Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
Editorial
. 2010 Jul 6;153(1):51-2.
doi: 10.7326/0003-4819-153-1-201007060-00012.

Aggregating and disaggregating patients in clinical trials and their subgroup analyses

David M Kent, Peter K Lindenauer
Editorial

Aggregating and disaggregating patients in clinical trials and their subgroup analyses

David M Kent et al. Ann Intern Med. .
No abstract available

PubMed Disclaimer

Figures

Figure 1
Figure 1
The risk distribution illustrated in the figure is generated from the simple assumptions described, and averages 3.4% for the population overall (i.e. based on the arithmetic mean across the subgroups). As illustrated, any subgroup (i.e. those with risk factor X or risk factor y or risk factor z comprised of patients with any one risk factor will have an outcome-risk of 4.5%--suggesting a benefit for 7 out of 8 patients. This is true even though within any of these “high risk” subgroups, ¾ of patients have risks lower than this average. More paradoxically, the average outcome-risk for patients with any risk factor in aggregate is only 3.7%. A risk-stratified analysis, which makes use of the 3 variables simultaneously, would demonstrate that only the highest risk 1/8 of patients would benefit from therapy.
Figure 1
Figure 1
The risk distribution illustrated in the figure is generated from the simple assumptions described, and averages 3.4% for the population overall (i.e. based on the arithmetic mean across the subgroups). As illustrated, any subgroup (i.e. those with risk factor X or risk factor y or risk factor z comprised of patients with any one risk factor will have an outcome-risk of 4.5%--suggesting a benefit for 7 out of 8 patients. This is true even though within any of these “high risk” subgroups, ¾ of patients have risks lower than this average. More paradoxically, the average outcome-risk for patients with any risk factor in aggregate is only 3.7%. A risk-stratified analysis, which makes use of the 3 variables simultaneously, would demonstrate that only the highest risk 1/8 of patients would benefit from therapy.
See this image and copyright information in PMC

Comment on

References

    1. Hull RD, Schellong SM, Tapson VF, Monreal M, Samama M, Nicol P, et al. Extended-Duration Venous Thromboembolism Prophylaxis in Acutely Ill Medical Patients with Recent Reduced Mobility: A randomized, controlled trial. Annals of Internal Medicine. 2010 In press. - PubMed
    1. Kent DM, Trikalinos TA. Therapeutic innovations, diminishing returns, and control rate preservation. JAMA. 2009;302:2254–56. - PMC - PubMed
    1. Glasziou PP, Irwig LM. An evidence based approach to individualising treatment. BMJ. 1995;311:1356–59. - PMC - PubMed
    1. Kent DM, Hayward RA. Limitations of applying summary results of clinical trials to individual patients: the need for risk stratification. JAMA. 2007;298:1209–12. - PubMed
    1. Sun X, Briel M, Walter SD, Guyatt GH. Is a subgroup effect believable? Updating criteria to evaluate the credibility of subgroup analyses. BMJ. 2010;340:c117. - PubMed

MeSH terms