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 Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Global inequities in the adoption of innovative clinical trial designs: a cross-sectional analysis of ClinicalTrials.gov.

BMJ open·2026
Same author

Ill Fate of Rectal Mucinous Adenocarcinoma: A Defect in Immunosurveillance or a Mucin Coating Effect?-The IMMUNOREACT 20 Study.

Cancers·2026
Same author

Integration of 2D and 3D Imaging Descriptors with Large Language Models for Assessing Pediatric Foreign-Body Aspiration Risk.

Children (Basel, Switzerland)·2026
Same author

Extracting structured clinical data from pediatric emergency records using LLMs: A multimodel retrospective study of children with medical complexity.

Digital health·2026
Same author

Enhancing Hospital Nutrition Assessment Through Artificial Intelligence: A Prospective Tray-Level Pilot Study.

Nutrients·2026
Same author

AI-assisted videolaryngoscopy improves intubation success: results from a randomized simulation trial.

Journal of clinical monitoring and computing·2026

Related Experiment Video

Updated: Jul 23, 2025

A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts
07:50

A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts

Published on: September 20, 2018

16.0K

Pediatric Injury Surveillance From Uncoded Emergency Department Admission Records in Italy: Machine Learning-Based

Danila Azzolina1, Silvia Bressan2, Giulia Lorenzoni3

  • 1Department of Environmental and Preventive Sciences, University of Ferrara, Ferrara, Italy.

JMIR Public Health and Surveillance
|July 12, 2023
PubMed
Summary

Machine learning techniques (MLTs) can automatically classify pediatric emergency department diagnoses, improving injury surveillance. This approach enhances the identification of injury cases and reduces manual coding efforts for health professionals.

Keywords:
child and adolescent healthdeathemergencyemergency departmentepidemiological surveillancehospitalizationinjurymachine learningpatient recordpediatric admissionpediatricssurveillancetext miningunintentional injury

More Related Videos

TBase - an Integrated Electronic Health Record and Research Database for Kidney Transplant Recipients
09:00

TBase - an Integrated Electronic Health Record and Research Database for Kidney Transplant Recipients

Published on: April 13, 2021

4.6K
Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

626

Related Experiment Videos

Last Updated: Jul 23, 2025

A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts
07:50

A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts

Published on: September 20, 2018

16.0K
TBase - an Integrated Electronic Health Record and Research Database for Kidney Transplant Recipients
09:00

TBase - an Integrated Electronic Health Record and Research Database for Kidney Transplant Recipients

Published on: April 13, 2021

4.6K
Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

626

Area of Science:

  • Pediatric emergency medicine
  • Public health surveillance
  • Computational epidemiology

Background:

  • Unintentional injury is a leading cause of death in young children.
  • Emergency department (ED) diagnoses are crucial for injury surveillance.
  • ED data often uses free-text, hindering efficient analysis.

Purpose of the Study:

  • Develop an automated tool for classifying pediatric ED diagnoses.
  • Identify injury cases and assess the burden of pediatric injuries in Padua, Italy.
  • Improve the efficiency of epidemiological surveillance for pediatric injuries.

Main Methods:

  • Utilized a dataset of 283,468 pediatric admissions from 2007-2018.
  • Trained machine learning classifiers (SVM, GBM, Random Forest) on ~40,000 manually classified diagnoses.
  • Classified diagnoses into injury vs. non-injury, intentional vs. unintentional injury, and type of unintentional injury.

Main Results:

  • Support Vector Machine (SVM) achieved 94.14% accuracy for injury vs. non-injury classification.
  • Gradient Boosting Method (GBM) showed 92% accuracy for intentional vs. unintentional injury classification.
  • SVM also performed best for unintentional injury subclassification.

Conclusions:

  • Machine learning techniques (MLTs) show promise for automated pediatric ED diagnosis classification.
  • MLTs enhance epidemiological surveillance by improving accuracy and reducing manual workload.
  • The developed system facilitates efficient identification and classification of pediatric injuries.