The primary task of survival analysis is to determine the timing of one or multiple events, which can signify the moment of a mechanical system malfunction, the period of transition from corporate deficit to surplus, the instance of patient fatality or so on, depending on the specific circumstance (Lee and Whitmore, 2006). Among all scenarios, survival analysis for medical data poses the most severe challenges (Collett, 2023). Some medical datasets are longitudinal, as exemplified by electronic health records (EHRs), where multiple observations of each patient's covariates over time are recorded. Survival models must be capable of handling such measurements and learning from their continuous temporal trends. Moreover, observations in longitudinal data are often sparse, necessitating the effective handling of missing values for any reliable survival model, even when the missing rates are exceedingly high (Singer and Willett, 1991). Additionally, censoring represents a fundamental aspect of survival data, referring to cases in which complete information regarding the survival time or event occurrence of a subject is not fully observed or available within the study period (Leung et al, 1997).