Sentinel Node Status is the Most Important Prognostic Information for Clinical Stage IIB and IIC Melanoma Patients

Non-proportional hazards model with a frailty term: Application with a melanoma dataset

“…The melanoma data set considered in this project was also initially studied by Calsavara et al (2020), where they evaluated only the effect of surgery covariate in a lifetime using a non-proportional hazards model with a frailty term. In our study, the goal was to assess the effect of surgery and other observed covariates available in the record, such as gender and age at diagnostic on specific survival.…”

“…It is common in a clinical study where prognostic factors, such as treatment, disappear with time. As mentioned in Calsavara et al (2020), some types of tumors may respond well to chemotherapy/radiotherapy initially, but the cancer cells may develop some tolerance to the treatment through genetic mechanisms, resulting in loss of the treatment effect over time. A problem to fit a Cox regression model can be inadequate and wrong conclusions can be made.…”

“…In contrast, Louzada-Neto (1997), Louzada-Neto (1999) proposed the extension of hybrid hazard models, the generalized time-dependent logistic (GTDL) model proposed by Mackenzie (1996) and extended by Milani et al (2015) for the gamma frailty model approach. Recently, Calsavara et al (2020) extended the GTDL model considering a power variance function (PVF) frailty model and incorporating covariate in the effect term. These models have been applied successfully to problems in which all subjects are susceptible to the event of interest.…”

“…If an important covariate is omitted from the model, the amount of unobservable heterogeneity will increase, affecting the model parameters' inferences. To include a random effect can help to alleviate this problem (CALSAVARA et al, 2020). Frailty models have been studied by several authors Clayton (1978), Vaupel, Manton andStallard (1979), Andersen et al (2012), Hougaard (1995, Sinha and Dey (1997), Oakes (1982).…”

“…Other authors as Aalen (1988), Hougaard, Myglegaard andBorch-Johnsen (1994), Price and Manatunga (2001), Peng, Taylor and Yu (2007), Yu and Peng (2008), Calsavara, Tomazella and Fogo (2013), Calsavara et al (2017) have considered cure rate models with frailty terms. Recently, Calsavara et al (2020) proposed a non-proportional hazards frailty model with the possibility of long-term survivors in patients diagnosed with melanoma in the state of São Paulo, Brazil.…”