A nomogram for predicting cancer-specific survival in patients with osteosarcoma as secondary malignancy

Survival analysis and prognostic model establishment of secondary osteosarcoma: a SEER-based study

Background

Surgical excision is considered one of the most effective treatments for secondary osteosarcoma (SO). It remains unclear whether the survival of patients with secondary osteosarcoma (SO) could be associated with their surgical willingness.

Materials and methods

The statistics of the patients diagnosed with SO between 1975 and 2008 were gathered from the surveillance epidemiology and end results (SEER) database. The patients were divided into three subgroups according to their surgical compliance. The authors used the multivariable Logistic regression analysis and cox regression method to reveal the influence of surgical compliance on prognosis and the risk factors of surgical compliance. Additionally, the authors formulated a nomogram model to predict the overall survival (OS) of patients. The concordance index (C-index) was used to evaluate the accuracy and practicability of the above prediction model.

Results

Sixty-three (9.2%) of the 688 patients with SO who were recommended for surgical treatment refused to undergo surgery. Lower surgical compliance can be ascribed to an earlier time of diagnosis and refusal of chemotherapy. The lower overall survival (OS) {[hazard ratio (HR)] 1.733, [CI] 1.205-2.494, P value [P]=0.003} of not surgical compliant patients was verified by the multivariate cox regression method, compared with surgical compliant patients. In addition, the discernibility of the nomogram model was proven to be relatively high (C-index=0.748), by which we can calibrate 3-year- and 5-year OS prediction plots to obtain good concordance to the actual situation.

Conclusions

Surgical compliance was proved to be an independent prognostic factor in the survival of patients with SO.

Risk factors for distant metastasis of Chondrosarcoma in the middle-aged and elderly people

Chondrosarcoma is the second most common primary bone malignancy with the highest incidence in middle-aged and elderly people, where distant metastasis (DM) still leads to poor prognosis. The purpose of this study was to construct a nomogram for studying the diagnosis of DM in middle-aged and elderly patients with chondrosarcoma. Data on chondrosarcoma patients aged ≥ 40 years diagnosed from 2004 to 2015 were extracted from the Surveillance, Epidemiology, and End Results (SEER) database. The data were divided into a training set and an internal validation set according to a 7:3 ratio, and the training set data were screened for independent risk factors for DM in chondrosarcoma patients using univariate and multivariate logistic regression analysis. The screened independent risk factors were then used to build a nomogram. In addition, data from 144 patients with chondrosarcoma aged ≥ 40 years diagnosed in a tertiary hospital in China from 2012 to 2021 were collected as the external validation set. The results were evaluated by receiver operating characteristic curves, calibration curves, and decision curve analysis in the training set, internal validation set, and external validation set. A total of 1462 middle-aged and elderly patients with chondrosarcoma were included, and 92 (6.29%) had DM at the time of diagnosis. Independent risk factors for DM in middle-aged and elderly patients with chondrosarcoma included being married (OR: 2.119, 95% CI: 1.094-4.105), histological type of dedifferentiated chondrosarcoma (OR: 1.290, 95% CI: 1.110-1.499), high-grade tumor (OR: 1.511, 95% CI: 1.079-2.115), T3 stage (OR: 4.184, 95% CI: 1.977- 8.858), and N1 staging (OR: 5.666, 95% CI: 1.964-16.342). The area under the receiver operating characteristic curve (AUC) was 0.857, 0.820, and 0.859 in the training set, internal validation set, and external validation set, respectively. The results of the calibration curve and decision curve analysis also confirmed that the established nomogram could accurately predict DM in middle-aged and elderly patients with chondrosarcoma. Married, histological type of dedifferentiated chondrosarcoma, high-grade tumor, T3 stage, and N1 stage are independent risk factors for DM in middle-aged and elderly chondrosarcoma patients, and clinicians should see more attention.

Risk factors for distant metastasis of chondrosarcoma: A population-based study

Chondrosarcoma is the second largest bone malignancy after osteosarcoma and mainly affects middle-aged adults, where patients with distant metastasis (DM) often have a poor prognosis. Although nomograms have been widely used to predict distant tumor metastases, there is a lack of large-scale data studies for the diagnostic evaluation of DM in chondrosarcoma. Data on patients diagnosed with chondrosarcoma from 2004 to 2015 were obtained from the Surveillance, Epidemiology, and End Results database. Independent risk factors for having DM from chondrosarcoma were screened using univariate and multivariate logistics regression analysis. A nomogram was created to predict the probability of DM from the screened independent risk factors. The nomogram was then validated using receiver operating characteristic curves and calibration curves. A total of 1870 chondrosarcoma patients were included in the study after data screening, of which 157 patients (8.40%) had DM at the time of diagnosis. Univariate and multivariate logistic regression analysis screened four independent risk factors, including grade, tumor number, T stage, and N stage. receiver operating characteristic curves and calibration curves showed good accuracy of the nomogram in both training and validation sets. The current study screened for independent risk factors for DM from chondrosarcoma, which will help clinicians evaluate patients.

Characteristics and prognostic factors of adult patients with osteosarcoma from the SEER database

Osteosarcoma is the most common bone malignancy. There are many studies on the prognostic factors of children and adolescents, but the characteristics and prognostic factors of adult osteosarcoma are rarely studied. The aim of this study was to construct a nomogram for predicting the prognosis of adult osteosarcoma. Information on all osteosarcoma patients aged ≥ 18 years from 2004 to 2015 was downloaded from the surveillance, epidemiology and end results database. A total of 70% of the patients were included in the training set and 30% of the patients were included in the validation set. Univariate log-rank analysis and multivariate cox regression analysis were used to screen independent risk factors affecting the prognosis of adult osteosarcoma. These risk factors were used to construct a nomogram to predict 3-year and 5-year prognosis in adult osteosarcoma. Multivariate cox regression analysis yielded 6 clinicopathological features (age, primary site, tumor size, grade, American Joint Committee on Cancer stage, and surgery) for the prognosis of adult osteosarcoma patients in the training cohort. A nomogram was constructed based on these predictors to assess the prognosis of adult patients with osteosarcoma. Concordance index, receiver operating characteristic and calibration curves analyses also showed satisfactory performance of the nomogram in predicting prognosis. The constructed nomogram is a helpful tool for exactly predicting the prognosis of adult patients with osteosarcoma, which could enable patients to be more accurately managed in clinical practice.

Construction of Osteosarcoma Diagnosis Model by Random Forest and Artificial Neural Network

Osteosarcoma accounts for 28% of primary bone malignancies in adults and up to 56% in children and adolescents (<20 years). However, early diagnosis and treatment are still inadequate, and new improvements are still needed. Missed diagnoses exist due to fewer traditional diagnostic methods, and clinical symptoms are often already present before diagnosis. This study aimed to develop novel and efficient predictive models for the diagnosis of osteosarcoma and to identify potential targets for exploring osteosarcoma markers. First, osteosarcoma and normal tissue expression microarray datasets were downloaded from the Gene Expression Omnibus (GEO). Then we screened the differentially expressed genes (DEGs) in the osteosarcoma and normal groups in the training group. Next, in order to explore the biologically relevant role of DEGs, Metascape and enrichment analyses were also performed on DEGs. The “randomForest” and “neuralnet” packages in R software were used to select representative genes and construct diagnostic models for osteosarcoma. The next step is to validate the model of the artificial neural network. Then, we performed an immune infiltration analysis by using the training set data. Finally, we constructed a prognostic model using representative genes for prognostic analysis. The copy number of osteosarcoma was also analyzed. A random forest classifier identified nine representative genes (ANK1, TGFBR3, RSF21, HSPB8, ITGA7, RHD, AASS, GREM2, NFASC). HSPB8, RHD, AASS, and NFASC were genes we identified that have not been previously reported to be associated with osteosarcoma. The osteosarcoma diagnostic model we constructed has good performance with areas under the curves (AUCs) of 1 and 0.987 in the training and validation groups, respectively. This study opens new horizons for the early diagnosis of osteosarcoma and provides representative markers for the future treatment of osteosarcoma. This is the first study to pioneer the establishment of a genetic diagnosis model for osteosarcoma and advance the development of osteosarcoma diagnosis and treatment.

Multiview Deep Forest for Overall Survival Prediction in Cancer

Overall survival (OS) in cancer is crucial for cancer treatment. Many machine learning methods have been applied to predict OS, but there are still the challenges of dealing with multiview data and overfitting. To overcome these problems, we propose a multiview deep forest (MVDF) in this paper. MVDF can learn the features of each view and fuse them with integrated learning and multiple kernel learning. Then, a gradient boost forest based on the information bottleneck theory is proposed to reduce redundant information and avoid overfitting. In addition, a pruning strategy for a cascaded forest is used to limit the impact of outlier data. Comprehensive experiments have been carried out on a data set from West China Hospital of Sichuan University and two public data sets. Results have demonstrated that our method outperforms the compared methods in predicting overall survival.

A new model of preoperative systemic inflammatory markers predicting overall survival of osteosarcoma: a multicenter retrospective study

BACKGROUND

The purpose of this study was to investigate the significance of preoperative C-reactive protein-to-albumin ratio (CAR), neutrophil-to-lymphocyte ratio (NLR) and platelet-to-lymphocyte ratio (PLR) in predicting overall survival (OS) of osteosarcoma, to establish a nomogram of an individualized prognostic prediction model for osteosarcoma.

METHODS

Two hundred thirty-five patients with osteosarcoma from multiple centers were included in this study. Receiver operating characteristic (ROC) and Youden index were used to determine the optimal cutoff values ​​for CAR, NLR, and PLR. Univariate analysis using COX proportional hazards model to identify factors associated with OS in osteosarcoma, and multivariate analysis of these factors to identify independent prognostic factors. R software (4.1.3-win) rms package was used to build a nomogram, and the concordance index (C-index) and calibration curve were used to assess model accuracy and discriminability.

RESULTS

Univariate analysis revealed that the OS of osteosarcoma is significantly correlated (P < 0.05) with CAR, NLR, PLR, Enneking stage, tumor size, age, neoadjuvant chemotherapy (NACT), and high alkaline phosphatase. Multivariate analysis confirmed that CAR, NLR, Enneking stage, NACT and tumor size are independent prognostic factors for OS of osteosarcoma. The calibration curve shows that the nomogram constructed from these factors has acceptable consistency and calibration capability.

CONCLUSION

Preoperative CAR and NLR were independent predictors of osteosarcoma prognosis, and the combination of nomogram model can realize individualized prognosis prediction and guide medical practice.

Interpretable clinical visualization model for prediction of prognosis in osteosarcoma: a large cohort data study

Background

Currently, the clinical prediction model for patients with osteosarcoma was almost developed from single-center data, lacking external validation. Due to their low reliability and low predictive power, there were few clinical applications. Our study aimed to set up a clinical prediction model with stronger predictive ability, credibility, and clinical application value for osteosarcoma.

Methods

Clinical information related to osteosarcoma patients from 2010 to 2016 was collected in the SEER database and four different Chinese medical centers. Factors were screened using three models (full subset regression, univariate Cox, and LASSO) via minimum AIC and maximum AUC values in the SEER database. The model was selected by the strongest predictive power and visualized by three statistical methods: nomogram, web calculator, and decision tree. The model was further externally validated and evaluated for its clinical utility in data from four medical centers.

Results

Eight predicting factors, namely, age, grade, laterality, stage M, surgery, bone metastases, lung metastases, and tumor size, were selected from the model based on the minimum AIC and maximum AUC value. The internal and external validation results showed that the model possessed good consistency. ROC curves revealed good predictive ability (AUC &gt; 0.8 in both internal and external validation). The DCA results demonstrated that the model had an excellent clinical predicted utility in 3 years and 5 years for North American and Chinese patients.

Conclusions

The clinical prediction model was built and visualized in this study, including a nomogram and a web calculator (https://dr-lee.shinyapps.io/osteosarcoma/), which indicated very good consistency, predictive power, and clinical application value.

An External-Validated Prediction Model to Predict Lung Metastasis among Osteosarcoma: A Multicenter Analysis Based on Machine Learning

BACKGROUND

Lung metastasis greatly affects medical therapeutic strategies in osteosarcoma. This study aimed to develop and validate a clinical prediction model to predict the risk of lung metastasis among osteosarcoma patients based on machine learning (ML) algorithms.

METHODS

We retrospectively collected osteosarcoma patients from the Surveillance Epidemiology and End Results (SEER) database and from four hospitals in China. Six ML algorithms, including logistic regression (LR), gradient boosting machine (GBM), extreme gradient boosting (XGBoost), random forest (RF), decision tree (DT), and multilayer perceptron (MLP), were applied to build predictive models for predicting lung metastasis using patient's demographics, clinical characteristics, and therapeutic variables from the SEER database. The model was internally validated using 10-fold cross-validation to calculate the mean area under the curve (AUC) and the model was externally validated using the Chinese multicenter osteosarcoma data. Relative importance ranking of predictors was plotted to understand the importance of each predictor in different ML algorithms. The correlation heat map of predictors was plotted to understand the correlation of each predictor, selecting the 10-fold cross-validation with the highest AUC value in the external validation ROC curve to build a web calculator.

RESULTS

Of all enrolled patients from the SEER database, 17.73% (194/1094) developed lung metastasis. The multiple logistic regression analysis showed that sex, N stage, T stage, surgery, and bone metastasis were all independent risk factors for lung metastasis. In predicting lung metastasis, the mean AUCs of the six ML algorithms ranged from 0.711 to 0.738 in internal validation and 0.697 to 0.729 in external validation. Among the six ML algorithms, the extreme gradient boosting (XGBoost) model had the highest AUC value with an average internal AUC of 0.738 and an external AUC of 0.729. The best performing ML algorithm model was used to build a web calculator to facilitate clinicians to calculate the risk of lung metastasis for each patient.

CONCLUSIONS

The XGBoost model may have the best prediction effect and the online calculator based on this model can help doctors to determine the lung metastasis risk of osteosarcoma patients and help to make individualized medical strategies.

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

•

Seven clinical factors were significantly related to the prognosis of patients with long bone osteosarcoma.

•

The established nomogram can help surgeons evaluate the prognosis of osteosarcoma patients in the most common sites.

•

High-risk individuals can be identified through risk-stratification system.

Background

Osteosarcoma (OS), most commonly occurring in long bone, is a group of malignant tumors with high incidence in adolescents. No individualized model has been developed to predict the prognosis of primary long bone osteosarcoma (PLBOS) and the current AJCC TNM staging system lacks accuracy in prognosis prediction. We aimed to develop a nomogram based on the clinicopathological factors affecting the prognosis of PLBOS patients to help clinicians predict the cancer-specific survival (CSS) of PLBOS patients.

Method

We studied 1199 PLBOS patients from the Surveillance, Epidemiology, and End Results (SEER) database from 2004 to 2015 and randomly divided the dataset into training and validation cohorts at a proportion of 7:3. Independent prognostic factors determined by stepwise multivariate Cox analysis were included in the nomogram and risk-stratification system. C-index, calibration curve, and decision curve analysis (DCA) were used to verify the performance of the nomogram.

Results

Age, Histological type, Surgery of primary site, Tumor size, Local extension, Regional lymph node (LN) invasion, and Distant metastasis were identified as independent prognostic factors. C-indexes, calibration curves and DCAs of the nomogram indicating that the nomogram had good discrimination and validity. The risk-stratification system based on the nomogram showed significant differences (P < 0.05) in CSS among different risk groups.

Conclusion

We established a nomogram with risk-stratification system to predict CSS in PLBOS patients and demonstrated that the nomogram had good performance. This model can help clinicians evaluate prognoses, identify high-risk individuals, and give individualized treatment recommendation of PLBOS patients.

Prevalence, Risk Factors, and Prognostic Factors of Primary Malignant Bone Neoplasms with Bone Metastasis at Initial Diagnosis: A Population-Based Study

Background. Bone metastasis (BM) has been proven to be responsible for the poor prognosis of primary malignant bone neoplasms (PMBNs). We aimed to identify the prevalence, risk factors, and prognostic factors for PMBNs patients with BM based on the Surveillance, Epidemiology, and End Results (SEER) database. Methods. 4,758 patients diagnosed with PMBNs from 2010 to 2018 were selected from the SEER database. All patients were divided into two groups: the BM group or the non-BM group. Pearson’s chi-square test and Fisher’s exact method were used to assess baseline characteristics, and logistic regression analysis was applied to assess risk factors. In addition, a nomogram was constructed based on the results of Cox regression analysis among 227 patients with BM. The good performance and clinical applicability of the nomogram were tested by the concordance index, operating characteristic curve, area under the curve, calibration curves, and decision curve analysis. Results. 227 (4.8%) patients had metastasis to bone at diagnosis. Primary site outside the extremities (axial: odds ratio, $\text{OR}=1.770$ ; others: $\text{OR}=1.951$ ), Ewing sarcoma ( $\text{OR}=2.845$ ), larger tumor size (5–8 cm: $\text{OR}=3.403$ ; >8 cm: $\text{OR}=5.562$ ), tumor extension beyond the periosteum ( $\text{OR}=2.477$ ), and regional lymph node metastasis ( $\text{OR}=2.900$ ) were associated with a higher risk of BM at the initial diagnosis of PMBNs. Five independent prognostic factors were found in the survival analysis: pathological type (chondrosarcoma vs. osteosarcoma: hazard ratio, $\text{HR}=0.342$ ; Ewing sarcoma vs. osteosarcoma: $\text{HR}=0.592$ ; and chordoma vs. osteosarcoma: $\text{HR}=0.015$ ), marital status ( $\text{HR}=2.457$ ), pulmonary metastasis ( $\text{HR}=1.934$ ), surgery at the primary site ( $\text{HR}=0.164$ ), and chemotherapy ( $\text{HR}=0.084$ ). A nomogram based on these prognostic factors could be a good predictor of cancer-specific survival. Conclusions. We identified the prevalence, risk factors, and prognostic factors correlated with BM in PMBNs patients. The related nomogram could be a practical tool for therapeutic decision-making and individual counseling.

Development and Validation of Prognostic Nomograms for Elderly Patients with Osteosarcoma

Background

The aim of the current study was to construct prognostic nomograms for individual risk prediction in elderly patients with osteosarcoma.

Methods

Data for 816 elderly patients (≥40 years old) with osteosarcoma between 2004 and 2016 from the Surveillance, Epidemiology, and End Results (SEER) database were randomly assigned to training (N=573) and internal validation (N=243) sets. The essential clinical predictors were identified based on least absolute shrinkage and selection operator (Lasso) Cox regression. Nomograms were constructed to predict the 1-, 3-, and 5-year cancer-specific survival (CSS) and overall survival (OS).

Results

Our LASSO regression analyses of the training set yielded five clinicopathological features (age, chemotherapy, surgery, AJCC stage, and summary stage) in the training cohort for the prognosis of elderly patients with osteosarcoma, while grade was only associated with OS and M stage was only associated with CSS. Construction of nomograms based on these predictors was performed to evaluate the prognosis of elderly patients with osteosarcoma. The C-index, calibration and decision curve analysis also showed the satisfactory performance of these nomograms for prognosis prediction.

Conclusion

The constructed nomograms are helpful tools for exactly predicting the prognosis of elderly patients with osteosarcoma, which could enable patients to be more accurately managed in clinical practice.

The Multiple Dimensions of Networks in Cancer: A Perspective

This perspective article gathers the latest developments in mathematical and computational oncology tools that exploit network approaches for the mathematical modelling, analysis, and simulation of cancer development and therapy design. It instigates the community to explore new paths and synergies under the umbrella of the Special Issue “Networks in Cancer: From Symmetry Breaking to Targeted Therapy”. The focus of the perspective is to demonstrate how networks can model the physics, analyse the interactions, and predict the evolution of the multiple processes behind tumour-host encounters across multiple scales. From agent-based modelling and mechano-biology to machine learning and predictive modelling, the perspective motivates a methodology well suited to mathematical and computational oncology and suggests approaches that mark a viable path towards adoption in the clinic.

Risk Factors, Prognostic Factors, and Nomograms for Distant Metastasis in Patients With Newly Diagnosed Osteosarcoma: A Population-Based Study

BACKGROUND

Osteosarcoma is the most common bone cancer, mainly occurring in children and adolescents, among which distant metastasis (DM) still leads to a poor prognosis. Although nomogram has recently been used in tumor areas, there are no studies focused on diagnostic and prognostic evaluation of DM in primary osteosarcoma patients.

METHODS

The data of osteosarcoma patients diagnosed between 2004 and 2015 were extracted from the Surveillance, Epidemiology, and End Results (SEER) database. Univariate and multivariate logistic regression analyses were used to identify independent risk factors for DM in osteosarcoma patients, and univariate and multivariate Cox proportional hazards regression analyses were used to determine independent prognostic factors of osteosarcoma patients with DM. We then established two novel nomograms and the results were evaluated by receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA).

RESULT

A total of 1,657 patients with osteosarcoma were included, and 267 patients (16.11%) had DM at the time of diagnosis. The independent risk factors for DM in patients with osteosarcoma include age, grade, T stage, and N stage. The independent prognostic factors for osteosarcoma patients with DM are age, chemotherapy and surgery. The results of ROC curves, calibration, DCA, and Kaplan-Meier (K-M) survival curves in the training, validation, and expanded testing sets, confirmed that two nomograms can precisely predict occurrence and prognosis of DM in osteosarcoma patients.

CONCLUSION

Two nomograms are expected to be effective tools for predicting the risk of DM for osteosarcoma patients and personalized prognosis prediction for patients with DM, which may benefit clinical decision-making.