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 Video

Updated: Jan 12, 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

Development, Validation, and Comparison of Machine Learning Models for Predicting Pediatric Surgical Site Infections

Carrie T Chan^1,2, Mark J Pletcher¹, Karthik Balakrishnan³

¹From the Department of Epidemiology and Biostatistics, University of California, San Francisco, San Francisco, CA (Chan, Pletcher, Hswen, Scheffler).

Journal of the American College of Surgeons

|November 3, 2025

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

Leveraging Self-Reporting in an Existing e-Cohort to Identify Clinically Relevant Mitral Valve Prolapse: Pilot Questionnaire Study.

JMIR formative research·2026

Same author

Neonatal Brain Network Integration Trajectories Predict Neurodevelopment in Congenital Heart Disease.

medRxiv : the preprint server for health sciences·2026

Same author

Hepatology e-consult responses generated by artificial intelligence demonstrate accuracy but require human oversight.

Hepatology communications·2026

Same author

Factors Associated With Evidence of Self-Measured Blood Pressure Adoption in an Urban Safety-Net Health System.

Journal of clinical hypertension (Greenwich, Conn.)·2026

Same author

Higher Medical Urgency Is Associated With Greater Psychosocial Risk Tolerance in Liver Transplant Listing and Selection.

Transplantation·2026

Same author

Correction: Estimating the Hawthorne Effect in Real-World Blood Pressure Control Trials: An Analysis of the BP Home Trial.

Journal of general internal medicine·2026

Same journal

Breaking the Polytrauma-Brain Barrier: Using Point-of-Care Biomarkers in Severely Injured Trauma Patients.

Journal of the American College of Surgeons·2026

Same journal

Going the Extra Mile: Picking the Right Trauma Center Destination for Critically Injured Patients in a Mature State-Wide Trauma System.

Journal of the American College of Surgeons·2026

Same journal

What Does It Mean for Surgeons to Be Flourishing?

Journal of the American College of Surgeons·2026

Same journal

Tailor-Made Solution to Trimming Venous Thromboembolism Risk.

Journal of the American College of Surgeons·2026

Same journal

NIH Funding in Surgical Artificial Intelligence: Who, What, Where, Why.

Journal of the American College of Surgeons·2026

Same journal

Eﬃcacy and Safety of Rezūm Water Vapor Thermal Ablation in Large and Small Prostates: A Multicenter Comparative Analysis of 2,725 Patients.

Journal of the American College of Surgeons·2026

See all related articles

This summary is machine-generated.

Machine learning models can predict surgical site infections (SSIs) in children. A regularized logistic regression model shows promise for clinical integration to personalize SSI risk and prevention strategies.

Area of Science:

Pediatric Surgery
Infectious Disease Epidemiology
Health Informatics

Background:

Surgical site infections (SSIs) significantly increase pediatric postoperative morbidity.
Rising SSI rates contrast with their largely preventable nature.
Existing SSI prediction models are primarily designed for adult populations, necessitating pediatric-specific tools.

Purpose of the Study:

To develop, validate, and compare machine learning (ML) models for predicting pediatric SSI risk.
To identify a suitable ML model for seamless integration into clinical workflows.
To enhance individualized risk assessment and targeted infection prevention strategies for pediatric patients.

Main Methods:

Retrospective cohort analysis of over 1.1 million pediatric cases from the NSQIP-P database (2012-2022).

More Related Videos

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

Related Experiment Videos

Last Updated: Jan 12, 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 Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

Development and comparison of five ML models: logistic regression, random forest, gradient boosted trees, k-nearest neighbors, and neural networks.

Performance evaluation using Brier scores, c-statistics, and calibration metrics, with bootstrap resampling for confidence intervals.

Main Results:

All developed ML models demonstrated comparable performance in predicting pediatric SSIs.
Regularized logistic regression exhibited strong predictive accuracy (c-statistic 0.77, Brier score 0.023) and was selected for its clinical feasibility.
Key predictors of SSI risk included procedural codes, diagnoses, comorbidities, acuity markers, laboratory values, and patient demographics.

Conclusions:

Machine learning models effectively predict pediatric SSI risk utilizing preoperative data.
The proposed regularized logistic regression model is a strong candidate for EHR integration, enabling personalized SSI risk estimation.
Future work includes external validation and user-centered implementation studies to facilitate clinical adoption.