Transparency in the Use of Propensity Score Methods

1
Transparency in the Use of Propensity Score
Methods

• John D. Seeger, PharmD, DrPH
• Chief Scientist, i3 Drug Safety
• Adjunct Assistant Professor, Harvard School of
  Public Health
• September 9, 2008

With thanks to Alec Walker, Tobias Kurth, Jeanne
Loughlin, Mona Eng, and Alex Cole
2
Propensity Score Analysis When?
Thanks to S. Schneeweiss
3
Motivation

• Assume matching when comparing 2 treatments
• For every drug user with given characteristics
• Find a comparator with identical characteristics
• Example Male, age 45, smoker, with HTN

• Matching fails
• Age (10 categories) x
• Sex (2 categories) x
• Prior diagnoses (5 _at_ 2 categories each)
• Prior drug therapy (5 _at_ 2 categories each)
• Preceding cost of care (5 categories)
• ?102,400 potential matching groups

4
Propensity Score Collapses Exposure Predictors

• Single value
• Probability subject will receive therapy vs
  comparator
• Removes confounding by components of the score
• Patient characteristics that favor one therapy
  over another
• Permits
• Restriction
• Matching
• Stratification
• Modeling
• Weighting

5
Should Propensity Scores Always be Used?

• More than 8 events per covariate leads to
  unbiased estimates
• So propensity score favored when
• Many more persons exposed to drug of interest
  than study outcomes
• Common exposure
• Rare outcome
• Allows for richer model (more predictors) of
  exposure than outcome
• Alternative hypotheses

Cepeda S, et al. Am J Epidemiol 2003158280-287.

6
Estimate Propensity Score

• Predict treatment from baseline covariates within
  database
• Inclusion of predictors
• a-priori (what characteristics are used to
  prescribe?)
• Empiric (what differentiates initiators?)
• Generic (what patterns of healthcare predict
  initiation?)
• Coefficients of propensity score
• Interpretable and Informative

7
Propensity Score Restriction
Sturmer T, et al. J Clin Epidemiol 200659437-47.
8
Propensity Score Restriction

• Potential for serious adverse events from error
  (name confusion)
• Amaryl (glimepiride an oral hypoglycemic)
• Reminyl (galantamine for Alzheimers disease)
• 36,816 people with AD diagnosis (14,626 Reminyl
  dispensings)
• 236 Amaryl recipients
• 24 Amaryl recipients in the lowest decile of the
  propensity score
• 13 with a single dispensing of Amaryl or no
  diabetes diagnoses
• 2 with no diabetes-related claims across entire
  claim history
• Medical record review suggested no error
• Propensity score restriction may be used as a
  screening method to identify unusual patterns of
  healthcare for closer scrutiny
• Possible medication dispensing errors
• Others
• Confirmation requires additional data, which
  could be obtained through medical record review.

9
Propensity Score Distribution and Strata
C-statistic 0.739
10
Effect of Temazepam Relative to Zopiclone
Transparent analysis Within-stratum
balance Stratum-specific effect estimates as
well as pooled estimate Explicit evaluation of
potential for effect measure modification
11
Matching on the Propensity Score

• Matching can be performed by
• Standard automated case-control matching programs
  where the matching range is specified
• Nearest available match based on the propensity
  score
• Greedy matching techniques(http//www2.sas.com.pr
  oceedings/sugi26/p214-26.pdf)

12
(No Transcript)
13
(No Transcript)
14
Characteristics Before Matching
15
Balance Achieved by Matching
16
Analysis by 2X2 Table
17
MI Outcome (After Matching)
31 (7-48) Risk Reduction
HR0.69 (0.52-0.93)
Cumulative Incidence
Statin Non-Initiators
Statin Initiators
Months of Follow-Up
18
Regression Adjustment with Propensity Scores

• Regression adjustment
• All study participants are used
• Still a two-step approach (exposure and outcome)
• More power compared to including all covariates
  into the model, since degrees of freedom are
  gained
• However, assumes the underlying association
  between the score and the outcome is modeled
  appropriately

19
Weighting
1 in treated (ê(X)/(1-ê(X)) in untreated
1/ê(X), in treated 1/(1- ê(X)), in untreated
IPTW
SMR
20
Baseline Characteristics
21
Cohort Results
22
Are Divergent Results Possible?
Kurth T, et al. Am J Epidemiol 2006163262-70.
23
What About Unmeasured Confounding?

• Obesity, Smoking, Exercise

24
Accounting for Variables had Little Effect
25
Conclusion

• Propensity score can be useful for addressing
  confounding (by indication)
• Allows for rich model of exposure to be developed
• Advantageous when number of people with a study
  outcome is small relative to number of exposed
  persons and number of potential confounders is
  large
• Drug effects (particularly adverse ones)
• Consider transparency
• When selecting propensity score
• When building propensity score
• When using propensity score

26

• Thank-You

John.Seeger_at_i3DrugSafety.com