A Benchmark Study on the Comparative Advantage of Random Survival Forest Analysis in Lung Cancer Survival Predictions

Globally, lung cancer continues to be the primary cause of cancer-related fatalities; the most common subtype is non-small cell lung cancer (NSCLC).Because of its inadequate prognosis and limited therapeutic choices, metastatic non-small cell lung cancer (NSCLC) presents a particularly difficult clinical situation.In order to predict survival in patients with metastatic NSCLC, we suggest comparing the Random Survival Forests (RSF) and Cox Proportional Hazards (CPH) models in this study.This approach involves preprocessing data from the Memorial Sloan Kettering Cancer Center and applying both RSF and CPH algorithms to estimate survival outcomes.In this investigation, each model's concordance index is assessed, and Kaplan-Meier estimators are used to visualize survival curves.In order to create individualized treatment plans for lung cancer patients, the study's findings attempt to shed light on how well RSF performs in comparison to conventional CPH approaches in predicting survival in metastatic NSCLC.