Risk‐adjusted monitoring of time to event in the presence of long‐term survivors

Abstract

The use of control charts for monitoring schemes in medical context should consider adjustments to incorporate the specific risk for each individual. Some authors propose the use of a risk-adjusted survival time cumulative sum (RAST CUSUM) control chart to monitor a time-to-event outcome, possibly right censored, using conventional survival models, which do not contemplate the possibility of cure of a patient. We propose to extend this approach considering a risk-adjusted CUSUM chart, based on a cure rate model. We consider a regression model in which the covariates affect the cure fraction. The CUSUM scores are obtained for Weibull and log-logistic promotion time model to monitor a scale parameter for nonimmune individuals. A simulation study was conducted to evaluate and compare the performance of the proposed chart (RACUF CUSUM) with RAST CUSUM, based on optimal control limits and average run length in different situations. As a result, we note that the RAST CUSUM chart is inappropriate when applied to data with a cure rate, while the proposed RACUF CUSUM chart seems to have similar performance if applied to data without a cure rate. The proposed chart is illustrated with simulated data and with a real data set of patients with heart failure treated at the Heart Institute (InCor), at the University of São Paulo, Brazil.

A new risk‐adjusted EWMA control chart based on survival time for monitoring surgical outcome quality

“…A comparison of different RA control charts based on continuous variables is given by Steiner and Jones 8 . Oliveira et al 27 took the chance of healing of the patients into account and proposed RA CUSUM chart based on a cure rate model to monitor survival time. Zhang et al 28 discussed the effect of estimation error on the performance of RAST CUSUM chart.…”

Evaluating quality of hospital care using time-to-event endpoints based on patient follow-up data

“…Revisions within a fixed follow-up period are most commonly analyzed using traditional methods like proportions or logistic regression (Mehrotra et al 2014;Bosco et al 2014;Kristoffersen et al 2015). It has, however, also been suggested to make use of survival analysis methods for analyzing hospital-specific time-to-event endpoints such as Kaplan-Meier curves (Kristoffersen et al 2015), proportional hazard models (He and Schaubel 2014) or CUSUM charts based on parametric or non-parametric time-to-event methods (Gandy et al 2010;Oliveira et al 2016). Compared to traditional methods, methods from survival analysis allow the inclusion of observations with incomplete follow-up times and, thus, make more efficient use of the available data.…”

Avaliação prognóstica em pacientes com insuficiência cardíaca com o emprego de redes neurais artificiais

“…O conhecimento da probabilidade de sobrevida no longo prazo como método de avaliação do prognóstico é de interesse para essa orientação; a menor sobrevida seria indicador de maior gravidade da condição. A sobrevida pode ser avaliada por diferentes métodos (Oliveira et al, 2016). Decorre também a identificação de variáveis associadas com a sobrevida (Marçula et al, 2011).…”