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

Informed prognosis [corrected] after abdominal aortic aneurysm repair using predictive modeling techniques

Vassilis Georgiou Hadjianastassiou1, Leonardo Franco, Jose M Jerez

  • 1Nuffield Department of Surgery, John Radcliffe Hospital, Oxford, United Kingdom. vassilis@doctors.org.uk

Journal of Vascular Surgery
|March 8, 2006
PubMed
Summary

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

Imaging of the Placenta and Umbilical Cord: What Radiologists in Common Practice Need to Know.

Radiographics : a review publication of the Radiological Society of North America, Inc·2026
Same author

3D-Printed Portable Video-Ooculography Device (UNySi cam): A New Tool for Eye Movement Assessment.

Otology & neurotology : official publication of the American Otological Society, American Neurotology Society [and] European Academy of Otology and Neurotology·2026
Same author

ICD-10 Neoplasm Location Using Text Classification Models in Spanish Electronic Health Records.

IEEE journal of biomedical and health informatics·2025
Same author

Named entity recognition for de-identifying Spanish electronic health records.

Computers in biology and medicine·2024
Same author

Editorial: AI and multi-omics for rare diseases: challenges, advances and perspectives, Volume III.

Frontiers in molecular biosciences·2024
Same author

Patient-reported outcome measures and surgery for Crohn's disease: systematic review.

BJS open·2023

Statistical models accurately predict postoperative mortality in abdominal aortic aneurysm (AAA) surgery patients, outperforming artificial neural networks (ANN) and clinician estimates for improved patient prognosis.

Area of Science:

  • Cardiovascular Surgery
  • Medical Informatics
  • Surgical Outcomes Research

Background:

  • Predicting postoperative mortality in abdominal aortic aneurysm (AAA) surgery is crucial for patient management.
  • Existing methods include clinician judgment, statistical models, and artificial neural networks (ANN).

Purpose of the Study:

  • To compare the accuracy of statistical modeling, ANN, and clinician estimates in predicting in-hospital mortality for AAA surgery patients.
  • To identify the optimal method for individual patient risk stratification.

Main Methods:

  • An observational multicenter study utilized prospectively collected data from 24 ICUs in the UK over 9 years.
  • Multiple regression and ANN models were developed using physiologic variables (age, APACHE II score, emergency operation, chronic health evaluation).

Related Experiment Videos

  • Model validity was tested against observed outcomes and clinician predictions using calibration, discrimination, and subgroup analysis.

    • Main Results:

    • In-hospital mortality was 9.3% for elective and 46.7% for emergency AAA surgery.
    • Both statistical and ANN models were more accurate than clinician predictions.
    • The statistical model demonstrated internal validity on the validation set, showing superior calibration and discrimination.

    Conclusions:

    • Multiple regression statistical modeling provides more accurate prediction of in-hospital mortality in AAA patients compared to ANN or clinician estimates.
    • This validated statistical model can serve as an objective tool to aid clinicians in providing informed prognoses.