Predictive value of a nomogram for melanomas with brain metastases at initial diagnosis

Nomogram Predicts Prognostic Factors for Head and Neck Cutaneous Melanoma: A Population-Based Analysis

BACKGROUND

The head and neck cutaneous melanoma (HNCM) accounts for 20% of newly diagnosed melanoma. Research on prognostic models for their survival yet remains largely unexplored. This study employed a nomogram approach to develop and validate a predictive model for both overall survival (OS) and disease-specific survival (DSS) in patients with HNCM.

METHODS

This study analyzed the HNCM patients diagnosed between 2004 and 2014 from Surveillance, Epidemiology, and End Results database. To identify independent prognostic factors for HNCM, we integrated results from univariate Cox regression analysis, random survival forests, and LASSO regression with cross-validation. A nomogram was designed and validated based on the identified characteristics to predict the 3-, 5-, and 8-year OS and DSS of patients with HNCM.

RESULTS

Age, Stage, Ulceration, Thickness, Chemotherapy, lymph node metastasis, and Radiation were identified as independent prognostic factors. The nomogram achieved a satisfactory performance with C-indices of 0.824(DSS) and 0.757(OS) in the training cohort and 0.827(DSS) and 0.749(OS) in the validation cohort, respectively. The area under the curves for the OS at 3, 5, and 8 years were 0.789, 0.788, and 0.794 for the training cohort, and 0.778, 0.776, and 0.795 for the validation cohort, respectively. For DSS, the area under the curves at 3, 5, and 8 years were 0.859, 0.842, and 0.828 in the training cohort, and 0.864, 0.844, and 0.834 in the validation cohort, respectively. The calibration curve showed that there was a strong correlation between the observed outcomes and the predicted survival probability.

CONCLUSIONS

This study established and validated predictive nomograms for HNCM patients with robust predictive performance.

Burden and Risk Factors of Brain Metastases in Melanoma: A Systematic Literature Review

Melanoma can frequently metastasize to the brain with severe consequences. However, variation of melanoma brain metastases (MBM) development among populations is not well studied, and underlying mechanisms and risk factors for MBM development are not consistently documented. We conducted a systematic literature review (SLR) including a total of 39 articles to evaluate the proportion of melanoma patients who are diagnosed with, or develop, brain metastases, and summarize the risk factors of MBM. The average proportion of MBM was calculated and weighted by the sample size of each study. Meta-analyses were conducted for the selected risk factors using a random-effects model. The proportion of MBM at diagnosis was 33% (975 with MBM out of 2948 patients) among patients with cutaneous melanoma (excluding acral) and 23% (651/2875) among patients with cutaneous mixed with other types of melanoma. The proportion at diagnosis was lower among populations with mucosal (9/96, 9%) or uveal (4/184, 2%) melanoma and among populations outside the United States and Europe. Meta-analysis demonstrated that male vs. female gender and left-sided tumors vs. right-sided were significantly associated with increased risk of melanoma brain metastases. These data may help clinicians to assess an individual patient's risk of developing melanoma brain metastases.

Systematic literature review and meta-analysis of clinical outcomes and prognostic factors for melanoma brain metastases

Background

More than 60% of all stage IV melanoma patients develop brain metastases, while melanoma brain metastases (MBM) is historically difficult to treat with poor prognosis.

Objectives

To summarize clinical outcomes and prognostic factors in MBM patients.

Methods

A systematic review with meta-analysis was conducted, and a literature search for relevant studies was performed on November 1, 2020. Weighted average of median overall survival (OS) was calculated by treatments. The random-effects model in conducting meta-analyses was applied.

Results

A total of 41 observational studies and 12 clinical trials with our clinical outcomes of interest, and 31 observational studies addressing prognostic factors were selected. The most common treatments for MBM were immunotherapy (IO), MAP kinase inhibitor (MAPKi), stereotactic radiosurgery (SRS), SRS+MAPKi, and SRS+IO, with median OS from treatment start of 7.2, 8.6, 7.3, 7.3, and 14.1 months, respectively. Improved OS was observed for IO and SRS with the addition of IO and/or MAPKi, compared to no IO and SRS alone, respectively. Several prognostic factors were found to be significantly associated with OS in MBM.

Conclusion

This study summarizes pertinent information regarding clinical outcomes and the association between patient characteristics and MBM prognosis.

Analysis of Demographics and Outcomes of Surgical Resection in the Central Nervous System of Patients With Metastatic Melanoma

Background

Patients with melanoma frequently develop central nervous system metastases. Oligometastatic disease is often treated either by surgical resection or by stereotactic radiotherapy. This study investigates the trends and clinical outcomes of patients with melanoma who have undergone surgical procedures on the central nervous system during their hospitalization.

Methods

A retrospective study was performed based on admissions of adult patients who underwent craniotomy for metastatic melanoma from 2000 to 2014 using the Nationwide Inpatient Sample database. The primary outcome measure was all-cause in-hospital mortality. Secondary outcomes included hospital length of stay (LOS) and discharge disposition (home/home with health care and skilled nursing facilities/long-term acute care (SNFs/LTAC)). Factors associated with in-hospital mortality were examined by multivariable logistic regression. We adjusted for patient and hospital characteristics, payer, and comorbid conditions. We also examined trends of mortality for the study years.

Results

There were an estimated 1,216 discharges of patients with melanoma undergoing craniotomy during the study period. Patients undergoing surgical interventions were typically males (69%) and whites (79%). Ninety-eight percent of procedures were performed at teaching hospitals. Unadjusted all-cause in-hospital mortality was 3.1%. There was no significant difference in mortality over 13 years. Age, gender, and race were not associated with increased in-hospital mortality. LOS was longer in elderly and those with higher Charlson Comorbidity Index. Of the survivors, 76% were discharged to home or with home healthcare while 24% were discharged to SNFs/LTAC. Patients with age > 65 (odds ratio (OR): 2.9; 95% confidence interval (CI): 2.2 - 3.9, P < 0.001) and those with higher Charlson Comorbidity Index (OR: 1.2; 95% CI: 1.1 - 1.3) had higher odds for being discharged to SNFs/LTAC.

Conclusions

Patients who undergo craniotomy for metastatic melanoma have a low in-hospital mortality rate. One quarter of patients were discharged to SNFs/LTAC.

Integrating additional factors into the TNM staging for cutaneous melanoma by machine learning

BACKGROUND

Integrating additional factors into the TNM staging system is needed for more accurate risk classification and survival prediction for patients with cutaneous melanoma. In the present study, we introduce machine learning as a novel tool that incorporates additional prognostic factors to improve the current TNM staging system.

METHODS AND FINDINGS

Cancer-specific survival data for cutaneous melanoma with at least a 5 years follow-up were extracted from the Surveillance, Epidemiology, and End Results Program of the National Cancer Institute and split into the training set (40,781 cases) and validation set (5,390 cases). Five factors were studied: the primary tumor (T), regional lymph nodes (N), distant metastasis (M), age (A), and sex (S). The Ensemble Algorithm for Clustering Cancer Data (EACCD) was applied to the training set to generate prognostic groups. Utilizing only T, N, and M, a basic prognostic system was built where patients were stratified into 10 prognostic groups with well-separated survival curves, similar to 10 AJCC stages. These 10 groups had a significantly higher accuracy in survival prediction than 10 stages (C-index = 0.7682 vs 0.7643; increase in C-index = 0.0039, 95% CI = (0.0032, 0.0047); p-value = 7.2×10-23). Nevertheless, a positive association remained between the EACCD grouping and the AJCC staging (Spearman's rank correlation coefficient = 0.8316; p-value = 4.5×10-13). With additional information from A and S, a more advanced prognostic system was established using the training data that stratified patients into 10 groups and further improved the prediction accuracy (C-index = 0.7865 vs 0.7643; increase in C-index = 0.0222, 95% CI = (0.0191, 0.0254); p-value = 8.8×10-43). Both internal validation using the training set and temporal validation using the validation set showed good stratification and a high predictive accuracy of the prognostic systems.

CONCLUSIONS

The EACCD allows additional factors to be integrated into the TNM to create a prognostic system that improves patient stratification and survival prediction for cutaneous melanoma. This integration separates favorable from unfavorable clinical outcomes for patients and improves both cohort selection for clinical trials and treatment management.

Comparing the characteristics and predicting the survival of patients with head and neck melanoma versus body melanoma: a population-based study

BACKGROUND

Previous studies reported cutaneous melanoma in head and neck (HNM) differed from those in other regions (body melanoma, BM). Individualized tools to predict the survival of patients with HNM or BM remain insufficient. We aimed at comparing the characteristics of HNM and BM, developing and validating nomograms for predicting the survival of patients with HNM or BM.

METHODS

The information of patients with HNM or BM from 2004 to 2015 was obtained from the Surveillance, Epidemiology, and End Results (SEER) database. The HNM group and BM group were randomly divided into training and validation cohorts. We used the Kaplan-Meier method and multivariate Cox models to identify independent prognostic factors. Nomograms were developed via the rms and dynnom packages, and were measured by the concordance index (C-index), the area under the curve (AUC) of the receiver operating characteristic (ROC) curve and calibration plots.

RESULTS

Of 70,605 patients acquired, 21% had HNM and 79% had BM. The HNM group contained more older patients, male sex and lentigo maligna melanoma, and more frequently had thicker tumors and metastases than the BM group. The 5-year cancer-specific survival (CSS) and overall survival (OS) rates were 88.1 ± 0.3% and 74.4 ± 0.4% in the HNM group and 92.5 ± 0.1% and 85.8 ± 0.2% in the BM group, respectively. Eight variables (age, sex, histology, thickness, ulceration, stage, metastases, and surgery) were identified to construct nomograms of CSS and OS for patients with HNM or BM. Additionally, four dynamic nomograms were available on web. The internal and external validation of each nomogram showed high C-index values (0.785-0.896) and AUC values (0.81-0.925), and the calibration plots showed great consistency.

CONCLUSIONS

The characteristics of HNM and BM are heterogeneous. We constructed and validated four nomograms for predicting the 3-, 5- and 10-year CSS and OS probabilities of patients with HNM or BM. These nomograms can serve as practical clinical tools for survival prediction and individual health management.

Type and timing of systemic therapy use predict overall survival for patients with brain metastases treated with radiation therapy

INTRODUCTION

This study aimed to investigate whether systemic therapy (ST) use surrounding radiation therapy (RT) predicts overall survival (OS) after RT for patients with brain metastases (BMs).

METHODS

Provincial RT and pharmacy databases were used to review all adult patients in British Columbia, Canada, who received a first course of RT for BMs between 2012 and 2016 (n = 3095). Multivariate analysis on a randomly selected subset was used to develop an OS nomogram.

RESULTS

In comparison to the 2096 non-recipients of ST after RT, the median OS of the 999 recipients of ST after RT was 5.0 (95% Confidence interval (CI) 4.1-6.0) months longer (p < 0.0001). Some types of ST after RT were independently predictive of OS: targeted therapy (hazard ratio (HR) 0.42, CI 0.37-0.48), hormone therapy (HR 0.45, CI 0.36-0.55), cytotoxic chemotherapy (HR 0.71, CI 0.64-0.79), and immunotherapy (HR 0.64, CI 0.37-1.06). Patients who discontinued ST after RT had 0.9 (CI 0.3-1.4) months shorter median OS than patients who received no ST before or after RT (p < 0.0001). In the multivariate analysis of the 220-patient subset, established prognostic variables (extracranial disease, performance status, age, cancer diagnosis, and number of BMs), and the novel variables "ST before RT" and "Type of ST after RT" independently predicted OS. The nomogram predicted 6- and 12-month OS probability and median OS (bootstrap-corrected Harrell's Concordance Index = 0.70).

CONCLUSIONS

The type and timing of ST use surrounding RT predict OS for patients with BMs.

A Novel Nomogram and Risk Classification System Predicting the Cancer-Specific Mortality of Patients with Initially Diagnosed Metastatic Cutaneous Melanoma

BACKGROUND

Cutaneous melanoma and distant organ metastasis has varying outcomes. Considering all prognostic indicators in a prediction model might assist in selecting cases who could benefit from a personalized therapy strategy.

OBJECTIVE

This study aimed to develop and validate a prognostic model for patients with metastatic melanoma.

METHODS

A total of 1535 cases diagnosed with metastatic cutaneous melanoma (stage IV) were identified from the Surveillance, Epidemiology, and End Results database. Patients were randomly divided into the training (n = 1023) and validation (n = 512) cohorts. A prognostic nomogram was established based predominantly on results from the competing-risk regression model for predicting cancer-specific death (CSD). The area under the time-dependent receiver operating characteristic curve (AUC), calibration curves, and decision curve analyses (DCAs) were used to evaluate the nomogram.

RESULTS

No significant differences were observed in the clinical characteristics between the training and validation cohorts. In the training cohort, patient-, tumor-, and treatment-related predictors of CSD for metastatic melanoma included age, sex, race, marital status, insurance, American Joint Committee on Cancer T and N stage, number of metastatic organs, surgical treatment, and chemotherapy. All these factors were used for nomogram construction. The time-dependent AUC values of the training and validation cohorts suggested a favorable performance and discrimination of the nomogram. The 6-, 12-, and 18-month AUC values were 0.706, 0.700, and 0.706 in the training cohort, and 0.702, 0.670, and 0.656 in the validation cohort, respectively. The calibration curves for the probability of death at 6, 12, and 18 months showed acceptable agreement between the values predicted by the nomogram and the observed outcomes in both cohorts. DCA curves showed good positive net benefits in the prognostic model among most of the threshold probabilities at different time points (death at 6, 12, and 18 months). Based on the total nomogram scores of each case, all patients were divided into the low-risk (n = 511), intermediate-risk (n = 512), and high-risk (n = 512) groups, and the risk classification could identify cases with a high risk of death in both cohorts.

CONCLUSIONS

A predictive nomogram and a corresponding risk classification system for CSD in patients with metastatic melanoma were developed in this study, which may assist in patient counseling and in guiding clinical decision making for cases with metastatic melanoma.

Development and validation of prognostic nomogram in patients with nonmetastatic malignant melanoma: a SEER population-based study

BACKGROUND

The condition of tumor recurrence and overall death can be worried in the progress of nonmetastatic malignant melanoma (NMMM). Our goal was to construct and validate a prognostic nomogram from a large population database, which is vital for physicians to predict the 3- and 5-year overall survival (OS) rates of patients with NMMM.

METHODS

According to the Surveillance, Epidemiology, and End Results (SEER) program, patients were collected and randomly assigned into the training and validation cohorts. Several independent risk factors were identified based on the methods of univariable and multivariable cox hazards regression and were incorporated to develop a nomogram. The concordance index (C-index), the area under the receiver operating characteristics (AUC) curve and calibration plot were confirmed to assess predictive power of the nomogram. Decision curve analysis (DCA) was performed to measure nomogram for the clinical practice.

RESULTS

A total of 66192 eligible patients, randomly assigned into 70% of training (n = 46 336) and 30% of validation cohorts (n = 19 856), were selected in this study. The selected independent factors were applied to develop a nomogram, and validated indexes indicated nomogram had a good discrimination ability. The C-index for OS rates was 0.817 (95% CI: 0.811-0.823) in training cohort and 0.817 (95% CI: 0.809-0.825) in validation cohort, respectively. The AUCs of 3- and 5-year OS rates were more than 0.79, and the calibration plots also showed a good power for the nomogram. DCA demonstrated that constructed nomogram can provide clinical net benefit.

CONCLUSION

We constructed a novel nomogram that more accurately and comprehensively predict OS with nonmetastatic malignant melanoma patients, which is vital for clinician to improve individual treatment, make reasonable clinical decisions, and set appropriate follow-up strategies.

Predictive value of a nomogram for melanomas with brain metastases at initial diagnosis

BACKGROUND

Estimation of incidence and prognosis of melanomas with brain metastases (MBM) at initial diagnosis based on a large cohort is lacking in current research. This study aims to construct an effective prognostic nomogram for newly diagnosed MBM.

MATERIALS AND METHODS

Patients diagnosed with melanomas from Surveillance, Epidemiology, and End Results program between 2010 and 2014 were enrolled in our study. Risk factors predicting brain metastases (BM) were identified using logistic regression analysis. Cox regression analysis was performed to identify prognostic factors of overall survival (OS). Nomogram for estimating 6-, 9-, and 12-month OS was established based on Cox regression analysis. The discriminative ability and calibration of the nomogram were tested using C statistics, calibration plots, and Kaplan-Meier curves.

RESULTS

Sixty-two thousand three hundred and sixty-nine melanoma patients were enrolled, including 928 with BM. Sex, marital status, insurance status, subsite, surgery of primary sites, radiation, chemotherapy, bone metastases, liver metastases, and lung metastases were associated with MBM at initial diagnosis. On multivariable Cox regression, the following eight variables were incorporated in the prediction of OS: age, unmarried status, absence of surgery to primary sites or unknown, absence of radiation or unknown, absence of chemotherapy or unknown, with bone metastases, with liver metastases, and with lung metastases. The nomogram showed good predictive ability as indicated by discriminative ability and calibration, with the C statistics of 0.716 (95% CI, 0.695-0.737).

CONCLUSIONS

The incidence and prognosis of MBM patients were well estimated in this study based on a large cohort. The nomogram performed well and could be a useful tool to predict prognosis.