Question on a study of back pain and heart disease

Extract from Statistical Questions in Evidence-based Medicine by Martin Bland and Janet Peacock.

We hope that the topic will be useful in own right, as well as giving a flavour of the book.

Question

A cohort study investigated the association between back pain and ischaemic heart disease. 8,816 Finnish farmers aged 30-66 were followed up for 13 years and cardiac events were noted. The following results were presented:

Age specific mortality (per 1000 people and 13 years) of men according to history of back pain
Age 30-49 years at start Back pain No back pain

Cause of death (n=1274) (n=586) P value
Ischaemic heart disease 18.1 3.4 0.02
Stroke 0.8 0.0 0.68
Other cardiovascular disease 3.9 5.1 0.49
All Causes 56.5 44.4 0.32
Age 50-66 years at start Back pain No back pain

Cause of death (n=1212) (n=576) P value
Ischaemic heart disease 54.5 72.5 0.15
Stroke 7.4 8.1 0.99
Other cardiovascular disease 22.3 26.2 0.74
All Causes 169.6 203.6 0.10

Age specific mortality (per 1000 people and 13 years) of men according to history of back pain
Age 30-49 years at start	Back pain	No back pain
Cause of death	(n=1274)	(n=586)	P value
Ischaemic heart disease	18.1	3.4	0.02
Stroke	0.8	0.0	0.68
Other cardiovascular disease	3.9	5.1	0.49
All Causes	56.5	44.4	0.32
Age 50-66 years at start	Back pain	No back pain
Cause of death	(n=1212)	(n=576)	P value
Ischaemic heart disease	54.5	72.5	0.15
Stroke	7.4	8.1	0.99
Other cardiovascular disease	22.3	26.2	0.74
All Causes	169.6	203.6	0.10

In women no association between back pain and any vascular disease was found. The author concluded that back pain may be an early manifestation of atheroschlerosis, which leads to ischaemic heart disease (Penttinen 1994).

1. Which subjects are missing from the table?
Check answer 1

2. How many tests of significance do you think the author did?
Check answer 2

3. How many significant relationships would you expect to find by chance in that number of tests if all the null hypotheses were true?
Check answer 3

! 4. What would you conclude from the significant difference in younger men?
Check answer 4

+ 5. How could we use these P values so as to test the null hypothesis that back pain is unrelated to mortality?
Check answer 5

Reference: Penttinen, J. (1994) Back pain and risk of fatal ischaemic heart disease: 13 year follow up of Finnish farmers. British Medical Journal 309 1267-8.
You can read the full paper on the BMJ website. Use the browser's back button to get back to this page.

Back to Statistical Questions in Evidence-based Medicine contents.

Back to Martin Bland's home page.

This page maintained by Martin Bland.
Last updated: 30 June, 2005.