Parametric Conditional Frailty Models for Recurrent Cardiovascular Events in the LIPID Study Dr Jisheng Cui Deakin University, Melbourne.

Slides:



Advertisements
Similar presentations
Topic: Several Approaches to Modeling Recurrent Event Data Presenter: Yu Wang.
Advertisements

The Long-Term Intervention with Pravastatin in Ischemic Disease (LIPID) The LIPID Study Group N Engl J Med 1998;339:
PH6415 Review Questions. 2 Question 1 A journal article reports a 95%CI for the relative risk (RR) of an event (treatment versus control as (0.55, 0.97).
Using time-dependent covariates in the Cox model THIS MATERIAL IS NOT REQUIRED FOR YOUR METHODS II EXAM With some examples taken from Fisher and Lin (1999)
Journal Club Alcohol and Health: Current Evidence July–August 2004.
Journal Club Alcohol, Other Drugs, and Health: Current Evidence May-June 2008.
Modeling clustered survival data The different approaches.
Slide Source: Lipids Online Slide Library Prospective Pravastatin Pooling Project: Coronary Event Rates in CARE and LIPID Patients.
C-REACTIVE PROTEIN, FIBRINOGEN, AND CARDIOVASCULAR DISEASE PREDICTION By Patrick Whitledge PA-S2 South University Physician Assistant Program.
17. Duration Modeling. Modeling Duration Time until retirement Time until business failure Time until exercise of a warranty Length of an unemployment.
Assessment of Lupus (SLE) Mortality in a Patient-Based Community Data Bank Frederick Wolfe 1, Kaleb Michaud 1,2, Tracy Li 3, Robert S. Katz 4 1 National.
HYPERLIPIDAEMIA. 4S 4444 patients –Hx angina or MI –Cholesterol Simvastatin 20mg (10-40) vs. placebo FU 5 years  total cholesterol 25%;  LDL.
COURAGE: Clinical Outcomes Utilizing Revascularization and Aggressive Drug Evaluation Purpose To compare the efficacy of optimal medical therapy (OMT)
Emily O’Brien, Emil Fosbol, Andrew Peng, Karen Alexander, Matthew Roe, Eric Peterson The Obesity Paradox: The Importance for Long-term Outcomes in Non-ST-Elevation.
Clinical implications. Burden of coronary disease 56 millions deaths worldwide in millions deaths worldwide in % due to CV disease (~ 16.
Quality of Life and Depression as Determinants of Treatment Adherence in Hypertensive Leonelo E. Bautista 1 ; Paul Smith 2 ; Cynthia Colombo 2 ; Dennis.
Pravastatin in Elderly Individuals at Risk of Vascular Disease Presented at Late Breaking Clinical Trials AHA 2002 PROSPER.
Cardiovascular Disease in Women Module I: Epidemiology.
Essentials of survival analysis How to practice evidence based oncology European School of Oncology July 2004 Antwerp, Belgium Dr. Iztok Hozo Professor.
Management of Elevated Cholesterol in the Primary Prevention Group of Adult Japanese (MEGA) Trial MEGA Trial Presented at The American Heart Association.
Analyses of Covariance Comparing k means adjusting for 1 or more other variables (covariates) Ho: u 1 = u 2 = u 3 (Adjusting for X) Combines ANOVA and.
Predicting risk of cardiovascular disease and the cost-effectiveness of interventions in Thailand Stephen Lim On Behalf of the Setting Priorities using.
Bayesian Analysis and Applications of A Cure Rate Model.
HPS: Heart Protection Study Purpose To determine whether simvastatin reduces mortality and vascular events in patients with and without coronary disease,
Laura Mucci, Pharm.D. Candidate Mercer University 2012 Preceptor: Dr. Rahimi February 2012.
The Prospective Pravastatin Pooling Project L I P I D CARECARE PPP Project Investigators Am J Cardiol 1995; 76:899–905.
WOSCOPS: West Of Scotland Coronary Prevention Study Purpose To determine whether pravastatin reduces combined incidence of nonfatal MI and death due to.
Modeling Cure Rates Using the Survival Distribution of the General Population Wei Hou 1, Keith Muller 1, Michael Milano 2, Paul Okunieff 1, Myron Chang.
AIRE: Acute Infarction Ramipril Efficacy study Purpose To determine whether the ACE inhibitor ramipril reduces mortality in patients with evidence of heart.
Relationship between total cholesterol and 90-day mortality after acute myocardial infarction in patients not on statins Rishi Parmar 2 nd year Medicine.
AA-2-1 Jerome D. Cohen, MD, FACC, FACP Professor of Internal Medicine / Cardiology Director, Preventive Cardiology Programs St. Louis University Health.
LIPID: Long-term Intervention with Pravastatin in Ischemic Disease Purpose To determine whether pravastatin will reduce coronary mortality and morbidity.
Pro gradu –thesis Tuija Hevonkorpi.  Basic of survival analysis  Weibull model  Frailty models  Accelerated failure time model  Case study.
SPARCL – Stroke Prevention by Aggressive Reduction in Cholesterol Levels (SPARCL) Jim McMorran Coventry GP GP with Specialist Interest in Diabetes and.
Collaborative Atorvastatin Diabetes Study CARDS Dr Sachin Kadoo.
ALLHAT 6/5/ CARDIOVASCULAR DISEASE OUTCOMES IN HYPERTENSIVE PATIENTS STRATIFIED BY BASELINE GLOMERULAR FILTRATION RATE (3 GROUPS by GFR)
C-1 Efficacy of the Combination: Meta-Analyses Donald A. Berry, Ph.D. Frank T. McGraw Memorial Chair of Cancer Research University of Texas M.D. Anderson.
4S: Scandinavian Simvastatin Survival Study
Journal Club Alcohol, Other Drugs, and Health: Current Evidence November-December, 2015.
1 Borgan and Henderson: Event History Methodology Lancaster, September 2006 Session 6.1: Recurrent event data Intensity processes and rate functions Robust.
6/5/ CARDIOVASCULAR DISEASE OUTCOMES IN HYPERTENSIVE PATIENTS STRATIFIED BY BASELINE GLOMERULAR FILTRATION RATE (4 GROUPS by GFR) ALLHAT.
Introduction to Biostatistics, Harvard Extension School, Fall, 2005 © Scott Evans, Ph.D.1 Contingency Tables.
Selenium supplementation for the primary prevention of cardiovascular disease: a Cochrane review Clinical
REGRESSION MODEL FITTING & IDENTIFICATION OF PROGNOSTIC FACTORS BISMA FAROOQI.
The MICRO-HOPE. Microalbuminuria, Cardiovascular and Renal Outcomes in the Heart Outcomes Prevention Evaluation Reference Heart Outcomes Prevention Evaluation.
The AURORA Trial Source: Holdaas H, Holme I, Schmieder RE, et al. Rosuvastatin in diabetic hemodialysis patient. J Am Soc Nephrol. 2011;22(7):1335–1341.
[Topic 11-Duration Models] 1/ Duration Modeling.
Date of download: 9/18/2016 Copyright © The American College of Cardiology. All rights reserved. From: Nonfasting Glucose, Ischemic Heart Disease, and.
Background/Objective
US cost-effectiveness of simvastatin in 20,536 people at different levels of vascular disease risk: randomised placebo-controlled trial UK Medical Research.
Efficacy and safety of more intensive lowering of LDL cholesterol: a meta-analysis of data from 170,000 participants in 26 randomised trials Ungroup once.
Health and Human Services National Heart, Lung, and Blood Institute
Diabetes mellitus, fasting blood glucose concentration, and risk of vascular disease: a collaborative meta-analysis of 102 prospective studies  The Emerging.
REVEAL: Randomized placebo-controlled trial of anacetrapib in 30,449 patients with atherosclerotic vascular disease Louise Bowman on behalf of the HPS.
Pravastatin in Elderly Individuals at Risk of Vascular Disease
AIM HIGH Niacin plus Statin to prevent vascular events
Jane Armitage on behalf of the HPS2-THRIVE Collaborative Group
Baseline characteristics of HPS participants by prior diabetes
The results of the SHARP trial
Section 7: Aggressive vs moderate approach to lipid lowering
Diabetes mellitus, fasting blood glucose concentration, and risk of vascular disease: a collaborative meta-analysis of 102 prospective studies  The Emerging.
Jeffrey E. Korte, PhD BMTRY 747: Foundations of Epidemiology II
Separate and combined associations of body-mass index and abdominal adiposity with cardiovascular disease: collaborative analysis of 58 prospective studies 
ASCORE : An up-to-date cardiovascular risk score for hypertensive patients reflecting. contemporary clinical practices developed. using the ASCOT trial.
Baseline Characteristics According to Sex
Diabetes mellitus, fasting blood glucose concentration, and risk of vascular disease: a collaborative meta-analysis of 102 prospective studies  The Emerging.
The results of the SHARP trial
PROSPER: trial design                                                                                                                                                                 
Dilip C. Nath, Atanu Bhattacharjee, Ramesh K. Vishwakarma 
Subgroup analysis on time-to-event: a Bayesian approach
Presentation transcript:

Parametric Conditional Frailty Models for Recurrent Cardiovascular Events in the LIPID Study Dr Jisheng Cui Deakin University, Melbourne

1. Introduction Repeated events & Unobserved frailty LIPID study (Long-term Intervention with Pravastatin in Ischaemic Disease) Risk prediction model for males & females Recurrent myocardial infarction (MI)

Analysis of recurrent event data: Marginal models 1. Wei, Lin & Weissfeld (1989; JASA) 2. Lin (1994; Statistics in Medicine) 3. Prentice, Williams & Peterson (1981; Biometrics)

Conditional models 1. Therneau & Grambsch (2000) 2. Cook & Lawless (2007) 3. Houggard (2000) Frailty model 1. Lancaster & Intrator (1998; JASA) 2. Huang & Wang (2004; JASA) 3. Liu, Wolfe & Huang (2004; Biometrics)

2. Methods LIPID study 1. Clinical trials commenced in Mean follow-up 6 years 3. Aged between 31 & 75 years 4. Majority (83%) males 5. Total of 8557 patients in analysis 6. Among 652 had MI, 14.3% recurrent

Nonstratified frailty model 1. Based on Cox model (1972; JRSSB) 2. Inefficient parameter estimates recurrent events (Lawless & Nadeau 1995; Aelen 1988; Statis. in Medicine) 3. Gap time between events 4. Censored: died or not have MI

Frailty specific to an individual 1. gamma distribution mean 1 variance 2. inverse Gaussian frailty Baseline : Weibull, Gompertz, log-logistic, log-normal, generalized gamma Weibull survival model :

Stratified nonfrailty model 1. Robust Huber and White estimator 2. Baseline rates stratified by events Strata model 1. Scale and shape parameter different Shape model 2. Only shape parameter different Covariate model 3. Indicator for recurrent in the model

Prognostic index 1. Tertiles used to classify into low-, medium, or high-risk group. 2. Cumulative risk Covariates: age, smoking status, treatment, whether has an MI event, total & HDL cholesterol, stroke, diabetes, hypertension, country, etc

Model selection 1. Backward selection 2. Akaike Information Criterion (AIC) 3. Bayesian Information Criterion (BIC)

3.Results Among 8557 patients, 745 recurrent MI 313/4286 (7.3%) in treatment 432/4271 (10.1%) in placebo Median time until 1st MI 2.8 years in treatment 2.7 years in placebo

Median time between 1st & 2nd MI 0.90 years in treatment 0.43 years in placebo Only 0.3% (23 patients) had >2 MI events Following analysis based on first 2 events 1062 (12.4%) patients died 6954 (81%) patients no MI & still alive 541 patients had ≥1 MI event & still alive

Table 1: Summary statistics _____________________________________________ Time (years)TreatmentPlacebo _________________________ NMedianNMedian _____________________________________________ To 1st MI st MI to 2nd MI nd MI to 3rd MI rd MI to 4th MI th MI to 5th MI _____________________________________________

Model comparison 1. Weibull model gamma frailty largest LL & smallest AIC and BIC 2. Variance frailty 1.01 (95% CI ) 3. Still has unobserved heterogeneity 4. Inverse Gaussian frailty model not fit data as well as gamma frailty

Table 2: Model comparison (gamma model for male) _____________________________________________ DistributionLLAICBICΘ _____________________________________________ Weibull Log-logistic Gompertz Log-normal _____________________________________________

Table 3: Model comparison (Weibull model for male) _____________________________________________ DistributionLLAICBIC _____________________________________________ Strata model Shape model Covariate model _____________________________________________ Strata model Weibull fits data best

Table 4: Model comparison (gamma model for female) _____________________________________________ DistributionLLAICBICΘ _____________________________________________ Weibull Log-logistic Gompertz Log-normal _____________________________________________ Weibull model fits data best

Table 5: Model comparison (Weibull model female) _____________________________________________ DistributionLLAICBIC _____________________________________________ Strata model Shape model Covariate model _____________________________________________

Model comparison 1. Weibull model gamma frailty largest LL & smallest AIC and BIC 2. Variance frailty 1.01 (95% CI ) 3. Still has unobserved heterogeneity 4. Inverse Gaussian frailty model not fit data as well as gamma frailty 5. Strata model with Weibull baseline fits data best

Table 6: Risk prediction model (male) _____________________________________________ Risk factorHR95% CIHR95% CI _____________________________________________ Age Smoking Total Chol … Treatment MI event _____________________________________________

Risk model for males 1. Although estimate of Θ varies, same subsets of covariates selected 2. The 95% CI overlap for best fitting frailty & nonfrailty models 3. Risk of MI who had an MI 3.65 times the risk who not have an MI 4. No evidence of significant interactions

Table 7: Risk prediction model (female) _____________________________________________ Risk factorHR95% CIHR95% CI _____________________________________________ Age HDL Chol … Treatment MI event _____________________________________________

Risk model for females 1. Smaller number of significant factors compared with males 2. No significant interactions between treatment and recurrent event

Figure 1: Cumulative risk for nonsmoking man

Cumulative risk for nonsmoking men 1. Aged 60 years, total chol. 5.0 mmol/L, HDL chol. 1.0 mmol/L, no history of stroke, diabetes 2. Placebo: 5-year MI 10.3% if MI event 5.6% if not had an MI 3. Treatment: 5-year MI 7.6% & 4.1%, respectively

Figure 2: Cumulative risk nonsmoking woman

Cumulative risk for nonsmoking women 1. Placebo: 5-year MI 16.2% if MI event 6.2% if not had an MI 3. Treatment: 5-year MI 12.5% & 4.7%, respectively

Table 8: Predicted risk within 5 years (male) _____________________________________________ Prognostic indexRangeTreatment Placebo _____________________________________________ First MI event Low≤ Medium High> Second MI event Low≤ Medium High> _____________________________________________

Risk prediction for men 1. Without an MI event: highest risk group 10.8% and 14.5% 2. Had an MI event: increase from 13.0% to 40.9% 3. Highest risk group 31.8% and 40.9%

Table 9: Predicted risk within 5 years (female) _____________________________________________ Prognostic indexRangeTreatment Placebo _____________________________________________ First MI event Low≤ Medium High> Second MI event Low≤ Medium High> _____________________________________________

Risk prediction for women 1. Without an MI event: highest risk group 8.6% and 11.2% 2. Had an MI event: increase from 25.4% to 60.0% 3. Highest risk group 50.1% and 60.0%

Risk prediction 1. Placebo: 5-year MI 16.2% if MI event 6.2% if not had an MI 3. Treatment: 5-year MI 12.5% & 4.7%, respectively

Figure 3: Predicted and observed first MI event

Comparison of predicted and observed risk 1. Predicted 5-year risk close agreement with observed rates 2. Especially in low- and medium-risk group and female high risk group

4. Summary Applied frailty & nonfrailty models Developed risk prediction model Heterogeneity in risk for MI events Stratified nonfrailty model fits data better Treatment effect robust across models and gender Validated internally close to observed data Cox frailty model intensive computing time