Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Videos

Feature mining and predictive model construction from severe trauma patient's data.

J Demsar¹, B Zupan, N Aoki

¹Faculty of Computer and Information Sciences, University of Ljubljana, Tr.aska 25, SI-1000 Ljubljana, Slovenia. janez.demsar@fri.uni-lj.si

International Journal of Medical Informatics

|August 24, 2001

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

Chirality in the Kagome Metal CsV_{3}Sb_{5}.

Physical review letters·2025

Same author

Cost-Effectiveness Analysis for Therapy Sequence in Advanced Cancer: A Microsimulation Approach with Application to Metastatic Prostate Cancer.

Medical decision making : an international journal of the Society for Medical Decision Making·2023

Same author

Direct observation of antiferromagnetic parity violation in the electronic structure of Mn<sub>2</sub>Au.

Journal of physics. Condensed matter : an Institute of Physics journal·2022

Same author

Yield and Cost-effectiveness of Computed Tomography Colonography Versus Colonoscopy for Post Colorectal Cancer Surveillance.

MDM policy & practice·2022

Same author

Reevaluating the Evidence for Intensive Postoperative Extracolonic Surveillance for Nonmetastatic Colorectal Cancer.

Value in health : the journal of the International Society for Pharmacoeconomics and Outcomes Research·2022

Same author

An Evaluation of Regional Cardiovascular Disease and Cancer Research Needs Using Conference Abstracts.

Annals of global health·2021

Same journal

BlockFedMed: A blockchain-federated learning framework for privacy-preserving mortality prediction across heterogeneous intensive care units.

International journal of medical informatics·2026

Same journal

Integrating clinical decision support systems in pediatric oncology: A scoping review of applications, implementation gaps, and management Implications.

International journal of medical informatics·2026

Same journal

Understanding digital health capability of allied health professionals - a mixed-methods study with content validity analysis.

International journal of medical informatics·2026

Same journal

On-premises open-source large language models for privacy-preserving multimodal depression screening.

International journal of medical informatics·2026

Same journal

Data mining methods, tasks, and algorithms for adverse drug reaction analysis in pharmacovigilance: A scoping review.

International journal of medical informatics·2026

Same journal

Development and validation of an interpretable machine learning model for predicting systemic inflammatory response syndrome after percutaneous nephrolithotomy: A multicenter study.

International journal of medical informatics·2026

See all related articles

Predicting severe trauma patient outcomes is crucial for damage control surgery. Machine learning models using key features like ICU pH and PTT can accurately forecast patient prognosis, aiding clinical decisions.

Area of Science:

Medical Informatics
Trauma Surgery
Machine Learning

Background:

Effective management of severe trauma necessitates accurate patient outcome prediction for damage control surgery.
Current decision-making processes can be enhanced by predictive models utilizing retrospective patient data.

Purpose of the Study:

To develop patient outcome prediction models using feature mining and machine learning on data from initial damage control surgery.
To identify the most relevant features for accurate prognostic modeling in severe trauma patients.

Main Methods:

Retrospective analysis of patient data post-initial damage control surgery.
Application of feature mining and machine learning techniques for model construction.
Focus on feature selection to identify critical prognostic indicators.

Related Experiment Videos

Main Results:

A small subset of features is sufficient for constructing reasonably accurate prognostic models.
Identified ICU pH and worst partial active thromboplastin time (PTT) as highly important predictors.
These factors align with known pathophysiological challenges in severe trauma: metabolic acidosis and coagulopathy.

Conclusions:

Machine learning models can effectively predict severe trauma patient outcomes using limited, relevant features.
ICU pH and PTT are critical indicators for prognosis in severe trauma patients.
These findings support the integration of data-driven predictive tools in trauma management.