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

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

Risk of Femoral Head Osteonecrosis Following Hip Trauma in Adults With Systemic Lupus Erythematosus.

Journal of clinical rheumatology : practical reports on rheumatic & musculoskeletal diseases·2026

Same author

Rule-Based Algorithm to Identify Recurrent Non-Hodgkin Lymphoma in Electronic Health Data.

JCO clinical cancer informatics·2026

Same author

Experiences and Acceptance of Community-Based Mobile Health Services Among People in Underserved Rural Areas of Korea: Mixed Methods Study.

JMIR formative research·2026

Same author

The HALO Model: A Learning Health System Framework for Artificial Intelligence.

Learning health systems·2026

Same author

A Structured Comparison of the Coalition for Health AI Responsible AI Guide and South Korea's Trustworthy AI Guideline for Health Care AI Assurance: Comparative Framework Analysis.

JMIR AI·2026

Same author

Dermatologic Conditions and Incident Anxiety in Young Adults: Propensity Score-Matched Retrospective Cohort Study.

JMIR dermatology·2026

Search research articles

Related Experiment Video

Updated: Jan 6, 2026

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model

Published on: April 18, 2025

Machine Learning-Enhanced Surveillance for Surgical Site Infections in Patients Undergoing Colon Surgery: Model

Ugur Celik¹, Feifan Liu², Kimiyoshi Kobayashi^2,3,4

¹Center for Clinical and Translational Sciences, University of Massachusetts Chan Medical School, Worcester, MA, United States.

JMIR Formative Research

|October 1, 2025

Summary

This summary is machine-generated.

Machine learning models can improve surgical site infection (SSI) surveillance by identifying high-risk patients after colon surgery. The XGBoost model demonstrated strong performance, aiding infection control efforts.

Keywords:

AI Extreme Gradient Boosting XGBoost artificial intelligence colon surgery electronic health records machine learning natural language processing random forest risk prediction surgical site infection surveillance

More Related Videos

Surgical Robot-Assisted Transanal Specimen Extraction Radical Sigmoidectomy Without an Auxiliary Abdominal Incision

Surgical Robot-Assisted Transanal Specimen Extraction Radical Sigmoidectomy Without an Auxiliary Abdominal Incision

Published on: June 13, 2025

Animal Model of Implant-Associated Infections in Mice

Animal Model of Implant-Associated Infections in Mice

Published on: June 27, 2025

Related Experiment Videos

Last Updated: Jan 6, 2026

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model

Published on: April 18, 2025

Surgical Robot-Assisted Transanal Specimen Extraction Radical Sigmoidectomy Without an Auxiliary Abdominal Incision

Surgical Robot-Assisted Transanal Specimen Extraction Radical Sigmoidectomy Without an Auxiliary Abdominal Incision

Published on: June 13, 2025

Animal Model of Implant-Associated Infections in Mice

Animal Model of Implant-Associated Infections in Mice

Published on: June 27, 2025

Area of Science:

Medical Informatics
Machine Learning in Healthcare
Infection Control

Background:

Surgical site infections (SSIs) are a major healthcare-associated infection, increasing patient morbidity and healthcare costs.
Effective surveillance is crucial for timely intervention and prevention of SSIs.

Purpose of the Study:

To develop and evaluate machine learning (ML) models for enhanced SSI surveillance post-colon surgery.
To prioritize high-risk patients for improved infection control efficiency.

Main Methods:

Retrospective study of 1508 colon surgery patients (2018-2023).
Utilized 78 structured variables and 2 natural language processing-derived features from clinical notes.
Trained logistic regression, random forest, and XGBoost models, addressing class imbalance.

Main Results:

XGBoost model achieved an AUC of 0.788, with key predictors including recovery duration and SSI keyword frequency.
Random forest showed perfect precision (100%) but lower recall (23%).
Natural language processing features ranked among the top 10 predictors, highlighting the value of unstructured data.

Conclusions:

ML models effectively augment traditional SSI surveillance by identifying at-risk patients.
The XGBoost model provides a practical tool for clinical workflows, balancing performance and calibration.
Integrating structured and unstructured EHR data improves model accuracy for efficient infection control.