Title: STATISTICAL CONSIDERATIONS IN POSTMARKETING SAFETY EVALUATION A. Lawrence Gould Merck Research Laboratories West Point, PA [goulda@merck.com] FDA/Industry Workshop 29 September 2006 Washington, DC
1STATISTICAL CONSIDERATIONS IN POSTMARKETING
SAFETY EVALUATIONA. Lawrence GouldMerck
Research LaboratoriesWest Point, PA
goulda_at_merck.comFDA/Industry Workshop29
September 2006Washington, DC
2OVERVIEW
3Spontaneous AE Reports
- Clinical trial safety information is limited
relatively short duration - Safety data collection continues after drug
approval - Detect rare adverse events
- Obtain tolerability information in a broader
population - Large amount of low-quality data collected
- Not usable for trt comparisons or risk assessment
- Unknown sensitivity specificity
- Evaluation by skilled clinicians
epidemiologists - Long history of research on issue
4Information Available Postmarketing
- Previously undetected adverse and beneficial
effects that may be uncommon or delayed, i.e.,
emerging only after extended treatment - Patterns of drug utilization
- Effect of drug overdoses
- Clinical experience with study drugs in their
natural environment
5The Pharmacovigilance Process
Traditional Methods
Data Mining
Detect Signals
Generate Hypotheses
Insight from Outliers
Public Health Impact, Benefit/Risk
Refute/Verify
Type A (Mechanism-based)
Estimate Incidence
Act
Inform
Type B (Idiosyncratic)
Restrict use/ withdraw
Change Label
6Considerations Issues (An Incomplete List!)
- Incomplete reports of events, not reactions
- Bias noise in system
- Difficult to estimate incidence because no. of
pats at risk, pat-yrs of exposure seldom reliable - Significant under reporting (esp. OTC)
- Synonyms for drugs events ? sensitivity loss
- Duplicate reporting
- No certainty that a drug caused the reaction
reported - Cannot use accumulated reports to calculate
incidence, estimate drug risk, or compare drugs
7DATA MINING
8Data Mining is a Part of Pharmacovigilance
- Identify subtle associations (e.g.,
drugdrugevent) and complex relationships not
apparent by simple summary - Identify potential toxicity early
- Finding real D-E associations similar to
finding potential active compounds or expressed
genes not exactly the same (no H0) more like
model selection - Still need initial case review
- respond to reports involving severe, potential
life-threatening events eg., Stevens-Johnson
syndrome, agranulocytosis, anaphylactic shock - Clinical/biological/epidemiological verification
of apparent associations is essential
9 Typical Data Display
No. Reports Target AE Other AE Total
Target Drug a b nTD
Other Drug c d nOD
Total nTA nOA n
Basic idea Flag when R a/E(a) is large
- Some possibilities
- Reporting Ratio E(a) nTD ? nTA/n
- Proportional Reporting Ratio E(a) nTD ?
c/nOD - Odds Ratio E(a) b ? c/d
- Need to accommodate uncertainty, especially if
a is small - Bayesian approaches provide a way to do this
10Currently Used Bayesian Approaches
- Empirical Bayes (DuMouchel, 1998) WHO (Bate,
1998) - Both use ratio nij / Eij where
- nij no. of reports mentioning both drug i
event j - Eij expected no. of reports of drug i event j
- Both report features of posterior distn of
information criterion - ICij log2 nij / Eij PRRij
- Eij usually computed assuming drug i event j
are mentioned independently - Ratio gt 1 (IC gt 0) ? combination mentioned more
often than expected if independent
11Comparative Example (DuMouchel, 1998)
- No. Reports 4,864,480, Mentioning drug 85,304
Headache Headache Polyneuritis Polyneuritis
Reports AE Both AE Both
Mentioning 71,209 1,614 262 3
Reporting Ratio 1.23 1.23 2.83 2.83
WHO FDA WHO FDA
Expected RR 1.29 1.23 0.76 1.42
5 Quantile -- 1.18 -- 0.58
Excess n 300 225 0 0
12DATA MINING EXAMPLES INCORPORATING STATISTICAL
REFINEMENTS
13Result From 6 Years of Reports on Lisinopril
Events w/Lower 5 RR Bnd gt 2 (Bold ? N ? 100)
14Persistence ( Reliability) of Early Signals
15Accumulating Information over Time
- Lower 5 quantiles of RR stabilized fairly soon
16Time-Sliced Evolution of Risk Ratios
- See how values of criteria change over time
within time intervals of fixed length
Change in ICij for reports of selected events on
A2A from 1995 to 2000 tension
hypotension failure heart
failure kalemia hyperkalemia edema
angioedema
17Masking of AE-Drug Relationships (1)
- Company databases smaller than regulatory
databases, more loaded with similar drugs - eg, Drug A is 2nd generation version of Drug B,
similar mechanism of action, many reports with B - Elevated reporting frequency on Drug B could mask
effect of Drug A - May be useful to provide results when reports
mentioning Drug B are omitted
18Masking of AE-Drug Relationships (2)
19Example 2 Vaccine-Vaccine Interaction
- From FDA VAERS database, reports from 1990-2002
- Intussusception is a serious intestinal malady
observed to affect infants vaccinated against
rotavirus - Look at reports of intussusception that mention
rotavirus vaccine (RV) and DTAP vaccine - DTAP is a benign combination vaccine commonly
administered to infants - Demonstration question Intussusception very
commonly reported with RV but does the
reporting rate depend on whether DTAP was
co-administered? - Not easy to address using standard
pharmacovigilance procedures
20Outline of Analysis
- Standard tools provide intussusception reporting
rate for pairs of vaccines, and for vaccines
singly - Result is a 3-way count table (corresponding to
RV or -, DTAP or -, and intussusception or
-) - Use log-linear model to see if intussusception is
mentioned with the two vaccines together more
often than the separate vaccine-intussusception
reporting associations would predict - Turns out that there is an association
Likelihood ratio chi-square is 17.41, 1 df,
highly significant
21Observed and Expected Report Rates
22Comments
- Intussusception seems to be reported more often
than expected when RV and DTAP are given together
than when RV is given without DTAP, after
adjusting for individual vaccine-intussusception
associations - Reports of intussception without RV are very
rare, about 4.5/10,000 reports if RV is not
mentioned - The joint effect of RV and DTAP on
intussusception reporting is small, but does
reach statistical significance - Not clear that apparent association means
anything -- actual synergy between RV and DTAP
seems unlikely, but explanation requires clinical
knowledge
23A NEW BAYESIAN APPROACH(Gould, Biometrical
Journal 2006, to appear)
24Model for Process Generating Observations
- ni no. of reports mentioning i-th drug-event
pair Poisson (true for EB approach as well) - f(ni Ei, ?i) fPois(ni ?iEi)
- ?i drawn from a gamma(a0, b0) distribution or
from a gamma(a1, b1) distribution - A model selection problem
- Distns reflect physician/epidemiologists
judgment as to what range of ? values corresponds
to signals, and what does not
Expected count under independence
Association measure
25Prior/Model Density of ?
- Bayes approach starts with a random mixture of
gamma densities, - f?0(? ?, a0, b0, a1, b1)
- (1 - ?)fgam(? a0, b0) ?fgam(? a1, b1)
- Use value of Ppost(g 1) for inference
- EB approach starts with expectation wrt ? given p
? nonrandom mixture of gamma densities, - f?0(? p, a0, b0, a1, b1)
- pfgam(? a0, b0) (1-p)fgam(? a1, b1)
- Use quantiles of posterior distn of ? for
inference
Analyst specifies parameter values
Data determine parameter values
26Comments
- Bayes and EB approaches both model strength of
drug-event reporting assn as a gamma mixture - Diagnostic properties of Bayes method can be
determined analytically or by simulation - Unknown separation of the true alternative
distns for ? more important than prior distn
used for analysis - Methods described here can be applied to other
models Scott Berger (2005) used normal
distributions could also use binomial instead
of Poisson, beta instead of gamma distributions
to develop screening methods for AEs in clinical
trials
27DISCUSSION
28Discussion
- Bayesian approaches may be useful for detecting
possible emerging signals, especially with few
events - MCA (UK) currently uses PRR for monitoring
emergence of drug-event associations - Signal detection combines numerical data
screening, statistical interpretation, and
clinical judgement - Most apparent associations represent known
problems - 25 may represent signals about previously
unknown associations - The actual false positive rate is unknown
29What Next?
- PhRMA/FDA working group has published a white
paper addressing many of these issues - Drug Safety (2005) 28 981-1007
- Further refine methods, look for associations
among combinations of drugs and events, timing of
reports - Data mining is like screening, need to evaluate
diagnostic properties of various approaches - Need good dictionaries many synonyms ? difficult
signal detection - Event names MedDRA may help
- Drug names Need a common dictionary of drug
names to minimize dilution effect of synonyms
30Data Used to Construct Plot
Intussception Intussception Intussception - Intussception -
Observed Expected Observed Expected
RV DTAP 85 74 1111 1122
DTAP - 29 40 608 597
RV - DTAP 4 15 33520 33509
DTAP - 293 282 610714 610725