A new approach for joint modelling of longitudinal measurements and survival times with a cure fraction

2012 ◽  
Vol 40 (2) ◽  
pp. 207-224 ◽  
Author(s):  
Hui Song ◽  
Yingwei Peng ◽  
Dongsheng Tu
Keyword(s):  
Survival Times ◽  
Joint Modelling ◽  
New Approach ◽  
Longitudinal Measurements ◽  
Cure Fraction

scholarly journals Evaluating Quality Adjusted Life Years in the Absence of Standard Utility Values- A Dynamic Joint Modelling Approach

2020 ◽  
Author(s):  
Vishal Deo ◽  
Gurprit Grover
Keyword(s):  
Joint Model ◽  
Monte Carlo Integration ◽  
Survival Times ◽  
Quality Adjusted Life Years ◽  
Joint Modelling ◽  
Utility Values ◽  
Decision Analytic Modelling ◽  
Life Years ◽  
Quality Adjusted Life ◽  
Modelling Approach

AbstractEstimation of Quality Adjusted Life Years (QALYs) is pivotal towards cost-effectiveness analysis (CEA) of medical interventions. Most of the CEA studies employ multi-state decision analytic modelling approach, where fixed utility values are assigned to each disease state and total QALYs are calculated on the basis of total lengths of stay in each state.In this paper, we have formulated a new approach to CEA by defining utility as a function of a longitudinal covariate which is significantly associated with disease progression. Association parameter between the longitudinal covariate and survival times is estimated through joint modelling of the longitudinal linear mixed effects model and the Weibull accelerated failure time survival model. Metropolis-Hastings algorithm and Monte Carlo integration are used to predict expected survival times of each censored case using the joint model. Fitted longitudinal model is further used to project values of the longitudinal covariate at all time points for each patient. Utility values calculated using these projected covariate values are used to evaluate QALYs for each patient.Retrospective survival data of HIV/ AIDS patients undergoing treatment at the Antiretroviral Therapy centre of Ram Manohar Lohia hospital in New Delhi is used to demonstrate the implementation of the proposed methodology. A simulation exercise is also carried out to gauge the predictive capability of the joint model in projecting the values of the longitudinal covariate.The proposed dynamic approach to calculate QALY provides a promising alternative to the popular multi-state decision analytic modelling approach, especially when the standard utility values for different stages of the concerned disease are not available.

Joint modelling of event counts and survival times

2006 ◽  
Vol 55 (1) ◽  
pp. 31-39 ◽  
Author(s):  
B. J. Cowling ◽  
J. L. Hutton ◽  
J. E. H. Shaw
Keyword(s):  
Survival Times ◽  
Joint Modelling

Temporal Trends in the Proportion Cured Among Patients Diagnosed with Acute Myeloid Leukemia in Sweden 1973-2001, a Population-Based Study.

Blood ◽  
2009 ◽  
Vol 114 (22) ◽  
pp. 1378-1378
Author(s):  
Åsa Rangert Derolf ◽  
Therese M-L Andersson ◽  
Paul C Lambert ◽  
Sigurdur Y Kristinsson ◽  
Sandra Eloranta ◽  
...  
Keyword(s):  
Acute Myeloid Leukemia ◽  
Myeloid Leukemia ◽  
Patient Survival ◽  
Age Groups ◽  
Population Based ◽  
Age Group ◽  
Survival Times ◽  
Population Based Study ◽  
Cure Fraction ◽  
Acute Myeloid

Abstract Abstract 1378 Poster Board I-400 Background: Acute myeloid leukemia (AML) is the most common type of acute leukemia in adults and is rapidly fatal without specific therapy. In a recently published population-based study we showed large differences in 1- and 5-year relative survival in AML patients in Sweden depending on age at diagnosis and year of diagnosis[1]. Here we use an alternative approach to study patient survival that simultaneously estimates the proportion of patients cured from AML and the survival time of those patients that are not cured. The cure proportion provides a better estimate of long-term survival than 5-year survival and is therefore of direct interest to patients and health care professions. Methods: We conducted a population-based cohort study including 6,439 patients aged 19-79 diagnosed with AML in Sweden 1973 to 2001. Patients are considered statistically cured when, as a group, their mortality returns the level of a comparable general population. We estimated mixture cure fraction models that provide estimates of both the cure proportion and the distribution of survival times of the “uncured”. Age at diagnosis was classified into four categories 19-40, 41-60, 61-70 and 71-80 and year of diagnosis was modeled using restricted cubic splines. Results: During the first years of the study period the cure fraction was less than 5% for all age groups and the median survival time for “uncured” approximately 0.5 years or less. In 2000 the estimated cure proportion was 68% (95% CI 56%-77%) for the youngest age group, 32% (25-39%) for those aged 41-60, 8.4% (3.1-21%) for those aged 61-70 at diagnosis and 4.3% (2.3-8.1%) for the oldest age group. The estimated median survival times for “uncured” were 0.74 (0.43-1.26), 0.71 (0.53-0.97), 0.69 (0.51-0.95) and 0.37 (0.31-0.44) years respectively (Table 1). The improvement in survival manifested as longer survival among the uncured during the early calendar years but increases in the cure proportion were observed during later years. Conclusion: There are large differences in the proportion cured between the age groups. In younger patients the cure proportion has increased dramatically, while survival of the “uncured” actually decreased in the last time period. In the older age groups improvement is merely seen within the survival of the “uncured”. [1] Derolf AR, Kristinsson SY, Andersson TM-L, Landgren O, Dickman PW, Björkholm M. Improved patient survival for acute myeloid leukemia: A population-based study of 9,729 patients diagnosed in Sweden 1973-2005. Blood. 2009 Apr 16;113(16):3666-72. Disclosures: No relevant conflicts of interest to declare.

Joint longitudinal and time-to-event cure models for the assessment of being cured

2019 ◽  
Vol 29 (4) ◽  
pp. 1256-1270
Author(s):  
Antoine Barbieri ◽  
Catherine Legrand
Keyword(s):  
Survival Data ◽  
Mixed Model ◽  
Linear Mixed Model ◽  
Medical Intervention ◽  
Time To Event ◽  
Mixture Cure Model ◽  
Longitudinal Measurements ◽  
Cure Fraction ◽  
Cure Models ◽  
Latent Structures

Medical time-to-event studies frequently include two groups of patients: those who will not experience the event of interest and are said to be “cured” and those who will develop the event and are said to be “susceptible”. However, the cure status is unobserved in (right-)censored patients. While most of the work on cure models focuses on the time-to-event for the uncured patients (latency) or on the baseline probability of being cured or not (incidence), we focus in this research on the conditional probability of being cured after a medical intervention given survival until a certain time. Assuming the availability of longitudinal measurements collected over time and being informative on the risk to develop the event, we consider joint models for longitudinal and survival data given a cure fraction. These models include a linear mixed model to fit the trajectory of longitudinal measurements and a mixture cure model. In simulation studies, different shared latent structures linking both submodels are compared in order to assess their predictive performance. Finally, an illustration on HIV patient data completes the comparison.

scholarly journals Performance of joint modelling of time-to-event data with time-dependent predictors: an assessment based on transition to psychosis data

PeerJ ◽  
2016 ◽  
Vol 4 ◽  
pp. e2582 ◽  
Author(s):  
Hok Pan Yuen ◽  
Andrew Mackinnon
Keyword(s):  
Cox Regression ◽  
Real Data ◽  
Longitudinal Component ◽  
Time To Event ◽  
Joint Models ◽  
Joint Modelling ◽  
Cox Regression Analysis ◽  
Time To Event Data ◽  
Longitudinal Measurements ◽  
Analyse Data

Joint modelling has emerged to be a potential tool to analyse data with a time-to-event outcome and longitudinal measurements collected over a series of time points. Joint modelling involves the simultaneous modelling of the two components, namely the time-to-event component and the longitudinal component. The main challenges of joint modelling are the mathematical and computational complexity. Recent advances in joint modelling have seen the emergence of several software packages which have implemented some of the computational requirements to run joint models. These packages have opened the door for more routine use of joint modelling. Through simulations and real data based on transition to psychosis research, we compared joint model analysis of time-to-event outcome with the conventional Cox regression analysis. We also compared a number of packages for fitting joint models. Our results suggest that joint modelling do have advantages over conventional analysis despite its potential complexity. Our results also suggest that the results of analyses may depend on how the methodology is implemented.

The O–C diagrams of minor planets − a new approach to modelling the rotation

1999 ◽  
Vol 173 ◽  
pp. 185-188
Author(s):  
Gy. Szabó ◽  
K. Sárneczky ◽  
L.L. Kiss
Keyword(s):  
Error Analysis ◽  
Time Dependence ◽  
Theoretical Work ◽  
Minor Planet ◽  
Minor Planets ◽  
New Approach ◽  
Preliminary Results ◽  
Ccd Observations

AbstractA widely used tool in studying quasi-monoperiodic processes is the O–C diagram. This paper deals with the application of this diagram in minor planet studies. The main difference between our approach and the classical O–C diagram is that we transform the epoch (=time) dependence into the geocentric longitude domain. We outline a rotation modelling using this modified O–C and illustrate the abilities with detailed error analysis. The primary assumption, that the monotonity and the shape of this diagram is (almost) independent of the geometry of the asteroids is discussed and tested. The monotonity enables an unambiguous distinction between the prograde and retrograde rotation, thus the four-fold (or in some cases the two-fold) ambiguities can be avoided. This turned out to be the main advantage of the O–C examination. As an extension to the theoretical work, we present some preliminary results on 1727 Mette based on new CCD observations.

Sign in / Sign up

Export Citation Format

Share Document