Statistical Comments on Retrospective Analysis Girish Aras, Ph.D. Jonathan Ma, Ph.D. Center for Drug Evaluation and Research, FDA.

Slides:



Advertisements
Similar presentations
Chapter 2 Describing Contingency Tables Reported by Liu Qi.
Advertisements

If we use a logistic model, we do not have the problem of suggesting risks greater than 1 or less than 0 for some values of X: E[1{outcome = 1} ] = exp(a+bX)/
Presentation title Date Responder endpoint and continuous endpoint, logistic regression or ANOVA? DSBS 24 OCT 2013 Søren Andersen.
Objective of the DAP A) Specify an analysis plan that can be applied to a wide variety of clinical HIV resistance studies. B) Include both Intervention.
Estimation and Reporting of Heterogeneity of Treatment Effects in Observational Comparative Effectiveness Research Prepared for: Agency for Healthcare.
Logistic Regression and Odds Ratios
Comparison of INSTI vs PI  FLAMINGO  GS  ACTG A5257.
Confidence Interval for Relative Risk
Practical Meta-Analysis -- D. B. Wilson
Basic Statistical Concepts Donald E. Mercante, Ph.D. Biostatistics School of Public Health L S U - H S C.
Generalized Linear Models
ACTG 333 The Antiviral Effect of Switching from Saquinavir to the New Formulation of Saquinavir vs. Switching to Indinavir After >1 year of Saquinavir.
Logistic Regression In logistic regression the outcome variable is binary, and the purpose of the analysis is to assess the effects of multiple explanatory.
Persisting long term benefit of genotypic guided treatment in HIV infected patients failing HAART and Importance of Protease Inhibitor plasma levels. Viradapt.
Stratification and Adjustment
JWM 11/99 Resistance Collaborative Group Re-Analysis of Studies and Review of Ongoing Prospective Studies John W. Mellors, MD Director, HIV/AIDS Program.
Switch to TDF/FTC/RPV  SPIRIT Study. SPIRIT study: Switch PI/r + 2 NRTI to TDF/FTC/RPV TDF/FTC/RPV STR 24 weeks 48 weeks Primary Endpoint Secondary Endpoint.
Risk of Osteoporotic Fractures Associated with Cumulative Exposure to Tenofovir and Other Antiretroviral Agents Roger Bedimo, MD; Song Zhang, PhD; Henning.
Prevalence of resistance mutations in a cohort of treatment-naïve people with chronic HIV infection in the U.S.: CPCRA 058 R M Novak 1, L Chen 2, R D MacArthur.
Predicting NNRTI Resistance – do polymorphisms matter? Nicola E Mackie 1, Lucy Garvey 1, Anna Maria Geretti 2, Linda Harrison 3, Peter Tilston 4, Andrew.
Increased phenotypic susceptibility (hypersusceptibility, HS) to NNRTIs is observed in ~30% of viral isolates with NRTI- resistance mutations 1 and has.
1 RESIST Trials - Grade 3 or 4 AST, ALT or Total Bilirubin: Actions and Outcomes Action Taken: TPV/r N=748 CPI/r N=737 Total Number of Grade 3 or 4 ALT,
TITAN = TMC114/r In Treatment-experienced pAtients Naïve to lopinavir
Arnold School of Public Health Health Services, Policy, and Management 1 Drug Treatment Disparities Among African Americans Living with HIV/AIDS Carleen.
LOGISTIC REGRESSION A statistical procedure to relate the probability of an event to explanatory variables Used in epidemiology to describe and evaluate.
HSRP 734: Advanced Statistical Methods July 17, 2008.
Combined PI and NNRTI Resistance Analysis of the Pooled DUET Trial: Towards a Regimen-Based Resistance Interpretation J. M. Schapiro, J. Vingerhoets, S.
1 THE ROLE OF COVARIATES IN CLINICAL TRIALS ANALYSES Ralph B. D’Agostino, Sr., PhD Boston University FDA ODAC March 13, 2006.
Comparison of NNRTI vs PI/r  EFV vs LPV/r vs EFV + LPV/r –A5142 –Mexican Study  NVP vs ATV/r –ARTEN  EFV vs ATV/r –A5202.
Regression Analysis Part C Confidence Intervals and Hypothesis Testing
SW318 Social Work Statistics Slide 1 Logistic Regression and Odds Ratios Example of Odds Ratio Using Relationship between Death Penalty and Race.
Mounir Ait-Khaled, The Predictive Quality of Genotype and Phenotype Data on Virological Response to Salvage Therapy in HIV-1 Infected Patients.
Evaluation of the WHO immunologic criteria for treatment failure among adults on first-line HAART in south India Snigdha Vallabhaneni 1, Sara Chandy 2,
Multiple Regression  Similar to simple regression, but with more than one independent variable R 2 has same interpretation R 2 has same interpretation.
Heart Disease Example Male residents age Two models examined A) independence 1)logit(╥) = α B) linear logit 1)logit(╥) = α + βx¡
HIV-1 Resistance Testing in Drug Development Antiviral Drugs Advisory Committee Meeting November 2-3, 1999.
1 Statistical Review of the Observational Studies of Aprotinin Safety Part II: The i3 Drug Safety Study CRDAC and DSaRM Meeting September 12, 2007 P. Chris.
Logistic regression. Recall the simple linear regression model: y =  0 +  1 x +  where we are trying to predict a continuous dependent variable y from.
Lecture 7 Odds, Odds Ratios and Risk STAT 3120 Statistical Methods I.
Logistic Regression An Introduction. Uses Designed for survival analysis- binary response For predicting a chance, probability, proportion or percentage.
Date of download: 5/28/2016 Copyright © 2016 American Medical Association. All rights reserved. From: Low-Frequency HIV-1 Drug Resistance Mutations and.
NURS 306, Nursing Research Lisa Broughton, MSN, RN, CCRN RESEARCH STATISTICS.
Previous SVR With Interferon-Based Therapy for HCV Lowers Risk of Hepatotoxicity in HIV/HCV-Coinfected Individuals on Antiretroviral Therapy Slideset on:
HIV Drug Resistance Surveillance Satellite Session: HIV Drug Resistance Surveillance and Control: a Global Concern Silvia Bertagnolio, MD WHO,
Tipranavir/Ritonavir Superior to Comparator PI/Ritonavir at Week 48 in Multiclass-Experienced Patients Slideset on: Hicks CB, Cahn P, Cooper DA, et al.
Rilpivirine-TDF-FTC versus Efavirenz-TDF-FTC STaR Trial
Comparison of PI vs PI ATV vs ATV/r BMS 089
undetectable (undetectable-6.25)
Virological and immunological efficacy of regimen including MVC
Figure 1 Inclusion criteria, exclusion criteria, and criteria for virologic failure. CDC, Centers for Disease Control and Prevention; ddC, zalcitabine;
Etravirine in Treatment Experienced DUET-2 (TMC125-C216)
Switch to RPV-TDF-FTC from Ritonavir-boosted PI Regimen SPIRIT STUDY
Etravirine versus Protease Inhibitor in ARV-Experienced TMC 125-C227
Copyright © 2009 American Medical Association. All rights reserved.
Introduction to logistic regression a.k.a. Varbrul
Simulation: Sensitivity, Bootstrap, and Power
Switch to DTG-containing regimen
Tutorial 4 For the Seat Belt Data, the Death Penalty Data, and the University Admission Data, (1). Identify the response variable and the explanatory.
Long-Term Clinical and Immunologic Outcomes Are Similar in HIV-Infected Persons Randomized to NNRTI versus PI versus NNRTI+PI-based Antiretroviral Regimens.
Switch to LPV/r monotherapy
Comparison of NNRTI vs PI/r
Comparison of PI vs PI ATV vs ATV/r BMS 089
G. Rocheleau, C.J. Brumme, J. Shoveller, V.D. Lima, P.R. Harrigan 
Switch to RAL-containing regimen
Comparison of NNRTI vs NNRTI
Forest plot of adjusted odds ratios (with 95% confidence intervals) from multivariable multinomial logistic regression analysis (table 4), by number of.
ARV-trial.com Switch to ATV/r + RAL HARNESS Study 1.
Background. Long-Term B/F/TAF Switch Efficacy in Patients with Archived Pre-Existing Resistance.
ARV-trial.com Switch to FTC + ddI + EFV ALIZE 1.
Relationship between darunavir IQ and the probability of virologic success (HIV-1 RNA
Presentation transcript:

Statistical Comments on Retrospective Analysis Girish Aras, Ph.D. Jonathan Ma, Ph.D. Center for Drug Evaluation and Research, FDA

Data Analysis Plan Logistic Regression model Dependent variable (Virological Failure) is ‘explained’ with independent variables ( baseline covariates ).

Baseline Covariates Baseline Log (HIV-1 RNA) New Drug Covariate Genotypic Measures –Genotypic Sensitivity Score –No. of PI, NRTI and NNRTI mutations Phenotypic Measures –Overall Sensitivity Score –No. of PI, NRTI and NNRTI drugs with Phenotypic sensitivity

Relative Risk (Risk Ratio, RR) P 0 = Probability of virological failure when a covariate is at a given level P 1 = Probability of virological failure when a covariate is at one unit higher than the previous level RR = P 1 / P 0

Odds ratio RR is the quantity of interest but typically not estimable from a retrospective study OR (Odds Ratio) = P 1 /(1-P 1 ) ÷ P 0 /(1-P 0 ) OR can be estimated from a retrospective study, but may not of interest in itself When P 1 and P 0 are small, RR  OR

Odds Ratios for Various Relative Risks — Relative Risk — Odds Ratio P1P1 P 0 =0.05 P 0 =0.1 P 0 =0.15 P 0 =0.2 P 0 =0.25 Odds Ratio or Relative Risk

Odds Ratios for Various Relative Risks P0P0 Odds Ratio RR=3 RR=2.5 RR=2 RR=1.5

Mutation-Drug Resistance Table Table 1 in DAP titled ‘mutations associated with resistance to specific antiretroviral drugs’ is largely based on in vitro data and/or exploratory subgroup analyses A general consensus is yet to emerge on this table.

Mutation-Drug Resistance Table Most of the studies were available to the resistance collaborative group before the DAP was developed

95% Confidence Interval for Odds Ratio for Overall Genotypic Sensitivity Score: Model C (Univariate) and E (Multivariate)

95% confidence interval for Odds ratio for Number of PI Mutations: Model D and F

95% Confidence Interval for Overall Phenotypic Score: Model C (Univariate) and Model G (Multivariate)

Conclusions These exploratory analyses suggest predictive link between virological failure and genotypic and phenotypic measures at the baseline They will provide insight in generating specific hypotheses to be tested in future confirmatory studies