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.

Circular RNA and its potential as prostate cancer biomarkers

STUDY QUESTION: Is there an association between the somatic loss of PTEN (phosphatase and tensin homolog) and ARID1A (AT-rich interaction domain 1A) and endometriosis disease severity and worse clinical outcomes? SUMMARY ANSWER: Somatic PTEN loss in endometriosis epithelium was associated with greater disease burden and subsequent surgical complexity. WHAT IS KNOWN ALREADY: Somatic cancer-driver mutations including those involving the PTEN and ARID1A genes exist in endometriosis without cancer; however, their clinical impact remains unclear. STUDY DESIGN, SIZE, DURATION: This prospective longitudinal study involved endometriosis tissue and clinical data from 126 participants who underwent surgery at a tertiary center for endometriosis (2013–2017), with a follow-up period of 5–9 years. PARTICIPANTS/MATERIALS, SETTING, METHODS: PTEN and ARID1A loss was assessed using established immunohistochemistry (IHC) methods as proxies for somatic loss by two independent raters. PTEN and ARID1A status for each participant was defined as loss (loss in at least one sample for a participant) or retained (no loss in all samples for a participant). Primary analyses examined associations between PTEN and ARID1A loss and disease burden based on anatomic subtype (superficial peritoneal endometriosis (SUP), deep endometriosis (DE), ovarian endometrioma (OMA)) and rASRM stage (I–IV). Secondary analyses explored associations of PTEN and ARID1A loss with demographics, surgical difficulty, and pain scores (baseline and follow-up). Additionally, using previously published data on KRAS codon 12 mutations for this cohort, we investigated associations between variables in the primary and secondary analyses and acquiring two or more somatic events (PTEN loss, ARID1A loss, or KRAS mutation) in this cohort. The risk of reoperation over the 5–9 years was also examined. MAIN RESULTS AND THE ROLE OF CHANCE: PTEN loss (68.3%; 86 participants) exceeded ARID1A loss (24.6%; 31 participants). Inter-rater reliability was substantial for PTEN (k = 0.69; 95% CI: 0.62–0.77) and ARID1A (k = 0.64; 95% CI: 0.51–0.77). PTEN loss was significantly associated with more severe anatomic subtypes (P < 0.001; participants with SUP only = 46.4%; participants with DE only or OMA only = 72.7%; participants with mixed subtypes = 85.1%), and higher stages (P = 0.024; Stage I = 47.8%; Stage II = 73.7%; Stage III = 80.8%; Stage IV = 81.0%). Results were similar for ARID1A loss, albeit with smaller sample size limiting power. PTEN loss was further associated with non-White ethnicities (P = 0.017) and greater surgical difficulty (more frequent need for ureterolysis) (P = 0.02). There were no differences in pain scores (baseline or follow-up) based on PTEN or ARID1A status. Reoperation was uncommon (13.5% of the cohort), and patterns in reoperation rates based on the presence of somatic alterations did not reach statistical significance. LIMITATIONS, REASONS FOR CAUTION: Sequencing was not performed to determine the type of PTEN and ARID1A somatic mutations resulting in loss of expression. WIDER IMPLICATIONS OF THE FINDINGS: These results demonstrate a link between PTEN somatic loss and greater endometriosis disease burden. These findings underscore the potential relevance of PTEN loss and other somatic driver mutations in a future molecular classification of endometriosis. STUDY FUNDING/COMPETING INTEREST(S): This study was funded by Canadian Institutes of Health Research (CIHR) project grant (MOP-142273 and PJT-156084). P.J.Y. was supported by a Health Professional Investigator award from Michael Smith Health Research BC, Canada, and a Canada Research Chair (Tier 2) in Endometriosis and Pelvic Pain. M.S.A. was supported by a Michael Smith Health Research BC Scholar award, and CIHR project grants (369990, 462997, and 456767). The sponsors did not play any role in the study design; in the collection, analysis, and interpretation of data; in the writing of the report; and in the decision to submit the article for publication. C.A. declares receiving payment from Pfizer for a symposium; being on advisory boards for AbbVie and Pfizer; being President and past President of the Canadian Society for the Advancement of Gynecologic Excellence (CanSAGE), co-lead of EndoAct Canada, and a board member of IPPS. M.A.B. has received consulting fees from AbbVie and Pfizer and grants from Ferring outside the scope of this work. D.G.H. is the founder of Canxeia Health but has no current affiliation. M.K. has received consulting fees from Helix Biopharma outside the scope of this work. M.S.A. received reimbursement of travel and registration fees to attend and present at the 2023 and 2024 annual meetings for the Society for Reproductive Investigation (SRI). P.J.Y. declares receiving: payment for a lecture from the International Society for the Study of Women’s Sexual Health (ISSWSH); honoraria from the CIHR; support to attend meetings from CanSAGE, ISSWSH, the International Pelvic Pain Society, the World Endometriosis Society (WES), the Society for the Study of Reproduction, and the Vulvodynia Summit; and discounted devices from Ohnut Wearable for a clinical trial. P.J.Y. is a data safety monitoring board member of a clinical trial funded by CIHR; and a strategic advisory board member for the Women’s Health Research Institute. P.J.Y. served as a board of directors member for CanSAGE and ISSWSH; was a junior board of directors member for WES; is a current board of directors member for WES; and was a committee chair for the Society of Obstetricians and Gynaecologists of Canada. A subset of these results was presented by the first author at the 71st Society for Reproductive Investigation Annual Scientific Meeting on 15 March 2024. Other authors have nothing to declare. TRIAL REGISTRATION NUMBER: N/A.

Endometriosis is a gynecological disorder associated with local inflammation and neuroproliferation. Increased nerve bundle density has been attributed to increased expression of nerve growth factor (NGF) and interleukin–1β (IL-1β). Immunohistochemical analysis was carried out on 12 patients presenting with all three anatomic subtypes of endometriosis (deep, superficial peritoneal, endometrioma) at surgery, with at least two surgically excised subtypes available for analysis. Immunolocalization for nerve bundle density around endometriosis using protein gene product 9.5 (PGP9.5), as well as NGF and IL-1β histoscores in endometriosis epithelium/stroma, was performed to evaluate differences in scores between lesions and anatomic subtypes per patient. Intra-individual heterogeneity in scores across lesions was assessed using the coefficient of variation (CV). The degree of score variability between subtypes was evaluated using the percentage difference between mean scores from one subtype to another subtype for each marker. PGP9.5 nerve bundle density was heterogenous across multiple subtypes of endometriosis, ranging from 50.0% to 173.2%, where most patients (8/12) showed CV ≥ 100%. The percentage difference in scores showed that PGP9.5 nerve bundle density and NGF and IL-1β expression were heterogenous between anatomic subtypes within the same patient. Based on these observations of intra-individual heterogeneity, we conclude that markers of neuroproliferation in endometriosis should be stratified by anatomic subtype in future studies of clinical correlation.

Prostate cancer is the second most common cancer and the fifth leading cause of cancer death. The incidence of prostate cancer is rising due to increased screening and awareness, and there is epidemiological evidence suggesting an interaction among biological and environmental risk factors in the development and progression of prostate cancer. Vegetables and fruits provide a wide range of antioxidants and phytochemicals that have been demonstrated to have a negative, positive, or no association with prostate cancer risk. Therefore, it is evident that the effect of dietary antioxidants on risk of prostate cancer remains undecided and inconclusive. The main focus of this review was to examine recent and past literature of the chemoprotective properties of five major groups of phytochemicals against prostate cancer development including both in vivo and in vitro findings.