Search

This paper considers the problem of obtaining a dynamic prediction for 5-year failure free survival after bone marrow transplantation in ALL patients using data from the EBMT, the European Group for Blood and Marrow Transplantation. The paper compares the new landmark methodology as developed by the first author and the established multi-state modeling as described in a recent Tutorial in Biostatistics in Statistics in Medicine by the second author and colleagues. As expected the two approaches give similar results. The landmark methodology does not need complex modeling and leads to easy prediction rules. On the other hand, it does not give the insight in the biological processes as obtained for the multi-state model.

AIMS: To study the temporal dynamics of depression symptom episodes in old-age and the related influence of risk factors. METHODS: Data from 41 362 old adults (54.61% women; mean age = 75.30, SD = 6.20) from the Ageing Trajectories of Health - Longitudinal Opportunities and Synergies (ATHLOS) project were used. Depressive symptoms were followed over an 18-year period. A multi-state model, comprising three statuses (no depression, new clinically relevant episode of symptoms and episode persistence), was fitted. Multinomial regression was used to study the role of risk factors in status transition. RESULTS: Almost 85% of participants showed no depression, but prevalence became lower over time (B = -0.25, P

Background Renal transplantation is a therapy for end-stage renal disease. During the study of recipients’ survival after renal transplantation, there are some events as intermediate events that not only affect the recipients’ survival but also events which are affected by various factors. The aim of this study was to handle these intermediate events in order to identify factors that affect recipients’ survival by using multi-state models. Methods This retrospective cohort study included 405 renal transplant patients from Afzalipour Hospital, Kerman, Iran, from 2004 to 2010. The survival time of these recipients was determined after transplantation and the effect of various factors on the death hazard with and without renal allograft failure and hazard of renal allograft failure was studied by using multi-state models. Results During 4.06 years (median) of follow-up; 28 (6.9%) recipients died and allograft failure occurred in 51 (12.6%) recipients. Based on the results of multi-state model, receiving a living kidney transplantation decreased the hazard of renal allograft failure (HR=0.38; 95% CI: 0.17- 0.87), pre-transplant hypertension (HR=2.94; 95% CI: 1.54- 5.63) and serum creatinine levels >1.6 upon discharge from the hospital (HR=7.38; 95% CI: 3.87- 7.08) increased the hazard of renal allograft failure. Receiving living kidney transplantation decreased the hazard of death directly (HR=0.18; 95% CI: 0.04- 0.93). Conclusion It was concluded that the effect of donor type, pre-transplant hypertension and having serum creatinine >1.6 upon discharge from the hospital was significant on hazard of renal allograft failure. The only variable that had a direct significant effect on hazard of death was donor type.

CD4-based multi-state back-calculation methods are key for monitoring the HIV epidemic, providing estimates of HIV incidence and diagnosis rates by disentangling their inter-related contribution to the observed surveillance data. This paper, extends existing approaches to age-specific settings, permitting the joint estimation of age- and time-specific incidence and diagnosis rates and the derivation of other epidemiological quantities of interest. This allows the identification of specific age-groups at higher risk of infection, which is crucial in directing public health interventions. We investigate, through simulation studies, the suitability of various bivariate splines for the non-parametric modelling of the latent age- and time-specific incidence and illustrate our method on routinely collected data from the HIV epidemic among gay and bisexual men in England and Wales.

In cognitive ageing study, older people are highly selected bya risk of death associated with poor cognitive performances. Modeling the natural history of cognitive decline is difficult in presence of incomplete longitudinal and survival data. Moreover, the non observed cognitive decline acceleration begining before the dementia diagnosis is difficult to evaluate. Cognitive decline is higly heterogeneous, e.g. there are various patterns associated with different risks of survival event. The objective is to study joint models for incomplete longitudinal and survival data to describe the cognitive evolution in older people. Latent variable approaches were used to take into account the non-observed mecanismes, e.g. heterogeneity and decline acceleration. First, we compared two approaches to consider missing data in longitudinal data analysis. Second, we propose a joint model with a latent state to model cognitive evolution and its pre-dementia acceleration, dementia risk and death risk., Dans l'étude du vieillissement cérébral, le suivi des personnes âgées est soumis à une forte sélection avec un risque de décès associé à de faibles performances cognitives. La modélisation de l'histoire naturelle du vieillissement cognitif est complexe du fait de données longitudinales et données de survie incomplètes. Par ailleurs, un déclin accru des performances cognitives est souvent observé avant le diagnostic de démence sénile, mais le début de cette accélération n'est pas facile à identifier. Les profils d'évolution peuvent être variés et associés à des risques différents de survenue d'un événement; cette hétérogénéité des déclins cognitifs de la population des personnes âgées doit être prise en compte. Ce travail a pour objectif d'étudier des modèles conjoints pour données longitudinales et données de survie incomplètes afin de décrire l'évolution cognitive chez les personnes âgées. L'utilisation d'approches à variables latentes a permis de tenir compte de ces phénomènes sous-jacents au vieillissement cognitif que sont l'hétérogénéité et l'accélération du déclin. Au cours d'un premier travail, nous comparons deux approches pour tenir compte des données manquantes dans l'étude d'un processus longitudinal. Dans un second travail, nous proposons un modèle conjoint à état latent pour modéliser simultanément l'évolution cognitive et son accélération pré-démentielle, le risque de démence et le risque de décès.

Motivated by data from an observational, prospective study of 286 patients with non-mild acute pancreatitis (AP) who entered the Intensive Care Unit (ICU) of the Donostia University Hospital between 2001 and mid-2017, we propose a multi-state modeling approach to describe the evolution of patients with acute pancreatitis and at least one organ failure or local complications. An extension of the illness-death model is used allowing to take into account the disease-related events of interest, that is, entry to ICU, discharge from ICU and death due to acute pancreatitis. To this end, the present study describes the course of AP patients and evaluates the effect of different prognostic factors on the multiple disease-related events.

One major goal in clinical applications of multi-state models is the estimation of transitionprobabilities. The usual nonparametric estimator of the transition matrix for nonhomogeneous Markov processes is the Aalen-Johansen estimator (Aalen and Johansen 1978). However, two problems may arise from using this estimator: first, its standard error may be large in heavy censored scenarios; second, the estimator may be inconsistent if the process is non-Markovian. The development of the R package TPmsm has been motivated by several recent contributions that account for these estimation problems. Estimation and statistical inference for transition probabilities can be performed using TPmsm. The TPmsm package provides seven di fferent approaches to three-state illness-death modeling. In two of these approaches the transition probabilities are estimated conditionally on current or past covariate measures. Two real data examples are included for illustration of software usage., This research was nanced by FEDER Funds through "Programa Operacional Factores de Competitividade - COMPETE" and by Portuguese Funds through "FCT -Fundação para a Ciência e a Tecnologia", in the form of grants PTDC/MAT/104879/2008 and PEst-OE/MAT/UI0013/2014.