Nomograms predicting long-term overall survival and cancer-specific survival in head and neck squamous cell carcinoma patients

Diagnostic and prognostic nomograms for laryngeal carcinoma patients with lung metastasis: a SEER-based study

PURPOSE

To establish two nomograms to quantify the risk of lung metastasis (LM) in laryngeal carcinoma (LC) and predict the overall survival of LC patients with LM.

METHODS

Totally 9515 LC patients diagnosed histologically from 2000 to 2019 were collected from the Surveillance, Epidemiology, and End Results database. The independent diagnostic factors for LM in LC patients and prognostic factors for LC patients with LM were identified by logistic and Cox regression analysis, respectively. Nomograms were established based on regression coefficients and evaluated by receiver operating characteristic curve, calibration curves, and decision curve analysis.

RESULTS

Patients with supraglottis, higher pathological grade, higher N stage, and distant metastasis (bone, brain, or liver) were more likely to have LM (P < 0.05). Chemotherapy, surgery and radiotherapy were independent factors of the overall survival of LC patients with LM (P < 0.05). The area under curve of diagnostic nomogram were 0.834 and 0.816 in the training and validation cohort respectively. For the prognostic nomogram, the area under curves of 1-, 2-, and 3-years were 0.735, 0.734, and 0.709 in the training cohort and 0.705, 0.803, and 0.809 in the validation cohort. The calibration curves and decision curve analysis indicated good performance of the nomograms.

CONCLUSION

Distant metastasis (bone, brain, or liver) and N stage should be considered for prediction of LM in LC patients. Chemotherapy is the most significant influencing prognostic factor improving the survival of LC patients with LM. Two nomograms may benefit for providing better precautionary measures and treatment decision.

Creation of a machine learning-based prognostic prediction model for various subtypes of laryngeal cancer

Depending on the source of the blastophore, there are various subtypes of laryngeal cancer, each with a unique metastatic risk and prognosis. The forecasting of their prognosis is a pressing issue that needs to be resolved. This study comprised 5953 patients with glottic carcinoma and 4465 individuals with non-glottic type (supraglottic and subglottic). Five clinicopathological characteristics of glottic and non-glottic carcinoma were screened using univariate and multivariate regression for CoxPH (Cox proportional hazards); for other models, 10 (glottic) and 11 (non-glottic) clinicopathological characteristics were selected using least absolute shrinkage and selection operator (LASSO) regression analysis, respectively; the corresponding survival models were established; and the best model was evaluated. We discovered that RSF (Random survival forest) was a superior model for both glottic and non-glottic carcinoma, with a projected concordance index (C-index) of 0.687 for glottic and 0.657 for non-glottic, respectively. The integrated Brier score (IBS) of their 1-year, 3-year, and 5-year time points is, respectively, 0.116, 0.182, 0.195 (glottic), and 0.130, 0.215, 0.220 (non-glottic), demonstrating the model's effective correction. We represented significant variables in a Shapley Additive Explanations (SHAP) plot. The two models are then combined to predict the prognosis for two distinct individuals, which has some effectiveness in predicting prognosis. For our investigation, we established separate models for glottic carcinoma and non-glottic carcinoma that were most effective at predicting survival. RSF is used to evaluate both glottic and non-glottic cancer, and it has a considerable impact on patient prognosis and risk factor prediction.

Development and validation of a nomogram to predict long-term cancer-specific survival for patients with osteosarcoma

The present work aimed to establish a new model to accurately estimate overall survival (OS) as well as cancer-specific survival (CSS) of osteosarcoma. Osteosarcoma cases were collected from the Surveillance, Epidemiology, and End Results (SEER) database between 2004 and 2017 and randomized as training or validation sets. Then, the OS- and CSS-related variables were discovered through multivariate Cox regression analysis to develop new nomograms to predict the 1-, 3- and 5-year OS and CSS. Besides, consistency index (C-index), decision curve analysis (DCA), along with calibration curve were adopted for assessing the predicting ability of our constructed nomograms after calibrating for 1-, 3- and 5-year OS and CSS. Altogether, 1727 osteosarcoma cases were enrolled in the present study and randomly divided as training (n = 1149, 70%) or validation (n = 576, 30%) set. As shown by univariate as well as multivariate Cox regression analyses, age, grade, T stage, M stage, surgery, chemotherapy, and histological type were identified to be the adverse factors to independently predict OS and CSS among the osteosarcoma cases. Besides, based on results of multivariate Cox regression analysis, we constructed the OS and CSS prediction nomograms. The C-index in training set was 0.806 (95% CI 0.769-0.836) for OS nomogram and 0.807 (95% CI 0.769-0.836) for CSS nomogram. In the meantime, C-index value in validation set was 0.818 (95% CI 0.789-0.847) for OS nomogram, while 0.804 (95% CI 0.773-0.835) for CSS nomogram. Besides, those calibration curves regarding the 3- and 5-year CSS of our constructed nomogram were highly consistent between the predicted values and the measurements in the training set as well as the external validation set. Our constructed nomogram outperformed the TNM stage in prediction. Our constructed nomogram is facile, creditable, and feasible; it efficiently predicts OS and CSS for osteosarcoma cases and can assist clinicians in assessing the prognosis for individuals and making decisions.

Population-based Long-term Outcomes for Squamous Cell Carcinoma of the Nasal Cavity

BACKGROUND

This study evaluates population-based outcomes of patients with squamous cell carcinoma (SCC) of the nasal cavity treated in British Columbia.

METHODS

A retrospective review of nasal cavity SCC treated from 1984 to 2014 was performed (n = 159). Locoregional recurrence (LRR) and overall survival (OS) were evaluated.

RESULTS

The 3-year OS was 74.2% for radiation alone, 75.8% for surgery alone, and 78.4% for surgery and radiation ( P = 0.16). The 3-year LRR was 28.4% for radiation alone, 28.2% for surgery alone, and 22.6% for surgery and radiation ( P = 0.21). On multivariable analysis, surgery and postoperative radiation relative to surgery alone was associated with a lower risk of LRR (hazard ratio: 0.36, P = 0.03). Poor Eastern Cooperative Oncology Group status, node-positive, orbital invasion, smoking, and advanced age were associated with worse OS (all P <0.05).

CONCLUSION

In this population-based analysis, multimodality treatment with surgery and adjuvant radiation were associated with improved locoregional control for SCC of the nasal cavity.

Machine Learning and Nomogram Prognostic Modeling for 2-Year Head and Neck Cancer-Specific Survival Using Electronic Health Record Data: A Multisite Study

PURPOSE

There is limited knowledge of the prediction of 2-year cancer-specific survival (CSS) in the head and neck cancer (HNC) population. The aim of this study is to develop and validate machine learning models and a nomogram for the prediction of 2-year CSS in patients with HNC using real-world data collected by major teaching and tertiary referral hospitals in New South Wales (NSW), Australia.

MATERIALS AND METHODS

Data collected in oncology information systems at multiple NSW Cancer Centres were extracted for 2,953 eligible adults diagnosed between 2000 and 2017 with squamous cell carcinoma of the head and neck. Death data were sourced from the National Death Index using record linkage. Machine learning and Cox regression/nomogram models were developed and internally validated in Python and R, respectively.

RESULTS

Machine learning models demonstrated highest performance (C-index) in the larynx and nasopharynx cohorts (0.82), followed by the oropharynx (0.79) and the hypopharynx and oral cavity cohorts (0.73). In the whole HNC population, C-indexes of 0.79 and 0.70 and Brier scores of 0.10 and 0.27 were reported for the machine learning and nomogram model, respectively. Cox regression analysis identified age, T and N classification, and time-corrected biologic equivalent dose in two gray fractions as independent prognostic factors for 2-year CSS. N classification was the most important feature used for prediction in the machine learning model followed by age.

CONCLUSION

Machine learning and nomogram analysis predicted 2-year CSS with high performance using routinely collected and complete clinical information extracted from oncology information systems. These models function as visual decision-making tools to guide radiotherapy treatment decisions and provide insight into the prediction of survival outcomes in patients with HNC.

Does Operable Stage IV Gingivobuccal Cancers Need Further Prognostic Subgrouping?

Background

Operable stage IV gingivobuccal complex cancer is classified as Stage IVA and IVB. Among patients with Stage IVA disease, different subgroups with likely different prognoses are combined. Patients with advanced nodal status tend to have a poorer prognosis. We divided these patients into four groups: group I (T4aN0), group II (T4aN1-2), group III (T1-3N2) constituting stage IVA category, and group IV (TanyN3) representing stage IVB. This study assesses if these patients can be prognostically subgrouped based on nodal status.

Methods

It is a prospective observational study done at a tertiary care center from July 2017 to June 2020. This study aims to analyze survival outcomes in these subgroups using Kaplan Meir, univariate and multivariate analysis.

Results

The study enrolled 113 patients of operable gingivobuccal complex stage IVA cancer with a median follow up of 26 months, disease-free survival (DFS) was 74% for group 1, while it was 55%, 26% and 32.2% for group 2, group 3 and group 4 respectively. Patients with T4N3 disease had DFS of just 15%. Patients in group 3 and 4 had the worst outcomes in terms of DFS and Overall Survival(OS) with HR-3.7 and 3.3 and 3.3 and 3.8 respectively (p value-0.001).

Conclusion

The nodal status is the most important prognostic factor affecting DFS and OS. Patients with small primary but advanced nodal stage do poorly than patients with advanced primary and node-negative disease. There is a need for subgrouping patients with Stage IVA tumors based on nodal status for better prognostication.

The prognostic value of machine learning techniques versus cox regression model for head and neck cancer

BACKGROUND

Accurate prognostic prediction for head and neck cancer (HNC) is important for the improvement of clinical management. We aimed to compare the prognostic value of various machine learning techniques (MLTs) and statistical Cox regression model for different types of HNC.

METHODS

Clinical data of HNC patients were extracted from the Surveillance, Epidemiology, and End Results (SEER) database from 1974 to 2016. The prediction performance of five ML models, including random forest (RF), gradient boosting decision tree (GBDT), support vector machine (SVM), neural network (NN) and deep learning (DL), were compared with the statistical Cox regression model by estimating the concordance index (C-index), integrated Brier score (IBS), time-dependent receiver operating characteristic (ROC) curve and the area under the curve (AUC).

RESULTS

Our results showed that the RF model outperformed all other models in prognostic prediction for all tumor sites of HNC, particularly for major salivary gland cancer (MSGC, C-index: 88.730 ± 0.8700, IBS: 7.680 ± 0.4800), oral cavity cancer (OCC, C-index: 84.250 ± 0.6700, IBS: 11.480 ± 0.3300) and oropharyngeal cancer (OPC, C-index: 82.510 ± 0.5400, IBS: 10.120 ± 0.1400). Meanwhile, we analyzed the importance of each clinical variable in the RF model, in which age and tumor size presented the strongest positive prognostic effects. Additionally, similar results can be observed in the internal (6th edition of the AJCC TNM staging system cohort) and external validations (the TCGA HNC cohort).

CONCLUSIONS

The RF model is a promising prognostic prediction tool for HNC patients, regardless of the anatomic subsites.

A Research Study to Measure the Efficacy of Terminating Cervical Cancer via Customized Optimum Pathway

Background

To develop a precise prognostic model of overall survival in patients with terminating cervical cancer based on surveillance, epidemiology, and end results (SEER) program.

Methods

The patients were retrieved from SEER data who are diagnosed with terminating cervical cancer from 2004 to 2016. The data were performed using univariate and multivariate analyses and constructed nomograms for predicting survival. Use C-index to validate the model accuracy.

Results

Totally 15839 patients diagnosed with cervical cancer were independently allocated into the training set (n = 11088) and validation set (n = 4751). The multivariate analysis results indicated that age, race, stage_T, stage_M, and stage_N were confirmed as independent risk predictors, and those factors are applied to construct this clinical model. The C-index of overall survival in the training set was 0.6816 (95% confidence intervene (CI), 0.694-0.763) and that in the validation set was 0.6931(95% CI, 0.613-0.779). All calibration curves of various factors were consistent with predicted and actual survival.

Conclusion

The nomogram provides a novel method for predicting the survival of patients with terminating cervical cancer, assisting in accurate therapeutic methods for patients with primary terminating cervical cancer.

Cross-institutional outcome prediction for head and neck cancer patients using self-attention neural networks

In radiation oncology, predicting patient risk stratification allows specialization of therapy intensification as well as selecting between systemic and regional treatments, all of which helps to improve patient outcome and quality of life. Deep learning offers an advantage over traditional radiomics for medical image processing by learning salient features from training data originating from multiple datasets. However, while their large capacity allows to combine high-level medical imaging data for outcome prediction, they lack generalization to be used across institutions. In this work, a pseudo-volumetric convolutional neural network with a deep preprocessor module and self-attention (PreSANet) is proposed for the prediction of distant metastasis, locoregional recurrence, and overall survival occurrence probabilities within the 10 year follow-up time frame for head and neck cancer patients with squamous cell carcinoma. The model is capable of processing multi-modal inputs of variable scan length, as well as integrating patient data in the prediction model. These proposed architectural features and additional modalities all serve to extract additional information from the available data when availability to additional samples is limited. This model was trained on the public Cancer Imaging Archive Head–Neck-PET–CT dataset consisting of 298 patients undergoing curative radio/chemo-radiotherapy and acquired from 4 different institutions. The model was further validated on an internal retrospective dataset with 371 patients acquired from one of the institutions in the training dataset. An extensive set of ablation experiments were performed to test the utility of the proposed model characteristics, achieving an AUROC of \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$80\%$$\end{document}80%, \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$80\%$$\end{document}80% and \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$82\%$$\end{document}82% for DM, LR and OS respectively on the public TCIA Head–Neck-PET–CT dataset. External validation was performed on a retrospective dataset with 371 patients, achieving \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$69\%$$\end{document}69% AUROC in all outcomes. To test for model generalization across sites, a validation scheme consisting of single site-holdout and cross-validation combining both datasets was used. The mean accuracy across 4 institutions obtained was \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$72\%$$\end{document}72%, \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$70\%$$\end{document}70% and \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$71\%$$\end{document}71% for DM, LR and OS respectively. The proposed model demonstrates an effective method for tumor outcome prediction for multi-site, multi-modal combining both volumetric data and structured patient clinical data.

Nomograms predicting the overall and cancer-specific survival of patients with buccal mucosa cancer

OBJECTIVES

To construct predictive models for predicting overall survival (OS) and cancer-specific survival (CSS) of patients with buccal mucosa cancer (BMC).

STUDY DESIGN

Data of 936 patients with BMC were extracted from the Surveillance, Epidemiology, and End Results (SEER) database from 2004 to 2015. Nomograms were constructed based on multivariate Cox regression analyses, and validated using calibration plots, time-dependent receiver operating characteristic curves, and decision curve analyses.

RESULTS

Age at diagnosis, marital status, grade, histopathology, SEER stage, tumor size, and surgery were associated with OS, whereas age at diagnosis, grade, histopathology, SEER stage, tumor size, and surgery were associated with CSS (all P < .05). The concordance indexes for OS and CSS were 0.79 and 0.80 in the training cohort, respectively, and those in the validation cohort were 0.78 and 0.80. Time-dependent receiver operating characteristic curves showed great predictability in nomograms. Decision curve analyses demonstrated good clinical value for OS (4%-88%) and CSS (3%-77%) nomograms. Patients were stratified into 3 risk groups, with the worst prognosis in the high-risk subgroup (P < .001).

CONCLUSIONS

We developed and validated 2 nomograms predicting OS and CSS and established the corresponding risk classification systems in patients with BMC. These models assisted in precise administration of individual therapeutic regimens.

The Clinical Characteristics and Prognostic Nomogram for Head and Neck Cancer Patients with Bone Metastasis

Background

Head and neck cancer (HNC) is the sixth most common malignancy globally, and many demographics and clinicopathological factors influence its prognosis. This study aimed to construct and validate a prognostic nomogram to predict the prognosis of HNC patients with bone metastasis (BM).

Methods

A total of 326 patients with BM from HNC were collected from the SEER database as the subjects of this study. In a ratio of 7 to 3, patients were randomly divided into training and validation groups. Independent prognostic factors for HNC patients with BM were identified by univariate and multivariate Cox regression analysis. The nomogram for predicting the prognosis was constructed, and the model was evaluated by receiver operating characteristic curves, calibration curves, and decision curve analysis.

Result

The independent prognostic factors for HNC patients with BM included age, primary site, lung metastasis, and chemotherapy. The area under the curve predicting overall survival at 12, 24, and 36 months was 0.768, 0.747, and 0.723 in the training group and 0.729, 0.723, and 0.669 in the validation group, respectively. The calibration curves showed good agreement between the predicted and actual values for overall survival. In addition, the decision curve analysis showed that this prognostic nomogram model has a high clinical application.

Conclusion

This study developed and validated a nomogram to predict overall survival in HNC patients with BM. The prognostic nomogram has high accuracy and utility to inform survival estimation and individualized treatment decisions.

Analysis of clinical characteristics and prognosis with cervical adenosquamous carcinoma: a large population-based study

Objective: The target of this work was to analyze the clinical characteristics and construct nomograms to predict prognosis in patients with cervical adenosquamous carcinoma (ASC). Methods: A total of 788 ASC patients were tracked in the Surveillance, Epidemiology and End Results database. We compared the clinical characteristics and prognostic factors of ASC. Cox regression models were established, and nomograms were constructed and verified. Results: ASC patients have lower age levels and higher histological grades than patients with squamous cell carcinoma. Nomograms were constructed with good consistency and feasibility in clinical practice. The C-indices for overall survival and cancer-specific survival were 0.783 and 0.787, respectively. Conclusion: ASC patients have unique clinicopathological and prognostic characteristics. Nomograms were successfully constructed and verified.

Development and validation of multiparametric MRI-based nomogram for predicting occult metastasis risk in early tongue squamous cell carcinoma

Background

Nomograms are currently used in predicting individualized outcomes in clinical oncology of several cancers. However, nomograms for evaluating occult nodal metastasis of patients with squamous cell carcinoma of lateral tongue (SCCLT) have not been widely investigated for their functionality. This retrospective cohort study was designed to address this question.

Methods

This study was divided into primary and validation cohorts. The primary cohort comprised 120 patients diagnosed between 2012 and 2017, whereas the validation cohort included 41 patients diagnosed thereafter. The diagnostic value of multiparametric MRI, including radiologic tumor thickness threshold (rTTT) in three-dimensions, paralingual distance, and sublingual distance were investigated. A nomogram was developed based on stepwise logistic regression of potential predictors associated with nodal metastasis in the primary cohort and then tested for predictive accuracy in the validation cohort using area under the curve (AUC) and goodness-of-fit tests.

Results

Multivariate analysis, tumor size (odd ratio [OR] 15.175, 95% confidence interval [CI] 1.436–160.329, P = 0.024), rTTT (OR 11.528, 95% CI 2.483–53.530, P = 0.002), paralingual distance (OR 11.976, 95% CI 1.981–72.413, P = 0.005), and tumor location (OR 6.311, 95% CI 1.514–26.304, P = 0.011) were included in the nomogram to predict the likelihood of having cervical metastasis. A nomogram cutoff value of 210 points (sensitivity 93.8%, specificity 87.5%) was significantly different to classify the patients metastasis risk group (P < 0.001). Nomogram showed predictive accuracy with AUC 0.881 (95% CI 0.779–0.983, P < 0.001) and good calibration after the validation.

Conclusions

A preoperative nomogram incorporating multiparametric MRI demonstrated good prediction and performed adequately in our study. Three-dimensional assessment of occult metastasis risk value obtained from this nomogram can assist in preoperative decision making for individual patients with early-stage SCCLT. The probability of nodal metastasis tended to be greater than 20% in patients with high metastasis risk or nomogram total score > 210 points.

Prognostic Nomograms to Predict Overall Survival and Cancer-Specific Survival of Patients With Pancreatic Neuroendocrine Tumors: A Population-Based Study

OBJECTIVE

The objective of this research was to construct and validate prognostic nomograms predicting overall survival (OS) and cancer-specific survival (CSS) in patients with pancreatic neuroendocrine tumors (pNETs).

METHODS

We extracted 3787 patients with pNETs from the Surveillance, Epidemiology and End Results database. Nomograms for estimating 3- and 5-year OS and CSS were first established. Then, we used Harrell's Concordance Index, calibration plots, and the area under receiver operating characteristic curve to evaluate the nomograms. The Kaplan-Meier curve was plotted to evaluate the different survival outcomes.

RESULTS

In the multivariate analysis, age, grade, functional status, American Joint Committee on Cancer stage, and surgery were associated with OS and CSS. The established nomograms had good discriminative ability, with a Harrell's Concordance Index of 0.830 for OS and 0.855 for CSS. The calibration plots also revealed good agreement. The area under receiver operating characteristic curve values of the nomograms predicting 3- and 5-year OS and CSS rates were 0.836, 0.816 and 0.859, 0.841, respectively. In addition, Kaplan-Meier curve indicated that patients with higher risk had worse survival outcomes.

CONCLUSIONS

We have proposed and validated the nomograms predicting OS and CSS of pNETs. They can be convenient individualized tools to facilitate clinical decision making.

Predictive nomograms for oral tongue squamous cell carcinoma applying the American Joint Committee on Cancer/Union Internationale Contre le Cancer 8th edition staging system

BACKGROUND

Nomograms applying the 8th edition of the TNM staging system aimed at predicting overall (OS), disease-specific (DSS), locoregional recurrence-free (LRRFS) and distant recurrence-free survivals (DRFS) for oral tongue squamous cell carcinoma (OTSCC) are still lacking.

METHODS

A training cohort of 438 patients with OTSCC was retrospectively enrolled from a single institution. An external validation set of 287 patients was retrieved from two independent institutions.

RESULTS

Internal validation of the multivariable models for OS, DSS, DRFS and LRRFS showed a good calibration and discrimination results with optimism-corrected c-indices of 0.74, 0.75, 0.77 and 0.70, respectively. The external validation confirmed the good performance of OS, DSS and DRFS models (c-index 0.73 and 0.77, and 0.73, respectively) and a fair performance of the LRRFS model (c-index 0.58).

CONCLUSIONS

The nomograms herein presented can be implemented as useful tools for prediction of OS, DSS, DRFS and LRRFS in OTSCC.

A novel prognostic model predicting the long-term cancer-specific survival for patients with hypopharyngeal squamous cell carcinoma

Background

Hypopharyngeal squamous cell carcinoma (HSCC) is a rare type of head and neck cancer with poor prognosis. However, till now, there is still no model predicting the survival outcomes for HSCC patients. We aim to develop a novel nomogram predicting the long-term cancer-specific survival (CSS) for patients with HSCC and establish a prognostic classification system.

Methods

Data of 2021 eligible HSCC patients were retrieved from the Surveillance, Epidemiology and End Results database between 2010 and 2015. We randomly split the whole cases (ratio: 7:3) into the training and the validation cohort. Cox regression as well as the Least absolute shrinkage and selection operator (LASSO) COX were used to select significant predictors of CSS. Based on the beta-value of these predictors, a novel nomogram was built. The concordance index (C-index), the calibration curve and the decision curve analysis (DCA) were utilized for the model validation and evaluation using the validation cohort.

Results

In total, cancer-specific death occurred in 974/2021 (48.2%) patients. LASSO COX indicated that age, race, T stage, N stage, M stage, surgery, radiotherapy and chemotherapy are significant prognosticators of CSS. A prognostic model based on these factors was constructed and visually presented as nomogram. The C-index of the model was 0.764, indicating great predictive accuracy. Additionally, DCA and calibration curves also demonstrated that the nomogram had good clinical effect and satisfactory consistency between the predictive CSS and actual observation. Furthermore, we developed a prognostic classification system that divides HSCC patients into three groups with different prognosis. The median CSS for HSCC patients in the favorable, intermediate and poor prognosis group was not reached, 39.0-Mo and 10.0-Mo, respectively (p < 0.001).

Conclusions

In this study, we constructed the first nomogram as well as a relevant prognostic classification system that predicts CSS for HSCC patients. We believe these tools would be helpful for clinical practice in patients’ consultation and risk group stratification.

Applying nomograms based on the surveillance, epidemiology and end results database to predict long-term overall survival and cancer-specific survival in patients with oropharyngeal squamous cell carcinomas: A case-control research

Few models regarding to the individualized prognosis assessment of oropharyngeal squamous cell carcinoma (OPSCC) patients were documented. The purpose of this study was to establish nomogram model to predict the long-term overall survival (OS) and cancer-specific survival (CSS) of OPSCC patients. The detailed clinical data for the 10,980 OPSCC patients were collected from the surveillance, epidemiology and end results (SEER) database. Furthermore, we applied a popular and reasonable random split-sample method to divide the total 10,980 patients into 2 groups, including 9881 (90%) patients in the modeling cohort and 1099 (10%) patients in the external validation cohort. Among the modeling cohort, 3084 (31.2%) patients were deceased at the last follow-up date. Of those patients, 2188 (22.1%) patients died due to OPSCC. In addition, 896 (9.1%) patients died due to other causes. The median follow-up period was 45 months (1-119 months). We developed 2 nomograms to predict 5- and 8- year OS and CSS using Cox Proportional Hazards model. The nomograms' accuracy was evaluated through the concordance index (C-index) and calibration curves by internal and external validation. The C-indexes of internal validation on the 5- and 8-year OS and CSS were 0.742 and 0.765, respectively. Moreover, the C-indexes of external validation were 0.740 and 0.759, accordingly. Based on a retrospective cohort from the SEER database, we succeeded in constructing 2 nomograms to predict long-term OS and CSS for OPSCC patients, which provides reference for surgeons to develop a treatment plan and individual prognostic evaluations.

A nomogram based on a gene signature for predicting the prognosis of patients with head and neck squamous cell carcinoma

BACKGROUND

Head and neck squamous cell carcinoma (HNSCC) is one of the most common malignant tumors. The purpose of this study was to establish and validate a gene-expression-based prognostic signature in non-metastatic patients with HNSCC.

MATERIALS AND METHODS

All the patients were retrieved from The Cancer Genome Atlas (TCGA) and Gene Expression Omnibus (GEO) databases. We randomly divided the GSE65858 samples into 70% (training cohort, n = 190) and 30% (internal validation cohort, n = 72). A total of 36 samples collected from the TCGA HNSCC databases were selected as an independent external validation cohort. The oligo package in R was used to normalize the raw data before analysis. Data characteristics were extracted, and a gene signature was built via the least absolute shrinkage and selection operator regression model. The predictive model was developed by multivariable Cox regression analysis. T stage, N stage, human papilloma virus status, and the gene signature were incorporated in this predictive model, which was shown as a nomogram. Calibration and discrimination were performed to assess the performance of the nomogram. The clinical utility of this nomogram was assessed by the decision curve analysis.

RESULTS

Overall, 2001 significant messenger RNAs in HNSCC samples were identified compared with normal samples. The gene signature contained seven genes and significantly correlated with overall survival. The gene signature was also significant in subgroup analysis of the primary cohort. The calibration was plotted in the external cohort (C-index 0.90, 95% CI 0.85, 0.95) compared with the training (C-index 0.76, 95% CI 0.73, 0.79) and internal (C-index 0.71, 95% CI 0.66, 0.77) cohorts. In clinic, a decision curve analysis demonstrated that the model including the prognostic gene signature score status was better than that without it.

CONCLUSION

This study developed and validated a predictive model, which can promote the individualized prediction of overall survival in non-metastatic patients with HNSCC.

Prognostic Nomograms for Predicting Overall Survival and Cancer-Specific Survival of Patients with Major Salivary Gland Mucoepidermoid Carcinoma

Background: The aim of this study was to develop and validate prognostic nomograms predicting overall (OS) and cancer-specific survival (CSS) of patients with major salivary gland (MaSG) mucoepidermoid carcinoma (MEC).

Methods: 1398 MaSG-MEC patients were identified from the Surveillance, Epidemiology and End Results (SEER) database. They were randomly and equally divided into a training cohort (n=699) and a validation cohort (n=699). The best subsets of covariates were identified to develop nomograms predicting OS and CSS based on the smallest Akaike Information Criterion (AIC) value in the multivariate Cox models. The nomograms were internally and externally validated by the bootstrap resampling method. The predictive ability was evaluated by Harrell's Concordance Index (C-index).

Results: For the training cohort, eight (age at diagnosis, tumor grade, primary site, surgery, radiation, T, N and M classification) and seven predictors (all the above factors except primary site) were selected to create the nomograms estimating the 3- and 5- year OS and CSS, respectively. C-index indicated better predictive performance of the nomograms than the 7th AJCC staging system, which was confirmed by both internal (via the training cohort: OS: 0.888 vs 0.785, CSS: 0.938 vs 0.821) and external validation (via the validation cohort: OS: 0.844 vs 0.743, CSS: 0.882 vs 0.787). The calibration plots also revealed good agreements between the nomogram-based prediction and observed survival.

Conclusions: We have proposed and validated the nomograms predicting OS and CSS of MaSG-MEC. They are proved to be of higher predictive value than the AJCC staging system and may be adopted in future clinical practice.

MRI-based radiomic signature as predictive marker for patients with head and neck squamous cell carcinoma

PURPOSE

To develop magnetic resonance imaging (MRI)-based radiomic signature and nomogram for preoperatively predicting prognosis in head and neck squamous cell carcinoma (HNSCC) patients.

METHOD

This retrospective study consisted of a training cohort (n = 85) and a validation cohort (n = 85) of patients with HNSCC. LASSO Cox regression model was used to select the most useful prognostic features with their coefficients, upon which a radiomic signature was generated. The receiver operator characteristics (ROC) analysis and association of the radiomic signature with overall survival (OS) of patients was assessed in both cohorts. A nomogram incorporating the radiomic signature and independent clinical predictors was then constructed. The incremental prognostic value of the radiomic signature was evaluated.

RESULTS

The radiomic signature, consisted of 7 selected features from MR images, was significantly associated with OS of patients with HNSCC (P < 0.0001 for training cohort, P = 0.0013 for validation cohort). The radiomic signature and TNM stage were proved to be independently associated with OS of HNSCC patients, which therefore were incorporated to generate the radiomic nomogram. In the training cohort, the nomogram showed a better prognostic capability than TNM stage only (P =  0.005), which was confirmed in the validation cohort (P =  0.01). Furthermore, the calibration curves of the nomogram demonstrated good agreement with actual observation.

CONCLUSIONS

MRI-based radiomic signature is an independent prognostic factor for HNSCC patients. Nomogram based on radiomic signature and TNM stage shows promising in non-invasively and preoperatively predicting prognosis of HNSCC patient in clinical practice.

Nomograms to predict survival of stage IV tongue squamous cell carcinoma after surgery

To develop clinical nomograms for prediction of overall survival (OS) and cancer-specific survival (CSS) in patients with stage IV tongue squamous cell carcinoma (TSCC) after surgery based on the Surveillance, Epidemiology, and End Results (SEER) program database.We collected data of resected stage IV TSCC patients from the SEER database, and divided them into the training set and validation set by 7:3 randomly. Kaplan-Meier analysis and Cox regression analysis were adopted to distinguish independent risk factors for OS and CSS. Clinical nomograms were constructed to predict the 3-year and 5-year probabilities of OS and CSS for individual patients. Calibration curves and Harrell C-indices were used for internal and external validation.A total of 1550 patients with resected stage IV TSCC were identified. No statistical differences were detected between the training and validation sets. Age, race, marital status, tumor site, AJCC T/N/M status, and radiotherapy were recognized as independent prognostic factors associated with OS as well as CSS. Then nomograms were developed based on these variables. The calibration curves displayed a good agreement between the predicted and actual values of 3-year and 5-year probabilities for OS and CSS. The C-indices predicting OS were corrected as 0.705 in the training set, and 0.664 in the validation set. As for CSS, corrected C-indices were 0.708 in the training set and 0.663 in the validation set.The established nomograms in this study exhibited good accuracy and effectiveness to predict 3-year and 5-year probabilities of OS and CSS in resected stage IV TSCC patients. They are useful tools to evaluate survival outcomes and helped choose appropriate treatment strategies.

Nomograms predicting overall survival and cancer-specific survival in osteosarcoma patients (STROBE)

The aim of this study was to develop nomograms to predict long-term overall survival and cancer-specific survival of patients with osteosarcoma.We carried out univariate and multivariate analyses and set up nomograms predicting survival outcome using osteosarcoma patient data collected from the Surveillance, Epidemiology and End Results (SEER) program of the National Cancer Institute (2004-2011, n = 1426). The patients were divided into a training cohort (2004-2008, n = 863) and a validation cohort (2009-2011, n = 563), and the mean follow-up was 55 months.In the training cohort, 304 patients (35.2%) died from osteosarcoma and 91 (10.5%) died from other causes. In the validation cohort, 155 patients (27.5%) died from osteosarcoma and (12.3%) died from other causes. Nomograms predicting overall survival (OS) and cancer-specific survival (CSS) were developed according to 6 clinicopathologic factors (age, tumor site, historic grade, surgery, AJCC T/N, and M), with concordance indexes (C-index) of 0.725 (OS) and 0.718 (CSS), respectively. The validation C-indexes were 0.775 and 0.742 for OS and CSS, respectively.Our results suggest that we have successfully developed highly accurate nomograms for predicting 5-year OS and CSS for osteosarcoma patients. These nomograms will help surgeons customize treatment and monitoring strategies for osteosarcoma patients.

Personalized prognostication in head and neck cancer: A systematic review of nomograms according to the AJCC precision medicine core (PMC) criteria

BACKGROUND

The American Joint Committee on Cancer (AJCC) Precision Medicine Core (PMC) has recognized the need for more personalized probabilistic predictions above the "TNM" staging system and has recently released a checklist of inclusion and exclusion criteria for evaluating prognostic models.

METHODS

A systematic review of articles in which nomograms were created for head and neck cancer (HNC) was carried out according to Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. The AJCC PMC criteria were used to score the individual studies.

RESULTS

Forty-four studies were included in the final qualitative analysis. The mean number of inclusion criteria met was 9.3 out of 13, and the mean number of exclusion criteria met was 2.1 out of 3. Studies were generally of high quality, but no single study fulfilled all of the AJCC PMC criteria.

CONCLUSION

This is the first study to utilize the AJCC checklist to comprehensively evaluate the published prognostic nomograms in HNC. Future studies should attempt to adhere to the AJCC PMC criteria. Recommendations for future research are given.

SUMMARY

The AJCC recently released a set of criteria to grade the quality of prognostic cancer models. In this study, we grade all published nomograms for head and neck cancer according to the new guidelines.

Quantitative prediction of oral cancer risk in patients with oral leukoplakia

Exfoliative cytology has been widely used for early diagnosis of oral squamous cell carcinoma. We have developed an oral cancer risk index using DNA index value to quantitatively assess cancer risk in patients with oral leukoplakia, but with limited success. In order to improve the performance of the risk index, we collected exfoliative cytology, histopathology, and clinical follow-up data from two independent cohorts of normal, leukoplakia and cancer subjects (training set and validation set). Peaks were defined on the basis of first derivatives with positives, and modern machine learning techniques were utilized to build statistical prediction models on the reconstructed data. Random forest was found to be the best model with high sensitivity (100%) and specificity (99.2%). Using the Peaks-Random Forest model, we constructed an index (OCRI2) as a quantitative measurement of cancer risk. Among 11 leukoplakia patients with an OCRI2 over 0.5, 4 (36.4%) developed cancer during follow-up (23 ± 20 months), whereas 3 (5.3%) of 57 leukoplakia patients with an OCRI2 less than 0.5 developed cancer (32 ± 31 months). OCRI2 is better than other methods in predicting oral squamous cell carcinoma during follow-up. In conclusion, we have developed an exfoliative cytology-based method for quantitative prediction of cancer risk in patients with oral leukoplakia.

Nomograms forecasting long-term overall and cancer-specific survival of patients with oral squamous cell carcinoma

Our aim was to establish a "nomogram" model to forecast the overall survival (OS) and cancer-specific survival (CSS) of oral squamous cell carcinoma (OSCC) patients. The clinicopathological data for the 10,533 OSCC patients were collected from the Surveillance, Epidemiology and End Results (SEER) database. We used a credible random split-sample method to divide 10,533 patients into two cohorts: 7046 patients in the modeling cohort and 3487 patients in the external validation cohort (split-ratio = 2:1). The median follow-up period was 32 months (1-119 months). We developed nomograms to predict 5- and 8-year OS and CSS of OSCC patients with a Cox proportional hazards model. The precision of the nomograms was assessed by the concordance index (C-index) and calibration curves through internal and external validation. The C-indexes of internal validation regarding 5- and 8-year OS and CSS were 0.762 and 0.783, respectively. In addition, the external validation's C-indexes were 0.772 and 0.800. Based on a large-sample analysis targeting the SEER database, we established two nomograms to predict long-term OS and CSS for OSCC patients successfully, which can assist surgeons in developing a more effective therapeutic regimen and conducting personalized prognostic evaluations.

Nomograms for predicting long-term overall survival and cancer-specific survival in patients with major salivary gland cancer: a population-based study

In this study, we aimed to develop and validate nomograms for predicting long-term overall survival (OS) and cancer-specific survival (CSS) in major salivary gland cancer (MSGC) patients. These nomograms were developed using a retrospective cohort (N=4218) from the Surveillance, Epidemiology, and End Results (SEER) database, and externally validated using an independent data cohort (N=244). We used univariate, and multivariate analyses, and cumulative incidence function to select the independent prognostic factors of OS and CSS. Index of concordance (c-index) and calibration plots were used to estimate the nomograms’ predictive accuracy. The median follow-up period was 34 months (1–119 months). Of 4218 MSGC patients, 1320 (31.3%) died by the end of the follow-up; of these 1320 patients, 883 (20.9%) died of MSGC. The OS nomogram, which had a c-index of 0.817, was based on nine variables: age, sex, tumor site, tumor grade, surgery performed, radiation therapy and TNM classifications. The CSS nomogram, which had a c-index of 0.829, was based on the same nine variables plus race. External validation c-indexes were 0.829 and 0.807 for OS and CSS, respectively. Based on SEER database, we have developed nomograms predicting five- and eight-years OS and CSS for MSGC patients with perfect accuracy. These nomograms will help clinicians customize treatment and monitoring strategies in MSGC patients.

Development of comprehensive nomograms for evaluating overall and cancer-specific survival of laryngeal squamous cell carcinoma patients treated with neck dissection

Background

Neck dissection for laryngeal squamous cell carcinoma (LSCC) patients could provide complementary prognostic information for AJCC N staging, like lymph node ratio (LNR). The aim of this study was to develop effective nomograms to better predict survival for LSCC patients treated with neck dissection.

Results

2752 patients were identified and randomly divided into training (n = 2477) and validation (n = 275) cohorts. The 3- and 5-year probabilities of cancer-specific mortality (CSM) were 30.1% and 37.2% while 3- and 5-year death resulting from other causes (DROC) rate were 6.2% and 11.3%, respectively. 13 significant prognostic factors including LNR for overall (OS) and 12 (except race) for CSS were enrolled in the nomograms. Concordance index as a commonly used indicator of predictive performance, showed the nomograms had superiority over the no-LNR models and TNM classification (Training-cohort: OS: 0.713 vs 0.703 vs 0.667, CSS: 0.725 vs 0.713 vs 0.688; Validation-cohort: OS: 0.704 vs 0.690 vs 0.658, cancer-specific survival (CSS): 0.709 vs 0.693 vs 0.672). All calibration plots revealed good agreement between nomogram prediction and actual survival.

Materials and Methods

We identified LSCC patients undergoing neck dissection diagnosed between 1988 and 2008 from Surveillance, Epidemiology, and End Results (SEER) database. Optimal cutoff points were determined by X-tile program. Cumulative incidence function was used to analyze cancer-specific mortality (CSM) and death resulting from other causes (DROC). Significant predictive factors were used to establish nomograms estimating overall (OS) and cancer-specific survival (CSS). The nomograms were bootstrapped validated both internally and externally.

Conclusions

Comprehensive nomograms were constructed to predict OS and CSS for LSCC patients treated with neck dissection more accurately.

Development and validation of a prognostic nomogram for IgA nephropathy

IgA nephropathy (IgAN) shows strong heterogeneity between individuals. IgAN prognosis is associated with pathological lesions and clinical indicators. However, simple tools for evaluating the clinical prognosis remain inadequate. Our objective was to develop an intuitive estimation tool for predicting the IgAN prognosis. 349 patients with IgAN at The Chinese People’s Liberation Army General Hospital were retrospectively analyzed from data between 2000 and 2006. A nomogram was developed using COX regression coefficients to predict decline of estimate Glomerular filtration rate (eGFR) ≥ 50% and end-stage renal disease (ESRD). The discriminative ability and predictive accuracy of the nomogram was determined via concordance index (C-index) and calibration curve. The results were verified in an independent validation cohort. In the derivation cohort, the nomogram was developed using mesangial hypercellularity, tubular atrophy/interstitial fibrosis, average proteinuria (A-P), and average mean arterial pressure (A-MAP) during hospitalization. The C-index of the nomogram was 0.88 (95% CI, 0.80 to 0.96). The calibration curve showed good agreement between prediction and actual observation. Furthermore, the nomogram demonstrated good discrimination (C-index = 0.87, 95% CI 0.78 to 0.95) and calibration in the validation cohort. The nomogram could predict the prognosis of IgAN effectively and intuitively.

Prognostic value of maximum standardized uptake value measured by pretreatment 18F-FDG PET/CT in locally advanced head and neck squamous cell carcinoma

PURPOSE/OBJECTIVES

To evaluate the prognostic impact of maximum standardized uptake value (SUV_max) in patients with locally advanced head and neck squamous cell carcinoma (HNSCC) undergoing pretreatment [F-18] fluoro-D-glucose-positron emission tomography/computed tomography (FDG PET/CT) imaging.

MATERIALS/METHODS

Fifty-eight patients undergoing FDG PET/CT before radical treatment with definitive radiotherapy (±concomitant chemotherapy) or surgery + postoperative (chemo)radiation were analyzed. The effects of clinicopathological factors (age, gender, tumor location, stage, Karnofsky Performance Status (KPS), and treatment strategy) including primary tumor SUV_max and nodal SUV_max on overall survival (OS), disease-free survival (DFS), locoregional control (LRC), and distant metastasis-free survival (DMFS) were evaluated. Kaplan-Meier survival curves were generated and compared with the log-rank test.

RESULTS

Median follow-up for the whole population was 31 months (range 2.3-53.5). Two-year OS, LRC, DFS and DMFS, for the entire cohort were 62.1, 78.3, 55.2 and 67.2%, respectively. Median pretreatment SUV_max for the primary tumor and lymph nodes was 11.85 and 5.4, respectively. According to univariate analysis, patients with KPS < 80% (p < 0.001), AJCC stage IVa or IVb vs III (p = 0.037) and patients undergoing radiotherapy vs surgery (p = 0.042) were significantly associated with worse OS. Patients with KPS < 80% (p = 0.003) or age ≥65 years (p = 0.007) had worse LRC. The KPS < 80% was the only factor associated with decreased DFS (p = 0.001). SUV_max of the primary tumor or the lymph nodes were not associated with OS, DFS or LRC. The KPS < 80% (p = 0.002), tumor location (p = 0.047) and AJCC stage (p = 0.025) were associated with worse cancer-specific survival (CSS). According to Cox regression analysis, on multivariate analysis KPS < 80% was the only independent parameter determining worse OS, DFS, CSS. Regarding LRC only patients with IK < 80% (p = 0.01) and ≥65 years (p = 0.01) remained statistically significant. Nodal SUV_max was the only factor associated with decreased DMFS. Patients with a nodal SUV_max > 5.4 presented an increased risk for distant metastases (HR, 3.3; 95% CI 1.17-9.25; p = 0.023).

CONCLUSIONS

The pretreatment nodal SUV_max in patients with locally advanced HNSCC is prognostic for DMFS. However, according to our results primary tumor SUV_max and nodal SUV_max were not significantly related to OS, DFS or LRC. Patients presenting KPS < 80% had worse OS, DFS, CSS and LRC.