To compare the accuracy of five major risk stratification systems (RSS) in classifying the risk of recurrence and nodal metastases in early-stage endometrial cancer (EC). Data of 553 patients with early-stage EC were abstracted from a prospective multicentre database between January 2001 and December 2012. The following RSS were identified in a PubMed literature search and included the Post Operative Radiation Therapy in Endometrial Carcinoma (PORTEC-1), the Gynecologic Oncology Group (GOG)-99, the Survival effect of para-aortic lymphadenectomy (SEPAL), the ESMO and the ESMO-modified classifications. The accuracy of each RSS was evaluated in terms of recurrence-free survival (RFS) and nodal metastases according to discrimination. Overall, the ESMO -modified RSS provided the highest discrimination for both RFS and for nodal metastases with a concordance index (C-index) of 0.73 (95% CI, 0.70-0.76) and an area under the curve (AUC) of 0.80 (0.78-0.72), respectively. The other RSS performed as follows: the PORTEC1, GOG-99, SEPAL, ESMO classifications gave a C-index of 0.68 (0.66-0.70), 0.65 (0.63-0.67), 0.66 (0.63-0.69), 0.71 (0.68-0.74), respectively, for RFS and an AUC of 0.69 (0.66-0.72), 0.69 (0.67-0.71), 0.68 (0.66-0.70), 0.70 (0.68-0.72), respectively, for node metastases. None of the five major RSS showed high accuracy in stratifying the risk of recurrence or nodal metastases in patients with early-stage EC, although the ESMO-modified classification emerged as having the highest power of discrimination for both parameters. Therefore, there is a need to revisit existing RSS using additional tools such as biological markers to better stratify risk for these patients.

Endometriosis—a systemic and chronic condition occurring in women of childbearing age—is a highly enigmatic disease with unresolved questions. While multiple biomarkers, genomic analysis, questionnaires, and imaging techniques have been advocated as screening and triage tests for endometriosis to replace diagnostic laparoscopy, none have been implemented routinely in clinical practice. We investigated the use of machine learning algorithms (MLA) in the diagnosis and screening of endometriosis based on 16 key clinical and patient-based symptom features. The sensitivity, specificity, F1-score and AUCs of the MLA to diagnose endometriosis in the training and validation sets varied from 0.82 to 1, 0–0.8, 0–0.88, 0.5–0.89, and from 0.91 to 0.95, 0.66–0.92, 0.77–0.92, respectively. Our data suggest that MLA could be a promising screening test for general practitioners, gynecologists, and other front-line health care providers. Introducing MLA in this setting represents a paradigm change in clinical practice as it could replace diagnostic laparoscopy. Furthermore, this patient-based screening tool empowers patients with endometriosis to self-identify potential symptoms and initiate dialogue with physicians about diagnosis and treatment, and hence contribute to shared decision making.

Lymphovascular space invasion (LVSI) is one of the most important predictors of nodal involvement and recurrence in early stage endometrial cancer (EC). Despite its demonstrated prognostic value, LVSI has not been incorporated into the European Society of Medical Oncology (ESMO) classification. The aim of this prospective multicentre database study is to investigate whether it may improve the accuracy of the ESMO classification in predicting the recurrence risk. Data of 496 patients with apparent early-stage EC who received primary surgical treatment between January 2001 and December 2012 were abstracted from prospective multicentre database. A modified ESMO classification including six risk groups was created after inclusion of the LVSI status in the ESMO classification. The primary end point was the recurrence accuracy comparison between the ESMO and the modified ESMO classifications with respect to the area under the receiver operating characteristic curve (AUC). The recurrence rate in the whole population was 16.1%. The median follow-up and recurrence time were 31 (range: 1-152) and 27 (range: 1-134) months, respectively. Considering the ESMO modified classification, the recurrence rates were 8.2% (8 out of 98), 23.1% (15 out of 65), 25.9% (15 out of 58), and 45.1% (28 out of 62) for intermediate risk/LVSI-, intermediate risk/LVSI+, high risk/LVSI-, and high risk/LVSI+, respectively (P<0.001). In the low risk group, LVSI status was not discriminant as only 7.0% (14 out of 213) had LVSI+. The staging accuracy according to AUC criteria for ESMO and ESMO modified classifications were of 0.71 (95% CI: 0.68-0.74) and 0.74 (95% CI: 0.71-0.77), respectively. The current modified classification could be helpful to better define indications for nodal staging and adjuvant therapy, especially for patients with intermediate risk EC.