History of Endometriosis Is Independently Associated with an Increased Risk of Ovarian Cancer

Sarría‐Santamera, Antonio; Khamitova, Zaukiya; Gusmanov, Arnur; Terzić, Milan; Polo-Santos, Mar; Ortega, Miguel Á.; Barco, Ángel Asúnsolo del

doi:10.3390/jpm12081337

Cited by 3 publications

(3 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, there may be misclassification bias in the case where women in this database are not definitively diagnosed laparoscopically with a biopsy, which is the gold standard. A possibility to overcome this limitation is the linkage of primary care with hospital data [ 62 ]. There may also be an under-diagnosis of cases of women whose GP may not have correctly identified a diagnosis of endometriosis in their medical records.…”

Section: Discussionmentioning

confidence: 99%

A Novel Classification of Endometriosis Based on Clusters of Comorbidities

Sarria-Santamera,

Yemenkhan,

Terzic

et al. 2023

Biomedicines

Self Cite

View full text Add to dashboard Cite

Endometriosis is a heterogeneous, complex, and still challenging disease, due to its epidemiological, etiological and pathogenic, diagnostic, therapeutic, and prognosis characteristics. The classification of endometriosis is contentious, and existing therapies show significant variability in their effectiveness. This study aims to capture and describe clusters of women with endometriosis based on their comorbidity. With data extracted from electronic records of primary care, this study performs a hierarchical clustering with the Ward method of women with endometriosis with a subsequent analysis of the distribution of comorbidities. Data were available for 4055 women with endometriosis, and six clusters of women were identified: cluster 1 (less comorbidity), cluster 2 (anxiety and musculoskeletal disorders), cluster 3 (type 1 allergy or immediate hypersensitivity); cluster 4 (multiple morbidities); cluster 5 (anemia and infertility); and cluster 6 (headache and migraine). Clustering aggregates similar units into similar clusters, partitioning dissimilar objects into other clusters at a progressively finer granularity—in this case, groups of women with similarities in their comorbidities. Clusters may provide a deeper insight into the multidimensionality of endometriosis and may represent diverse “endometriosis trajectories” which may be associated with specific molecular and biochemical mechanisms. Comorbidity-based clusters may be important to the scientific study of endometriosis, contributing to the clarification of its clinical complexity and variability. An awareness of those comorbidities may help elucidate the etiopathogenesis and facilitate the accurate earlier diagnosis and initiation of treatments targeted toward particular subgroups.

show abstract

Section: Discussionmentioning

confidence: 99%

A Novel Classification of Endometriosis Based on Clusters of Comorbidities

Sarria-Santamera,

Yemenkhan,

Terzic

et al. 2023

Biomedicines

Self Cite

View full text Add to dashboard Cite

show abstract

“…Codes indicating a diagnosis of endometriosis are based on clinical providers' reporting (primary care or hospital specialists). The data available do not permit us to determine whether the diagnosis is based on signs and symptoms, diagnostic images, laparoscopic visualization, or biopsy [28]. The dataset used is exempt from ethical approval, as it is a secondary anonymized dataset that is publicly available from the Spanish Ministry of Health.…”

Section: Study Populationmentioning

confidence: 99%

Diagnosis of Endometriosis Based on Comorbidities: A Machine Learning Approach

Tore,

Abilgazym,

Asunsolo-del-Barco

et al. 2023

Biomedicines

Self Cite

View full text Add to dashboard Cite

Endometriosis is defined as the presence of estrogen-dependent endometrial-like tissue outside the uterine cavity. Despite extensive research, endometriosis is still an enigmatic disease and is challenging to diagnose and treat. A common clinical finding is the association of endometriosis with multiple diseases. We use a total of 627,566 clinically collected data from cases of endometriosis (0.82%) and controls (99.18%) to construct and evaluate predictive models. We develop a machine learning platform to construct diagnostic tools for endometriosis. The platform consists of logistic regression, decision tree, random forest, AdaBoost, and XGBoost for prediction, and uses Shapley Additive Explanation (SHAP) values to quantify the importance of features. In the model selection phase, the constructed XGBoost model performs better than other algorithms while achieving an area under the curve (AUC) of 0.725 on the test set during the evaluation phase, resulting in a specificity of 62.9% and a sensitivity of 68.6%. The model leads to a quite low positive predictive value of 1.5%, but a quite satisfactory negative predictive value of 99.58%. Moreover, the feature importance analysis points to age, infertility, uterine fibroids, anxiety, and allergic rhinitis as the top five most important features for predicting endometriosis. Although these results show the feasibility of using machine learning to improve the diagnosis of endometriosis, more research is required to improve the performance of predictive models for the diagnosis of endometriosis. This state of affairs is in part attributed to the complex nature of the condition and, at the same time, the administrative nature of our features. Should more informative features be used, we could possibly achieve a higher AUC for predicting endometriosis. As a result, we merely perceive the constructed predictive model as a tool to provide auxiliary information in clinical practice.

show abstract

“…Sarria-Santamera and colleagues highlighted that endometriosis is correlated with a 2.66-fold greater risk of ovarian cancer, compared to the general population [ 18 ]. In addition, it has been estimated that the lifetime risk of ovarian cancer in women with endometriosis is 2.5% [ 1 ].…”

Section: Introductionmentioning

confidence: 99%

Endometriosis-Related Ovarian Cancers: Evidence for a Dichotomy in the Histogenesis of the Two Associated Histotypes

et al. 2023

View full text Add to dashboard Cite

Evidence indicates that different pathways of malignant degeneration underlie the development of endometriosis-associated ovarian tumors of endometrioid and clear cell histotypes. The aim of this study was to compare data from patients affected by these two histotypes to investigate the hypothesis of a dichotomy in the histogenesis of these tumors. Clinical data and tumor characteristics of 48 patients who were diagnosed with either pure clear cell ovarian cancer and mixed endometrioid–clear cell ovarian cancer arising from endometriosis (ECC, n = 22) or endometriosis-associated endometrioid ovarian cancer (EAEOC, n = 26) were compared. A previous diagnosis of endometriosis was detected more frequently in the ECC group (32% vs. 4%, p = 0.01). The incidence of bilaterality was significantly higher in the EAOEC group (35% vs. 5%, p = 0.01) as well as a solid/cystic rate at gross pathology (57.7 ± 7.9% vs. 30.9 ± 7.5%, p = 0.02). Patients with ECC had a more advanced disease stage (41% vs. 15%; p = 0.04). A synchronous endometrial carcinoma was detected in 38% of EAEOC patients. A comparison of the International Federation of Gynecology and Obstetrics (FIGO) stage at diagnosis showed a significantly decreasing trend for ECC compared to EAEOC (p = 0.02). These findings support the hypothesis that the origin, clinical behavior and relationship with endometriosis might be different for these histotypes. ECC, unlike EAEOC, seems to develop within an endometriotic cyst, thus representing a window of possibility for ultrasound-based early diagnosis.

show abstract

History of Endometriosis Is Independently Associated with an Increased Risk of Ovarian Cancer

Cited by 3 publications

References 46 publications

A Novel Classification of Endometriosis Based on Clusters of Comorbidities

A Novel Classification of Endometriosis Based on Clusters of Comorbidities

Diagnosis of Endometriosis Based on Comorbidities: A Machine Learning Approach

Endometriosis-Related Ovarian Cancers: Evidence for a Dichotomy in the Histogenesis of the Two Associated Histotypes

Contact Info

Product

Resources

About