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

PLoS ONE ◽  
2021 ◽  
Vol 16 (9) ◽  
pp. e0257949
Author(s):  
Charles Q. Yang ◽  
Huan Wang ◽  
Zhenqiu Liu ◽  
Matthew T. Hueman ◽  
Aadya Bhaskaran ◽  
...  
Keyword(s):  
Cutaneous Melanoma ◽  
Staging System ◽  
Tnm Staging ◽  
P Value ◽  
Survival Prediction ◽  
Training Set ◽  
Prognostic System ◽  
Tnm Staging System ◽  
Prognostic Groups ◽  
Validation Set

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.

scholarly journals Comparison of a Tumor-Ratio–Metastasis Staging System and the 8th AJCC TNM Staging System for Gastric Cancer

2021 ◽  
Vol 11 ◽  
Author(s):  
Miaoquan Zhang ◽  
Chao Ding ◽  
Lin Xu ◽  
Biyi Ou ◽  
Shoucheng Feng ◽  
...  
Keyword(s):  
Gastric Cancer ◽  
Likelihood Ratio ◽  
Staging System ◽  
Tnm Staging ◽  
Stage Migration ◽  
Training Set ◽  
Discriminatory Ability ◽  
Tnm Staging System ◽  
Staging Systems ◽  
Validation Set

BackgroundDespite the implementation of the 8th American Joint Committee on Cancer (AJCC) TNM staging system for gastric cancer (GC) in 2017, it still holds a significant level of stage migration which affects patients’ proper classification and accurate prognosis. Here, to reduce this effect, we evaluated the prognostic value of a lymph node ratio (LNR) and established a novel tumor–ratio–metastasis (TRM) staging system.MethodThe data of 15,206 GC patients from the Sun Yat-sen University Cancer Center (Training set; n=2,032) and the US Surveillance, Epidemiology, and End Results (SEER) database (Validation set; n=13,174) were analyzed. The training set was classified into 5 LNR categories, based on which the novel TRM staging system was constructed. The overall survival (OS) between the TRM and AJCC TNM systems was compared in the training set and validated in the validation set. The likelihood ratio x2, liner trend x2, C-index, and Akaike information criterion (AIC) values were used to measure the discriminatory ability between the two different staging systems. Decision curve analyses (DCAs) were conducted to test the clinical value of the two staging systems.ResultThe patients were classified into the following categories: LNR0: 0%, LNR1: 0%<LNR ≤ 10%, LNR2: 10%<LNR ≤ 25%, LNR 3a: 25%<LNR ≤ 60%, and LNR 3b: LNR>60%. Univariate analyses demonstrated that the log-rank x2 of the LNR stage (Training/Validation set: x2 = 463.1/2880.8) was larger than the AJCC pN stage (Training/Validation set: x2 = 281.5/2240.8). For both the training set and validation set, stratified analyses using the Kaplan-Meier method identified significantly heterogeneous OS in every pN category but only one using the LNR. The TRM staging system had higher likelihood ratio x2, liner trend x2, C-index and smaller AIC values than the TNM system.ConclusionThe TRM staging system demonstrated improved homogeneity and discriminatory ability in predicting the prognosis of GC patients compared with the AJCC TNM staging system.

scholarly journals Integrated analysis of serum lipid profile for predicting clinical outcomes of patients with malignant biliary tumor

BMC Cancer ◽  
2020 ◽  
Vol 20 (1) ◽  
Author(s):  
Lejia Sun ◽  
Xin Ji ◽  
Dongyue Wang ◽  
Ai Guan ◽  
Yao Xiao ◽  
...  
Keyword(s):  
Serum Lipids ◽  
Predictive Ability ◽  
Staging System ◽  
Tnm Staging ◽  
Integrated Analysis ◽  
Survival Prediction ◽  
Related Factors ◽  
Tnm System ◽  
Tnm Staging System ◽  
Lipid Parameters

Abstract Background Serum lipids were reported to be the prognostic factors of various cancers, but their prognostic value in malignant biliary tumor (MBT) patients remains unclear. Thus we aim to assess and compare prognosis values of different serum lipids, and construct a novel prognostic nomogram based on serum lipids. Methods Patients with a confirmed diagnosis of MBT at our institute from 2003 to 2017 were retrospectively reviewed. Prognosis-related factors were identified via univariate and multivariate Cox regression analyses. Then the novel prognostic nomogram and a 3-tier staging system were constructed based on these factors and further compared to the TNM staging system. Results A total of 368 patients were included in this study. Seven optimal survival-related factors—TC/HDL >  10.08, apolipoprotein B >  0.9 g/L, lipoprotein> 72 mg/L, lymph node metastasis, radical cure, CA199 > 37 U/mL, and tumor differentiation —were included to construct the prognostic nomogram. The C-indexes in training and validation sets were 0.738 and 0.721, respectively. Besides, ROC curves, calibration plots, and decision curve analysis all suggested favorable discrimination and predictive ability. The nomogram also performed better predictive ability than the TNM system and nomogram without lipid parameters. And the staging system based on nomogram also presented better discriminative ability than TNM system (P < 0.001). Conclusions The promising prognostic nomogram based on lipid parameters provided an intuitive method for performing survival prediction and facilitating individualized treatment and was a great complement to the TNM staging system in predicting overall survival.

scholarly journals A Model for the Prediction of Survival in Patients With Upper Tract Urothelial Carcinoma After Surgery

Dose-Response ◽  
2019 ◽  
Vol 17 (4) ◽  
pp. 155932581988287
Author(s):  
Guang-lin Zhang ◽  
Wei Zhou
Keyword(s):  
Urothelial Carcinoma ◽  
Predictive Ability ◽  
Staging System ◽  
Tnm Staging ◽  
Upper Tract Urothelial Carcinoma ◽  
Cancer Specific Survival ◽  
Upper Tract ◽  
Tnm Staging System ◽  
Prediction Of Survival ◽  
Validation Set

Objective: We aimed to formulate and validate prognostic nomograms that can be used to predict the prognosis of patients with upper tract urothelial carcinoma (UTUC). Methods: By consulting the Surveillance, Epidemiology, and End Results (SEER) database, we identified patients who were surgically treated for UTUC between 2004 and 2013. Variables were analyzed in both univariate and multivariate analyses. Nomograms were constructed based on independent prognostic factors. The prognostic nomogram models were established and validated internally and externally to determine their ability to predict the survival of patients with UTUC. Results: A total of 4990 patients were collected and enrolled in our analyses. Of these, 3327 patients were assigned to the training set and 1663 to the validation set. Nomograms were effectively applied to predict the 3- and 5-year survivals of patients with UTUC after surgery. The nomograms exhibited better accuracy for predicting overall survival (OS) and cancer-specific survival (CSS) than the tumor-node-metastasis (TNM) staging system and the SEER stage in both the training and validation sets. Calibration curves indicated that the nomograms exhibited high correlation to actual observed results for both OS and CSS. Conclusions: The nomogram models showed stronger predictive ability than the TNM staging system and the SEER stage. Precise estimates of the prognosis of UTUC might help doctors to make better treatment decisions.

scholarly journals Development and validation of a nomogram to predict overall survival for patients with metastatic renal cell carcinoma

2020 ◽  
Author(s):  
Wenwen Zheng ◽  
Weiwei Zhu ◽  
Shengqiang Yu ◽  
Kangqi Li ◽  
Yuexia Ding ◽  
...  
Keyword(s):  
Renal Cell Carcinoma ◽  
Overall Survival ◽  
Staging System ◽  
Survival Prediction ◽  
Seer Database ◽  
Training Set ◽  
Ajcc Staging System ◽  
Validation Set ◽  
Ajcc Staging ◽  
Metastatic Rcc

Abstract Background: The prognosis of metastatic renal cell carcinoma (RCC) patients vary widely because of clinical and pathological heterogeneity. We aimed to develop a novel nomogram to predict overall survival (OS) for this population. Methods: Metastatic RCC patients were selected from the Surveillance, Epidemiology, and End Results (SEER) database between 2010 and 2016. These patients were randomly assigned to a training set and a validation set at a ratio of 1:1. Significant prognostic factors of survival were identified through Cox regression models and then integrated to form a nomogram to predict 1-, 3- and 5-year OS. The nomogram was subsequently subjected to validations via the training and the validation sets. The performance of this model was evaluated by using Harrell’s concordance index (C-index), calibration curve, integrated discrimination improvement (IDI), net reclassification improvement (NRI), and decision curve analysis (DCA). Results: Overall, 2315 eligible metastatic RCC patients were enrolled from the SEER database. A nomogram of survival prediction for patients of newly diagnosed with metastatic RCC was established, in which eight clinical factors significantly associated with OS were involved, including Fuhrman grade, lymph node status, sarcomatoid feature, cancer-directed surgery, bone metastasis, brain metastasis, liver metastasis, and lung metastasis. The new model presented better discrimination power than the American Joint Committee on Cancer (AJCC) staging system (7th edition) in the training set (C-indexes, 0.701 vs. 0.612, P <0.001) and the validation set (C-indexes, 0.676 vs. 0.600, P <0.001). The calibration plots of the nomogram exhibited optimal agreement between the predicted values and the observed values. The results of NRI and IDI also indicated the superior predictive capability of the nomogram relative to the AJCC staging system. The DCA plots revealed higher clinical use of our model in survival prediction. Conclusions: We developed and validated an effective nomogram to provide individual OS prediction for metastatic RCC patients, which would be beneficial to clinical trial design, patient counseling, and therapeutic modality selection.

2010 TNM Staging System for Cutaneous Melanoma…and Beyond

2010 ◽  
Vol 17 (6) ◽  
pp. 1475-1477 ◽  
Author(s):  
Jeffrey E. Gershenwald ◽  
◽  
Seng-jaw Soong ◽  
Charles M. Balch
Keyword(s):  
Cutaneous Melanoma ◽  
Staging System ◽  
Tnm Staging ◽  
Tnm Staging System

Construction and validation of a simple-to-use nomogram incorporating clinicopathological parameters into the TNM staging system to predict prognosis for stage II colorectal cancer.

2020 ◽  
Vol 38 (4_suppl) ◽  
pp. 31-31
Author(s):  
Shaobo Mo ◽  
Yaqi Li ◽  
Junjie Peng ◽  
SanJun Cai
Keyword(s):  
Colorectal Cancer ◽  
Large Population ◽  
Disease Free Survival ◽  
Staging System ◽  
Tnm Staging ◽  
Stage Ii ◽  
Clinicopathological Parameters ◽  
Tnm Staging System ◽  
Stage Ii Colorectal Cancer ◽  
Validation Set

31 Background: Survival outcomes are significant different in stage II colorectal cancer (CRC) patients with diverse clinicopathological features. Objective of this study is to establish a credible prognostic nomogram incorporating easily obtained parameters for stage II CRC patients. Methods: A total of 1708 stage II CRC patients at Fudan University Shanghai Cancer Center (FUSCC) during 2008 to 2013 were retrospectively analyzed in this study. Cases were randomly separated into training set (n = 1084) and validation set (n = 624). Univariate and multivariate Cox regression analyses were used to identify independent prognostic factors which were subsequently incorporated into a nomogram. The performance of the nomogram was evaluated by C-index and ROC curve to calculate the area under the curve (AUC). The clinical utility of the nomogram was evaluated using decision curve analysis (DCA). Results: In univariate and multivariate analyses, eight parameters were correlated with disease free survival (DFS), which were subsequently selected to draw prognostic nomogram based on DFS. For DFS predictions, the predicted concordance index (C-index) of the nomogram was 0.842 (95% confidence interval (CI), 0.710-0.980), and 0.701 (95% CI, 0.610-0.770) for training and validation set, respectively. The AUC values of ROC predicted 1, 3 and 5-year survival of nomogram in the training and validation groups were 0.869, 0.858, 0.777 and 0.673, 0.714, 0.706, respectively. The recurrence probability calibration curve showed good consistency between actual observations and nomogram-based predictions. DCA showed better clinical application value for the nomogram compared with TNM staging system. Conclusions: A novel nomogram based on a large population study was established and validated, which is a simple-to-use tool for physicians to facilitate the postoperative personalized prognostic evaluation and determine therapeutic strategies for stage II CRC patients.

scholarly journals Expanding the TNM for cancers of the colon and rectum using machine learning: a demonstration

ESMO Open ◽  
2019 ◽  
Vol 4 (3) ◽  
pp. e000518 ◽  
Author(s):  
Matthew Hueman ◽  
Huan Wang ◽  
Donald Henson ◽  
Dechang Chen
Keyword(s):  
Lymph Nodes ◽  
Prediction Accuracy ◽  
Staging System ◽  
Risk Groups ◽  
P Value ◽  
Survival Prediction ◽  
Prognostic System ◽  
Tumour Location ◽  
Colon And Rectum ◽  
Ajcc Staging

ObjectiveThe American Joint Committee on Cancer (AJCC) system for staging cancers of the colon and rectum includes depth of tumour penetration, number of positive lymph nodes and presence or absence of metastasis. Using machine learning, we demonstrate that these factors can be integrated with age, carcinoembryonic antigen (CEA) interpretation and tumour location, to form prognostic systems that expand the tumour, lymph node, metastasis (TNM) staging system.MethodsTwo datasets on colon and rectal cancers were extracted from the Surveillance, Epidemiology and End Results Programme of the National Cancer Institute. Dataset 1 included three factors (tumour, lymph nodes and metastasis). Dataset 2 contained six factors (tumour, lymph nodes, metastasis, age, CEA interpretation and tumour location). The Ensemble Algorithm for Clustering Cancer Data (EACCD) and the C-index were applied to generate prognostic groups.ResultsThe EACCD prognostic system based on dataset 1 stratified patients into 10 risk groups, analogous to the 10 stages of the AJCC staging system. There was a strong inter-system association between EACCD grouping and AJCC staging (Spearman’s rank correlation=0.9046, p value=1.6×10−17). However, the EACCD system had a significantly higher survival prediction accuracy than the AJCC system (C-index=0.7802 and 0.7695, respectively for the EACCD system and AJCC system, p value=4.9×10−91). Adding age, or CEA interpretation, or location improved the prediction accuracy of the prognostic system-involving tumour, lymph nodes and metastasis. The EACCD prognostic system based on dataset 2 and all six factors stratified patients into 10 groups with the highest survival prediction accuracy (C-index=0.7914).ConclusionsThe EACCD can integrate multiple factors to stratify patients with colon or rectal cancer into risk groups that predict survival with a high accuracy.

scholarly journals Development and validation of a nomogram to predict the prognosis of patients with squamous cell carcinoma of the bladder

2019 ◽  
Vol 39 (12) ◽  
Author(s):  
Mei-Di Hu ◽  
Si-Hai Chen ◽  
Yuan Liu ◽  
Ling-Hua Jia
Keyword(s):  
Squamous Cell Carcinoma ◽  
Cell Carcinoma ◽  
Squamous Cell ◽  
Staging System ◽  
Clinical Effectiveness ◽  
Tnm Staging ◽  
Ratio Test ◽  
Tnm Staging System ◽  
Carcinoma Of The Bladder ◽  
Validation Set

Abstract Background: The present study aimed to develop and validate a nomogram based on expanded TNM staging to predict the prognosis for patients with squamous cell carcinoma of the bladder (SCCB). Methods: A total of 595 eligible patients with SCCB identified in the Surveillance, Epidemiology, and End Results (SEER) dataset were randomly divided into training set (n = 416) and validation set (n = 179). The likelihood ratio test was used to select potentially relevant factors for developing the nomogram. The performance of the nomogram was validated on the training and validation sets using a C-index with 95% confidence interval (95% CI) and calibration curve, and was further compared with TNM staging system. Results: The nomogram included six factors: age, T stage, N stage, M stage, the method of surgery and tumor size. The C-indexes of the nomogram were 0.768 (0.741–0.795) and 0.717 (0.671–0.763) in the training and validation sets, respectively, which were higher than the TNM staging system with C-indexes of 0.580 (0.543–0.617) and 0.540 (0.484–0.596) in the training and validation sets, respectively. Furthermore, the decision curve analysis (DCA) proved that the nomogram provided superior clinical effectiveness. Conclusions: We developed a nomogram that help predict individualized prognosis for patients with SCCB.

Sign in / Sign up

Export Citation Format

Share Document