Predicting the presence of rectovaginal endometriosis from the clinical history: a retrospective observational study

Endometriosis Predictive Models Based on Self-Assessment Questionnaire, Evidence from Clinical Examination or Imaging Findings: A Narrative Review

OBJECTIVE

The aim of this narrative review is to evaluate existing questionnaires on predictive models for endometriosis. These symptom-based models have the potential to serve as screening tools for adult women to detect endometriosis.

DATA SOURCES

A comprehensive search of PubMed and Embase databases was conducted to identify studies on endometriosis screening.

SELECTION OF STUDIES

The search targeted predictive models for endometriosis localisation, bowel involvement, need for bowel surgery and fertility. Due to the heterogeneity identified, a systematic review was not possible. A total of 23 studies were identified.

DATA EXTRACTION AND SYNTHESIS

Among these studies, twelve included measures for general endometriosis, two targeted specific sites, four focused on deep infiltrating endometriosis (DIE), and three addressed the need for endometriosis-related bowel surgery. Many measures combined clinical, imaging and laboratory tests with patient questionnaires. Validation of these models as screening tools was lacking in all studies, as the focus was on diagnosis rather than screening.

CONCLUSION

This review did not identify any fully validated, symptom-based questionnaires for endometriosis screening in adult women. Substantial validation work remains to establish the efficacy of such tools.

Evaluating the risk of endometriosis based on patients' self-assessment questionnaires

BACKGROUND

Endometriosis is a condition that significantly affects the quality of life of about 10 % of reproductive-aged women. It is characterized by the presence of tissue similar to the uterine lining (endometrium) outside the uterus, which can lead lead scarring, adhesions, pain, and fertility issues. While numerous factors associated with endometriosis are documented, a wide range of symptoms may still be undiscovered.

METHODS

In this study, we employed machine learning algorithms to predict endometriosis based on the patient symptoms extracted from 13,933 questionnaires. We compared the results of feature selection obtained from various algorithms (i.e., Boruta algorithm, Recursive Feature Selection) with experts' decisions. As a benchmark model architecture, we utilized a LightGBM algorithm, along with Multivariate Imputation by Chained Equations (MICE) and k-nearest neighbors (KNN), for missing data imputation. Our primary objective was to assess the model's performance and feature importance compared to existing studies.

RESULTS

We identified the top 20 predictors of endometriosis, uncovering previously overlooked features such as Cesarean section, ovarian cysts, and hernia. Notably, the model's performance metrics were maximized when utilizing a combination of multiple feature selection methods. Specifically, the final model achieved an area under the receiver operator characteristic curve (AUC) of 0.85 on the training dataset and an AUC of 0.82 on the testing dataset.

CONCLUSIONS

The application of machine learning in diagnosing endometriosis has the potential to significantly impact clinical practice, streamlining the diagnostic process and enhancing efficiency. Our questionnaire-based prediction approach empowers individuals with endometriosis to proactively identify potential symptoms, facilitating informed discussions with healthcare professionals about diagnosis and treatment options.

Multi-Center Studies of the Global Impact of Endometriosis and the Predictive Value of Associated Symptoms

Introduction

Endometriosis can be difficult to diagnose clinically and models that use symptoms to predict whether the disease is present or not are based on limited patient populations. Endometriosis also influences health-related quality of life, but little is known about its impact across the world. We therefore initiated two integrated multi-center studies to collect prospective, standardized, epidemiological data, to 1) examine the global impact of endometriosis and relative effect of risk-factors, and 2) develop a symptom-based diagnostic tool.

Methods

The Global Study of Women's Health (GSWH) and the Women's Health Symptom Survey (WHSS) prospectively recruit 18–45 year old women having a laparoscopy across 23 and 19 centers, respectively, worldwide. Women with a previous surgical diagnosis of endometriosis are excluded. Multi-lingual patient questionnaires and a surgical questionnaire, incorporating validated instruments, are used to collect the data. The GSWH aims to recruit >2,000 women by December 2009; the WHSS to recruit 1,000 women in each of the two model-generating and validation stages.

Results

A six-week pilot study in Oxford, UK, established the feasibility of the study protocols. Of 32 eligible women, 27 participated (response rate - 84.4%); 26% completed the questionnaire online. Endometriosis was found in 47.4%. Extrapolating the recruitment rates from the pilot study, the target sample sizes for the GWSH and WHSS were deemed feasible.

Conclusions

Using standardized data collection, the GSWH and WHSS will provide insight into the global impact of endometriosis and develop a validated, symptom-based, diagnostic tool. They have the potential to provide the basis for future, longitudinal, follow-up studies and a collaborative Endometriosis Biobank implementing standardized collection of DNA and tissue samples

Patient-completed or symptom-based screening tools for endometriosis: a scoping review

PURPOSE

The objective of this review was to evaluate existing patient-completed screening questionnaires and/or symptom-based predictive models with respect to their potential for use as screening tools for endometriosis in adult women. Validated instruments were of particular interest.

METHODS

We conducted structured searches of PubMed and targeted searches of the gray literature to identify studies reporting on screening instruments used in endometriosis. Studies were screened according to inclusion and exclusion criteria that followed the PICOS (population, intervention, comparison, outcomes, study design) framework.

RESULTS

A total of 16 studies were identified, of which 10 described measures for endometriosis in general, 2 described measures for endometriosis at specific sites, and 4 described measures for deep-infiltrating endometriosis. Only 1 study evaluated a questionnaire that was solely patient-completed. Most measures required physician, imaging, or laboratory assessments in addition to patient-completed questionnaires, and several measures relied on complex scoring. Validation for use as a screening tool in adult women with potential endometriosis was lacking in all studies, as most studies focused on diagnosis versus screening.

CONCLUSIONS

This literature review did not identify any fully validated, symptom-based, patient-reported questionnaires for endometriosis screening in adult women.

Do fluctuations in ovarian hormones affect gastrointestinal symptoms in women with irritable bowel syndrome?

BACKGROUND

An increase in gastrointestinal (GI) symptoms, including bowel discomfort, abdominal pain/discomfort, bloating, and alterations in bowel patterns, has been reported during premenses and menses menstrual cycle phases and the perimenopause period in women with and without irritable bowel syndrome (IBS).

OBJECTIVE

This article reviews the literature related to one possible physiological mechanism-declining or low ovarian hormone levels--that may underlie the occurrence or exacerbations of abdominal pain/discomfort at times of low ovarian hormones (menses, menopause) in women with or without IBS.

METHODS

To identify English-only review and data-based articles, PubMed was searched between January 1980 and September 2008 using the following terms: irritable bowel syndrome, functional gastrointestinal disorders, gastrointestinal motility, immune, pain, hyperalgesia, menstrual cycle, menopause, pregnancy, estrogen, estradiol (E(2)), and progesterone. Studies in animals and in humans were included; drug trials were excluded.

RESULTS

From our review of the literature, 18 papers were identified that were related either to the mechanisms accounting for menstrual cycle fluctuations (n = 12) or to the impact of menopausal status on symptoms of IBS (n = 6). One study reported that visceral pain sensitivity was significantly higher during menses than at other menstrual cycle phases in women with IBS (P < 0.05). Other menstrual cycle phase-linked symptoms, dysmenorrheal symptoms (cramping pain) in particular, were more intense in women with IBS. Animal studies have shed some light on the relationship of ovarian hormones to GI sensorimotor function.

CONCLUSION

The increase in GI symptoms around the time of menses and early menopause occurs at times of declining or low ovarian hormones, suggesting that estrogen and progesterone withdrawal may contribute either directly or indirectly. This review highlights the need for confirmatory preclinical and clinical studies to unravel the role of ovarian hormones in women with IBS.