I am working on a small grant that will review best practices in risk
adjustment in a sample of research papers. This is a pilot study, but
one of the long range goals is to see how rapidly new innovations in
research methodology (e.g., the use of propensity scores) make there way
from the statistical theory journal into application in medical
journals. If you're curious, you can read an early version of this grant at
--> http://www.pmean.com/11/PilotGrant.html
One of the suggestions I have received is to develop a timeline of major
developments in this area. I listed a few things that I could think of
easily and find through Google, PubMed, and Wikipedia. Are there any
other major events or milestones that I am missing?
Also, are there any errors in my list? For example, is there an earlier
example of the use of instrumental variables in medicine?
Thanks in advance for any help you can provide.
TIMELINE
1948: First randomized trial in medicine is published (Streptomycin in
Tuberculosis Trials Committee (1948). "Streptomycin treatment of
pulmonary tuberculosis. A Medical Research Council investigation". Br
Med J 2 (4582): 769–82. doi:10.1136/bmj.2.4582.769. PMC 2091872. PMID
18890300.)
1948: Framingham Heart Study initiated.
1950: Four major case control studies of lung cancer and smoking
published (Levin et al 1950; Wynder & Graham 1950; Schrek et al. 1950;
Doll & Hill 1950)
1954: Major prospective cohort study of study of smoking published (Doll
R, Hill AB. (1954). "The mortality of doctors in relation to their
smoking habits". BMJ 328 (7455): 1529. doi:10.1136/bmj.328.7455.1529.
PMC 437141. PMID 15217868.)
1962: First description of multivariate logistic regression for
examining and adjusting for multiple risk factors (Cornfield J (1962).
Joint dependence of risk of coronary heart disease on serum cholesterol
and systolic blook pressure: a discriminant function analysis.
Federation Proceedings 21, 58-61.).
1962: First statistical package (BIMED, later called BMDP) is released
for IBM mainframe computers. Other statistical packages for mainframes
(SAS, SPSS) rapidly follow.
1972: First description of Cox Proportional Hazards model, which allows
for risk adjustment in time to event models (Cox 1972).
1977: Apple II microcomputer released. A flood of statistical software
programs for this and other microcomputers rapidly follows.
1980: First version of Diagnosis-Related Groups (DRGs) used, which
allows for case mix adjustments to control for risk.
1983: First description of propensity scores (Rosenbaum, P. R., and
Rubin, D. B., (1983), "The Central Role of the Propensity Score in
Observational Studies for Causal Effects," Biometrika 70, 41–55.)
1993: First application of instrumental variables in medicine is
published (Stat Med. 1993 Jun 15;12(11):1005-18. Reducing attrition bias
with an instrumental variable in a regression model: results from a
panel of rheumatoid arthritis patients. Leigh JP, Ward MM, Fries JF.)
1997: First version of R software released. This is the first widely
used open source statistical software package.
--
Steve Simon, [log in to unmask], Standard Disclaimer.
Sign up for the Monthly Mean, the newsletter that
dares to call itself average at www.pmean.com/news
|