Search research articles

Search research articles

Related Experiment Video

Updated: Apr 21, 2026

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

Predicting Prolonged Hospital Length of Stay in Trauma Patients Using Machine Learning Techniques: A Cross-Sectional

Maasoumeh Maghsoudi¹, Azadeh Bashiri², Vahid Rahmanian³

¹Student Research Committee, Department of Health Information Management, School of Health Management and Information Sciences Shiraz University of Medical Sciences Shiraz Iran.

Health Science Reports

|April 20, 2026

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

Comparing Ovulation Outcomes of Letrozole-Tamoxifen-Estradiolwith and without Vitamin E in Infertile Women with PolycysticOvary Syndrome: A Double-Blind, Randomized Clinical Trial.

International journal of fertility & sterility·2026

Same author

Effectiveness of a developed self-care mobile application for chest trauma patients: an interventional study.

BMC health services research·2026

Same author

Exploring the Requirements for an mHealth App to Prevent and Manage Perinatal Anxiety and Depression.

Health science reports·2025

Same author

Utilization of telerehabilitation in TKR patients: A systematic review.

PloS one·2025

Same author

Knowledge, Attitudes, and Practices toward Cutaneous Leishmaniasis as a Neglected Tropical Disease among the General Population: A Systematic Review and Meta-Analysis.

Journal of epidemiology and global health·2025

Same author

Optimal Timing of Transvaginal Ultrasound to Diagnose Endometrial Polyps in Women with Abnormal Uterine Bleeding.

Journal of obstetrics and gynaecology of India·2025

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

Machine learning models accurately predict trauma patient hospital length of stay (LOS). Random Forest and Extreme Gradient Boosting achieved 93% accuracy, aiding healthcare resource management.

Area of Science:

Medical Informatics
Health Services Research
Machine Learning in Healthcare

Background:

Trauma hospitalizations incur substantial financial costs for healthcare systems, patients, and insurers.
Accurate prediction of hospital length of stay (LOS) is crucial for optimizing resource management and improving patient care.
This study leverages machine learning to address the challenge of predicting trauma patient LOS.

Purpose of the Study:

To develop and evaluate machine learning models for predicting the length of stay (LOS) of trauma patients.
To identify key clinical factors influencing trauma patient LOS.
To enhance healthcare resource allocation and operational efficiency through predictive modeling.

Main Methods:

A retrospective analysis of 795 trauma patients from Jahrom University of Medical Sciences (March 2021 - December 2022).

Keywords:

length of stay machine learning prediction trauma

Related Experiment Videos

Last Updated: Apr 21, 2026

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

Implementation and comparison of seven machine learning algorithms: Support Vector Machine, K-Nearest Neighbors, Random Forest, Adaptive Boosting, Decision Tree, Artificial Neural Network, and Extreme Gradient Boosting.

Model performance evaluation using accuracy, precision, recall, F-measure, and Area Under the ROC Curve (AUC).

Main Results:

Random Forest and Extreme Gradient Boosting models achieved the highest performance with 93% accuracy, precision, and recall.
The Decision Tree algorithm yielded the highest Area Under the ROC Curve (0.74).
Significant predictive features included oxygen saturation, Glasgow Coma Scale, ICU stay duration, Injury Severity Score, Abbreviated Injury Scale, and comorbidities.

Conclusions:

Machine learning models, particularly Decision Tree, Extreme Gradient Boosting, and Random Forest, demonstrate strong predictive capabilities for trauma patient LOS.
These predictive models can significantly aid in resource allocation, healthcare policy development, and strategic planning.
Improved prediction accuracy facilitates enhanced hospital efficiency and patient care outcomes.