Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Spline regression in clinical research.

Z D Mulla1

  • 1Department of Obstetrics and Gynecology, Texas Tech University Health Sciences Center, School of Medicine at El Paso, 4800 Alberta Ave, El Paso, Texas 79905, USA. zuber.mulla@ttuhsc.edu

The West Indian Medical Journal
|July 12, 2007
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Hospital Outcomes of Robotic Versus Laparoscopic Hysterectomy: A Texas Statewide Analysis.

Journal of minimally invasive gynecology·2016
Same author

Multiple sclerosis and breast cancer.

Journal of the neurological sciences·2015
Same author

Group B streptococcal colonization and the risk of pre-eclampsia.

Epidemiology and infection·2012
Same author

Anaphylaxis in Spain: where are the bees and other observations.

Clinical and experimental allergy : journal of the British Society for Allergy and Clinical Immunology·2012
Same author

Gastrointestinal symptomatology as a predictor of severe outcomes of invasive group A streptococcal infections.

Epidemiology and infection·2009
Same author

A population-based epidemiologic analysis of deaths from anaphylaxis in Florida.

Allergy·2008

Spline regression offers a more accurate way to analyze the relationship between serum albumin and hospital mortality compared to traditional methods. This statistical technique provides a smoother, more clinically relevant dose-response curve.

Area of Science:

  • Clinical research methodology
  • Biostatistics
  • Epidemiology

Background:

  • Serum albumin levels are associated with patient outcomes.
  • Traditional statistical methods may oversimplify complex dose-response relationships.
  • Spline regression is an under-utilized statistical tool in clinical research.

Purpose of the Study:

  • To illustrate the application and benefits of spline regression in clinical research.
  • To assess the dose-response association between serum albumin and hospital mortality using spline regression.

Main Methods:

  • Utilized data from a cohort of 117 patients hospitalized with invasive group A streptococcal disease.
  • Compared a traditional categorical analysis of serum albumin (SA) with a quadratic spline regression model.

Related Experiment Videos

  • Assessed the association between admission serum albumin levels and unadjusted hospital mortality.

    • Main Results:

    • Categorical analysis showed mortality rates of 40.7% (< 2.5 g/dL), 14.8% (2.5-3.4 g/dL), and 8.3% (≥ 3.5 g/dL).
    • Spline regression generated a smooth curve, providing a more nuanced and clinically plausible representation of the dose-response relationship.
    • The spline model avoids the assumption of uniform risk within arbitrary categories.

    Conclusions:

    • Spline regression provides a more flexible and realistic approach to analyzing continuous risk factors like serum albumin.
    • It overcomes limitations of categorical analysis, such as imposing homogeneity within groups and allowing abrupt risk changes between categories.
    • Clinicians should consider spline regression for a more accurate assessment of dose-response associations in research.