Background: Central lymph node metastasis (CLNM) occurs frequently in patients with papillary thyroid cancer (PTC), but performing prophylactic central lymph node dissection is still controversial. There are no reliable models for predicting CLNM. This study aimed to develop predictive models for CLNM by machine learning (ML) algorithms. Methods: Patients with PTC who underwent initial thyroid resection at our hospital between January 2018 and December 2019 were enrolled. A total of 22 variables, including clinical characteristics and ultrasonography (US) features, were used for conventional univariate and multivariate analysis and to construct ML-based models. A 5-fold cross validation strategy was used for validation and a feature selection approach was applied to identify risk factors. Results: The areas under the receiver operating characteristic curve (AUC) of 7 models ranged from 0.680 to 0.731. All models performed significantly better than US (AUC=0.623) in predicting CLNM (P<0.05). In decision curve, most of the models also performed better than US. The gradient boosting decision tree model with 7 variables was identified as the best model because of its best performance in both ROC (AUC=0.731) and decision curves. Based on multivariate analysis and feature selection, young age, male sex, low serum thyroid peroxidase antibody and US features such as suspected lymph nodes, microcalcification and tumor size > 1.1 cm were the most contributing predictors for CLNM. Conclusions: It is feasible to develop predictive models of CLNM in PTC patients by incorporating clinical characteristics and US features. The ML algorithm may be a useful tool for the prediction of lymph node metastasis in thyroid cancer.
Background
This study aimed to examine the treatment and prognosis of patients with type B2 + B3 thymoma and compare it with those patients with type B2 and B3 thymoma.
Methods
We conducted a retrospective analysis of the results of 39 patients with type B2 + B3 thymoma, 133 patients with type B2 thymoma, and 64 patients with type B3 thymoma. The Kaplan–Meier technique was used to generate survival curves. For multivariate analysis, the Cox proportional hazard model was applied.
Results
With a median follow‐up of 60 months (range: 1–128 months), the percentage of patients with tumor, node, metastasis (TNM) stage III and IV disease gradually increased from 19.5% to 25.6% to 35.9% among those with histological subtypes B2, B2 + B3, and B3, respectively, p = 0.045. Twenty‐three patients experienced recurrence or metastasis. The total 10‐year progression‐free survival (PFS) rates were 86.0% overall (85.0% in type B2, 87.2% in type B2 + B3, and 87.5% in type B3). Age, R0 resection, and Masaoka–Koga stage were found to have a significant on PFS in all patients. There was no statistically significant difference in PFS between different histotypes of thymoma, p = 0.650. PFS was predicted by R0 resection in all histotypes and by the Masaoka–Koga stage in the type B2 subgroup.
Conclusion
Combining the two staging methods to guide the diagnosis and treatment of patients with B2 + B3 thymoma is recommended. R0 resection is recommended to reduce recurrence. Patients with B2 + B3 thymoma have a prognosis similar to those with a B2 thymoma or a B3 thymoma alone.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.