Title: EPI235: Epi Methods in HSR
1EPI235 Epi Methods in HSR
May 3, 2007 L10 Outcomes and Effectiveness
Research 4 HMO/Network (Dr. Schneeweiss) Methodo
logic issues in benchmarking physician and
hospital performance. Analysis of patient data
clustered in physicians and in clinics using
hierarchical (multi-level) models. Reporting
benchmarking results. Background reading
Austin PC, Goel V, van Walraven C. An
introduction to multilevel regression models. Can
J Public Health 200192150-154. Austin PC, Tu
JV, Alter DA Comparing hierarchical modeling
with traditional logistic regression analysis
among patients hospitalized with acute myocardial
infarction Should we be analyzing cardiovascular
outcomes data differently? Am Heart J
200314527-35. Carey K A multilevel modeling
approach to analysis of patient costs under
managed care. Health Econ 20009435-446 .
2(No Transcript)
3(No Transcript)
4Pennsylvania Consumer Report
www.phc4.org
5(No Transcript)
6(No Transcript)
7(No Transcript)
8(No Transcript)
9(No Transcript)
10(No Transcript)
11Quality improvement by quality measurement in NY
Hannan ED et al. JAMA 1995
12Risk factor reporting in the NY Bypass Reporting
System ()
13(No Transcript)
14(No Transcript)
15(No Transcript)
16(No Transcript)
17CABG Mortality among 55 hospitals
MLwiN
18(No Transcript)
19(No Transcript)
20(No Transcript)
21(No Transcript)
22(No Transcript)
23(No Transcript)
24(No Transcript)
25(No Transcript)
26What is the best comparator for benchmarking? 1)
Average of all institutions 2) Stratified by
institution characteristics
Austin et al. Am Heart J 2004
27(No Transcript)
28Dealing with clustering
- Generalized estimating equations (GEE)
- SAS proc genmod
- Random effects modeling (multi-level modeling)
29Effect of physician specialty on patient outcomes
Attending cardiology specialty
Austin et al. Am Heart J 2003
30Teaching hospital
31GEE vs. random effects model
Expl. Risk factors of increased cholesterol
levels
Twisk, Eur J Epi, 2004
32(No Transcript)
33GEE
Rand. intercept
34Final Note Parameter Interpretation
- Marginal parameters are often thought to be more
appropriate for policy questions, What is the
difference in the rate of illness in the treated
population versus the untreated? - Conditional parameter estimates closer to
individual effects, What is the effect of
treatment in an individual person? - Conditional parameter are more clinically
relevant?