Incorporation of Tumor-Free Distance and Other Alternative Ultrasound Biomarkers into a Myometrial Invasion-Based Model Better Predicts Lymph Node Metastasis in Endometrial Cancer: Evidence and Future Prospects

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.

Tumor free distance from serosa and survival rates of endometrial cancer patients: A meta-analysis

Myometrial invasion and its extent have been directly associated with the risk of relapse as well as the overall survival of endometrial cancer patients. Tumor free distance from the serosal surface of the uterine wall has been investigated the last years by several studies, however, to date, its importance remains unknown. The present meta-analysis is based on a systematic search of the Medline, Scopus, Clinicaltrials.gov, EMBASE, Cochrane Central Register of Controlled Trials CENTRAL and Google Scholar databases and has been designed according to the PRISMA guidelines. Nine studies were included in the present systematic review that recruited pathology slides from 1,598 endometrial cancer patients and their meta-analysis indicated that TFD was significantly associated with the progression free survival of patients with endometrial cancer (OR 0.36, 95% CI 0.20, 0.65). The disease specific survival was not affected by the TFD (OR 0.30, 95% CI 0.09, 1.01). Sensitivity analyses revealed, however, that both the progression free and overall survival rates were associated with TFD. Significant discrepancies were observed in terms of histological subtypes and stage of the disease among included patients, hence, the actual importance of TFD in specific subgroups remains unknown. Future studies must evaluate the importance of this pathology marker particularly in patients with endometrioid subtypes and early-stage disease, as it is believed that in this group its importance will be more predictive as it will not be skewed by the presence of more important factors such as more aggressive histology and advanced stage disease.