replacement test, it demonstrated considerable inter study heterogeneity in diagnostic estimates, the source of which could not be determined. Several endometrial biomarkers, such as endometrial proteome, 17βHSD2, IL-1R2, caldesmon and other neural markers (VIP, CGRP, SP, NPY and combination of VIP, PGP 9.5 and SP) showed promising evidence of diagnostic accuracy, but there was insufficient or poor quality evidence for any clinical recommendations. Laparoscopy remains the gold standard for the diagnosis of endometriosis, and using any non-invasive tests should only be undertaken in a research setting. We have also identified a number of biomarkers that demonstrated no diagnostic value for endometriosis. We recommend that researchers direct future studies towards biomarkers with high diagnostic potential in good quality diagnostic studies.

Update on Biomarkers for the Detection of Endometriosis

Endometriosis is histologically characterized by the displacement of endometrial tissue to extrauterine locations including the pelvic peritoneum, ovaries, and bowel. An important cause of infertility and pelvic pain, the individual and global socioeconomic burden of endometriosis is significant. Laparoscopy remains the gold standard for the diagnosis of the condition. However, the invasive nature of surgery, coupled with the lack of a laboratory biomarker for the disease, results in a mean latency of 7–11 years from onset of symptoms to definitive diagnosis. Unfortunately, the delay in diagnosis may have significant consequences in terms of disease progression. The discovery of a sufficiently sensitive and specific biomarker for the nonsurgical detection of endometriosis promises earlier diagnosis and prevention of deleterious sequelae and represents a clear research priority. In this review, we describe and discuss the current status of biomarkers of endometriosis in plasma, urine, and endometrium.

Biomarker development in endometriosis

Endometriosis is a common gynecologic disorder histologically characterized by the displacement of endometrial tissue to extra-uterine locations. A significant cause of infertility and pelvic pain, the global socioeconomic burden of endometriosis is staggering. Laparoscopy remains the gold standard for the diagnosis of the condition. However, the invasive nature of surgery, coupled with the lack of a laboratory biomarker for the disease, results in a mean latency of 6-7 years from onset of symptoms to definitive diagnosis. Unfortunately, the delay in diagnosis may have significant consequences in terms of disease progression. The discovery of a sufficiently sensitive and specific biomarker for the non-surgical detection of endometriosis promises earlier diagnosis and prevention of deleterious sequelae, and remains a top research priority. The enigmatic pathophysiology of endometriosis presents unique challenges to biomarker development that are now well outlined. Within the past decade, significant advancements in understanding the molecular hallmarks of endometriosis have occurred, and promising biomarker candidates are emerging.

Ovarian endometriosis signatures established through discovery and directed mass spectrometry analysis

New molecular information on potential therapeutic targets or tools for noninvasive diagnosis for endometriosis are important for patient care and treatment. However, surprisingly few efforts have described endometriosis at the protein level. In this work we enumerate the proteins in patient endometrium and ovarian endometrioma by extensive and comprehensive analysis of minute amounts of cryosectioned tissues in a three-tiered mass spectrometric approach. Quantitative comparison of the tissues revealed 214 differentially expressed proteins in ovarian endometrioma and endometrium. These proteins are reported here as a resource of SRM (selected reaction monitoring) assays that are unique, standardized, and openly available. Pathway analysis of the proteome measurements revealed a potential role for Transforming growth factor β-1 in ovarian endometriosis development. Subsequent mRNA microarray analysis further revealed clear ovarian endometrioma specificity for a subset of these proteins, which was also supported by further in silico studies. In this process two important proteins emerged, Calponin-1 and EMILIN-1, that were additionally confirmed in ovarian endometrioma tissues by immunohistochemistry and Western blotting. This study provides the most comprehensive molecular description of ovarian endometriosis to date and researchers with new molecular methods and tools for high throughput patient screening using the SRM assays.

Proteomics analysis of plasma for early diagnosis of endometriosis

OBJECTIVE

To test the hypothesis that differential surface-enhanced laser desorption/ionization time-of-flight mass spectrometry protein or peptide expression in plasma can be used in infertile women with or without pelvic pain to predict the presence of laparoscopically and histologically confirmed endometriosis, especially in the subpopulation with a normal preoperative gynecologic ultrasound examination.

METHODS

Surface-enhanced laser desorption/ionization time-of-flight mass spectrometry analysis was performed on 254 plasma samples obtained from 89 women without endometriosis and 165 women with endometriosis (histologically confirmed) undergoing laparoscopies for infertility with or without pelvic pain. Data were analyzed using least squares support vector machines and were divided randomly (100 times) into a training data set (70%) and a test data set (30%).

RESULTS

Minimal-to-mild endometriosis was best predicted (sensitivity 75%, 95% confidence interval [CI] 63-89; specificity 86%, 95% CI 71-94; positive predictive value 83.6%, negative predictive value 78.3%) using a model based on five peptide and protein peaks (range 4.898-14.698 m/z) in menstrual phase samples. Moderate-to-severe endometriosis was best predicted (sensitivity 98%, 95% CI 84-100; specificity 81%, 95% CI 67-92; positive predictive value 74.4%, negative predictive value 98.6%) using a model based on five other peptide and protein peaks (range 2.189-7.457 m/z) in luteal phase samples. The peak with the highest intensity (2.189 m/z) was identified as a fibrinogen β-chain peptide. Ultrasonography-negative endometriosis was best predicted (sensitivity 88%, 95% CI 73-100; specificity 84%, 95% CI 71-96) using a model based on five peptide peaks (range 2.058-42.065 m/z) in menstrual phase samples.

CONCLUSION

A noninvasive test using proteomic analysis of plasma samples obtained during the menstrual phase enabled the diagnosis of endometriosis undetectable by ultrasonography with high sensitivity and specificity.

LEVEL OF EVIDENCE

II.

Combined mRNA microarray and proteomic analysis of eutopic endometrium of women with and without endometriosis

BACKGROUND

An early semi-invasive diagnosis of endometriosis has the potential to allow early treatment and minimize disease progression but no such test is available at present. Our aim was to perform a combined mRNA microarray and proteomic analysis on the same eutopic endometrium sample obtained from patients with and without endometriosis.

METHODS

mRNA and protein fractions were extracted from 49 endometrial biopsies obtained from women with laparoscopically proven presence (n= 31) or absence (n= 18) of endometriosis during the early luteal (n= 27) or menstrual phase (n= 22) and analyzed using microarray and proteomic surface enhanced laser desorption ionization-time of flight mass spectrometry, respectively. Proteomic data were analyzed using a least squares-support vector machines (LS-SVM) model built on 70% (training set) and 30% of the samples (test set).

RESULTS

mRNA analysis of eutopic endometrium did not show any differentially expressed genes in women with endometriosis when compared with controls, regardless of endometriosis stage or cycle phase. mRNA was differentially expressed (P< 0.05) in women with (925 genes) and without endometriosis (1087 genes) during the menstrual phase when compared with the early luteal phase. Proteomic analysis based on five peptide peaks [2072 mass/charge (m/z); 2973 m/z; 3623 m/z; 3680 m/z and 21133 m/z] using an LS-SVM model applied on the luteal phase endometrium training set allowed the diagnosis of endometriosis (sensitivity, 91; 95% confidence interval (CI): 74-98; specificity, 80; 95% CI: 66-97 and positive predictive value, 87.9%; negative predictive value, 84.8%) in the test set.

CONCLUSION

mRNA expression of eutopic endometrium was comparable in women with and without endometriosis but different in menstrual endometrium when compared with luteal endometrium in women with endometriosis. Proteomic analysis of luteal phase endometrium allowed the diagnosis of endometriosis with high sensitivity and specificity in training and test sets. A potential limitation of our study is the fact that our control group included women with a normal pelvis as well as women with concurrent pelvic disease (e.g. fibroids, benign ovarian cysts, hydrosalpinges), which may have contributed to the comparable mRNA expression profile in the eutopic endometrium of women with endometriosis and controls.

Detection of mitochondrial biomarkers in eutopic endometria of endometriosis using surface-enhanced laser desorption/ionization time-of-flight mass spectrometry

OBJECTIVES

To detect specific mitochondrial proteins in eutopic endometrial samples from women with and without endometriosis and to build diagnostic models.

DESIGN

Eutopic endometrial samples from women with endometriosis (excluding adenomyosis) and women with benign indications as control were studied by using surface-enhanced laser desorption/ionization time-of-flight mass spectrometry protein-chip technology. After finding the biomarkers, the diagnostic model was evaluated and validated by leave-one cross-validation.

SETTING

Collaborative investigation in an academic research environment.

PATIENT(S)

Twenty-four patients with endometriosis (excluding adenomyosis) and 29 patients with benign indications as control.

INTERVENTION(S)

Surgical excision of eutopic endometrial biopsy of patients with endometriosis and controls.

MAIN OUTCOME MEASURE(S)

Mitochondrial protein expression.

RESULT(S)

Seventy-eight qualified mitochondrial protein peaks were detected, ten of them had a significant difference. Three combined potential biomarkers, with mass-to-charge ratios (m/z) of 15,334, 15,128, and 16,069, were found, and the diagnostic system distinguished endometriosis from control samples with a specificity of 86.2% and a sensitivity of 87.5%.

CONCLUSION(S)

We discovered potential mitochondrial biomarkers of eutopic endometrium in endometriosis and set up a diagnostic model. Further identification of the proteins we found will help to explain pathology, new diagnoses, and therapeutic approaches for endometriosis.

TRIzol treatment of secretory phase endometrium allows combined proteomic and mRNA microarray analysis of the same sample in women with and without endometriosis

BACKGROUND

According to mRNA microarray, proteomics and other studies, biological abnormalities of eutopic endometrium (EM) are involved in the pathogenesis of endometriosis, but the relationship between mRNA and protein expression in EM is not clear. We tested for the first time the hypothesis that EM TRIzol extraction allows proteomic Surface Enhanced Laser Desorption/Ionisation Time-of-Flight Mass Spectrometry (SELDI-TOF MS) analysis and that these proteomic data can be related to mRNA (microarray) data obtained from the same EM sample from women with and without endometriosis.

METHODS

Proteomic analysis was performed using SELDI-TOF-MS of TRIzol-extracted EM obtained during secretory phase from patients without endometriosis (n = 6), patients with minimal-mild (n = 5) and with moderate-severe endometriosis (n = 5), classified according to the system of the American Society of Reproductive Medicine. Proteomic data were compared to mRNA microarray data obtained from the same EM samples.

RESULTS

In our SELDI-TOF MS study 32 peaks were differentially expressed in endometrium of all women with endometriosis (stages I-IV) compared with all controls during the secretory phase. Comparison of proteomic results with those from microarray revealed no corresponding genes/proteins.

CONCLUSION

TRIzol treatment of secretory phase EM allows combined proteomic and mRNA microarray analysis of the same sample, but comparison between proteomic and microarray data was not evident, probably due to post-translational modifications.