Control Charts in Medicine

[David Kerridge <dfkerridge@mac.com>]

DEN readers may be interested to know that members of
the (former BDA) Statistics Research Group have managed
to interest a leading medical journal in the use of control
charts - or one use, at least.

Currently there is a government-imposed system of "league
tables" for hospitals in the UK. This has caused a great deal
of distress, because most of the variation is common cause
variation, but the effects on morale for those at the "bottom
of the leaugue" are really serious. You can imagine how the
newspapers and politicians react: "If one hospital can get
good results, why can't all the others?"

At the same time, there are a few genuine special causes,
like a certain Dr Shipman, who has been convicted of
murdering large numbers of patients. Thus a genuine way
to compare success rates is badly needed.

The paper is:

Mohammed MA, Cheng KK, Rouse A, Marshall T.
"Bristol, Shipman and clinical governance: Shewhart's forgotten lessons."
Lancet 2001;357:463-67. (to be published on the internet 9th of Feb
http://www.thelancet.com/ and on the 10th in paper form)


-- 
Best wishes

David

dfkerridge@mac.com