Development and Validation of a Nomogram Prediction Model for Endometrial Malignancy in Patients with Abnormal Uterine Bleeding

Models for predicting risk of endometrial cancer: a systematic review

BACKGROUND

Endometrial cancer (EC) is the most prevalent gynaecological cancer in the UK with a rising incidence. Various models exist to predict the risk of developing EC, for different settings and prediction timeframes. This systematic review aims to provide a summary of models and assess their characteristics and performance.

METHODS

A systematic search of the MEDLINE and Embase (OVID) databases was used to identify risk prediction models related to EC and studies validating these models. Papers relating to predicting the risk of a future diagnosis of EC were selected for inclusion. Study characteristics, variables included in the model, methods used, and model performance, were extracted. The Prediction model Risk-of-Bias Assessment Tool was used to assess model quality.

RESULTS

Twenty studies describing 19 models were included. Ten were designed for the general population and nine for high-risk populations. Three models were developed for premenopausal women and two for postmenopausal women. Logistic regression was the most used development method. Three models, all in the general population, had a low risk of bias and all models had high applicability. Most models had moderate (area under the receiver operating characteristic curve (AUC) 0.60-0.80) or high predictive ability (AUC > 0.80) with AUCs ranging from 0.56 to 0.92. Calibration was assessed for five models. Two of these, the Hippisley-Cox and Coupland QCancer models, had high predictive ability and were well calibrated; these models also received a low risk of bias rating.

CONCLUSIONS

Several models of moderate-high predictive ability exist for predicting the risk of EC, but study quality varies, with most models at high risk of bias. External validation of well-performing models in large, diverse cohorts is needed to assess their utility.

REGISTRATION

The protocol for this review is available on PROSPERO (CRD42022303085).

Application of artificial intelligence to ultrasound imaging for benign gynecological disorders: systematic review

OBJECTIVE

Although artificial intelligence (AI) is increasingly being applied to ultrasound imaging in gynecology, efforts to synthesize the available evidence have been inadequate. The aim of this systematic review was to summarize and evaluate the literature on the role of AI applied to ultrasound imaging in benign gynecological disorders.

METHODS

Web of Science, PubMed and Scopus databases were searched from inception until August 2024. Inclusion criteria were studies applying AI to ultrasound imaging in the diagnosis and management of benign gynecological disorders. Studies retrieved from the literature search were imported into Rayyan software and quality assessment was performed using the Quality Assessment Tool for Artificial Intelligence-Centered Diagnostic Test Accuracy Studies (QUADAS-AI).

RESULTS

Of the 59 studies included, 12 were on polycystic ovary syndrome (PCOS), 11 were on infertility and assisted reproductive technology, 11 were on benign ovarian pathology (i.e. ovarian cysts, ovarian torsion, premature ovarian failure), 10 were on endometrial or myometrial pathology, nine were on pelvic floor disorder and six were on endometriosis. China was the most highly represented country (22/59 (37.3%)). According to QUADAS-AI, most studies were at high risk of bias for the subject selection domain (because the sample size, source or scanner model was not specified, data were not derived from open-source datasets and/or imaging preprocessing was not performed) and the index test domain (AI models were not validated externally), and at low risk of bias for the reference standard domain (the reference standard classified the target condition correctly) and the workflow domain (the time between the index test and the reference standard was reasonable). Most studies (40/59) developed and internally validated AI classification models for distinguishing between normal and pathological cases (i.e. presence vs absence of PCOS, pelvic endometriosis, urinary incontinence, ovarian cyst or ovarian torsion), whereas 19/59 studies aimed to automatically segment or measure ovarian follicles, ovarian volume, endometrial thickness, uterine fibroids or pelvic floor structures.

CONCLUSION

The published literature on AI applied to ultrasound in benign gynecological disorders is focused mainly on creating classification models to distinguish between normal and pathological cases, and on developing models to automatically segment or measure ovarian volume or follicles. © 2025 The Author(s). Ultrasound in Obstetrics & Gynecology published by John Wiley & Sons Ltd on behalf of International Society of Ultrasound in Obstetrics and Gynecology.

A risk prediction model for endometrial hyperplasia/endometrial carcinoma in premenopausal women

This study investigated the risk factors for endometrial hyperplasia (EH) and endometrial carcinoma (EC) in premenopausal women. The goal was to establish a nomogram model to predict the risk of EH/EC and quantitative standards in clinical practice, which improved the clinical prognosis of EH/EC patients. Data were collected from premenopausal women with suspected EH/EC who underwent hysteroscopic endometrial biopsy. Patients (n = 1541) were divided into training and validation groups at a 3:1 ratio. Univariable and multivariable logistic regression analyses were conducted to identify risk factors for EH/EC and establish a predictive model. The model's discrimination was evaluated using the area under the receiver operating characteristic curve (AUC), its calibration was assessed using calibration plots, and its clinical effectiveness was evaluated using decision curve analysis (DCA). The optimal score and probability cutoff values were determined to differentiate between low and high-risk populations, guiding clinical medical practice. BMI, age at menarche, intrauterine device (IUD), diabetes, polycystic ovary syndrome (PCOS), endometrial thickness (ET), and uterine cavity fluid were identified as independent risk factors for EH/EC and were incorporated into the predictive nomogram model. The model demonstrated good discrimination with AUCs of 0.845 and 0.905 in the training and validation sets, respectively. The calibration plots and DCA showed excellent model calibration and clinical effectiveness. EH/EC is significantly associated with BMI, age at menarche, IUD use, diabetes, PCOS, ET, and uterine cavity fluid. The nomogram model can be used to predict the risk of EH/EC in premenopausal women and facilitate rapid screening.

Role of artificial intelligence applied to ultrasound in gynecology oncology: A systematic review

The aim of this paper was to explore the role of artificial intelligence (AI) applied to ultrasound imaging in gynecology oncology. Web of Science, PubMed, and Scopus databases were searched. All studies were imported to RAYYAN QCRI software. The overall quality of the included studies was assessed using QUADAS-AI tool. Fifty studies were included, of these 37/50 (74.0%) on ovarian masses or ovarian cancer, 5/50 (10.0%) on endometrial cancer, 5/50 (10.0%) on cervical cancer, and 3/50 (6.0%) on other malignancies. Most studies were at high risk of bias for subject selection (i.e., sample size, source, or scanner model were not specified; data were not derived from open-source datasets; imaging preprocessing was not performed) and index test (AI models was not externally validated) and at low risk of bias for reference standard (i.e., the reference standard correctly classified the target condition) and workflow (i.e., the time between index test and reference standard was reasonable). Most studies presented machine learning models (33/50, 66.0%) for the diagnosis and histopathological correlation of ovarian masses, while others focused on automatic segmentation, reproducibility of radiomics features, improvement of image quality, prediction of therapy resistance, progression-free survival, and genetic mutation. The current evidence supports the role of AI as a complementary clinical and research tool in diagnosis, patient stratification, and prediction of histopathological correlation in gynecological malignancies. For example, the high performance of AI models to discriminate between benign and malignant ovarian masses or to predict their specific histology can improve the diagnostic accuracy of imaging methods.

Analysis of Characteristics of Endometrial Carcinoma in Peri- and Postmenopausal Women with Abnormal Uterine Bleeding

Objective

To analyze the menstrual characteristics of endometrial carcinoma and investigate whether abnormal uterine bleeding in the perimenopausal period differs from postmenopausal bleeding.

Methods

We conducted a retrospective analysis of 928 cases of endometrial carcinoma in patients admitted from January 2016 to December 2022. We gathered fundamental clinical data and analyzed distinct clinical risk factors between the perimenopausal and postmenopausal groups. Furthermore, we computed the statistical variances in menarche, regular menstrual cycles, and the duration of abnormal uterine bleeding.

Results

Perimenopausal patients with endometrial carcinoma exhibit similar factors to postmenopausal patients, especially if they have a history of menstrual cycles lasting more than 30 years, hypertension, abnormal uterine bleeding for over 1 year, and a high risk of endometrial carcinoma. Early intervention for abnormal uterine bleeding during the perimenopausal stage can prevent up to 80% of women from developing endometrial carcinoma.

Conclusion

Perimenopause women experiencing abnormal uterine bleeding should be mindful of the risk of endometrial carcinoma, as this awareness can substantially decrease the occurrence of the disease.

Risk stratification model integrating nutritional and inflammatory factors for predicting 1-year mortality after valvular heart surgery: a retrospective cohort study

INTRODUCTION

Existing risk-scoring systems for cardiac surgery include only standard preoperative factors without considering nutritional and inflammatory status or intraoperative factors. The objective of this study was to develop a comprehensive prediction model for mortality incorporating nutritional, inflammatory, and perioperative factors in patients undergoing valvular heart surgery.

MATERIALS AND METHODS

In this retrospective review of 2046 patients who underwent valvular heart surgery, Cox and LASSO regression analyses were performed to identify independent prognostic factors for 1-year postoperative mortality among various perioperative factors known to affect prognosis, including objective nutritional and inflammatory indices. A novel nomogram model incorporating selected prognostic factors was developed, and its discrimination ability was evaluated using the C-index. The model was validated in internal and external cohorts.

RESULTS

The 1-year mortality rate after valvular heart surgery was 5.1% (105 of 2046 patients) and was significantly associated with several preoperative objective inflammatory and nutritional indices. Cox and LASSO analyses identified the following five independent prognostic factors for mortality: monocyte-to-lymphocyte ratio (an objective inflammatory index), EuroSCORE II, Controlling Nutritional Status score, cardiopulmonary bypass time, and number of erythrocyte units transfused intraoperatively. The nomogram model incorporating these five factors had a C-index of 0.834 (95% CI: 0.791-0.877), which was higher than that of EuroSCORE II alone (0.744, 95% CI: 0.697-0.791) ( P <0.001). The nomogram achieved good discrimination ability, with C-indices of 0.836 (95% CI: 0.790-0.878) and 0.727 (95% CI: 0.651-0.803) in the internal and external validation cohorts, respectively, and showed well-fitted calibration curves.

CONCLUSIONS

A nomogram model incorporating five inflammatory, nutritional, and perioperative factors, as well as EuroSCORE II, was a better predictor of 1-year mortality after valvular heart surgery than EuroSCORE II alone, with good discrimination and calibration power for predicting mortality in both internal and external validation cohorts.

Rapid identification of endometrial hyperplasia and endometrial endometrioid cancer in young women

PURPOSE

We investigated endometrial hyperplasia (EH) and endometrial endometrioid cancer (EEC) and developed a nomogram model to predict the EH/EEC risk and improve patients' clinical prognosis.

METHODS

Data were collected from young females (age: ≤ 40 years) who complained of abnormal uterine bleeding (AUB) or abnormal ultrasound endometrial echoes. The patients were randomly divided into training and validation cohorts at a 7:3 ratio. The risk factors for EH/EEC were determined through the optimal subset regression analysis and a prediction model was developed. We used the concordance-index (C-index), and calibration plots in the training and validation sets to assess the prediction model. We drew the ROC curve in the validation set and calculated the area under the curve (AUC), as well as its accuracy, sensitivity, specificity, negative predictive value, and positive predictive value, and finally, converted the nomogram into a web page dynamic nomogram.

RESULTS

Predictors included in the nomogram model were body mass index (BMI), polycystic ovary syndrome (PCOS), anemia, infertility, menostaxis, AUB type, and endometrial thickness. The C-index of the model in the training and validation sets were 0.863 and 0.858. The nomogram model had good discriminatory power and was well-calibrated. According to the prediction model, the AUC of EH/EC, EH without atypia, and AH/EC were 0.889, 0.867, and 0.956, respectively.

CONCLUSIONS

The nomogram of EH/EC is significantly associated with risk factors, namely BMI, PCOS, anemia, infertility, menostaxis, AUB type, and endometrial thickness. The nomogram model can be used to predict the EH/EC risk and rapidly screen risk factors in a women population with high risk.