Subgroup Analysis in Cost-Effectiveness Analysis ISPOR Issues Panel May 17, 2004 Joseph Heyse John Cook Merck Research Laboratories.

Slides:



Advertisements
Similar presentations
Statistical Analysis and Data Interpretation What is significant for the athlete, the statistician and team doctor? important Will Hopkins
Advertisements

V.: 9/7/2007 AC Submit1 Statistical Review of the Observational Studies of Aprotinin Safety Part I: Methods, Mangano and Karkouti Studies CRDAC and DSaRM.
LSU-HSC School of Public Health Biostatistics 1 Statistical Core Didactic Introduction to Biostatistics Donald E. Mercante, PhD.
Exploring uncertainty in cost effectiveness analysis NICE International and HITAP copyright © 2013 Francis Ruiz NICE International (acknowledgements to:
Departments of Medicine and Biostatistics
CONSENSUS: Cooperative North Scandinavian Enalapril Survival Study Purpose To determine whether the ACE inhibitor enalapril reduces mortality in patients.
Douglas Almond Joseph J. Doyle, Jr. Amanda E. Kowalski Heidi Williams
Gillian D Sanders Ph.D.Lurdes Y Inoue Ph.D. Associate Professor of MedicineAssociate Professor of Biostatistics Duke UniversityUniversity of Washington.
ODAC May 3, Subgroup Analyses in Clinical Trials Stephen L George, PhD Department of Biostatistics and Bioinformatics Duke University Medical Center.
Challenges When Conducting Economic Evaluation Alongside Clinical Trials: Experience Of Economic Appraisal In Cardiovascular Disease Andrew Briggs University.
Henry C. Ginsberg, MD College of Physicians & Surgeons, Columbia University, New York For The ACCORD Study Group.
The Long-Term Intervention with Pravastatin in Ischemic Disease (LIPID) The LIPID Study Group N Engl J Med 1998;339:
Recursive Partitioning Method on Survival Outcomes for Personalized Medicine 2nd International Conference on Predictive, Preventive and Personalized Medicine.
Confounding And Interaction Dr. L. Jeyaseelan Department Of Biostatistics CMC, Vellore.
the Cox proportional hazards model (Cox Regression Model)
EPIDEMIOLOGY AND BIOSTATISTICS DEPT Esimating Population Value with Hypothesis Testing.
1.A 33 year old female patient admitted to the ICU with confirmed pulmonary embolism. It was noted that she had elevated serum troponin level. Does this.
Common Problems in Writing Statistical Plan of Clinical Trial Protocol Liying XU CCTER CUHK.
Journal Club Alcohol, Other Drugs, and Health: Current Evidence March–April 2015.
Sample Size Determination Ziad Taib March 7, 2014.
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.
Are the results valid? Was the validity of the included studies appraised?
COURAGE: Clinical Outcomes Utilizing Revascularization and Aggressive Drug Evaluation Purpose To compare the efficacy of optimal medical therapy (OMT)
BEAUTI f UL: morBidity-mortality EvAlUaTion of the I f inhibitor ivabradine in patients with coronary disease and left ventricULar dysfunction Purpose.
Clinical Trials. What is a clinical trial? Clinical trials are research studies involving people Used to find better ways to prevent, detect, and treat.
Evidence-Based Medicine 4 More Knowledge and Skills for Critical Reading Karen E. Schetzina, MD, MPH.
Economic evaluation of health programmes Department of Epidemiology, Biostatistics and Occupational Health Class no. 17: Economic Evaluation using Decision.
Economic evaluation of health programmes Department of Epidemiology, Biostatistics and Occupational Health Class no. 20: More on dealing with uncertainty.
Chapter 6 Introduction to Statistical Inference. Introduction Goal: Make statements regarding a population (or state of nature) based on a sample of measurements.
Basic Statistical Concepts. Chapter 2 Reading instructions 2.1 Introduction: Not very important 2.2 Uncertainty and probability: Read 2.3 Bias and variability:
Fenofibrate Intervention and Event Lowering in Diabetes FIELDFIELD Presented at The American Heart Association Scientific Sessions, November 2005 Presented.
Antidepressants and Suicidality in Adults: Statistical Evaluation Mark Levenson, Ph.D.* and Chris Holland, M.S. Statistical Safety Reviewers Quantitative.
Scandinavian Simvastatin Survival Study (4S) The Lancet, Vol 344, November 19, 1994.
Estimating Incremental Cost- Effectiveness Ratios from Cluster Randomized Intervention Trials M. Ashraf Chaudhary & M. Shoukri.
BEST: Beta-blocker Evaluation Survival Trial Purpose To determine whether the β-blocker bucindolol reduces morbidity and mortality in patients with advanced.
1 THE ROLE OF COVARIATES IN CLINICAL TRIALS ANALYSES Ralph B. D’Agostino, Sr., PhD Boston University FDA ODAC March 13, 2006.
Use of Candidate Predictive Biomarkers in the Design of Phase III Clinical Trials Richard Simon, D.Sc. Chief, Biometric Research Branch National Cancer.
Lecture 9: Analysis of intervention studies Randomized trial - categorical outcome Measures of risk: –incidence rate of an adverse event (death, etc) It.
Parametric Conditional Frailty Models for Recurrent Cardiovascular Events in the LIPID Study Dr Jisheng Cui Deakin University, Melbourne.
1 Study Design Issues and Considerations in HUS Trials Yan Wang, Ph.D. Statistical Reviewer Division of Biometrics IV OB/OTS/CDER/FDA April 12, 2007.
Lecture 5: The Natural History of Disease: Ways to Express Prognosis
BC Jung A Brief Introduction to Epidemiology - XIII (Critiquing the Research: Statistical Considerations) Betty C. Jung, RN, MPH, CHES.
ALLHAT 6/5/ CARDIOVASCULAR DISEASE OUTCOMES IN HYPERTENSIVE PATIENTS STRATIFIED BY BASELINE GLOMERULAR FILTRATION RATE (3 GROUPS by GFR)
EBM --- Journal Reading Presenter :呂宥達 Date : 2005/10/27.
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.
Postgraduate books recommended by Degree Management and Postgraduate Education Bureau, Ministry of Education Medical Statistics (the 2nd edition) 孙振球 主.
4S: Scandinavian Simvastatin Survival Study
Effect of Rosiglitazone on the Risk of Myocardial Infarction And Death from Cardiovascular Causes Alternative Interpretations of the Evidence George A.
9-1 Copyright © 2016 McGraw-Hill Education. All rights reserved. No reproduction or distribution without the prior written consent of McGraw-Hill Education.
CV-1 Trial 709 The ISEL Study (IRESSA ® Survival Evaluation in Lung Cancer) Summary of Data as of December 16, 2004 Kevin Carroll, MSc Summary of Data.
1 CONFIDENTIAL – DO NOT DISTRIBUTE ARIES mCRC: Effectiveness and Safety of 1st- and 2nd-line Bevacizumab Treatment in Elderly Patients Mark Kozloff, MD.
Research Design Evidence Based Medicine Concepts and Glossary.
Learning Objectives After this section, you should be able to: The Practice of Statistics, 5 th Edition1 DESCRIBE the shape, center, and spread of the.
6/5/ CARDIOVASCULAR DISEASE OUTCOMES IN HYPERTENSIVE PATIENTS STRATIFIED BY BASELINE GLOMERULAR FILTRATION RATE (4 GROUPS by GFR) ALLHAT.
Paz Bailey G 1, Sternberg M 1, Puren AJ 2, Markowitz LE 1, Ballard R 1, Delany S 3, Hawkes S 4, Nwanyanwu O 1, Ryan C 1, and Lewis DA 5 1. NCHHSTP, CDC.
© 2010 Jones and Bartlett Publishers, LLC. Chapter 12 Clinical Epidemiology.
Survival with Cardiac- Resynchronization Therapy in Mild Heart Failure.
CHEST 2013; 144(3): R3 김유진 / Prof. 장나은. Introduction 2  Cardiovascular diseases  common, serious comorbid conditions in patients with COPD cardiac.
Methods of Presenting and Interpreting Information Class 9.
The SPRINT Research Group
Upfront Combination Therapy vs Step-Up Approach for PAH:
The Importance of Adequately Powered Studies
Statistical Core Didactic
NAPLEX preparation: Biostatistics
Simulation: Sensitivity, Bootstrap, and Power
Mark Rothmann U.S. Food and Drug Administration September 14, 2018
Distribution of the Sample Proportion
A decade after the Surgical Treatment for Ischemic Heart Failure (STICH) trial: Weaving firm clinical recommendations from lessons learned  Robert E.
China PEACE risk estimation tool for in-hospital death from acute myocardial infarction: an early risk classification tree for decisions about fibrinolytic.
Helen Barraclough, MSc, Ramaswamy Govindan, MD 
Presentation transcript:

Subgroup Analysis in Cost-Effectiveness Analysis ISPOR Issues Panel May 17, 2004 Joseph Heyse John Cook Merck Research Laboratories

ISPOR Issues Panel 2004.ppt.2 Definition Encyclopedia of Biostatistics Subgroup Analysis in Clinical Trials see Treatment-Covariate Interaction

ISPOR Issues Panel 2004.ppt.3 Treatment-Covariate Interaction l A treatment-covariate interaction exists when the effect of a treatment varies according to the value of a specific covariate. l Covariates are defined according to patient characteristics such as gender, race, age, study center country, or disease risk factors. Subgroups are sets of patients with common values of covariates.

ISPOR Issues Panel 2004.ppt.4 Importance Identifying and evaluating interactions is a key step in the analysis of clinical trial data. –Assess the appropriateness of an overall estimate of treatment effect. –Improve precision of estimated treatment effect. –Adjust estimate of treatment effect for common value of covariates. –Explore the consistency of the treatment among subgroups. –Identify subgroups of patients with greater/lesser levels of treatment effect.

ISPOR Issues Panel 2004.ppt.5 Characterizing Interaction (Gail and Simon, 1985) Quantitative: Treatment effect varies among the subgroups of patients. Qualitative: The direction of the true treatment differences varies among the subgroups of patients. This is sometimes called crossover interaction.

ISPOR Issues Panel 2004.ppt.6 Test of Quantitative Interaction (Gail & Simon, 1985) – Compare H to  2 with K-1 d.f. Large value of H implies treatment differences exists among countries/centers Suppose there are K countries, each with mean treatment effect D i and standard deviation S i – Compute: where

ISPOR Issues Panel 2004.ppt.7 Test of Qualitative Interaction #1 (Gail & Simon, 1985)  Compute Q - and Q + for positive and negative differences: ; Test Statistic: Large value of Q implies differences exist in direction of treatment effect among countries

ISPOR Issues Panel 2004.ppt.8 Test of Qualitative Interaction #2 (Piantadosi & Gail, 1993; Pan & Wolfe, 1997)  Construct confidence intervals for each country (L i, U i ): D i ± Z  S i, for i = 1, 2…, K where  * = ½(1-P K ) P K = 2(1-  ) 1/(k-1) - 1  Qualitative interaction exists if there are two countries ( i and j ) with intervals such that: U i 0 ; Pan & Wolfe discuss relative merit of methods

ISPOR Issues Panel 2004.ppt.9 Scandinavian Simvastatin Survival Study (4S) l Randomized, double-blind, placebo-controlled, N=4444 patients in Scandinavian countries. -Denmark (N=713)-Norway (N=1025) -Finland (N=868)-Sweden (N=1681) -Iceland (N=157) l Patients with previous MI followed median period of 5.4 years. l Simvastatin therapy associated with 30% reduction in deaths and 34% fewer hospital days.

ISPOR Issues Panel 2004.ppt.10 4S: Proportion of Patients Dying by Country for Placebo and Simvastatin Patients

ISPOR Issues Panel 2004.ppt.11 4S: Cardiovascular Hospitalizations Per Patient Year by Country for Placebo and Simvastatin Patients

Testing for Interaction: CE Ratios l Homogeneity among countries in costs and effects does not imply homogeneity in the ratio l Challenges with the CE ratio ; Analytic challenges: Lack of uniqueness with ratio When  E = 0 ; Conceptual challenge: What is a qualitative interaction? l Recommend using an angular transformation of the CE Ratio. ISPOR Issues Panel 2004.ppt.12

ISPOR Issues Panel 2004.ppt.13 Angular Transformation l Apply angular transformation to (∆C, ∆E) to obtain the CE angle: Tan -1 [  C / SD(  C),  E / SD(  E)] if  C  o +Tan -1 [  C / SD(  C),  E / SD(  E)] if  C < 0 l Construct 95% confidence limits for angle (counter clockwise and clockwise limits) –Can use either normal theory or percentile bootstrap methods l Must reverse transform angles back to ratios!

ISPOR Issues Panel 2004.ppt.14 Testing for Interaction: CE Ratio l What is a qualitative interaction for the ratio: –Requires specification of CE threshold ( ) CE ratios “below” are deemed cost-effective CE ratios “above” are deemed not cost- effective –Qualitative interaction exists if some countries are cost-effective, while others are not.

ISPOR Issues Panel 2004.ppt.15 4S: CE Ratio Incremental Survival Probability Incremental Cost (U.S.$) Denmark Finland Iceland Norway Sweden Overall  = 75K

4S: Cost Per Additional Survivor with 95% Confidence Intervals ISPOR Issues Panel 2004.ppt.16

ISPOR Issues Panel 2004.ppt.17 Concluding Remarks l It is important to assess the consistency of treatment effects on costs, effects, and cost-effectiveness across subgroups of patients. l This analysis includes a characterization of possible interactions being quantitative or qualitative. l Available tests for interaction can be applied to cost- effectiveness ratios and net health benefits. l The results of the analysis can be used to improve the precision of the estimate and evaluate the generalizability of study conclusions.

ISPOR Issues Panel 2004.ppt.18 Selected References Armitage P and Colton T, Editors. Encyclopedia of Biostatistics, Volume 6, John Wiley & Sons: New York, Gail MH and Simon R. Testing for qualitative interactions between effects and patient subsets. Biometrics 1985; 41: Pan G and Wolfe DA. Test for qualitative interaction of clinical significance. Statistics in Medicine 1997; 16: Cook JR, Drummond MF, Glick H, and Heyse JF. Assessing the appropriateness of combining economic data from multinational clinical trials. Statistics in Medicine 2003; 22: Cook JR and Heyse JF. Use of an angular transformation for ratio estimation in cost-effectiveness analysis. Statistics in Medicine 2000; 19: