A predictive model with a risk-classification system for cancer-specific survival in patients with primary osteosarcoma of long bone

Ensemble learning guided survival prediction and chemotherapy benefit analysis in high-grade chondrosarcoma: A study based on the surveillance, epidemiology, and end results (SEER) database

Purpose: The chemotherapy benefit for high-grade chondrosarcoma remains controversial. Ensemble learning has better overall performance than single computational approaches for clinical decision. The primary objective was to select prognostic variables and develop optimal ensemble learning algorithms for survival prediction and analyzing chemotherapy benefit in high-grade chondrosarcoma. The secondary objective included identifying specific patient groups with estimated survival benefit for guidance in chemotherapy strategies. Methods: The data of 1931 patients with chondrosarcoma from 2000 to 2019 were obtained from the Surveillance, Epidemiology, and End Results database to conduct the retrospective analysis. Among 468 patients with high-grade chondrosarcoma, cox proportional hazards models and random survival forests were used for feature selection. Ensemble learning and survival support vector machine with different kernel methods were developed and compared for their prognostic performance. Results: Ensemble learning outperformed the single models, with the concordance index reaching 0.764 (based on inverse probability of censoring weights) and the mean area under time-dependent receiver operating characteristic curve of 0.851. According to the ensemble model, overall survival generally improved in younger patients after chemotherapy. Age-stratified analysis revealed differential chemotherapy benefits across various clinical subgroups. Survival benefits were observed in: Age ≤ 10 with dedifferentiated chondrosarcoma, amputation, local surgical treatment, absence of distant metastasis, or grade III tumor; Age ≤ 20 who were male with clear cell chondrosarcoma, non-axial primary sites, or no radiotherapy; Age ≤ 30 who were female with primary site at pelvis/limb, received radiotherapy, extension beyond periosteum, further extension, or distant metastasis; Age≤40 with chondrosarcoma NOS (including mesenchymal, juxtacortical and classical chondrosarcoma); Age ≤ 50 with grade IV tumor or no surgery received. Conclusion: Ensemble learning algorithms demonstrate outstanding overall performance in prognostic assessment of high-grade chondrosarcoma and identification of age-specific factors associated with chemotherapy benefit for tailored chemotherapy strategy.

Inhibiting Bruton's Tyrosine Kinase to Counteract Chemoresistance and Stem Cell-Like Properties in Osteosarcoma

Osteosarcoma, a highly aggressive bone cancer, often develops resistance to conventional chemotherapeutics, leading to poor prognosis and survival rates. The malignancy and chemoresistance of osteosarcoma pose significant challenges in its treatment, highlighting the critical need for novel therapeutic approaches. Bruton's tyrosine kinase (BTK) plays a pivotal role in B-cell development and has been linked to various cancers, including breast, lung, and oral cancers, where it contributes to tumor growth and chemoresistance. Despite its established importance in these malignancies, the impact of BTK on osteosarcoma remains unexplored. Our study delves into the expression levels of BTK in osteosarcoma tissues by data from the GEO and TCGA database, revealing a marked increase in BTK expression compared with primary osteoblasts and a potential correlation with primary site progression. Through our investigations, we identified a subset of osteosarcoma cells, named cis-HOS, which exhibited resistance to cisplatin. These cells displayed characteristics of cancer stem cells (CSCs), demonstrated a higher angiogenesis effect, and had an increased migration ability. Notably, an upregulation of BTK was observed in these cisplatin-resistant cells. The application of ibrutinib, a BTK inhibitor, significantly mitigated these aggressive traits. Our study demonstrates that BTK plays a crucial role in conferring chemoresistance in osteosarcoma. The upregulation of BTK in cisplatin-resistant cells was effectively countered by ibrutinib. These findings underscore the potential of targeting BTK as an effective strategy to overcome chemoresistance in osteosarcoma treatment.

A deep learning model for accurately predicting cancer-specific survival in patients with primary bone sarcoma of the extremity: a population-based study

PURPOSE

Primary bone and joint sarcomas of the long bone are relatively rare neoplasms with poor prognosis. An efficient clinical tool that can accurately predict patient prognosis is not available. The current study aimed to use deep learning algorithms to develop a prediction model for the prognosis of patients with long bone sarcoma.

METHODS

Data of patients with long bone sarcoma in the extremities was collected from the Surveillance, Epidemiology, and End Results Program database from 2004 to 2014. Univariate and multivariate analyses were performed to select possible prediction features. DeepSurv, a deep learning model, was constructed for predicting cancer-specific survival rates. In addition, the classical cox proportional hazards model was established for comparison. The predictive accuracy of our models was assessed using the C-index, Integrated Brier Score, receiver operating characteristic curve, and calibration curve.

RESULTS

Age, tumor extension, histological grade, tumor size, surgery, and distant metastasis were associated with cancer-specific survival in patients with long bone sarcoma. According to loss function values, our models converged successfully and effectively learned the survival data of the training cohort. Based on the C-index, area under the curve, calibration curve, and Integrated Brier Score, the deep learning model was more accurate and flexible in predicting survival rates than the cox proportional hazards model.

CONCLUSION

A deep learning model for predicting the survival probability of patients with long bone sarcoma was constructed and validated. It is more accurate and flexible in predicting prognosis than the classical CoxPH model.

Predicting overall survival in chordoma patients using machine learning models: a web-app application

OBJECTIVE

The goal of this study was to evaluate the efficacy of machine learning (ML) techniques in predicting survival for chordoma patients in comparison with the standard Cox proportional hazards (CoxPH) model.

METHODS

Using a Surveillance, Epidemiology, and End Results database of consecutive newly diagnosed chordoma cases between January 2000 and December 2018, we created and validated three ML survival models as well as a traditional CoxPH model in this population-based cohort study. Randomly, the dataset was divided into training and validation datasets. Tuning hyperparameters on the training dataset involved a 1000-iteration random search with fivefold cross-validation. Concordance index (C-index), Brier score, and integrated Brier score were used to evaluate the performance of the model. The receiver operating characteristic (ROC) curves, calibration curves, and area under the ROC curves (AUC) were used to assess the reliability of the models by predicting 5- and 10-year survival probabilities.

RESULTS

A total of 724 chordoma patients were divided into training (n = 508) and validation (n = 216) cohorts. Cox regression identified nine significant prognostic factors (p < 0.05). ML models showed superior performance over CoxPH model, with DeepSurv having the highest C-index (0.795) and the best discrimination for 5- and 10-year survival (AUC 0.84 and 0.88). Calibration curves revealed strong correlation between DeepSurv predictions and actual survival. Risk stratification by DeepSurv model effectively discriminated high- and low-risk groups (p < 0.01). The optimized DeepSurv model was implemented into a web application for clinical use that can be found at https://hust-chengp-ml-chordoma-app-19rjyr.streamlitapp.com/ .

CONCLUSION

ML algorithms based on time-to-event results are effective in chordoma prediction, with DeepSurv having the best discrimination performance and calibration.

Risk stratification system and web-based nomogram constructed for predicting the overall survival of primary osteosarcoma patients after surgical resection

Background

Previous prediction models of osteosarcoma have not focused on survival in patients undergoing surgery, nor have they distinguished and compared prognostic differences among amputation, radical and local resection. This study aimed to establish and validate the first reliable prognostic nomogram to accurately predict overall survival (OS) after surgical resection in patients with osteosarcoma. On this basis, we constructed a risk stratification system and a web-based nomogram.

Methods

We enrolled all patients with primary osteosarcoma who underwent surgery between 2004 and 2015 in the Surveillance, Epidemiology, and End Results (SEER) database. In patients with primary osteosarcoma after surgical resection, univariate and multivariate cox proportional hazards regression analyses were utilized to identify independent prognostic factors and construct a novel nomogram for the 1-, 3-, and 5-year OS. Then the nomogram's predictive performance and clinical utility were evaluated by the concordance index (C-index), receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA).

Result

This study recruited 1,396 patients in all, with 837 serving as the training set (60%) and 559 as the validation set (40%). After COX regression analysis, we identified seven independent prognostic factors to develop the nomogram, including age, primary site, histological type, disease stage, AJCC stage, tumor size, and surgical method. The C-index indicated that this nomogram is considerably more accurate than the AJCC stage in predicting OS [Training set (HR: 0.741, 95% CI: 0.726–0.755) vs. (HR: 0.632, 95% CI: 0.619–0.645); Validation set (HR: 0.735, 95% CI: 0.718–0.753) vs. (HR: 0.635, 95% CI: 0.619–0.652)]. Moreover, the area under ROC curves, the calibration curves, and DCA demonstrated that this nomogram was significantly superior to the AJCC stage, with better predictive performance and more net clinical benefits.

Conclusion

This study highlighted that radical surgery was the first choice for patients with primary osteosarcoma since it provided the best survival prognosis. We have established and validated a novel nomogram that could objectively predict the overall survival of patients with primary osteosarcoma after surgical resection. Furthermore, a risk stratification system and a web-based nomogram could be applied in clinical practice to assist in therapeutic decision-making.