Effective Strategies and Techniques Used for Pulmonary Carcinoma Survival Analysis

Survival analysis is a branch of statistics used to predict how long it will be until the event of interest occurs. The availability of an appropriate data structure means that its use is not restricted to biomedical issues; rather, it can be applied to challenges in virtually any field. Recent research has shown that this method is effective for risk categorization. Several studies have improved upon the findings obtained by combining survival analysis and machine learning algorithms because it is a well-established statistical technique. It is well established in the field of machine learning that using many data modalities enhances the accuracy of predictive models. Modeling the survival data and developing robust predictive models for time-to-event estimation has been the primary focus of survival analysis research. Clustering based on risk profiles is under-explored in machine learning but has significant practical implications in fields like healthcare decision making. When there is a portion of the population that is unknown, cluster-based survivability can be a huge benefit. In this review, we describe findings from the aforementioned field, focusing on methods for clustering censored data and classifying individuals into distinct risk categories.