Empirical Evidences on Predictive Accuracy of Survival Models

Breast cancer is the most common cancer among women and is considered a major public health concern worldwide. Biogeography-based optimization (BBO) is a novel metaheuristic algorithm. This study analyzed the relationship between the clinicopathologic variables of breast cancer using Cox proportional hazard (PH) regression on the basis of the BBO algorithm. The dataset is prospectively maintained by the Division of Breast Surgery at Kaohsiung Medical University Hospital. A total of 1896 patients with breast cancer were included and tracked from 2005 to 2017. Fifteen general breast cancer clinicopathologic variables were collected. We used the BBO algorithm to select the clinicopathologic variables that could potentially contribute to predicting breast cancer prognosis. Subsequently, Cox PH regression analysis was used to demonstrate the association between overall survival and the selected clinicopathologic variables. C-statistics were used to test predictive accuracy and the concordance of various survival models. The BBO-selected clinicopathologic variables model obtained the highest C-statistic value (80%) for predicting the overall survival of patients with breast cancer. The selected clinicopathologic variables included tumor size (hazard ratio [HR] 2.372, p = 0.006), lymph node metastasis (HR 1.301, p = 0.038), lymphovascular invasion (HR 1.606, p = 0.096), perineural invasion (HR 1.546, p = 0.168), dermal invasion (HR 1.548, p = 0.028), total mastectomy (HR 1.633, p = 0.092), without hormone therapy (HR 2.178, p = 0.003), and without chemotherapy (HR 1.234, p = 0.491). This number was the minimum number of discriminators required for optimal discrimination in the breast cancer overall survival model with acceptable prediction ability. Therefore, on the basis of the clinicopathologic variables, the survival prediction model in this study could contribute to breast cancer follow-up and management.

Download Full-text

SURVIVAL MODELS IN THE CONTEXT OF MULTIPLICATIVE AND ADDITIVE HAZARDS

REVISTA BRASILEIRA DE BIOMETRIA ◽

10.28951/rbb.v37i3.391 ◽

2019 ◽

Vol 37 (3) ◽

pp. 306

Author(s):

Suely Ruiz GIOLO ◽

Jaqueline Aparecida RAMINELLI

Keyword(s):

Survival Analysis ◽

Primary Biliary Cirrhosis ◽

Goodness Of Fit ◽

Operating Characteristic ◽

Graphical Representation ◽

Predictive Accuracy ◽

Time Dependent ◽

Survival Models ◽

Biliary Cirrhosis ◽

Additive Hazards

In survival analysis, multiplicative and additive hazards models provide the two principal frameworks to study the association between the hazard and covariates. When these models are considered for analyzing a given survival dataset, it becomes relevant to evaluate the overall goodness-of-fit and how well each model can predict those subjects who subsequently will or will not experience the event. In this paper, this evaluation is based on a graphical representation of the Cox-Snell residuals and also on a time-dependent version of the area under the receiver operating characteristic (ROC) curve, denoted by AUC(t). A simulation study is carried out to evaluate the performance of the AUC(t) as a tool for comparing the predictive accuracy of survival models. A dataset from the Mayo Clinic trial in primary biliary cirrhosis (PBC) of the liver is also considered to illustrate the usefulness of these tools to compare survival models formulated under distinct hazards frameworks.

Download Full-text