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

Machine Learning-Based Prediction Model for Infectious Complications in Trauma and Its Association With In-Hospital

Youngmin Kim¹, Jiyeon Oh^2,3, Hyunjee Kim^2,4

¹Department of Trauma Surgery, Gachon University Gil Medical Center, Incheon, South Korea.

World Journal of Surgery

|May 7, 2026

Related Concept Videos

Steps in Outbreak Investigation

Steps in Outbreak Investigation

In the ever-evolving field of public health, statistical analysis serves as a cornerstone for understanding and managing disease outbreaks. By leveraging various statistical tools, health professionals can predict potential outbreaks, analyze ongoing situations, and devise effective responses to mitigate impact. For that to happen, there are a few possible stages of the analysis:

You might also read

Related Articles

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

Sort by

Same author

Prenatal Exposure to Acid-Suppressive Medications and Incident Risk of Inflammatory Bowel Disease in Children.

JAMA network open·2026

Same author

Association between residential greenness and the risk of inflammatory bowel disease in patients with COVID-19: A Korean nationwide cohort study.

Saudi journal of gastroenterology : official journal of the Saudi Gastroenterology Association·2026

Same author

Prenatal Opioid Exposure and Subsequent Risk of Fractures in Children: An Emulated Target Trial Using a Nationwide Birth Cohort.

Indian pediatrics·2026

Same author

Bone marrow immunosuppressive states associate with survival after guadecitabine and atezolizumab therapy in HMA-R/R MDS.

Blood neoplasia·2026

Same author

Author Correction: Global burden of amphetamine, cannabis, cocaine and opioid use in 204 countries, 1990-2023: a Global Burden of Disease Study.

Nature medicine·2026

Same author

Incidence, prevalence, and global burden of attention-deficit/hyperactivity disorder from 1990 to 2021 across 204 countries in individuals under age 20: data, with critical appraisal, from the 2021 Global Burden of Disease study.

Molecular psychiatry·2026

Same journal

Surgical Infrastructure and Workforce Readiness in Rwanda's District and Level 2 Teaching Hospitals: A Nationwide Facility-Based Survey.

World journal of surgery·2026

Same journal

From General Preparedness to Injury-Pattern-Specific Trauma Resource Planning.

World journal of surgery·2026

Same journal

Prevalence and Outcomes of Thrombocytopenia at ICU Admission Among Critically Ill Patients in a Resource-Limited Setting.

World journal of surgery·2026

Same journal

Transition of Care From Pediatric to Adult Services for Patients With Anorectal Malformations: A Qualitative Study.

World journal of surgery·2026

Same journal

Analysis of Intraoperative Complications and Outcomes Associated With Obesity During Elective Laparoscopic Cholecystectomy.

World journal of surgery·2026

Same journal

Methodological Concern Regarding Laparoscopic Versus Open Repair of Recurrent Incisional Hernia.

World journal of surgery·2026

See all related articles

Summary

This summary is machine-generated.

A new machine learning model accurately predicts infectious complications after trauma by integrating prehospital and in-hospital data. Higher predicted infection risk strongly correlates with increased mortality, aiding early intervention strategies.

Area of Science:

Medical Informatics
Machine Learning in Healthcare
Trauma Surgery

Background:

Infectious complications like sepsis are common and serious after trauma.
Existing risk models lack comprehensive data, hindering accurate prediction.
Need for improved models integrating prehospital and in-hospital data.

Purpose of the Study:

Develop and validate an interpretable ensemble machine learning model.
Predict infectious complications following trauma.
Integrate prehospital and in-hospital clinical data for enhanced prediction.

Main Methods:

Utilized Korean Trauma Data Bank (discovery n=227,567; validation n=8,867).
Defined infectious complications as pneumonia, UTI, CRBSI, SSI, osteomyelitis, or severe sepsis.

Keywords:

artificial intelligence infectious complications machine learning trauma

Related Experiment Videos

Ensembled logistic regression, categorical boosting, and extreme gradient boosting models.

Applied Shapley Additive Explanations (SHAP) for predictor importance.

Main Results:

Ensemble model achieved AUC of 0.796 (discovery) and 0.717 (validation).
Key predictors included age, accident type, Glasgow Coma Scale, and sex.
Increased predicted infection risk tertiles showed strong association with mortality (aORs 2.52-6.19).

Conclusions:

Developed an interpretable ensemble ML model for predicting post-traumatic infectious complications.
Model integrates early clinical data (within 24h) for robust prediction.
Predicted risk is proportionally associated with mortality, informing clinical decisions and interventions.