Establishment and evaluation of a risk-scoring system for lymph node metastasis in early-stage endometrial carcinoma: Achieving preoperative risk stratification

Risk factors for pelvic and para-aortic lymph node metastasis in non-endometrioid endometrial cancer

PURPOSE

The aim of this study was to evaluate the risk factors for pelvic lymph node metastasis (LNM) and para-aortic LNM in non-endometrioid endometrial cancer (non-EEC).

METHODS

A total of 283 patients with non-EEC hospitalized in the First Affiliated Hospital of Zhengzhou University from January 2012 to December 2020 were included. Various characteristics were retrospectively analyzed in relation to LNM.

RESULTS

Univariable and multivariable logistic regression analysis revealed cervical stromal invasion (OR = 3.441, 95% CI = 1.558-7.6, p = 0.002), myometrial invasion ≥1/2 (OR = 2.661, 95% CI = 1.327-5.337, p < 0.006), lymphovascular space involvement (LVSI) (OR = 4.118, 95% CI = 1.919-8.837, p < 0.001), positive peritoneal cytology (OR = 2.962, 95% CI = 1.344-6.530, p = 0.007), CA125 (OR = 1.002, 95% CI = 1-1.004, p = 0.026) were the independent risk factors for pelvic LNM. And myometrial invasion ≥1/2 (OR = 5.881, 95% CI = 2.056-16.427, p = 0.001), LVSI (OR = 4.962, 95% CI = 1.933-12.740, p = 0.001), adnexal (OR = 5.921, 95% CI = 2.003-17.502, p = 0.001) were the independent risk factors for para-aortic LNM. With the increase of independent risk factors, the rates of LNM were increased significantly.

CONCLUSIONS

Cervical stromal invasion, myometrial invasion ≥1/2, LVSI, positive peritoneal cytology, and CA125 were risk factors for pelvic LNM. Myometrial invasion ≥1/2, LVSI and involvement of the adnexa were risk factors for para-aortic LNM which could provide a good basis to help predict which non-EEC patients are at higher risk for LNM.

The value of machine learning in preoperative identification of lymph node metastasis status in endometrial cancer: a systematic review and meta-analysis

Background

The early identification of lymph node metastasis status in endometrial cancer (EC) is a serious challenge in clinical practice. Some investigators have introduced machine learning into the early identification of lymph node metastasis in EC patients. However, the predictive value of machine learning is controversial due to the diversity of models and modeling variables. To this end, we carried out this systematic review and meta-analysis to systematically discuss the value of machine learning for the early identification of lymph node metastasis in EC patients.

Methods

A systematic search was conducted in Pubmed, Cochrane, Embase, and Web of Science until March 12, 2023. PROBAST was used to assess the risk of bias in the included studies. In the process of meta-analysis, subgroup analysis was performed according to modeling variables (clinical features, radiomic features, and radiomic features combined with clinical features) and different types of models in various variables.

Results

This systematic review included 50 primary studies with a total of 103,752 EC patients, 12,579 of whom had positive lymph node metastasis. Meta-analysis showed that among the machine learning models constructed by the three categories of modeling variables, the best model was constructed by combining radiomic features with clinical features, with a pooled c-index of 0.907 (95%CI: 0.886-0.928) in the training set and 0.823 (95%CI: 0.757-0.890) in the validation set, and good sensitivity and specificity. The c-index of the machine learning model constructed based on clinical features alone was not inferior to that based on radiomic features only. In addition, logistic regression was found to be the main modeling method and has ideal predictive performance with different categories of modeling variables.

Conclusion

Although the model based on radiomic features combined with clinical features has the best predictive efficiency, there is no recognized specification for the application of radiomics at present. In addition, the logistic regression constructed by clinical features shows good sensitivity and specificity. In this context, large-sample studies covering different races are warranted to develop predictive nomograms based on clinical features, which can be widely applied in clinical practice.

Systematic review registration

https://www.crd.york.ac.uk/PROSPERO, identifier CRD42023420774.

Artificial Intelligence and Big Data Technologies in the Construction of Surgical Risk Prediction Model for Patients with Coronary Artery Bypass Grafting

The objective of this work was to predict the risk of mortality rate in patients with coronary artery bypass grafting (CABG) based on the risk prediction model of CABG using artificial intelligence (AI) and big data technologies. The clinical data of 2,364 patients undergoing CABG in our hospital from January 2019 to August 2021 were collected in this work. Based on AI and big data technology, business requirement analysis, system requirement analysis, complication prediction module, big data mining technology, and model building are carried out, respectively; the successful CABG risk prediction system includes case feature analysis service, risk warning service, and case retrieval service. The commonly used precision, recall, and F1-score were adopted to evaluate the quality of the gradient-boosted tree (GBT) model. The analysis proved that the GBT model was the best in terms of precision, F1-score, and area under the receiver operating characteristic curve (ROC). According to the CABG risk prediction model, 1,382 patients had a score of <0, 463 patients had a score of 0 ≤ score ≤ 2, 252 patients had a score of 2 < score ≤ 5, and 267 patients had a score of >5, which were stratified into four groups: A, B, C, and D. The actual number of in-hospital deaths was 25, and the in-hospital mortality rate was 1.05%. The mortality rate predicted by the CABG risk prediction model was 2.67 ± 1.82% (95% confidential interval (CI) (2.87-2.98)), which was higher than the actual value. The CABG risk prediction model showed the credible results only in group B with AUC = 0.763 > 0.7. In group B, 3 patients actually died, the actual mortality rate was 0.33%, and the predicted mortality rate was 0.96 ± 0.78 (95% CI (0.82-0.87)), which overestimated the mortality rate of patients in group B. It successfully constructed a CABG risk prediction model based on the AI and big data technologies, which would overestimate the mortality of patients with intermediate risk, and it is suitable for different types of heart diseases through continuous research and development and innovation, and provides clinical guidance value.

Construction and Evaluation of a Clinical Prediction Scoring System for Positive Cervical Margins Under Colposcopy

Introduction

Currently, the commonly used surgical methods for cervical lesions include loop electrosurgical excision procedure (LEEP) and cold knife conization (CKC). However, the positive rate of surgical margins after LEEP is relatively high, which leads to disease recurrence and places further demand on clinical treatment. This study investigated factors related to positive margins after LEEP and established a scoring system to enhance preoperative risk assessment and surgical selection.

Materials and Methods

A retrospective analysis of the clinical data of 411 patients undergoing LEEP surgery for cervical lesions in the First Affiliated Hospital of University of Science and Technology of China (USTC), from January 2016 to March 2021, was performed. Cases were divided into a negative margin group (349 cases) and a positive margin group according to postoperative pathology. In the positive group (62 cases), single-factor and multi-factor analyses screened influencing factors; a logistic and additive scoring system was established; furthermore, a ROC curve was used to evaluate scoring effectiveness.

Results

The positive rate of resection margins after LEEP was 15.1%. Univariate analysis indicated a relationship to patient age, menopause, preoperative ThinPrep Cytology Test (TCT) results, lesion quadrant number under colposcopy, cervical biopsy, and the result of endocervical curettage (ECC). Multivariate analysis showed that age >35 y, menopause, preoperative TCT being high-grade squamous intraepithelial lesion (HSIL), four quadrants being involved under colposcopy, and ECC being HSIL were all independent influencing factors of positive margins after LEEP (P < 0.05). These were included with the above factors to establish a logistic and additive scoring system. When the logistic score was 17, the sensitivity and specificity of predicting positive margins after LEEP were 80.6 and 61.6%, respectively. When the additive score was 6, the sensitivity and specificity were 74.2 and 66.2%, respectively. Both scoring systems had good predictability (area under the curve AUC >0.75).

Conclusions

This study quantified factors influencing positive margins after LEEP and established a scoring system for evaluating patients before surgery to provide a basis for individualized treatment and selection of surgical methods.

Clinical features related to lymphatic metastasis in grade 3 endometroid endometrial cancer: a retrospective cross-sectional study

BACKGROUND

Endometrial cancer (EC) has been one of the most general cancers with respect to gynecological malignancies; however, there are debates on clinical strategies concerning treatments especially for patients with grade 3 (G3) endometroid endometrial cancer (EEC). Present study aimed to evaluate the lymphatic metastasis (LM) related factors and figure out the necessity of lymphadenectomy for G3 EEC patients.

METHODS

From January 2009 to April 2019, 3751 EC patients were admitted to Obstetrics and Gynecology Hospital of Fudan University. Clinical characteristics include age, grade, stage, and clinical pathological features. A total of 1235 EEC patients were involved in the multivariable analysis. Three hundred and eighty-one patients were involved in the survival analysis and the data attributed to sufficient follow-up information. Kaplan-Meier curve and log-rank test were utilized to analyze the survival rate.

RESULTS

Among the 1235 EEC patients, 181 (14.7%) were categorized as G3 and 1054 (85.3%) were grade 1 to grade 2 (G1-2). Multivariate analysis demonstrated that lymphovascular space invasion, adnexal involvement, and cervical stroma involvement were independent risk factors of LM in G3 cohort with odds ratio 3.4, 5.8, and 8.9; 95% confidence interval 1.1-10.6, 1.5-22.4, and 2.8-28.0, respectively. LM rates increased from 3.3% (3/92) to 75% (9/12) for G3 EEC cohort as related factor numbers increased from one to three. There were no differences between G3 and G1-2 EEC in overall survival and progression free survival. Additionally, no survival advantage was observed for G3 EEC patients at early stage with different plans of adjuvant treatment.

CONCLUSIONS

For G3 EEC patients without other pathological positive factor, the LM rate is lower than those with other pathological positive factor. Survival analysis showed no difference between G3 cohort and G1-2 cohort. Also, different adjuvant treatments had no impact on the overall survival for G3 EEC patients.