Treatment of endometriosis: a review with comparison of 8 guidelines

Kalaitzopoulos, Dimitrios Rafail; Samartzis, Nicolas; Kolovos, Georgios; Mareti, Εvangelia; Samartzis, Eleftherios Pierre; Eberhard, Markus; Dinas, Kostantinos; Daniilidis, Angelos

doi:10.1186/s12905-021-01545-5

Cited by 104 publications

(108 citation statements)

References 55 publications

(43 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A variety of hormonal medications are used to suppress endometrial growth, such as contraceptive pills, GnRH agonists, and recently, a GnRH antagonist [ 18 ]. These can be used to relieve endometriosis symptoms, support the diagnosis of endometriosis, or prevent recurrence after surgery [ 19 ]. Endometriosis symptoms have a substantial impact on the physical and emotional well-being of young women [ 20 ].…”

Section: Introductionmentioning

confidence: 99%

Revisiting the Risk Factors for Endometriosis: A Machine Learning Approach

Blass

Sahar

Shraibman

et al. 2022

JPM

View full text Add to dashboard Cite

Endometriosis is a condition characterized by implants of endometrial tissues into extrauterine sites, mostly within the pelvic peritoneum. The prevalence of endometriosis is under-diagnosed and is estimated to account for 5–10% of all women of reproductive age. The goal of this study was to develop a model for endometriosis based on the UK-biobank (UKB) and re-assess the contribution of known risk factors to endometriosis. We partitioned the data into those diagnosed with endometriosis (5924; ICD-10: N80) and a control group (142,723). We included over 1000 variables from the UKB covering personal information about female health, lifestyle, self-reported data, genetic variants, and medical history prior to endometriosis diagnosis. We applied machine learning algorithms to train an endometriosis prediction model. The optimal prediction was achieved with the gradient boosting algorithms of CatBoost for the data-combined model with an area under the ROC curve (ROC-AUC) of 0.81. The same results were obtained for women from a mixed ethnicity population of the UKB (7112; ICD-10: N80). We discovered that, prior to being diagnosed with endometriosis, affected women had significantly more ICD-10 diagnoses than the average unaffected woman. We used SHAP, an explainable AI tool, to estimate the marginal impact of a feature, given all other features. The informative features ranked by SHAP values included irritable bowel syndrome (IBS) and the length of the menstrual cycle. We conclude that the rich population-based retrospective data from the UKB are valuable for developing unified machine learning endometriosis models despite the limitations of missing data, noisy medical input, and participant age. The informative features of the model may improve clinical utility for endometriosis diagnosis.

show abstract

Section: Introductionmentioning

confidence: 99%

Revisiting the Risk Factors for Endometriosis: A Machine Learning Approach

Blass

Sahar

Shraibman

et al. 2022

JPM

View full text Add to dashboard Cite

show abstract

“…In a recent study [ 17 ], reviewing eight most widely accepted guidelines concerning the management of endometriosis, most patients with endometriosis seek management because of pain and/or infertility. Though for the pain group, there is nearly an agreement on medical and conservative treatment as a 1st line option, there are controversies regarding infertility.…”

Section: Discussionmentioning

confidence: 99%

A review of more than 2000 cases of site-specific pelvic endometriosis rates by MRI: a guide to minimizing under/overdiagnosis non-invasively

Hajati¹,

Hajati

2022

Insights Imaging

View full text Add to dashboard Cite

Objectives To statistically study the incidence of endometrioma and deep infiltrating endometriosis (DIE) in various anatomical sites and to illustrate the significance and potential implications for each site. Furthermore, to improve the knowledge of the community for a non-invasive diagnosis alternative to laparoscopy. Methods This study includes 2040 patients who had been referred with clinical evidence of pelvic endometriosis. These patients had been examined and undergone transvaginal sonography by the referring gynecologists. The imaging modality used to discover and locate various anatomical locations of involvement was MRI with contrast. Two radiologists with expertise in endometriosis separately assessed the patients' MRIs and highlighted the involved areas. Results In total, 79.1% were positive for either endometrioma or DIE. We detected both DIE and ovarian endometrioma in 78.2% of positive cases. Isolated endometrioma or DIE was present exclusively in 13.7% and 8.1% of patients, respectively. Uterosacral ligaments were detected as the most common (73.8%) site of DIE involvements and in 2.9% of cases were the sole affected location. Interestingly, very rare independent involvement of the genitourinary tract was seen in two patients. Conclusions In this study, MRI was used to assess the likely involvement sites of endometrioma and DIE, as well as the frequency of incidences in various places and their relationships over a large dataset. Understanding the possibly involved sites, their statistics, and their co-existence can provide radiologists with a roadmap for non-invasive endometriosis diagnosis and treatment planning. These principles should hopefully assist reduce under- and overdiagnosis.

show abstract

“…A study by Yu et al [129] showed that treatment with puerarin reduced the levels of estradiol and PGE2 in endometriotic rats, by inhibiting the aromatase enzyme P450 and COX-2, in addition to increasing the expression of 17β-HSD2, thus preventing the growth of endometrial tissue. Kim et al [130][131][132][133] showed that treatment with an extract obtained from flowers of P. lobata reduced the adhesion and migration of these cells, also reducing the formation of endometriotic lesions in mice. Figure 3 summarizes the main treatment options for endometriosis.…”

Section: Puerarinmentioning

confidence: 99%

Endometriosis: A Disease with Few Direct Treatment Options

2022

View full text Add to dashboard Cite

Endometriosis is a gynecological condition characterized by the growth of endometrium-like tissues inside and outside the pelvic cavity. The evolution of the disease can lead to infertility in addition to high treatment costs. Currently, available medications are only effective in treating endometriosis-related pain; however, it is not a targeted treatment. The objective of this work is to review the characteristics of the disease, the diagnostic means and treatments available, as well as to discuss new therapeutic options.

show abstract

Treatment of endometriosis: a review with comparison of 8 guidelines

Cited by 104 publications

References 55 publications

Revisiting the Risk Factors for Endometriosis: A Machine Learning Approach

Revisiting the Risk Factors for Endometriosis: A Machine Learning Approach

A review of more than 2000 cases of site-specific pelvic endometriosis rates by MRI: a guide to minimizing under/overdiagnosis non-invasively

Endometriosis: A Disease with Few Direct Treatment Options

Contact Info

Product

Resources

About