The patterns of distant metastasis and prognostic factors in patients with primary metastatic Ewing sarcoma of the bone

Stereotactic Body Radiation Therapy and Concurrent Targeted Therapy for Lung Metastases in Pediatric Sarcoma

Purpose

The purpose of this investigation was to evaluate the efficacy and safety of stereotactic body radiation therapy (SBRT) for pulmonary metastases from pediatric sarcomas.

Methods and Materials

This study was a single institutional retrospective chart review including patients younger than 21 years of age at diagnosis who had received SBRT for pulmonary metastasis from metastatic sarcoma. Our current electronic record system was queried for all eligible patients. Primary endpoint was tumor response as defined by Respone Evaluation Criteria in Solid Tumors 1.1 criteria. Secondarily, we analyzed factors that affected tumor response as well as toxicity of treatment. Median dose was 50 Gy ranging from 30 to 60 Gy in 5 fractions to the planning tumor volume.

Results

There were 7 patients, ranging in age from 6 to 21 years with a total of 14 pulmonary lesions treated with SBRT. Median and mean follow-up times for the 7 patients were 10.6 months and 15.9 months, respectively. The complete response rate was 50%, partial response 21%, stable disease 21%, and progressive disease 7%. Four of the 7 patients were treated with concurrent systemic therapy, 3 of which were targeted oral therapies. Additionally, we observed that patients who were on targeted therapy such as regorafenib or pazopanib seemed to have better local control compared with patients without targeted therapy.

Conclusions

With an overall response rate of 92%, SBRT provided a noninvasive effective palliative treatment option with few side effects in this small retrospective study of 7 patients. A larger prospective clinical trial is warranted to evaluate the role of SBRT in the treatment of unresectable metastatic pediatric sarcomas.

A machine learning-based model for clinical prediction of distal metastasis in chondrosarcoma: a multicenter, retrospective study

Background

The occurrence of distant metastases (DM) limits the overall survival (OS) of patients with chondrosarcoma (CS). Early diagnosis and treatment of CS remains a great challenge in clinical practice. The aim of this study was to investigate metastatic factors and develop a risk stratification model for clinicians' decision-making.

Methods

Six machine learning (ML) algorithms, including logistic regression (LR), plain Bayesian classifier (NBC), decision tree (DT), random forest (RF), gradient boosting machine (GBM) and extreme gradient boosting (XGBoost). A 10-fold cross-validation was performed for each model separately, multicenter data was used as external validation, and the best (highest AUC) model was selected to build the network calculator.

Results

A total of 1,385 patients met the inclusion criteria, including 82 (5.9%) patients with metastatic CS. Multivariate logistic regression analysis showed that the risk of DM was significantly higher in patients with higher pathologic grades, T-stage, N-stage, and non-left primary lesions, as well as those who did not receive surgery and chemotherapy. The AUC of the six ML algorithms for predicting DM ranged from 0.911-0.985, with the extreme gradient enhancement algorithm (XGBoost) having the highest AUC. Therefore, we used the XGB model and uploaded the results to an online risk calculator for estimating DM risk.

Conclusions

In this study, combined with adequate SEER case database and external validation with data from multicenter institutions in different geographic regions, we confirmed that CS, T, N, laterality, and grading of surgery and chemotherapy were independent risk factors for DM. Based on the easily available clinical risk factors, machine learning algorithms built the XGB model that predicts the best outcome for DM. An online risk calculator helps simplify the patient assessment process and provides decision guidance for precision medicine and long-term cancer surveillance, which contributes to the interpretability of the model.

The clinical characteristics, novel predictive tool, and risk classification system for primary Ewing sarcoma patients that underwent chemotherapy: A large population-based retrospective cohort study

BACKGROUND

This study aims to determine the independent prognostic predictors of cancer-specific survival (CSS) in patients with primary Ewing sarcoma (ES) that underwent chemotherapy and create a novel prognostic nomogram and risk stratification system.

METHODS

Demographic and clinicopathologic characteristics related to patients with primary ES that underwent chemotherapy between 2000 and 2018 were extracted from the Surveillance, Epidemiology, and End Results (SEER) database. CSS was the primary endpoint of this study. First, independent prognostic predictors of CSS identified from univariate and multivariate Cox regression analyses were used to construct a prognostic nomogram for predicting 1-, 3-, and 5-year CSS of patients with primary ES that underwent chemotherapy. Then, calibration curves and receiver operating characteristic (ROC) curves were used to evaluate the nomogram's prediction accuracy, while decision curve analysis (DCA) was used to evaluate the nomogram's clinical utility. Finally, a mortality risk stratification system was constructed for this subpopulation.

RESULTS

A total of 393 patients were included in this study. Age, tumor size, bone metastasis, and surgery were independent prognostic predictors of CSS. The calibration curves, ROC, and DCA showed that the nomogram had excellent discrimination and clinical value, with the 1-, 3-, and 5-year AUCs higher than 0.700. Moreover, the mortality risk stratification system could effectively divide all patients into three risk subgroups and achieve targeted patient management.

CONCLUSIONS

Based on the SEER database, a novel prognostic nomogram for predicting 1-, 3-, and 5- year CSS in patients with primary ES that underwent chemotherapy has been constructed and validated. The nomogram showed relatively good performance, which could be used in clinical practice to assist clinicians in individualized treatment strategies.

Application of an Interpretable Machine Learning Model to Predict Lymph Node Metastasis in Patients with Laryngeal Carcinoma

Objectives

A more accurate preoperative prediction of lymph node metastasis (LNM) plays a decisive role in the selection of treatment in patients with laryngeal carcinoma (LC). This study aimed to develop a machine learning (ML) prediction model for predicting LNM in patients with LC.

Methods

We collected and retrospectively analysed 4887 LC patients with detailed demographical characteristics including age at diagnosis, race, sex, primary site, histology, number of tumours, T-stage, grade, and tumour size in the National Institutes of Health (NIH) Surveillance, Epidemiology, and End Results (SEER) database from 2005 to 2015. A correlation analysis of all variables was evaluated by the Pearson correlation. Independent risk factors for LC patients with LNM were identified by univariate and multivariate logistic regression analyses. Afterward, patients were randomly divided into training and test sets in a ratio of 8 to 2. On this basis, we established logistic regression (LR), k-nearest neighbor (KNN), support vector machine (SVM), extreme gradient boosting (XGBoost), random forest (RF), and light gradient boosting machine (LightGBM) algorithm models based on ML. The area under the receiver operating characteristic curve (AUC) value, accuracy, precision, recall rate, F1-score, specificity, and Brier score was adopted to evaluate and compare the prediction performance of the models. Finally, the Shapley additive explanation (SHAP) method was used to interpret the association between each feature variable and target variables based on the best model.

Results

Of the 4887 total LC patients, 3409 were without LNM (69.76%), and 1478 had LNM (30.24%). The result of the Pearson correlation showed that variables were weakly correlated with each other. The independent risk factors for LC patients with LNM were age at diagnosis, race, primary site, number of tumours, tumour size, grade, and T-stage. Among six models, XGBoost displayed a better performance for predicting LNM, with five performance metrics outperforming other models in the training set (AUC: 0.791 (95% CI: 0.776–0.806), accuracy: 0.739, recall rate: 0.638, F1-score: 0.663, and Brier score: 0.165), and similar results were observed in the test set. Moreover, the SHAP value of XGBoost was calculated, and the result showed that the three features, T-stage, primary site, and grade, had the greatest impact on predicting the outcomes.

Conclusions

The XGBoost model performed better and can be applied to forecast the LNM of LC, offering a valuable and significant reference for clinicians in advanced decision-making.

A Machine Learning-Based Predictive Model for Predicting Lymph Node Metastasis in Patients With Ewing's Sarcoma

Objective

In order to provide reference for clinicians and bring convenience to clinical work, we seeked to develop and validate a risk prediction model for lymph node metastasis (LNM) of Ewing’s sarcoma (ES) based on machine learning (ML) algorithms.

Methods

Clinicopathological data of 923 ES patients from the Surveillance, Epidemiology, and End Results (SEER) database and 51 ES patients from multi-center external validation set were retrospectively collected. We applied ML algorithms to establish a risk prediction model. Model performance was checked using 10-fold cross-validation in the training set and receiver operating characteristic (ROC) curve analysis in external validation set. After determining the best model, a web-based calculator was made to promote the clinical application.

Results

LNM was confirmed or unable to evaluate in 13.86% (135 out of 974) ES patients. In multivariate logistic regression, race, T stage, M stage and lung metastases were independent predictors for LNM in ES. Six prediction models were established using random forest (RF), naive Bayes classifier (NBC), decision tree (DT), xgboost (XGB), gradient boosting machine (GBM), logistic regression (LR). In 10-fold cross-validation, the average area under curve (AUC) ranked from 0.705 to 0.764. In ROC curve analysis, AUC ranged from 0.612 to 0.727. The performance of the RF model ranked best. Accordingly, a web-based calculator was developed (https://share.streamlit.io/liuwencai2/es_lnm/main/es_lnm.py).

Conclusion

With the help of clinicopathological data, clinicians can better identify LNM in ES patients. Risk prediction models established in this study performed well, especially the RF model.

A SEER-based nomogram accurately predicts prognosis in Ewing's sarcoma

Ewing's sarcoma is a high-grade malignancy bone and soft tissue tumor that most commonly occurs in children and adolescents. Although the overall prognosis of Ewing's sarcoma has improved, the 5-year survival rate has not improved significantly. The study aimed to determine the risk factors independently associated with the prognosis of Ewing's sarcoma and to construct a nomogram to predict patient survival. Patients diagnosed with Ewing's sarcoma were collected from the Surveillance, Epidemiology, and End Results program database between 2004 and 2015 and further divided into training and validation cohort. Univariate and multivariate Cox regression analyses were used to identify meaningful independent prognostic factors. The nomogram was used to predict 3- and 5-year overall survival (OS) and cancer-specific survival (CSS). Finally, the nomogram was verified internally and externally through the training and validation cohorts, and the predictive capability was evaluated using the receiver operating characteristic (ROC) curve, C-index, and calibration curve and compared with that of the 7th TNM stage. A total of 1120 patients were divided into training (n = 713) and validation (n = 407) cohorts. Based on the multivariate analysis of the training cohort, a nomogram that integrated age, tumor size, primary site, N stage, and M stage was constructed (P < 0.05). The predicted C-indexes of OS and CSS of the training cohort were 0.744 (95% CI 0.717–0.771) and 0.743 (95% CI 0.715–0.770), respectively. However, the TNM stage had a C-index of 0.695 (95% CI 0.666–0.724) and 0.698 (95% CI 0.669–0.727) for predicting OS and CSS, respectively. The nomogram showed higher C-indexes than those in the TNM stage. Furthermore, the internal and external calibration curves showed good consistency between the predicted and observed values. Age, tumor size, primary site, N stage, and M stage are independent risk factors affecting the OS and CSS in Ewing’s sarcoma patients. Compared with the 7th TNM staging, the nomogram consisting of these factors was more accurate for risk assessment and survival prediction in patients with Ewing’s sarcoma, thus providing a novel reliable tool for risk assessment and survival prediction in Ewing’s sarcoma patients.