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

Outcome prediction in trauma.

Omar Bouamra1, Alan Wrotchford, Sally Hollis

  • 1The University of Manchester, The Trauma Audit & Research Network, Clinical Sciences Building, Hope Hospital, Salford M6 8HD, UK. Omar.Bouamra@man.ac.uk

Injury
|November 8, 2006
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

Stroke Associated-Infections after Mechanical Thrombectomy: Analysis of the Stroke-Associated INfection afTer Mechanical Thrombectomy (SAINT-MT) study.

Cerebrovascular diseases extra·2026
Same author

Statistical reviewing for a medical journal: summary of workshop proceedings.

Research integrity and peer review·2026
Same author

PGT-A is associated with a reduced live birth rate in routine practice: evidence from the UK ART register.

Reproductive biomedicine online·2026
Same author

Accuracy of major trauma triage using the MATTS tool: a cohort study.

Emergency medicine journal : EMJ·2026
Same author

Developing a national triage tool for use in NHS regional trauma networks: the MATTS mixed methods study.

Health technology assessment (Winchester, England)·2026
Same author

Feasibility study of a smartphone app to monitor systemic sclerosis-related digital ulcers-a potential new tool for remote clinical monitoring.

Rheumatology advances in practice·2026
Same journal

Impact of osteoporosis on outcomes following ankle open reduction and internal fixation.

Injury·2026
Same journal

Cumulative traumatic life events and increased risk for emergency department and inpatient utilization after physical injury hospitalization.

Injury·2026
Same journal

Advances in the management of chest wall injuries - Influence of new technical options.

Injury·2026
Same journal

Trauma nursing as frontline health diplomacy: A binational ATCN program for Palestinian and Israeli nurses during conflict.

Injury·2026
Same journal

Corrigendum to "Neutralizing the odds: Biomechanical protection by adiposity offsets physiological burden to explain the trauma.'obesity-paradox`" [Injury 57 (2) (2026) 112913].

Injury·2026
Same journal

Agreement between ChatGPT and emergency physicians in laceration management: A prospective study.

Injury·2026
See all related articles

A new trauma outcome prediction model significantly improves upon the TRISS methodology by reducing missing data and enhancing predictive accuracy. This advanced model offers better performance for trauma patient data analysis.

Area of Science:

  • Trauma research
  • Medical statistics
  • Outcome prediction modeling

Background:

  • The Trauma Audit and Research Network (TARN) in Europe has used the TRISS methodology for outcome prediction since 1989.
  • TRISS methodology faces limitations due to significant data loss from missing information.
  • A novel model was developed to address TRISS shortcomings and improve trauma data analysis.

Purpose of the Study:

  • To develop and validate a new trauma outcome prediction model.
  • To improve data completeness and predictive performance compared to the existing TRISS model.
  • To incorporate a wider range of trauma patient subsets into the prediction model.

Main Methods:

  • Utilized a dataset of 100,399 hospital trauma admissions (1996-2001).

Related Experiment Videos

  • Incorporated the Glasgow Coma Score (GCS) to minimize missing data, alongside age, Injury Severity Score (ISS) transformation, gender, and gender-by-age interaction.
  • Tested the model on traditionally excluded patient groups, including children, penetrating injuries, and ventilated/transferred patients.

    • Main Results:

    • The new model demonstrated strong discriminant ability, with Area Under the Receiver Operating Characteristic (AROC) curve values of 0.947 (prediction set) and 0.952 (validation set).
    • TRISS model AROC values were 0.937 (prediction set) and 0.941 (validation set), indicating superior performance of the new model.
    • The new model achieved significantly better predictive performance than TRISS.

    Conclusions:

    • The developed model successfully includes previously excluded trauma patient subsets, reducing data loss.
    • The new model exhibits significantly enhanced predictive performance compared to the TRISS model.
    • This advancement offers improved accuracy in trauma outcome prediction within large networks like TARN.