Establishment and validation of a nomogram model for predicting distant metastasis in medullary thyroid carcinoma: An analysis of the SEER database based on the AJCC 8th TNM staging system

Improved survival after primary tumor resection in distant metastasis medullary thyroid carcinoma: a population-based cohort study with propensity score matching

Few studies have investigated the impact of primary tumor resection (PTR) on patients with distant metastasis medullary thyroid carcinoma (DMMTC). This population-based study aims to assess the application of PTR in DMMTC patients, ascertain its benefits, and identify optimal surgical indications. DMMTC Patients diagnosed between 2010 and 2020 were included through the Surveillance, Epidemiology, and End Results (SEER) program. Logistic regression analysis identified driving factors of surgical decision-making. Propensity score matching (PSM), Kaplan-Meier method, and Cox regression were utilized to compare overall survival (OS) and disease-specific survival (DSS) between surgical and non-surgical groups. Subgroup analyses were performed to determine optimal surgical indications. Of 238 DMMTC patients included, 122 (51.3%) patients underwent PTR. Extrathyroidal extension and N1 stage emerged as independent factors promoting the surgical decision. PSM-adjusted survival analyses revealed significant advantages in both OS and DSS for the surgical group. Moreover, subgroup analyses indicated that except for patients aged ≥ 65 years, tumors ≤ 20 mm, or with multiple metastasized sites (> 1), the others significantly benefit from PTR. PTR significantly improves prognosis in selected DMMTC patients. The decision to undergo PTR in other patients should be based on a comprehensive assessment of the disease, surgeon's experience, and family discussions for potential survival benefits.

Machine learning based on SEER database to predict distant metastasis of thyroid cancer

OBJECTIVE

Distant metastasis of thyroid cancer often indicates poor prognosis, and it is important to identify patients who have developed distant metastasis or are at high risk as early as possible. This paper aimed to predict distant metastasis of thyroid cancer through the construction of machine learning models to provide a reference for clinical diagnosis and treatment.

MATERIALS & METHODS

Data on demographic and clinicopathological characteristics of thyroid cancer patients between 2010 and 2015 were extracted from the National Institutes of Health (NIH) Surveillance, Epidemiology, and End Results (SEER) database. Our research used univariate and multivariate logistic models to screen independent risk factors, respectively. Decision Trees (DT), ElasticNet (ENET), Logistic Regression (LR), Extreme Gradient Boosting (XGBoost), Random Forest (RF), Multilayer Perceptron (MLP), Radial Basis Function Support Vector Machine (RBFSVM) and seven machine learning models were compared and evaluated by the following metrics: the area under receiver operating characteristic curve (AUC), calibration curve, decision curve analysis (DCA), sensitivity(also called recall), specificity, precision, accuracy and F1 score. Interpretable machine learning was used to identify possible correlation between variables and distant metastasis.

RESULTS

Independent risk factors for distant metastasis, including age, gender, race, marital status, histological type, capsular invasion, and number of lymph nodes metastases were screened by multifactorial regression analysis. Among the seven machine learning algorithms, RF was the best algorithm, with an AUC of 0.948, sensitivity of 0.919, accuracy of 0.845, and F1 score of 0.886 in the training set, and an AUC of 0.960, sensitivity of 0.929, accuracy of 0.906, and F1 score of 0.908 in the test set.

CONCLUSIONS

The machine learning model constructed in this study helps in the early diagnosis of distant thyroid metastases and helps physicians to make better decisions and medical interventions.

Machine Learning for Predicting Distant Metastasis of Medullary Thyroid Carcinoma Using the SEER Database

Objectives

We aimed to establish an effective machine learning (ML) model for predicting the risk of distant metastasis (DM) in medullary thyroid carcinoma (MTC).

Methods

Demographic data of MTC patients were extracted from the Surveillance, Epidemiology, and End Results (SEER) database of the National Institutes of Health between 2004 and 2015 to develop six ML algorithm models. Models were evaluated based on accuracy, precision, recall rate, F1-score, and area under the receiver operating characteristic curve (AUC). The association between clinicopathological characteristics and target variables was interpreted. Analyses were performed using traditional logistic regression (LR).

Results

In total, 2049 patients were included and 138 developed DM. Multivariable LR showed that age, sex, tumor size, extrathyroidal extension, and lymph node metastasis were predictive features for DM in MTC. Among the six ML models, the random forest (RF) had the best predictability in assessing the risk of DM in MTC, with an accuracy, precision, recall rate, F1-score, and AUC higher than those of the traditional binary LR model.

Conclusion

RF was superior to traditional LR in predicting the risk of DM in MTC and can provide a valuable reference for clinicians in decision-making.

Early postoperative prediction of the risk of distant metastases in medullary thyroid cancer

Purpose

The purpose of this study was to develop and validate a nomogram for estimating the risk of distant metastases (DM) in the early postoperative phase of medullary thyroid cancer (MTC).

Patients and methods

We retrospectively reviewed cases of patients diagnosed with MTC from the Surveillance, Epidemiology, and End Results (SEER) database from 2007 to 2017. In addition, we gathered data on patients who diagnosed as MTC at Department of Thyroid Surgery in the First Hospital of Jilin University between 2009 and 2021. Four machine learning algorithms were used for modeling, including random forest classifier (RFC), gradient boosting decision tree (GBDT), logistic regression (LR), and support vector machine (SVM). The optimal model was selected based on accuracy, recall, specificity, receiver operating characteristic curve (ROC), and area under curve (AUC). After that, the Hosmer-Lemeshow goodness-of-fit test, the brier score (BS) and calibration curve were used for validation of the best model, which allowed us to measure the discrepancy between the projected value and the actual value.

Results

Through feature selection, we finally clarified that the following four features are associated with distant metastases of MTC, which are age, surgery, primary tumor (T) and nodes (N). The AUC values of the four models in the internal test set were as follows: random forest: 0.8786 (95% CI, 0.8070-0.9503), GBDT: 0.8402 (95% CI, 0.7606-0.9199), logistic regression: 0.8670(95%CI,0.7927-0.9413), and SVM: 0.8673 (95% CI, 0.7931-0.9415). As can be shown, there was no statistically significant difference in their AUC values. The highest AUC value of the four models were chosen as the best model since. The model was evaluated on the internal test set, and the accuracy was 0.84, recall was 0.76, and specificity was 0.87. The ROC curve was drawn, and the AUC was 0.8786 (95% CI, 0.8070-0.9503), which was higher than the other three models. The model was visualized using the nomogram and its net benefit was shown in both the Decision Curve Analysis (DCA) and Clinical Impact Curve (CIC).

Conclusion

Proposed model had good discrimination ability and could preliminarily screen high-risk patients for DM in the early postoperative period.

De-escalating chemotherapy for stage I-II gastric neuroendocrine carcinoma? A real-world competing risk analysis

BACKGROUND

The role of adjuvant chemotherapy in gastric neuroendocrine neoplasms (GNEC) has not been well clarified yet. The study was designed to investigate the potential effect of adjuvant chemotherapy in stage I-II GNEC patients and construct a predictive nomogram.

METHOD

Stage I-II GNEC patients were included in the Surveillance, Epidemiology, and End Results (SEER) database and divided into chemotherapy and no-chemotherapy groups. We used Kaplan-Meier survival analyses, propensity score matching (PSM), and competing risk analyses. The predictive nomogram was then built and validated.

RESULTS

Four hundred four patients with stage I-II GNEC were enrolled from the SEER database while 28 patients from Hangzhou TCM Hospital were identified as the external validation cohort. After PSM, similar 5-year cancer-specific survival was observed in two groups. The outcomes of competing risk analysis indicated a similar 5-year cumulative incidence of cancer-specific death (CSD) between the two cohorts (35.4% vs. 31.4%, p = 0.731). And there was no significant relation between chemotherapy and CSD in the multivariate competing risks regression analysis (HR, 0.79; 95% CI, 0.48-1.31; p = 0.36). Furthermore, based on the variables from the multivariate analysis, a competing event nomogram was created to assess the 1-, 3-, and 5-year risks of CSD. The 1-, 3-, and 5-year area under the receiver operating characteristic curve (AUC) values were 0.770, 0.759, and 0.671 in the training cohort, 0.809, 0.782, and 0.735 in the internal validation cohort, 0.786, 0.856, and 0.770 in the external validation cohort. Furthermore, calibration curves revealed that the expected and actual probabilities of CSD were relatively consistent.

CONCLUSION

Stage I-II GNEC patients could not benefit from adjuvant chemotherapy after surgery. De-escalation of chemotherapy should be considered for stage I-II GNEC patients. The proposed nomogram exhibited excellent prediction ability.