Search

Objective: To identify predictive clinico-pathologic factors for concurrent endometrial carcinoma (EC) among patients with endometrial intraepithelial neoplasia (EIN) using machine learning., Methods: a retrospective analysis of 160 patients with a biopsy proven EIN. We analyzed the performance of multiple machine learning models (n = 48) with different parameters to predict the diagnosis of postoperative EC. The prediction variables included: parity, gestations, sampling method, endometrial thickness, age, body mass index, diabetes, hypertension, serum CA-125, preoperative histology and preoperative hormonal therapy. Python 'sklearn' library was used to train and test the models. The model performance was evaluated by sensitivity, specificity, PPV, NPV and AUC. Five iterations of internal cross-validation were performed, and the mean values were used to compare between the models., Results: Of the 160 women with a preoperative diagnosis of EIN, 37.5% (60) had a post-op diagnosis of EC. In univariable analysis, there were no significant predictors of EIN. For the five best machine learning models, all the models had a high specificity (71%-88%) and a low sensitivity (23%-51%). Logistic regression model had the highest specificity 88%, XG Boost had the highest sensitivity 51%, and the highest positive predictive value 62% and negative predictive value 73%. The highest area under the curve was achieved by the random forest model 0.646., Conclusions: Even using the most elaborate AI algorithms, it is not possible currently to predict concurrent EC in women with a preoperative diagnosis of EIN. As women with EIN have a high risk of concurrent EC, there may be a value of surgical staging including sentinel lymph node evaluation, to more precisely direct adjuvant treatment in the event EC is identified on final pathology., (© 2024 The Authors. Published by Elsevier Ltd. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).)

The aim of this study was to evaluate the impact of discordant endometrial sampling on the prognosis of patients finally diagnosed with uterine papillary serous carcinoma (UPSC) and to analyze UPSC mutational profile. Retrospective cohort study comparing outcomes of patients post-operatively diagnosed with UPSC and preoperatively diagnosed with endometrioid endometrial cancer (EEC) or UPSC. Genes commonly implicated in carcinogenesis were analyzed in a subgroup of 40 patients post-operatively diagnosed with UPSC, using next generation sequencing. 61 patients with UPSC on post-surgical, final pathology were included in the study. Prior to surgery, 15 were diagnosed with EEC (discordant) and 46 were correctly diagnosed with UPSC (concordant). After a median follow-up of 41.6 months [5.4-106.7], a preoperative diagnosis of EEC was associated with better 3-year progression-free survival (100% vs. 60.9%, P = 0.003) and longer disease free interval (63.5 versus 15 months, P = 0.026) compared to patients with an initial diagnosis of UPSC. Patients with a concordant diagnosis of UPSC were 5 times more likely to progress or die compared to those with a discordant EEC diagnosis (P = 0.02, P = 0.03, respectively), and their tumors were associated with higher rates of TP53 (88.9% vs. 61.5%, P = 0.04), and a lower rate of PTEN (14.8% vs. 38.5%, P = 0.09) and ARID1A (3.7% vs. 23.1%, P = 0.05) mutations. A pre-surgical diagnosis of EEC is associated with improved prognosis in patients with UPSC. Some histologically defined UPSC tumors contain endometrioid-like molecular characteristics that may confer a survival advantage, suggesting a possible need for molecular approaches to better stratify patients into risk groups., Competing Interests: The authors report no conflict of interest., (© 2019 The Author(s).)

Objective: Evaluation of the impact of lower uterine segment involvement (LUSI) in type II endometrial cancer, and mutational profile of uterine papillary serous carcinomas (UPSC)., Methods: Retrospective cohort study comparing patients with type II endometrial cancer with LUSI to patients without LUSI. Genes commonly implicated in carcinogenesis were analyzed in a subgroup of 42 patients with UPSC using next generation sequencing., Results: 83 patients with type II endometrial cancer were included in the study, of these, LUSI was diagnosed in 31.3%. During a median follow-up of 45.5 months, patients with LUSI developed more local and distant recurrences (local: 19.2% vs. 3.5%, P  = .03; distant: 50% vs. 17.5%, P  = .004) and progression events (73.1% vs. 26.3%, P  < .001), with shorter mean progression-free survival (16 months compared to 26.5 months, P  < .01). In a multivariate analysis, LUSI was the only significant pathological factor, associated with a 2.9-fold increase in the risk of progression ( P  = .007), and a 2.6-fold increase in the risk of death ( P  = .02). In the subgroup of patients with UPSC, mutations were identified in 54 genes, including TP53 (80%), PPP2R1A (40%), and PTEN (22.5%). Frequent mutations in the PTEN-PI3K-AKT signaling pathway were found in patients with tumor in the upper uterine segment only ( P  = .04), with PTEN being mutated in 29% of the samples ( P  = .07)., Conclusion: Type II endometrial cancers presenting in the LUS have a significantly worse prognosis and this might be associated with a unique mutational profile.