0
Special Article |

In Search of Fewer Independent Risk Factors

Daniel J. Brotman, MD; Esteban Walker, PhD; Michael S. Lauer, MD; Ralph G. O’Brien, PhD
Arch Intern Med. 2005;165(2):138-145. doi:10.1001/archinte.165.2.138.
Text Size: A A A
Published online

More than 1100 articles now appear annually investigating “independent risk factors” or “independent predictors” for various clinical outcomes. In medical research, independence is generally defined in a statistical sense: a variable is called an independent risk factor if it has a significant contribution to an outcome in a statistical model that includes established risk factors. As such, independence is based on a specific statistical model and depends on the set of established risk factors included in that model. Even when strong statistical evidence indicates that a variable is an independent risk factor for an outcome, this does not necessarily indicate that the risk factor causally contributes to the outcome. The opposite is also true: risk factors that have causal relationships with the outcome will not necessarily prove to be independent risk factors. These are basic statistical principles that are too often given short shrift in medical research. Herein, we discuss the clinical implications conferred by the above definition of independence, primarily using examples from recent cardiovascular literature. A glossary and schema are provided to help clinicians and researchers understand and discuss these matters effectively.

Figures in this Article

Sign In to Access Full Content

Don't have Access?

Register and get free email Table of Contents alerts, saved searches, PowerPoint downloads, CME quizzes, and more

Subscribe for full-text access to content from 1998 forward and a host of useful features

Activate your current subscription (AMA members and current subscribers)

Purchase Online Access to this article for 24 hours

Figures

Place holder to copy figure label and caption
Figure 1.

Increase in the number of articles per year that contain the terms independent risk factor or independent predictor in their title or abstract.

Grahic Jump Location
Place holder to copy figure label and caption
Figure 2.

Arrows denote causation in this idealized example to illustrate the distinctions between 3 types of risk factors. Bidirectional arrows, which may exist in real life, are not included, and this example does not include all possible relationships. In medical research, it may be impossible to discern whether a particular risk factor is a direct causal risk factor, a noncausal risk factor, or an indirect causal risk factor or if it falls into more than 1 category.

Grahic Jump Location
Place holder to copy figure label and caption
Figure 3.

Hypothetical model with 2 uncorrelated direct causal factors, 3 noncausal risk factors, and an outcome. All variables are binary. Odds ratios (ORs) define relationships between the variables. Percentages define prevalence rates for the risk factors and the incidence rate for the outcome. For simplicity, bidirectional arrows and interaction terms are not included in this idealized example. Table 3 lists power probabilities for various statistical models applied to this scenario.

Grahic Jump Location
Place holder to copy figure label and caption
Figure 4.

Hypothetical model in which a therapy affects a noncausal risk factor and a causal factor. When multiple clinical variables are favorably affected by an efficacious therapy, it may be impossible to discern which of these variables are causal for the outcome.

Grahic Jump Location

Tables

Interactive Graphics

Video

Country-Specific Mortality and Growth Failure in Infancy and Yound Children and Association With Material Stature

Use interactive graphics and maps to view and sort country-specific infant and early dhildhood mortality and growth failure data and their association with maternal

References

Correspondence

CME
Accreditation Information
The American Medical Association is accredited by the Accreditation Council for Continuing Medical Education to provide continuing medical education for physicians. The AMA designates this journal-based CME activity for a maximum of 1 AMA PRA Category 1 CreditTM per course. Physicians should claim only the credit commensurate with the extent of their participation in the activity. Physicians who complete the CME course and score at least 80% correct on the quiz are eligible for AMA PRA Category 1 CreditTM.
Note: You must get at least of the answers correct to pass this quiz.
You have not filled in all the answers to complete this quiz
The following questions were not answered:
Sorry, you have unsuccessfully completed this CME quiz with a score of
The following questions were not answered correctly:
Commitment to Change (optional):
Indicate what change(s) you will implement in your practice, if any, based on this CME course.
Your quiz results:
The filled radio buttons indicate your responses. The preferred responses are highlighted
For CME Course: A Proposed Model for Initial Assessment and Management of Acute Heart Failure Syndromes
Indicate what changes(s) you will implement in your practice, if any, based on this CME course.
NOTE:
Citing articles are presented as examples only. In non-demo SCM6 implementation, integration with CrossRef’s “Cited By” API will populate this tab (http://www.crossref.org/citedby.html).
Submit a Comment

Some tools below are only available to our subscribers or users with an online account.

Web of Science® Times Cited: 47

Sign In to Access Full Content

Related Content

Customize your page view by dragging & repositioning the boxes below.

Articles Related By Topic
Related Topics
PubMed Articles
Jobs
JAMAevidence.com

Users' Guides to the Medical Literature
Clinical Scenario

Users' Guides to the Medical Literature
In contrast, the authors of the Clopidogrel Versus Aspirin in Patients at Risk of Ischaemic...