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.
Rojas HE et al., 2026·Journal of women's health (2002)
To characterize differences between individuals with and without mid-cycle pain in a registry cohort with endometriosis. Prospective analysis of data from the Endometriosis Pelvic Pain Interdisciplinary Cohort Data Registry (Clinicaltrials.gov #NCT02911090) at a tertiary referral center in Western Canada. Three hundred forty-five individuals aged 18-49 years who: (1) had at least one episode of menstrual bleeding in the last 3 months, (2) attended a baseline initial visit, and (3) subsequently had surgery with histological confirmation of endometriosis between January 2018 and December 2023. Exclusion criteria included (1) previous hysterectomy; (2) hormonal suppressive therapy use in the last 3 months; and (3) missing data on mid-cycle pain, history of hormonal therapy use, or menstrual cycle regularity. N/A. Mid-cycle pain in the last month versus No mid-cycle pain in the last month. Of the 345 participants, 67% (n = 232) reported mid-cycle pain in the last month. Mid-cycle pain in the last month was significantly associated with higher mean Central Sensitization Inventory score (48 ± 17 versus 36 ± 16, p < 0.001) and more months of prior hormonal suppressive therapy use (58 [14-120] versus 26 [0-109], p = 0.012). Abnormal anatomy at the time of surgery (e.g., endometrioma, ovarian adhesions) was not associated with mid-cycle pain in the last month. In this endometriosis cohort at a tertiary referral center, most participants reported mid-cycle pain in the last month, which was associated with central sensitization but was not clearly related to endometriosis anatomical distortion.
Balachandran S et al., 2026·Journal of obstetrics and gynaecology Canada : JOGC = Journal d'obstetrique et gynecologie du Canada : JOGC
To assess the impact of the COVID-19 pandemic on reproductive outcomes in patients with recurrent pregnancy loss (RPL) and the influence of material and social deprivation on these outcomes.
This retrospective cohort study included RPL patients seen at a specialized clinic between March 1, 2018, and February 28, 2022. Patients were categorized into two groups based on care period: pre-pandemic (March 1, 2018-February 29, 2020) and pandemic (March 1, 2020-February 28, 2022). Cumulative probabilities of birth were estimated using the cumulative incidence function within a competing risk framework, treating pregnancy loss as a competing event. Fine and Gray regression models calculated sub-distribution hazard ratio (sHR) of birth.
544 patients were included in the study, with 255 in the pre-pandemic group and 289 in the pandemic group. Individuals in the pandemic group were less likely to achieve pregnancy than those in the pre-pandemic group (relative risk = 0.50, 95% confidence interval [CI] 0.39 - 0.66). Among those who conceived, the cumulative probability of live birth was 0.77 in both groups. Relative to individuals residing in high-social deprivation neighborhoods, those living in moderately deprived areas had higher sub-distribution hazards of live birth (adjusted sHR = 1.97, 95% CI 1.25 - 3.10; P = 0.003).
Within specialized RPL care and a universal maternity care system, pregnancy rates were lower during the first two years of the COVID-19 pandemic. However, among those who conceived, the probability of achieving a live birth remained similar between the pre-pandemic and pandemic periods.
Bouchard TP et al., 2026·Reproductive biomedicine online·Free to read
Does formation of the corpus luteum help to identify the day of ovulation on ultrasound when follicular collapse is missed, and how reliable are sonographers versus a review panel in identifying the day of ovulation on ultrasound? Sonographers in a clinic in Canada performed serial endovaginal ultrasound scans (six to eight per cycle) to identify the day of ovulation in regularly cycling women (n = 40) who were followed for one to five cycles (n = 85). The day of ovulation was identified by: (i) identification of the dominant follicle; (ii) disappearance of the dominant follicle; and (iii) identification and dating of the corpus luteum. The main outcome measures were inter-rater reliability between two sonographers, and Bland-Altman agreement between the supervising sonographer and a panel that reviewed each scan to identify the day of ovulation. Of the 85 menstrual cycles reviewed, two cycles did not have sufficient data to date ovulation, one cycle showed an incidental dermoid cyst, and 11 cycles showed anovulatory patterns. This left a total of 71 cycles (84%) for which intra-rater reliability between two sonographers for identifying the day of ovulation was high (intraclass correlation coefficient = 0.99, P < 0.0001), and Bland-Altman agreement showed no significant difference in the estimated day of ovulation between the supervising sonographer and the panel (t = -0.28, P = 0.78). Corpus luteum criteria were necessary to help identify the day of ovulation in 14 of 71 cycles (20%). The estimated day of ovulation can be determined reliably on ultrasound by trained sonographers using collapse of the dominant follicle and formation of the corpus luteum based on six to eight scans per cycle.
Yong PJ et al., 2026·Journal of obstetrics and gynaecology Canada : JOGC = Journal d'obstetrique et gynecologie du Canada : JOGC
To provide health care professionals with an evidence-based approach to the management of endometriosis and its associated symptoms.
Women and gender-diverse individuals affected by endometriosis.
BENEFITS, HARMS, Timely and effective management of endometriosis has the potential to reduce pain, improve fertility and quality of life, and enhance long-term health outcomes. Early intervention may also help mitigate the financial and health system burdens associated with delayed diagnosis and treatment.
Published literature was retrieved through searches of PubMed, Ovid, Medline, Embase, Scopus, and the Cochrane Library from August 2010 through December 2025, using relevant MeSH heading and keywords. Results were restricted to systematic reviews, meta-analyses, randomized controlled trials/controlled clinical trials, observational studies, and clinical practice guidelines. Results were limited to English or French language materials. Evidence was supplemented with references from the 2010 Society of Obstetricians and Gynaecologists of Canada guideline No. 244.
The authors rated the quality of evidence and strength of recommendations using the Grading of Recommendations Assessment, Development and Evaluation (GRADE) approach. See online Appendix A (Tables A1 for definitions and A2 for interpretations of strong and conditional recommendations).
Health care providers involved in the care of individuals with endometriosis.
Early identification and management of endometriosis can significantly improve patient outcomes, reduce long-term health care costs and improve their quality of life.
RECOMMENDATIONS.
Dungate B et al., 2024·Women's health (London, England)·Free full text on PubMed Central
Endometriosis, a chronic condition characterized by the growth of endometrial-like tissue outside of the uterus, poses substantial challenges in terms of diagnosis and treatment. Artificial intelligence (AI) has emerged as a promising tool in the field of medicine, offering opportunities to address the complexities of endometriosis. This review explores the current landscape of endometriosis diagnosis and treatment, highlighting the potential of AI to alleviate some of the associated burdens and underscoring common pitfalls and challenges when employing AI algorithms in this context. Women's health research in endometriosis has suffered from underfunding, leading to limitations in diagnosis, classification, and treatment approaches. The heterogeneity of symptoms in patients with endometriosis has further complicated efforts to address this condition. New, powerful methods of analysis have the potential to uncover previously unidentified patterns in data relating to endometriosis. AI, a collection of algorithms replicating human decision-making in data analysis, has been increasingly adopted in medical research, including endometriosis studies. While AI offers the ability to identify novel patterns in data and analyze large datasets, its effectiveness hinges on data quality and quantity and the expertise of those implementing the algorithms. Current applications of AI in endometriosis range from diagnostic tools for ultrasound imaging to predicting treatment success. These applications show promise in reducing diagnostic delays, healthcare costs, and providing patients with more treatment options, improving their quality of life. AI holds significant potential in advancing the diagnosis and treatment of endometriosis, but it must be applied carefully and transparently to avoid pitfalls and ensure reproducibility. This review calls for increased scrutiny and accountability in AI research. Addressing these challenges can lead to more effective AI-driven solutions for endometriosis and other complex medical conditions.
Kiser AC et al., 2024·PLoS One·Free full text on PubMed Central
Endometriosis is a debilitating, chronic disease that is estimated to affect 11% of reproductive-age women. Diagnosis of endometriosis is difficult with diagnostic delays of up to 12 years reported. These delays can negatively impact health and quality of life. Vague, nonspecific symptoms, like pain, with multiple differential diagnoses contribute to the difficulty of diagnosis. By investigating previously imprecise symptoms of pain, we sought to clarify distinct pain symptoms indicative of endometriosis, using an artificial intelligence-based approach. We used data from 473 women undergoing laparoscopy or laparotomy for a variety of surgical indications. Multiple anatomical pain locations were clustered based on the associations across samples to increase the power in the probability calculations. A Bayesian network was developed using pain-related features, subfertility, and diagnoses. Univariable and multivariable analyses were performed by querying the network for the relative risk of a postoperative diagnosis, given the presence of different symptoms. Performance and sensitivity analyses demonstrated the advantages of Bayesian network analysis over traditional statistical techniques. Clustering grouped the 155 anatomical sites of pain into 15 pain locations. After pruning, the final Bayesian network included 18 nodes. The presence of any pain-related feature increased the relative risk of endometriosis (p-value < 0.001). The constellation of chronic pelvic pain, subfertility, and dyspareunia resulted in the greatest increase in the relative risk of endometriosis. The performance and sensitivity analyses demonstrated that the Bayesian network could identify and analyze more significant associations with endometriosis than traditional statistical techniques. Pelvic pain, frequently associated with endometriosis, is a common and vague symptom. Our Bayesian network for the study of pain-related features of endometriosis revealed specific pain locations and pain types that potentially forecast the diagnosis of endometriosis.
De Corte P et al., 2025·BJOG : an international journal of obstetrics and gynaecology·Free full text on PubMed Central
Endometriosis diagnosis reportedly faces delays of up to 10 years. Despite growing awareness and improved guidelines, information on the current status is limited. To systematically assess the published evidence on the status of time to diagnosis in individuals with endometriosis, with respect to the definition of time to diagnosis, geographical location and patient characteristics. MEDLINE (via PubMed) and Embase were searched for publications reporting time to diagnosing endometriosis since 2018. No restrictions to population or comparators were applied. All publications were screened by two independent reviewers. Search results were limited to primary publications of randomised controlled trials, non-randomised trials and observational studies. Case reports, secondary publications and grey literature were excluded. No restrictions were made regarding language, provided that an English title and abstract were available. Publications were assessed with respect to time to diagnosis, diagnostic methods, study type, study country and potential bias. The 17 publications eligible for inclusion in this literature review were all observational studies. The publications reported diagnosis times between 0.3 and 12 years, with variations depending on the definition of time to diagnosis (overall, primary, or clinical), geographical location and characteristics of the included study population. Evidence was of poor to good quality overall. Diagnostic delay is still present, primarily driven by physicians, and this review underscores the need for standardised definitions, increased awareness and targeted diagnostic interventions.
Endometriosis is an estrogen-dependent, chronic inflammatory disorder characterized by the presence of endometrium-like tissue outside the uterus, affecting approximately 10% of individuals of reproductive age. It contributes to chronic pelvic pain, dysmenorrhea, and subfertility, resulting in substantial societal economic burdens. Genetic and environmental risk factors have been identified, and recent research suggests that endometriosis functions as a systemic disease affecting nonreproductive systems and increasing susceptibility to other health conditions. Various phenotypes-superficial peritoneal endometriosis, ovarian endometriomas, and deep endometriosis-may develop under different mechanisms, yet the relationship between these presentations remains unclear. Diagnosis relies on clinical evaluation, imaging, and surgical staging, and the advent of advanced ultrasonography and magnetic resonance imaging has helped to enhance accuracy. Although medical management focuses on hormonal modulation to alleviate symptoms, surgical intervention remains a critical tool for refractory symptoms. Postoperative care and patient education are essential to manage recurrence and to improve quality of life. Current research emphasizes the need for comprehensive, interdisciplinary approaches to endometriosis management, incorporating novel diagnostic tools, diverse therapeutic avenues, and patient-centered care models. Addressing disparities in treatment access is essential to improving outcomes. To achieve this, recruiting and analyzing data from racially, socioeconomically, and geographically diverse cohorts will reveal how disease presentation and treatment efficacy vary across populations. Continued efforts in research and health care policy are necessary to develop effective and personalized strategies in managing endometriosis.
Endometriosis › Diagnosis › Diagnostic Delay · General Gynecology › Clinical Practice › Practice Patterns
Brintha Sivajohan, Mohamed Elgendi, Carlo Menon, Catherine Allaire, Mohamed A Bedaiwy
B Sivajohan, M Elgendi, C Menon, Cathy Allaire, Kate Allaire, C Allaire, M Bedaiwy
PMID 35927426 35927426 DOI 10.1038/s41746-022-00638-1 10.1038/s41746-022-00638-1 Sivajohan et al. 2022, Sivajohan 2022
