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

Abstract

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.

Keywords

chemotherapy high-grade chondrosarcoma ensemble learning machine learning survival SEER

Brief introduction

Chondrosarcoma accounts for nearly one-third of adult musculoskeletal malignant tumors and its incidence ranks the second only to osteosarcoma.^1–3 Histologically, chondrosarcomas are characterized by non‐osteoid cartilage matrix produced by neoplastic cells, including primary chondrosarcomas derived from sporadic mutations and secondary chondrosarcomas originating from malignant transformations of benign cartilaginous lesions, such as osteochondromas or enchondromas.^4,5 The histological grade is one of the most powerful prognostic factors for overall survival (OS), metastasis and recurrence. Lower-grade tumors with less cellularity, rich cartilage matrix and poor metastatic behavior are prone to favorable outcomes after surgical curettage or resection, with survival rates between 88.5% and 95.8% at 5 years.^3,6,7 On the other hand, metastatic relapse was observed in 70% of higher-grade cases, and advanced cases exhibited a higher grade of malignancy, with the median OS reported as poor as 18 months.^6,8,9 Patients with higher-grade chondrosarcomas, especially in advanced clinical settings, might be insensitive or even resistant to conventional chemotherapy.^4,8,10 At present, few prognostic studies have focused on the efficacy of chemotherapy for higher-grade tumors.

Tumor size, stage, pathological subtype, age, location and margin status are among the key prognostic indicators that have been identified to influence the survival of patients with chondrosarcoma.^1,2,11,12 However, the clinical profiles of patients have changed due to the evolution of treatment regimes in recent years, which affects the reliability of previously published studies.^2,4 On the other hand, owing to the low morbidity and scarcity of several pathological types, most investigations were subjected to single-institution series with limited sample size, which makes clinical decision-making and survival prediction difficult.^11,13–15 The large multi‐institutional datasets provided by the Surveillance, Epidemiology, and End Results (SEER) database ensure statistical power and population‐level representation of the rarity such as chondrosarcoma.¹⁶ The analysis of the SEER database will surely be a practical way to investigate the characteristics of chondrosarcoma in a modern context. The SEER database has been kept up-to-date with new cases enrolled over the past decade. To date, no study has comprehensively evaluated the prognosis of high-grade chondrosarcoma via assessing the latest edition of the SEER database.

The Cox proportional hazards (CoxPH) model is widely accepted for integrating and measuring significant clinical factors of patients when evaluating the odds of occurrence of events.^1,13,17 However, most studies using the CoxPH model merely focused on using linearity assumptions rather than translating nonlinear variables into predictive models for real-world practice. Additionally, the conventional statistical model does not consider the fact that the effect of predictor variables on individual patients changes at different time points, which is far from providing comprehensive insight into the patient’s long-term outcomes.¹¹ Computational approaches such as machine learning and deep learning have been reported in long-term survival prediction of chondrosarcoma.^18,19 Machine learning enables recognizing complex combinations of predictors from the existing huge amounts of data and performing model improvement over time.²⁰ The limitations of single machine learning models are obvious in model interpretability and flexibility due to simplification of the event when dealing with multi-dimensional information. Moreover, these models lack stability due to bias related to data collection or model selection.^20,21 Compared to single machine learning models, ensemble learning model exhibits improved discriminative performance and enhanced data handling capabilities. The performance improvement of ensemble learning model has been reported to reach 25%.²² On the other hand, deep learning tends to overfit when dealing with relatively small amounts of data. The average performance of ensemble learning has been reported to be approximately 8% greater than that of deep learning models.^21,23,24 Overall, ensemble learning takes non-proportionalities, multicollinearity and nonlinearity of datasets into account, which produces better calibration and discriminative performance by combining results from multiple models.²⁰ The application of ensemble learning methods in therapy decisions and prognostic prediction for patients with chondrosarcoma has not received much attention in recent studies.

The primary objective of this study was to develop the ensemble learning algorithm with selected prognostic features which outperforms the Cox regression and single computational models in survival prediction and analysis of benefit of chemotherapy of high-grade chondrosarcoma based on SEER data. The secondary objective was to implement the optimal algorithm for identifying specific patient groups most likely to benefit from chemotherapy and guidance in chemotherapy strategies for high-grade chondrosarcoma.

Materials and methods

Patient selection and data collection

A flowchart of the detailed study process was shown in Figure 1. The data of patients with diagnosis of chondrosarcoma from January 2000 to December 2019 were obtained from the Surveillance, Epidemiology, and End Results (SEER) database. The International Classification of Diseases for Oncology, 3rd edition (ICD-O-3), was used to identify patients with chondrosarcoma. Inclusion criteria were all the diagnoses of chondrosarcoma as per ICD-O-3 definition, including those with ICD-O-3 code 9220/3 (Chondrosarcoma, NOS), 9221/3 (Juxtacortical chondrosarcoma), 9231/3 (Myxoid chondrosarcoma), 9240/3 (Mesenchymal chondrosarcoma), 9242/3 (Clear cell chondrosarcoma), and 9243/3 (Dedifferentiated chondrosarcoma). Patients with missing or ambiguous information, a secondary tumor at diagnosis, or a primary site of tumor other than the bone or joints were excluded from the study. In total, 1931 patients were included. The histological grade of the SEER database consists of four categories, with Grades I, II, III, and IV refer to well differentiated, moderately differentiated, poorly differentiated, and undifferentiated lesions, respectively.^16,25 Tumor grade was classified as either high (Grade III or IV, 468 patients) or low (Grade I or II, 1463 patients) according to the commonly recognized standards in the clinical and academic fields.^1,18,26,27 The patients with low-grade chondrosarcoma (n = 1463) were further excluded and 468 patients with high-grade chondrosarcoma were finally included in this study. Ethical approval was not sought for this study as the studies using the SEER database, including this one, were exempt from institutional review board approval. Informed consent was not applicable because the data from the SEER database were anonymous, and the study was an observational one.

Figure 1.

Study profile and analysis pipeline.

Data preprocessing and feature selection

The ordinal features were encoded as ordinal numeric values. Binary categorical features were coded as 0 or 1. Dummy encoding was used to deal with categorical features. Kaplan-Meier analyses were used for evaluating overall survival (OS) preliminarily, with the log-rank test used for determining the statistical difference between the estimated survival curves of different chondrosarcoma grades. CoxPH models and random survival forests (RSF) were applied to select the potential features that were associated with overall survival benefit in patients with high-grade chondrosarcoma for further model training. The concordance index (c-index) was used to evaluate the predictive power of the Cox regression model. The permutation importance is a method used to evaluate the contribution of each feature to the predictive power of a model. In this study, the RSF model combined with the permutation importance method was used to evaluate the importance of clinical characteristics. Among the five features with the smallest ranked value of c-index according to cox model, those with an RSF mean importance of no more than 0 were considered as lowly correlated features and were merged into reference features.

Model design and development

Ensemble learning algorithm was used in model design and development for prognostic prediction of high-grade chondrosarcoma in this study. The primary predictive outcome was overall survival (OS). The subjects were separated into training (70%, n = 327) and test (30%, n = 141) sets. For comparing ensemble learning model with single computational models, survival support vector machine regression models with different kernels (polynomial and radial basis function kernels) were developed and trained. These single models were chosen due to their ability to predict survival time quantitatively based on prior work on dealing with nonlinearity of clinical features. Moreover, a multivariate CoxPH model was constructed for comparison. To reduce the influence of potential confounding variables, the RSF model retrained on the training set was used as a feature scaler. The permutation importance of the obtained features was weighted to each feature by linear transformation. The model training involved a weighted summation of survival support vector machines trained with different kernel functions. To find the best configuration for our proposed model, hyperparameter tuning was conducted through 1000 iterations of random search and cross-validation on the training dataset. After the training was completed, the models were weighted and integrated to obtain the final model.

Model evaluation

The models were assessed for discrimination, calibration, and overall performance. The concordance index (c-index) based on the inverse probability of censoring weights was selected as the measurement of discrimination. Its value ranged from 0.5 to 1.0, with 1.0 indicating perfect discrimination. Receiver operating characteristic (ROC) curves and area under the curve (AUC) values at each time point (from the 12th to the 120th month, every 6 months) were obtained for evaluating the time-dependent specificities and sensitivities of the models. The survival data predicted by the ensemble learning model with the real data from the test set were presented case by case via a scatter plot, respectively.

Model interpretation

For prognostic evaluation of the effect of chemotherapy, we included different prognostic features in the ensemble learning model for survival prediction. The virtual patients for prediction were generated in each group according to different age groups (10, 20, 30, 40, 50, 60, 70, or 80 years old) with specific prognostic factors selected. We adjusted the imbalanced numbers of the patients in each age group with specific factors selected, which enables balanced and comparable sample size for matched age-stratified survival analysis. Some clinical features with fewer patients in real datasets could therefore be evaluated. Among these virtual patients with an estimated survival of more than 36 months in each group, the numbers of those who received chemotherapy to those who did not receive chemotherapy were counted to determine the ratio. In addition, χ2 tests (n > 40) and Fisher exact test (n ≤ 40) were performed in each group to compare the number of the virtual patients who received chemotherapy and those who did not receive chemotherapy, with specific prognostic factor selected and the estimated survival more than or no more than 36 months.

For further identification of the effect of chemotherapy with specific prognostic factors selected, the virtual patients in each group were further divided into subgroup A, B and C. Subgroup A contained those with longer predicted survival time if receiving chemotherapy regardless of tumor size. Subgroup B contained those with specific tumor size intervals which could be referred to for choosing chemotherapy or not to get longer survival time. Subgroup C contained those with shorter predicted survival time if receiving chemotherapy, regardless of tumor size. We counted the patients in each subgroup as a percentage of the total number of patients. Among the different age groups with specific prognostic factor selected, if the percentage of subgroup A differed from that of subgroup C by more than 25%, the patients in this group were considered to benefit from chemotherapy.

Statistical analysis

Percentages and frequencies were used to characterize categorical variables. Medians and ranges were used to characterize continuous variables. Clinical characteristics were compared using a Wilcoxon rank sum test for continuous variables and Fisher exact test for categorical variables. Log-rank test was performed to evaluate the statistical significance of the differences between the survival curves. The 36-month survival time was used as the standard for judging the pros and cons of chemotherapy in different age groups, with specific prognostic factor selected. χ2 testing (n > 40) and Fisher exact test (n ≤ 40) were used to examine the differences between the number of the patients who received chemotherapy and those who did not receive chemotherapy, with specific prognostic factor selected and estimated survival more than or no more than 36 months. p < .05 was considered statistically significant.

Python packages

The python environment was based on version 3.7. Numpy and Pandas were used to construct the basic data structure. Scikit-learn, lifelines and Scikit-survival were used to train and validate the survival-related machine models. All the images in this article were plotted with matplotlib. Supporting information shows further details of the code [see Supplemental Material].

Results

Demographic and clinical features of high-grade chondrosarcoma patients for prognostic evaluation based on SEER data

The demographic information (gender, age, status and survival months), tumor characteristics (histologic type, size, number, primary site, grade, tumor extension, and distant metastasis), and treatment strategy (chemotherapy, radiotherapy and surgery) of the patients with high-grade chondrosarcoma are shown in Table 1. The estimated survival curves of the patients with chondrosarcoma in 4 grades are shown in Figure 2(A). Log-rank test confirmed the statistical difference among these grade levels. In addition, the statistical difference between the estimated survival curves of the patients with high-grade (grade III and IV) and low-grade (grade I and II) chondrosarcoma was significant (Figure 2(B)). Hazard Ratio (HR) of each risk factor and c-index of each Cox model are shown in Table 2. The estimated feature importance of each risk factor in the RSF model is shown in Table 3. Among the five features (juxtacortical chondrosarcoma, primary site at upper limb, clear cell chondrosarcoma, primary site at vertebrae and mesenchymal chondrosarcoma) with the smallest ranked value of c-index according to cox model, those (juxtacortical chondrosarcoma, mesenchymal chondrosarcoma and primary site at upper limb) with RSF mean importance of no more than 0 were considered as lowly correlated features. Lowly correlated features might sabotage the further model training and increase the computational cost. Thus, lowly correlated features were merged into reference features (Juxtacortical chondrosarcoma and mesenchymal chondrosarcoma merged with chondrosarcoma NOS into chondrosarcoma NOS, etc; Primary site at upper limb merged with lower limb into primary site at limb).

Table 1.

Demographic and clinical characteristics of the patients with high- and low-grade chondrosarcoma.

Characteristic	High-grade cohort n = 468	Low-grade cohort n = 1463
Age, median (range)	59 (2 - 92)	52 (4 - 98)
Gender, n (%)
Female	187 (40.0)	660 (45.1)
Male	281 (60.0)	803 (54.9)
Histological type, n (%)
Clear cell chondrosarcoma	6 (1.3)	7 (0.5)
Dedifferentiated chondrosarcoma	144 (30.8)	17 (1.2)
Juxtacortical chondrosarcoma	5 (1.1)	19 (1.3)
Mesenchymal chondrosarcoma	34 (7.3)	7 (0.5)
Myxoid chondrosarcoma	51 (10.9)	171 (11.7)
Chondrosarcoma, NOS	228 (48.7)	1242 (84.9)
Primary site, n (%)
Pelvis	121 (24.7)	305 (20.8)
Upper limb	71 (16.1)	272 (18.6)
Vertebrae	8 (2.8)	55 (3.8)
Lower limb	148 (27.5)	375 (25.6)
Other	120 (29.0)	456 (31.2)
Surgery, n (%)
Amputation	94 (20.0)	137 (9.4)
Local treatment	341 (72.9)	1217 (83.2)
Not received	33 (7.1)	109 (7.5)
Radiotherapy, n (%)	109 (23.3)	165 (11.3)
Chemotherapy, n (%)	116 (24.8)	52 (3.6)
Tumor size, mm, median (range)	85 (6 - 989)	60 (4 - 890)
Number of tumors, median (range)	1 (1 - 4)	1 (1 - 5)
Tumor extension, n (%)
No break in periosteum	88 (18.8)	477 (32.6)
Extension beyond periosteum	351 (75)	943 (64.5)
Further extension	29 (6.2)	43 (2.9)
Presence of metastasis, n (%)
Metastasis	401 (85.7)	46 (3.1)
Non metastasis	67 (14.3)	1417 (96.9)
Grade, n (%)
Grade I	/	650 (44.4)
Grade II	/	813 (55.6)
Grade III	275 (58.8)	/
Grade IV	193 (41.2)	/
Status, n (%)
Dead	271 (57.9)	375 (25.6)
Alive	197 (42.1)	1088 (74.4)
Survival months, median (range)	48 (1 - 191)	90 (1 - 191)

NOS, not otherwise specified.

Figure 2.

Kaplan–Meier survival curves for the patients with different grade of chondrosarcoma. Log-rank test was performed to compare the difference between each pair of grade levels. (a) The difference between the 4 grades was significant. (b) Grade I and II were classified as low-grade chondrosarcoma. Grades III, and IV were classified as high-grade chondrosarcoma. The difference between the two categories was significant.

Table 2.

Cox Proportional Hazards Analysis of the effect of various characteristics on overall survival.

Risk factor	HR	95% CI	p-value	C-index
Age	1.03	1.02 - 1.04	<0.001	0.645262
Tumor size	1.00	1.00 - 1.00	0.557	0.625073
Metastasis
Detected metastasis	Ref	Ref	Ref	Ref
Non metastasis	0.31	0.22 - 0.43	<0.001	0.591226
Grade	1.49	1.14 - 1.96	0.003	0.583704
Surgery
Amputation	Ref	Ref	Ref	Ref
Local treatment	0.78	0.56 - 1.09	0.141	0.575845
Not received	1.61	0.98 - 2.66	0.062	0.543348
Chemotherapy
Not received	Ref	Ref	Ref	Ref
Received	0.95	0.68 - 1.32	0.746	0.529947
Radiotherapy
Not received	Ref	Ref	Ref	Ref
Received	0.91	0.66 - 1.26	0.576	0.528247
Tumor extension
Extension beyond periosteum	Ref	Ref	Ref	Ref
No break in periosteum	0.61	0.42 - 0.88	0.009	0.549601
Further extension	1.26	0.79 - 2.03	0.336	0.525004
Number of tumors	1.20	0.95 - 1.53	0.133	0.524521
Gender
Female	Ref	Ref	Ref	Ref
Male	1.52	1.17 - 1.97	0.002	0.522687
Histological type
Chondrosarcoma NOS	Ref	Ref	Ref	Ref
Dedifferentiated chondrosarcoma	1.94	1.44 - 2.63	<0.001	0.617726
Myxoid chondrosarcoma	1.17	0.74 - 1.85	0.499	0.520719
Mesenchymal chondrosarcoma	1.24	0.69 - 2.20	0.470	0.513885
Clear cell chondrosarcoma	0.75	0.23 - 2.41	0.624	0.505094
Juxtacortical chondrosarcoma	1.22	0.29 - 5.12	0.787	0.502346
Primary site
Lower limb	Ref	Ref	Ref	Ref
Other	0.86	0.59 - 1.26	0.446	0.562950
Pelvis	1.24	0.88 - 1.75	0.223	0.517255
Vertebrae	3.16	1.39 - 7.21	0.006	0.508569
Upper limb	0.89	0.59 - 1.35	0.594	0.503464

A p-value of <0.05 was considered statistically significant. HR, hazard ratio. CI, confidence interval. C-index, c-index on cox model of each variable. Ref, reference category. NOS, not otherwise specified.

Table 3.

Feature importance of various characteristics estimated by Random Survival Forest (RSF).

Risk factor	Importance (mean)	Importance (standard)
Age	0.03353325	0.012658
Tumor size	0.008529921	0.013079
Grade	0.004469323	0.007391
Gender (male)	0.005037985	0.004695
Histological type
Clear cell chondrosarcoma	0.0004264961	0.000504
Dedifferentiated chondrosarcoma	0.04929139	0.018143
Juxtacortical chondrosarcoma	0	0
Mesenchymal chondrosarcoma	−0.0009329601	0.003102
Myxoid chondrosarcoma	0.0002043627	0.001923
Primary site
Pelvis	0.0009063041	0.004028
Upper limb	−0.00186592	0.003497
Vertebrae	0.001377227	0.002193
Other	0.00624639	0.006705
Surgery
Local treatment	0.01347905	0.007493
Not received	0.008663201	0.005605
Radiotherapy	2.960595E-17	0.002547
Chemotherapy	0.00424719	0.006669
Number of tumors	0.003296459	0.002737
Tumor extension
No break in periosteum	0.01093785	0.003275
Further extension	−0.001750411	0.001634
Non metastasis	0.05095739	0.010834

Will ensemble learning algorithms outperform the cox regression and single computational models in prognostic evaluation of high-grade chondrosarcoma?

The scatter plot shows the survival data predicted case by case by each learning model and the real survival data from the test set, with the Pearson correlation coefficient of 0.640. (Figure 3). In Figure 4(A), AUC values at each time point are presented as the broken line. In general, AUC values of the ensemble learning model were above 0.83 at different follow-up times and were superior to those of the other two models, which showed that the ensemble learning model had far better accuracy than the other two machine learning models (Svm_rbf, support vector machine with radial basis function kernel, and Svm_poly, support vector machine with polynomial kernel) for survival prediction. Moreover, cox proportional hazard model seemed to perform better than the other three models at first few years but was lately surpassed by ensemble learning model after approximately 7 years. In Figure 4(A), time-dependent mean AUC values of each model are presented as the dotted line (0.851, 0.843, 0.834 and 0.813 for ensemble learning, CoxPH, Svm_rbf and Svm_poly model, respectively). The C-indexes, which indicates the performance of various machine learning models, were 0.764 for ensemble learning model, 0.748 for Svm_rbf model, 0.724 for Svm_poly model, and 0.753 for CoxPH model, respectively (Figure 4(B)). The ensemble learning model had better performance metrics than the other models.

Figure 3.

Survival data predicted by the ensemble model and the real data of the test set. The scatter plot was generated for comparing the survival time predicted by the ensemble model with the real data of the test set one by one regardless of the last follow-up status.

Figure 4.

Performance assessment of ensemble model, CoxPH model and the single models of Svm_rbf and Svm_poly (a) The area under the curve (AUC) values of the receiver operating characteristics (ROC) curve at each time point and its mean value. AUC values of ROC curve at each time point (from the 12th to the 120th month) were presented as the broken lines. Time-dependent mean AUC value of each model was presented as the dotted line. The ensemble learning model predicted the risk of survival status far better than the other two single machine models alone. At the same time, Cox model performed better at first but was surpassed in reverse after approximately 7 years. (b) C-index of the ensemble learning model compared with those of the Cox model and the single model of Svm_rbf and Svm_poly. Svm_rbf, support vector machine with radial basis function kernel; Svm_poly, support vector machine with polynomial kernel; Ensemble, ensemble learning; CoxPH, Cox proportional hazards.

Among distinct age groups with specific factors, what kind of patients with high-grade chondrosarcoma is expected to benefit most from chemotherapy?

For clarity of the prognostic prediction from the ensemble learning model, the virtual patients were generated according to different age group (10, 20, 30, 40, 50, 60, 70, or 80 years old) with specific prognostic factors selected (Table 4). The 2 × 2 contingency table (Table 5) was designed for χ2 or Fisher exact test to determine the statistical difference between the number of the patients who received chemotherapy and those who did not receive chemotherapy, with specific prognostic factor selected and estimated survival more than or no more than 36 months. Generally, overall survival improved in younger patients after chemotherapy. The prognostic factors with statistical difference and the ratio >1 were considered related to more benefit from chemotherapy. These prognostic factors were: Dedifferentiated chondrosarcoma, amputation, or grade III with the age no more than 10; Male, clear cell, primary site other, local treatment, no radiotherapy, or no distant metastasis with the age no more than 20; Female, primary site at pelvis, primary site at limb, radiotherapy, extension beyond periosteum, further extension, or distant metastasis with the age no more than 30; Chondrosarcoma, NOS, etc (including mesenchymal, juxtacortical and classical chondrosarcoma) with the age no more than 40; No surgery received or grade IV with the age no more than 50.

Table 4.

The ratio of the patients who receive chemotherapy or not with survival over 36 months.

Prognostic factor	Age: 10	Age: 20	Age: 30	Age: 40
Gender
Male	1.153216*	1.131682*	1.062235	1.022222
Female	1.183263*	1.167824*	1.122605*	1.049435
Histological type
Dedifferentiated chondrosarcoma	1.196721*	1.138776	1.09205	1.04386
Clear cell chondrosarcoma	1.193948*	1.192042*	1.089936	0.991935
Myxoid chondrosarcoma	1.058228	1.037234	0.980609	0.946429
Chondrosarcoma, NOS, etc	1.212471*	1.201389*	1.196217*	1.149254*
Primary site
Pelvis	1.196581*	1.169742*	1.1167*	1.064877
Vertebrae	1.194175	1.138889	0.928571	0.755556
Limb	1.186567*	1.166333*	1.115217*	1.074519
Other	1.12*	1.117761*	1.069182	1
Surgery
Local treatment	1.104918*	1.105937*	1.061021	1.006812
Amputation	1.118196*	1.071547	1.015873	0.994197
Not received	1.547718*	1.654971*	1.683333*	1.54023*
Radiotherapy	1.194737*	1.204492*	1.141009*	1.068017
No radiotherapy	1.140165*	1.092994*	1.043236	1.003091
Tumor extension
Further extension	1.321782*	1.309309*	1.167235*	1.04
No break in periosteum	1.063114	1.04236	1.01642	0.98913
Extension beyond periosteum	1.18915*	1.180534*	1.137755*	1.083955
Presence of metastasis
No distant metastasis	1.085502*	1.077287*	1.04655	1.025916
Distant metastasis	1.4163*	1.407713*	1.292683*	1.091324
Grade
Grade III	1.079592*	1.045952	1.006017	0.936592
Grade IV	1.275946*	1.284519*	1.204856*	1.166954*

Prognostic factor	Age: 50	Age: 60	Age: 70	Age: 80
Gender
Male	0.990584	0.860987*	0.790909*	0.57265*
Female	1.020033	0.974684	0.850543*	0.714286*
Histological type
Dedifferentiated chondrosarcoma	1.037037	1.014706	0.811765	0.268293*
Clear cell chondrosarcoma	0.978417	0.79602*	0.681159*	0.476636*
Myxoid chondrosarcoma	0.891525	0.896825	0.836364	0.732955*
Chondrosarcoma, NOS, etc	1.103261	0.97281	0.890196	0.759259*
Primary site
Pelvis	1.028721	0.907937	0.831933*	0.692771*
Limb	1.031792	0.978495	0.853211	0.701987*
Vertebrae	0.8125	0.583333	0.631579	0.4375
Other	0.97561	0.903974	0.798206*	0.562092*
Surgery
Local treatment	1.003205	0.954813	0.834171*	0.712727*
Amputation	0.950783	0.841689*	0.795848*	0.555024*
Not received	1.457627*	1.28125	1.090909	1
Radiotherapy	1.026846	0.969008	0.868984*	0.69434*
No radiotherapy	0.983146	0.864679*	0.768519*	0.588235*
Tumor extension
Further extension	0.988506	0.915094	0.574074*	0.071429*
No break in periosteum	0.937751	0.88862	0.83908*	0.714286*
Extension beyond periosteum	1.087336	0.952618	0.847973*	0.592965*
Presence of metastasis
No distant metastasis	1.014433	0.937805	0.854714*	0.653445*
Distant metastasis	0.95625	0.77	0.411765*	0.142857
Grade
Grade III	0.908133*	0.822262*	0.731935*	0.594156*
Grade IV	1.145923*	1.068871	0.966543	0.735955*

*Statistical difference with p < .05 when the number of the patients who received chemotherapy and those who did not receive chemotherapy, with specific prognostic factor selected and estimated survival more than or no more than 36 months, were compared; NaN, not a number, which means the number of the patients who did not receive chemotherapy, with specific prognostic factor selected and estimated survival more than 36 months, was zero and the ratio of the number of the patients who received chemotherapy to those who did not receive chemotherapy could not be calculated. NOS, not otherwise specified.

Table 5.

The 2 × 2 contingency table design for χ2 or Fisher exact test in each group in Table 4.

The number of the patients who received chemotherapy with the estimated survival more than 36 months	The number of the patients who did not receive chemotherapy with the estimated survival more than 36 months
The number of the patients who received chemotherapy with the estimated survival less than 36 months	The number of the patients who did not receive chemotherapy with the estimated survival less than 36 months

Furthermore, survival time of the virtual patients in subgroup A (Figure 5(A)), B (Figure 5(B)) and C (Figure 5(C)) with different tumor sizes ranging from 40 to 120 mm was analyzed by the ensemble learning model. In each age group with specific prognostic factors selected, we counted the number in subgroup A, B and C as a percentage of the total (Table 6). We noted that among the aforementioned factors that were identified to contribute to increased benefit from chemotherapy in Table 4, the factors leading to more than 25% difference in the percentage of the patients in subgroup A and C in Table 6 were: Dedifferentiated chondrosarcoma, amputation, local treatment, no distant metastasis, or grade III with the age no more than 10; Male, clear cell, primary site other, or no radiotherapy with the age no more than 20; Female, primary site at pelvis, primary site at limb, radiotherapy, extension beyond periosteum, further extension, or distant metastasis with the age no more than 30; Chondrosarcoma, NOS, etc (including mesenchymal, juxtacortical and classical chondrosarcoma) with the age no more than 40; No surgery received or grade IV with the age no more than 50. Under these factors, the benefit from chemotherapy was definite. Besides, tumor extension, no surgery received and grade IV tumor led to more than 40% differences in the percentage of patient number between subgroup A and C among all age groups, which indicates the decisive effect of these factors on evaluating chemotherapy benefit.

Figure 5.

Relationships between predicted survival time and tumor size of the patients in each subgroup (a) Subgroup A included the patients whose survival time was longer if they received chemotherapy, regardless of tumor size. (b) Subgroup B included the patients with specific tumor size intervals which can be referred to for choosing chemotherapy or not to obtain longer survival time. (c) Subgroup C included the patients with shorter predicted survival time if receiving chemotherapy, regardless of tumor size.

Table 6.

The proportion of patients with extra or no benefit from chemotherapy in different age groups.

Prognostic factor	Age: 10 (a% / b% / c%)	Age: 20 (a% / b% / c%)	Age: 30 (a% / b% / c%)	Age: 40 (a% / b% / c%)
Gender
Male	74.74%/4.82%/20.44%	69.23%/4.34%/26.43%	64.89%/4.6%/30.51%	60.24%/5.34%/34.42%
Female	76.95%/4.25%/18.79%	71.7%/4.86%/23.44%	67.19%/4.64%/28.17%	63.98%/4.34%/31.68%
Histological type
Dedifferentiated chondrosarcoma	87.41%/3.56%/9.03%	81.6%/4.34%/14.06%	77.08%/4.51%/18.4%	73.26%/4.51%/22.22%
Clear cell chondrosarcoma	73.87%/4.51%/21.61%	69.97%/3.65%/26.39%	66.58%/3.56%/29.86%	62.67%/4.17%/33.16%
Myxoid chondrosarcoma	66.32%/3.56%/30.12%	59.64%/4.17%/36.2%	54.43%/3.91%/41.67%	50.52%/4.25%/45.23%
Chondrosarcoma NOS, etc	75.78%/6.51%/17.71%	70.66%/6.25%/23.09%	66.06%/6.51%/27.43%	61.98%/6.42%/31.6%
Primary site
Pelvis	76.65%/4.95%/18.4%	71.01%/4.43%/24.57%	66.49%/4.17%/29.34%	61.89%/4.95%/33.16%
Limb	76.22%/3.99%/19.79%	71.09%/4.69%/24.22%	67.01%/5.47%/27.52%	64.15%/4.6%/31.25%
Vertebrae	80.47%/4.17%/15.36%	75.52%/2.78%/21.7%	70.31%/2.69%/27.0%	65.62%/3.12%/31.25%
Other	70.05%/5.03%/24.91%	64.24%/6.51%/29.25%	60.33%/6.16%/33.51%	56.77%/6.68%/36.55%
Surgery
Local treatment	64.06%/6.45%/29.49%	56.38%/6.45%/37.17%	50.39%/6.12%/43.49%	45.57%/6.45%/47.98%
Amputation	64.45%/6.51%/29.04%	56.77%/6.58%/36.65%	50.98%/5.99%/43.03%	46.03%/6.12%/47.85%
Not received	99.02%/0.65%/0.33%	98.24%/0.78%/0.98%	96.74%/1.76%/1.5%	94.73%/1.95%/3.32%
Radiotherapy	81.68%/4.08%/14.24%	76.09%/3.86%/20.05%	71.48%/4.38%/24.13%	67.58%/4.34%/28.08%
No radiotherapy	70.01%/4.99%/25.0%	64.84%/5.34%/29.82%	60.59%/4.86%/34.55%	56.64%/5.34%/38.02%
Tumor extension
Further extension	92.77%/2.21%/5.01%	88.15%/2.86%/8.98%	84.77%/2.73%/12.5%	81.45%/3.52%/15.04%
No break in periosteum	62.04%/5.79%/32.16%	56.18%/5.6%/38.22%	51.5%/5.6%/42.9%	47.98%/4.56%/47.46%
Extension beyond periosteum	72.72%/5.6%/21.68%	67.06%/5.34%/27.6%	61.85%/5.53%/32.62%	56.9%/6.45%/36.65%
Presence of metastasis
No distant metastasis	62.93%/6.64%/30.43%	56.77%/5.6%/37.63%	52.04%/6.12%/41.84%	47.87%/5.86%/46.27%
Distant metastasis	88.76%/2.43%/8.81%	84.16%/3.6%/12.24%	80.03%/3.12%/16.84%	76.35%/3.82%/19.84%
Grade
Grade III	64.67%/5.16%/30.16%	57.42%/5.56%/37.02%	52.04%/5.47%/42.49%	47.4%/5.34%/47.27%
Grade IV	87.02%/3.91%/9.07%	83.51%/3.65%/12.85%	80.03%/3.78%/16.19%	76.82%/4.34%/18.84%

Prognostic factor	Age: 50 (a% / b% / c%)	Age: 60 (a% / b% / c%)	Age: 70 (a% / b% / c%)	Age: 80 (a% / b% / c%)
Gender
Male	56.81%/4.77%/38.41%	53.95%/4.21%/41.84%	51.35%/4.17%/44.49%	49.44%/3.95%/46.61%
Female	60.85%/4.73%/34.42%	58.38%/4.86%/36.76%	56.42%/4.3%/39.28%	55.16%/4.08%/40.76%
Histological type
Dedifferentiated chondrosarcoma	70.23%/3.91%/25.87%	68.32%/3.39%/28.3%	66.58%/3.12%/30.3%	65.97%/3.12%/30.9%
Clear cell chondrosarcoma	59.46%/4.34%/36.2%	56.51%/4.25%/39.24%	54.95%/3.04%/42.01%	52.6%/3.56%/43.84%
Myxoid chondrosarcoma	46.44%/4.6%/48.96%	43.49%/4.08%/52.43%	40.54%/4.43%/55.03%	39.06%/3.82%/57.12%
Chondrosarcoma, NOS, etc	59.2%/6.16%/34.64%	56.34%/6.42%/37.24%	53.47%/6.34%/40.19%	51.56%/5.56%/42.88%
Primary site
Pelvis	58.77%/4.51%/36.72%	56.08%/4.25%/39.67%	53.04%/4.86%/42.1%	51.56%/4.25%/44.18%
Limb	62.15%/4.69%/33.16%	60.16%/5.21%/34.64%	58.51%/4.51%/36.98%	56.94%/4.69%/38.37%
Vertebrae	60.33%/3.73%/35.94%	56.42%/2.95%/40.62%	53.39%/2.86%/43.75%	50.87%/2.6%/46.53%
Other	54.08%/6.08%/39.84%	52.0%/5.73%/42.27%	50.61%/4.69%/44.7%	49.83%/4.51%/45.66%
Surgery
Local	42.32%/5.53%/52.15%	39.39%/5.01%/55.6%	37.96%/3.91%/58.14%	36.85%/3.97%/59.18%
Treatment
Amputation	42.06%/5.86%/52.08%	39.45%/5.92%/54.62%	37.04%/5.27%/57.68%	36.07%/4.43%/59.51%
Not received	92.12%/2.86%/5.01%	89.65%/2.67%/7.68%	86.65%/3.52%/9.83%	83.98%/3.65%/12.37%
Radiotherapy	63.72%/4.6%/31.68%	61.37%/4.04%/34.59%	58.98%/4.04%/36.98%	57.73%/3.95%/38.32%
No radiotherapy	53.95%/4.9%/41.15%	50.95%/5.03%/44.01%	48.78%/4.43%/46.79%	46.88%/4.08%/49.05%
Tumor extension
Further extension	78.97%/3.45%/17.58%	77.15%/3.45%/19.4%	75.59%/3.12%/21.29%	75.26%/2.8%/21.94%
No break in periosteum	44.4%/5.01%/50.59%	41.6%/4.69%/53.71%	38.54%/5.01%/56.45%	35.68%/5.01%/59.31%
Extension beyond periosteum	53.12%/5.79%/41.08%	49.74%/5.47%/44.79%	47.53%/4.56%/47.92%	45.96%/4.23%/49.8%
Presence of metastasis
No distant metastasis	44.18%/5.95%/49.87%	41.36%/5.43%/53.21%	38.85%/5.25%/55.9%	36.85%/5.08%/58.07%
Distant metastasis	73.48%/3.56%/22.96%	70.96%/3.65%/25.39%	68.92%/3.21%/27.86%	67.75%/2.95%/29.3%
Grade
Grade III	43.92%/4.64%/51.43%	40.93%/4.25%/54.82%	38.15%/3.95%/57.9%	36.15%/3.86%/59.98%
Grade IV	73.74%/4.86%/21.4%	71.4%/4.82%/23.78%	69.62%/4.51%/25.87%	68.45%/4.17%/27.39%

^aThe percentage of the patients with longer estimated survival if receiving chemotherapy in different age groups with selected prognostic factor, regardless of tumor size.

^bThe percentage of the patients with specific tumor size intervals in different age groups under selected prognostic factor, which can be referred to for choosing chemotherapy or not to get longer survival time.

^cThe percentage of the patients with shorter estimated survival if receiving chemotherapy in different age groups with selected prognostic factor, regardless of tumor size.

Specific factors with adverse prognostic outcomes after chemotherapy in different age groups were also identified. These factors were: Grade III with the age over 50; Amputation with the age over 60; Local surgical treatment, no break in periosteum, extension beyond periosteum, or no distant metastasis with the age over 70; myxoid chondrosarcoma or no radiotherapy with the age over 80. These factors led to statistical difference of χ2 or Fisher exact test with the ratio <1 in Table 4 and were also associated with opposite difference in the percentage of the patients in subgroup A and C (subgroup A% < subgroup C%) in Table 6.

Discussion

To the best of our knowledge, this study represents the first attempt to combine ensemble learning methods with multiple prognostic factors to predict survival and evaluate the efficacy of chemotherapy. In this study, the statistical difference among the estimated survival curves of the patients with different grades of chondrosarcoma further validated the poor prognosis of high-grade chondrosarcoma. CoxPH analysis and the RSF method were used to identify potential variables associated with the prognosis of high-grade chondrosarcoma. Survival support vector machine with different kernel methods were utilized for training purposes. We successfully developed an ensemble-learning based model for survival prediction in patients with high-grade chondrosarcoma.

Ensemble learning algorithms outperform CoxPH and single computational models in prognostic evaluation of high-grade chondrosarcoma

Computational approaches such as machine learning have made significant contributions to predicting metastasis, drug response, survival and recurrence rate in the field of clinical oncology, especially for chondrosarcoma. However, the limitations of single machine learning models are evident.^18,19 In our study, the ensemble learning model outperformed the other models when dealing with large samples and multiple variables, followed by support vector machines with polynomial kernel, support vector machine with radial basis function kernel, and CoxPH. A 1000-repeated random search with cross-validation for hyperparameter tuning was conducted to obtain the best model configuration with stability and accuracy.

Previous studies have focused mainly on nomogram models based on CoxPH analysis of the SEER data of various bone sarcomas. The c-indexes for model evaluation in these studies were lower than those in the studies of machine learning models (including this study).^28–31 Moreover, the c-index of the ensemble model in our study was significantly better than those reported for The American Joint Committee on Cancer (AJCC) staging system.^28,32,33 Thio et al. developed the machine learning -based Skeletal Oncology Research Group (SORG) algorithm and analyzed the SEER data to predict the 5-year survival of the patients who were surgically treated.¹⁸ The c-index of moderately and poorly differentiated tumors (sorting of tumor grade) reached 0.74 ²⁷. The commonly used c-index for discriminative performance was considered inappropriate when predicting the risk for the time-to-event result, due to a higher c-index of mis-specified model under a defined time interval.^32,34 Thus, time-dependent AUC was also utilized for describing time-dependent specificities and sensitivities at all time points. The AUC value of the ensemble model in this study was over 0.85 (highly reliable), which is higher than those of the reported nomograms from the SEER database.^30–32,35 In addition, the ensemble model demonstrated no inferior AUC value when compared to various computational models.³⁶ Sung et al. used neural network machine learning algorithms to analyze the role and outcomes of surgical resection and radiation therapy in spino-pelvic chondrosarcoma with the mean AUC reached 0.84 ¹⁹. The SORG algorithm model showed good discriminative ability and overall performance when applied in the SEER derivation cohort and external validation cohort, with the AUC for 5-year survival around 0.85.^18,27

The model in our study demonstrated superiority in terms of c-index and mean AUC over those of previous studies. Moreover, our study model reflected a larger and more recent collection of patients from numerous centers available via the SEER database. There was significant superiority in our performance metrics favoring the ensemble learning model over the other three single algorithms for survival prediction. Therefore, by using various optimized algorithms to fit time-to-event data, the ensemble learning model becomes more accurate and flexible when handling complex and nonlinear data.

Identification of distinct age groups with specific factors of chondrosarcoma for tailored use of chemotherapy

A previous study comparing the tumor features revealed significant differences in median survival between chondrosarcoma subtypes, with the highest median survival in the juxtacortical subtype (97 months), followed by clear cell (79 months), myxoid (60 months), and mesenchymal subtypes (33.5 months), and the lowest in dedifferentiated subtype (11 months).¹¹ The rate of metastasis emerged as the only prognostic variable for decreased long-term survival and differed significantly with 2.1% in juxtacortical, 5.7 % in clear cell, 7.6% in myxoid, 10.6% in mesenchymal, and 19.8% in dedifferentiated subtype.¹¹ As the median OS for advanced chondrosarcoma with a higher grade of malignancy was reported as poor as 18 months and the survival rate at 5 years was very low,^6,8,9 the time point for survival prediction would be appropriate between 18 and 60 months. Although the performance superiority of the ensemble learning model over traditional models in real datasets appeared after 36 months in this study, we adjusted the imbalanced number of virtual patients in several groups in Table 4 for reaching comparable sample size. Some clinical features with fewer patients in real datasets could be examined individually, considering that these patients have shorter survival times. Therefore, the survival prediction based on the ensemble learning model was judged based on a 36-month period in this study.

Distant disease is the dominant mode of treatment failure in dedifferentiated subtype.^3,4 Whether chemotherapy should be used for dedifferentiated chondrosarcoma has been one of the controversies in the medical field. Italiano et al. reported that conventional chemotherapy had relatively better efficacy for patients with advanced mesenchymal and dedifferentiated chondrosarcoma than for those with other advanced subtypes, although the benefit was limited.⁸ In this study, the benefit of chemotherapy over no chemotherapy for dedifferentiated chondrosarcoma was significant only when patients were as young as 10 years old (Tables 4 and 6). Such benefit was limited with no statistical significance in other age groups (from 10 to 50 years old). Consistent with the finding of previous studies, our study confirmed the efficacy of age-adapted chemotherapy for treating dedifferentiated chondrosarcoma with aggressive entity.

It is a well-established fact that the only definitive treatment for chondrosarcoma is wide resection. Conventional surgery for chondrosarcoma still subjects the limitation of treatment failure given the presence of distant metastasis and incomplete resection.^14,17 Previous studies evaluating the efficacy of neoadjuvant or adjuvant chemotherapy for high-grade tumors have yielded controversial conclusions regarding improvements in progress-free survival and OS. Two separate studies from Cranmer et al. and Liu et al. both revealed no definitive improvement in survival associated with primary chemotherapy in treating high-grade tumors, such as dedifferentiated chondrosarcoma.^1,37 Li et al. suggested that chemotherapy was even a risk factor for patient prognosis.³⁶ On the other hand, some studies demonstrated that aggressive administration of chemotherapy led to favorable results and contributed to the achievement of a surgical complete remission which was considered the crucial factor associated with prolonged OS.^5,13,38,39 The specific clinicopathologic or treatment factors, such as primary disease arising in the context of osteochondroma or a large osteo-sarcomatous component, were found meaningful in identifying the patients who would gain benefit from neoadjuvant or adjuvant chemotherapy.^13,39 In our study (Tables 4 and 6), the benefit of chemotherapy over no chemotherapy in the patient who underwent surgery was limited with the age no more than 10 years old. The variations in the results of perioperative chemotherapy on high-grade chondrosarcoma is likely caused by differences in the inclusion criteria (such as the inclusion of the cases with large tumor size or extensive metastasis when chemotherapy has to be chosen), the innate limitations of the retrospective or noncomparative studies and small sample size.^{11,13,14,17,36}

Previous studies have demonstrated that the patients would survive longer after surgical resection, even with metastatic condition.^15,36,40 In our study, we found that among the patients who underwent surgical treatment and had an estimated survival of more than 36 months, the number of those who received chemotherapy was greater when the age was no more than 50 years old. Thus, it is suggested that every effort, including perioperative chemotherapy, should be made to perform surgical resection for younger patients and prevent transformation into high-grade disease when feasible. Perioperative administration of chemotherapy in osteosarcoma, another high-risk bone malignancy, has shown encouraging outcomes and has been recommended by various management guidelines.^4,10,13 Given the frequent existence of an osteo-sarcomatous component in high-grade chondrosarcoma and the osteosarcoma treatment protocols being proposed as a model for dedifferentiated chondrosarcoma treatment, it is reasonable to consider perioperative chemotherapy in other chondrosarcoma subtypes under careful consideration, or a clinical trial.^1,9,10,39

Therapeutic plans based on calculated hazard ratio (HR) value of the classical CoxPH model are usually constant owing to its linearity assumption of variable fitting.^9,14,41 Conventional cytotoxic agents have limited effects on advanced chondrosarcomas with higher tumor grades, whereas more active systemic therapies are considered probably meaningful in these cases stratified by age.^2,3,41 Studies have identified age, tumor size and histological grade as prognostic factors which significantly associated with survival.^2,7,12 However, no evidence-based prediction exists for the definite association between these factors and survival after receiving chemotherapy or not. We have generated estimated OS value for patients in the chemotherapy and non-chemotherapy group with various age distributions and tumor size, for reference in study design and statistical power calculations. In our study, grade IV tumor in younger patients (aged no more than 50 years) tended to benefit more from chemotherapy, while such benefits were not significant in older patients. Notably, chondrosarcoma is more common in older patients who may not tolerate more radical treatment regimens due to poor physical status.^2,10 Understanding these treatment differences among different patient groups will positively affect risk‐benefit decisions for appropriate treatment recommendations. Furthermore, the model will also provide survival guidance and benchmarks for stratification in future clinical trials.

This study has several limitations. First, the inherent limitations of the SEER database should be mentioned when considering the potential confounding variables. Although the patients in this study have better reflected the actual diversity with complete and comprehensive incidence and survival data, most were classified as “Chondrosarcoma, NOS, etc.” (accounting for 48.7% and 84.9% of cases in the grade III/IV and grade I/II cohorts, respectively). SEER does not provide information about the chemotherapy administered, dose intensity, length of therapy, or other treatments (such as surgery and radiotherapy).²⁵ SEER does not provide a clear distinction between unknown treatment status and nonreceipt of chemotherapy. Consequently, patients who received chemotherapy but were classified in the no/unknown status group might inadvertently downplay the impact of chemotherapy treatment. Second, pathology results in the SEER database rely on the confirmation from participating institutions instead of the central review. It is possible that some cases may have been pathologically misclassified in the database, necessitating caution when interpreting the results. Third, the algorithm developed in this study requires validation with external datasets to assess its generalizability and reliability. Adequate validation with multi-institution cohorts is encouraged to improve the accuracy of the model.

Conclusion

The ensemble learning algorithm demonstrated outstanding performance for prognostic assessment of chemotherapy benefit in high-grade chondrosarcoma, particularly within specific age groups under specific factors. However, the findings must be viewed cautiously, given the substantial limitations of the SEER database and the lack of clinical validation of the prediction model. Future studies focusing on the identification of patient subsets that are more likely to benefit from chemotherapy are desired to improve the practicability of the prediction model.

Supplemental Material

Supplemental Material - 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

Supplemental Material for 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 by Xu Zheng, Longqiang Shu, Shanyi Lin, Hanqiang Jin, Xiaoyu Wang and Ting Yuan in Journal of Orthopaedic Surgery

Footnotes

Authors’ contributions

XZ and XYW conceived and designed the study. XZ, LQS and XYW collected the data and contributed to image analysis. XZ, HQJ and XYW analyzed the data and drafted the manuscript. SYL, HQJ, XYW, and TY offered administrative, technical, and/or material support. All authors contributed to the manuscript revision and approved the final version of the manuscript. All authors read and approved the final manuscript.

Declaration of conflicting interests

The author(s) declared no potential conflicts of interest with respect to the research, authorship, and/or publication of this article.

Funding

The author(s) received no financial support for the research, authorship, and/or publication of this article.

ORCID iD

Xiaoyu Wang

Data Availability Statement

The datasets supporting the conclusions of this article are available in the Surveillance, Epidemiology, and End Results cancer registry () and are also available from the corresponding author on reasonable request. All data generated or analyzed during this study are included in this published article and its Supplemental Material.

Supplemental Material

Supplemental material for this article is available online.

Appendix

References

Cranmer

Chau

Mantilla

, et al. Is chemotherapy associated with improved overall survival in patients with dedifferentiated chondrosarcoma? A SEER database analysis. Clin Orthop Relat Res 2022; 480: 748–758. DOI: 10.1097/corr.0000000000002011.

van Praag Veroniek

Rueten-Budde

, et al. Incidence, outcomes and prognostic factors during 25 years of treatment of chondrosarcomas. Surg Oncol 2018; 27: 402–408. DOI: 10.1016/j.suronc.2018.05.009.

Strauss

Frezza

Abecassis

, et al. Bone sarcomas: ESMO-EURACAN-GENTURIS-ERN PaedCan clinical practice guideline for diagnosis, treatment and follow-up. Ann Oncol : Official Journal of the European Society for Medical Oncology 2021; 32: 1520–1536. DOI: 10.1016/j.annonc.2021.08.1995.

Strauss

Whelan

. Current questions in bone sarcomas. Curr Opin Oncol 2018; 30: 252–259. DOI: 10.1097/cco.0000000000000456.

Weinschenk

Wang

Lewis

. Chondrosarcoma. J Am Acad Orthop Surg 2021; 29: 553–562. DOI: 10.5435/jaaos-d-20-01188.

Bindiganavile

Han

Yun

, et al. Long-term outcome of chondrosarcoma: a single institutional experience. Cancer research and treatment 2015; 47: 897–903. DOI: 10.4143/crt.2014.135.

Gao

Ren

Song

, et al. Marital status and survival of patients with chondrosarcoma: a population-based analysis. Med Sci Monit : International Medical Journal of Experimental and Clinical Research 2018; 24: 6638–6648. DOI: 10.12659/msm.911673.

Italiano

Mir

Cioffi

, et al. Advanced chondrosarcomas: role of chemotherapy and survival. Ann Oncol : Official Journal of the European Society for Medical Oncology 2013; 24: 2916–2922. DOI: 10.1093/annonc/mdt374.

Wagner

Livingston

Patel

, et al. Chemotherapy for bone sarcoma in adults. Journal of oncology practice 2016; 12: 208–216. DOI: 10.1200/jop.2015.009944.

10.

Whelan

Davis

. Osteosarcoma, chondrosarcoma, and chordoma. J Clin Oncol : Official Journal of the American Society of Clinical Oncology 2018; 36: 188–193. DOI: 10.1200/jco.2017.75.1743.

11.

Amer

Munn

Congiusta

, et al. Survival and prognosis of chondrosarcoma subtypes: SEER database analysis. J Orthop Res : Official Publication of the Orthopaedic Research Society 2020; 38: 311–319. DOI: 10.1002/jor.24463.

12.

Nota

Braun

Schwab

, et al. The identification of prognostic factors and survival statistics of conventional central chondrosarcoma. Sarcoma 2015; 2015: 623746. DOI: 10.1155/2015/623746.

13.

Miao

Choy

Raskin

, et al. Prognostic factors in dedifferentiated chondrosarcoma: a retrospective analysis of a large series treated at a single institution. Sarcoma 2019; 2019: 9069272. DOI: 10.1155/2019/9069272.

14.

Bishop

Bird

Conley

, et al. Extraskeletal myxoid chondrosarcomas: combined modality therapy with both radiation and surgery improves local control. American journal of clinical oncology 2019; 42: 744–748. DOI: 10.1097/coc.0000000000000590.

15.

Fromm

Klein

Baur-Melnyk

, et al. Survival and prognostic factors in conventional central chondrosarcoma. BMC Cancer 2018; 18: 849. DOI: 10.1186/s12885-018-4741-7.

16.

Overview of the SEER program. Available from: https://seer.cancer.gov/about/overview.html

17.

Wagner

Chau

Loggers

, et al. Long-term outcomes for extraskeletal myxoid chondrosarcoma: a SEER database analysis. Cancer epidemiology, biomarkers & prevention : A Publication of the American Association for Cancer Research, Cosponsored by the American Society of Preventive Oncology 2020; 29: 2351–2357. DOI: 10.1158/1055-9965.epi-20-0447.

18.

Thio

Karhade

Ogink

, et al.

Can machine-learning techniques Be used for 5-year survival prediction of patients with chondrosarcoma?

Clin Orthop Relat Res 2018; 476: 2040–2048. DOI: 10.1097/corr.0000000000000433.

19.

Ryu

Seo

Lee

. Novel prognostication of patients with spinal and pelvic chondrosarcoma using deep survival neural networks. BMC Med Inf Decis Making 2020; 20: 3. DOI: 10.1186/s12911-019-1008-4.

20.

Obermeyer

Emanuel

. Predicting the future - big data, machine learning, and clinical medicine. N Engl J Med 2016; 375: 1216–1219. DOI: 10.1056/NEJMp1606181.

21.

Bang

Bernard

, et al. Artificial intelligence to predict outcomes of head and neck radiotherapy. Clinical and translational radiation oncology 2023; 39: 100590. DOI: 10.1016/j.ctro.2023.100590.

22.

Vos

Trinh

Sarnyai

, et al. Ensemble machine learning model trained on a new synthesized dataset generalizes well for stress prediction using wearable devices. J Biomed Inf 2023; 148: 104556. DOI: 10.1016/j.jbi.2023.104556.

23.

Coen-Pirani

Jiang

. Empirical study of overfitting in deep learning for predicting breast cancer metastasis. Cancers (Basel) 2023; 15. DOI: 10.3390/cancers15071969.

24.

Nguyen

Ong

, et al. Ensemble learning using traditional machine learning and deep neural network for diagnosis of Alzheimer's disease. IBRO Neurosci Rep 2022; 13: 255–263. DOI: 10.1016/j.ibneur.2022.08.010.

25.

National Cancer Institute . Surveillance, epidemiology and end results (SEER) program. SEER Incidence Data 1975 - 2020. https://seer.cancer.gov/data

26.

Song

Shi

Wang

, et al.

Can a nomogram help to predict the overall and cancer-specific survival of patients with chondrosarcoma?

Clin Orthop Relat Res 2018; 476: 987–996. DOI: 10.1007/s11999.0000000000000152.

27.

Bongers

MER

Karhade

Setola

, et al.

How does the skeletal oncology research group algorithm's prediction of 5-year survival in patients with chondrosarcoma perform on international validation?

Clin Orthop Relat Res 2020; 478: 2300–2308. DOI: 10.1097/corr.0000000000001305.

28.

Tian

Liu

Qing

, et al. A predictive model with a risk-classification system for cancer-specific survival in patients with primary osteosarcoma of long bone. Transl Oncol 2022; 18: 101349. DOI: 10.1016/j.tranon.2022.101349.

29.

Huang

Wang

Tang

, et al. Development and validation of nomogram-based prognosis tools for patients with extremity osteosarcoma: a SEER population study. Journal of oncology 2022; 2022: 9053663. DOI: 10.1155/2022/9053663.

30.

Xiao

Guo

Chen

, et al. Prevalence, risk factors, and prognostic factors of primary malignant bone neoplasms with bone metastasis at initial diagnosis: a population-based study. Journal of oncology 2022; 2022: 9935439. DOI: 10.1155/2022/9935439.

31.

Huang

Zhao

Wang

, et al. Clinical characteristics, prognostic factors, and predictive model for elderly primary spinal tumor patients who are difficult to tolerate surgery or refuse surgery. Frontiers in oncology 2022; 12: 991599. DOI: 10.3389/fonc.2022.991599.

32.

Sun

Ouyang

Zhang

, et al. Development and validation of a nomogram for predicting prognosis of high-grade chondrosarcoma: a surveillance, epidemiology, and end results-based population analysis. J Orthop Surg 2023; 31: 10225536231174255. DOI: 10.1177/10225536231174255.

33.

Compton

Cates

JMM

. Evidence-based tumor staging of skeletal chondrosarcoma. Am J Surg Pathol 2020; 44: 111–119. DOI: 10.1097/pas.0000000000001397.

34.

Blanche

Kattan

Gerds

. The c-index is not proper for the evaluation of $t$-year predicted risks. Biostatistics 2018; 20: 347–357. DOI: 10.1093/biostatistics/kxy006.

35.

Dong

Xie

Kang

, et al. A competing risk-based prognostic model to predict cancer-specific death of patients with spinal and pelvic chondrosarcoma. Spine 2021; 46: E1192–e1201. DOI: 10.1097/brs.0000000000004073.

36.

Wang

, et al. Dynamic predictive models with visualized machine learning for assessing chondrosarcoma overall survival. Frontiers in oncology 2022; 12: 880305. DOI: 10.3389/fonc.2022.880305.

37.

Liu

, et al. Dedifferentiated chondrosarcoma: radiological features, prognostic factors and survival statistics in 23 patients. PLoS One 2017; 12: e0173665. DOI: 10.1371/journal.pone.0173665.

38.

Tsuda

Ogura

Hakozaki

, et al. Mesenchymal chondrosarcoma: a Japanese musculoskeletal oncology group (JMOG) study on 57 patients. J Surg Oncol 2017; 115: 760–767. DOI: 10.1002/jso.24567.

39.

Dhinsa

DeLisa

Pollock

, et al. Dedifferentiated chondrosarcoma demonstrating Osteosarcomatous differentiation. Oncol Res Treat 2018; 41: 456–460. DOI: 10.1159/000487803.

40.

Song

Chen

, et al.

Does resection of the primary tumor improve survival in patients with metastatic chondrosarcoma?

Clin Orthop Relat Res 2019; 477: 573–583. DOI: 10.1097/corr.0000000000000632.

41.

van Maldegem

Conley

Rutkowski

, et al. Outcome of first-line systemic treatment for unresectable conventional, dedifferentiated, mesenchymal, and clear cell chondrosarcoma. Oncologist 2019; 24: 110–116. DOI: 10.1634/theoncologist.2017-0574.

Supplementary Material

Please find the following supplemental material available below.

For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.

For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.

0.00 MB

0.54 MB