Uncertainty in Clinical Prediction Rules: The Value of Credible Intervals

Haskins, Robin; Osmotherly, Peter G.; Tuyl, Frank; Rivett, Darren A.

doi:10.2519/jospt.2014.4877

Cited by 10 publications

(3 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Second, many studies reported incomplete statistical analyses. CPR accuracy, post-test probabilities and associated uncertainty intervals would enable improved interpretation of a CPR's predictive ability 68,69 . Descriptions of missing values and the use of imputation methods, where applicable should also be included 67 .…”

Section: Discussionmentioning

confidence: 99%

Clinical prediction rules for prognosis and treatment prescription in neck pain: A systematic review

Kelly

Ritchie

Sterling

2017

Musculoskeletal Science and Practice

View full text Add to dashboard Cite

Clinical prediction rules (CPRs) developed to identify sub-groups of people with neck pain for different prognoses (i.e. prognostic) or response to treatments (i.e. prescriptive) have been recommended as a research priority to improve health outcomes for these conditions. A systematic review was undertaken to identify prognostic and prescriptive CPRs relevant to the conservative management of adults with neck pain and to appraise stage of development, quality and readiness for clinical application. Six databases were systematically searched from inception until 4th July 2016. Two independent reviewers assessed eligibility, risk of bias (PEDro and QUIPS), methodological quality and stage of development. 9840 records were retrieved and screened for eligibility. Thirty-two studies reporting on 26 CPRs were included in this review. Methodological quality of included studies varied considerably. Most prognostic CPR development studies employed appropriate designs. However, many prescriptive CPR studies (n = 12/13) used single group designs and/or analysed controlled trials using methods that were inadequate for identifying treatment effect moderators. Most prognostic (n = 11/15) and all prescriptive (n = 11) CPRs have not progressed beyond the derivation stage of development. Four prognostic CPRs relating to acute whiplash (n = 3) or non-traumatic neck pain (n = 1) have undergone preliminary validation. No CPRs have undergone impact analysis. Most prognostic and prescriptive CPRs for neck pain are at the initial stage of development and therefore routine clinical use is not yet supported. Further validation and impact analyses of all CPRs are required before confident conclusions can be made regarding clinical utility.

show abstract

Section: Discussionmentioning

confidence: 99%

Clinical prediction rules for prognosis and treatment prescription in neck pain: A systematic review

Kelly

Ritchie

Sterling

2017

Musculoskeletal Science and Practice

View full text Add to dashboard Cite

show abstract

“…The Bayesian approach in the evaluation of experimental results has been proposed in the field of medicine 6,10 and has become more common in many fields such as psychology 11,12 and technical disciplines, 13,14 whereas in other areas, such as nursing 15 or physical therapy and rehabilitation, 16 it is less common. For example, when key words such as "Bayes," "Bayesian," or similar are used in searches in the rehabilitation category of the Sciences Citation Index, very few articles are obtained.…”

Section: Methods and Contentsmentioning

confidence: 99%

“…22 An equivalent Bayesian concept is the CI. 16 Instead of considering the unknown parameters as fixed quantities, the Bayesian approach considers them as random variables. In this way, researchers can express their confidence for certain values for a parameter (e.g., the mean pain level, the effect size), by considering it as a random variable with some (prior) distribution.…”

Section: Applications In Rehabilitation Researchmentioning

confidence: 99%

Bayesian Methods in the Field of Rehabilitation

Quintela-del-Rı́o¹,

Rodríguez‐Romero²,

Robles-García³

et al. 2019

Am J Phys Med Rehabil

View full text Add to dashboard Cite

Bayesian techniques, as an alternative method of statistical analysis in rehabilitation studies, have some advantages such as handling small sample sizes, allowing incorporation of previous experience of the researchers or clinicians, being suitable for different kinds of studies, and managing highly complex models. These characteristics are important in rehabilitation research. In the present article, the Bayesian approach is displayed through three examples in previously analyzed data with traditional or frequentist methods. The studies used as examples have small sample sizes and show that the Bayesian procedures enhance the statistical information of the results. The Bayesian credibility interval includes the true value of the corresponding parameter diminishing uncertainty about the treatment effect. In addition, the Bayes factor value quantifies the evidence provided by the data in favor of the alternative hypothesis as opposed to the null hypothesis. Bayesian inference could be an interesting and adaptable alternative statistical method for physical medicine and rehabilitation applications.

show abstract