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

Automated Identification of Surgical Site Infections From Electronic Medical Records: Retrospective Observational

Arjun Chakraborty¹, Peter Tarczy-Hornoch^1,2,3, Dustin Long⁴

¹Department of Biomedical Informatics and Medical Education, School of Medicine, University of Washington, 222 15th Street SW, Rochester, MN, 55902, United States, 1 5107095904.

JMIR Perioperative Medicine

|June 26, 2026

Summary

Related Concept Videos

Healthcare Associated Infections II: Preventive Measures

Healthcare Associated Infections II: Preventive Measures

Essential infection prevention measures are based on the knowledge of the infection chain, the modes of transmission in healthcare settings, and the use of the best practices in all healthcare settings. Compulsory public reporting of healthcare-associated infection rates is needed to allow individuals and the community to make informed choices regarding selecting a healthcare facility.
The best practices for preventing healthcare-associated infections include hand hygiene, patient risk...

You might also read

Related Articles

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

Sort by

Same author

A New Era of Data-Driven Cancer Research and Care: Opportunities and Challenges.

Cancer discovery·2024

Same author

Contribution of the patient microbiome to surgical site infection and antibiotic prophylaxis failure in spine surgery.

Science translational medicine·2024

Same author

Cell-Free DNA Detects <i>Pseudomonas aeruginosa</i> Lung Infection in Modulator-treated People with Cystic Fibrosis.

American journal of respiratory and critical care medicine·2023

Same author

Dynamics of Cutibacterium repopulation onto the skin surface of the shoulder after chlorhexidine application.

International orthopaedics·2023

Same author

Updates in Prevention of Surgical Site Infection: Reply.

Anesthesiology·2023

Same author

Emerging Paradigms in the Prevention of Surgical Site Infection: The Patient Microbiome and Antimicrobial Resistance.

Anesthesiology·2022

Automated surveillance using deep learning and electronic health records significantly improves surgical site infection (SSI) prediction. This approach enhances efficiency and data availability for reducing SSI rates.

Area of Science:

Medical informatics
Artificial intelligence in healthcare
Infectious disease surveillance

Background:

Surgical site infections (SSIs) impact hundreds of thousands of patients annually, leading to increased mortality, complications, and substantial healthcare costs.
Traditional manual chart reviews for SSI surveillance are resource-intensive and costly.
Effective surveillance is crucial for developing strategies to mitigate SSI outcomes.

Purpose of the Study:

To evaluate an automated SSI surveillance system utilizing natural language processing and deep learning.
To determine if this automated approach can outperform previous methods in accuracy and efficiency.
To assess the potential for enabling more efficient infection surveillance.

Main Methods:

Utilized a dataset of approximately 30,000 surgical cases from two medical centers, including structured EHR data and clinical text notes.

Keywords:

deep learning diagnosis electronic health record epidemiology large language models machine learning natural language processing neural networks computer surgical wound infection

Related Experiment Videos

Applied various machine learning approaches, including deep learning and natural language processing, for SSI prediction.

Incorporated multimodal data, such as clinical text and temporal laboratory values, to enhance prediction performance.

Main Results:

Multimodal EHR data, including clinical text and temporal information, significantly improved SSI prediction compared to structured data alone (F1=0.68 vs. F1=0.55).
Deep learning models, particularly those leveraging large language models, outperformed traditional rule-based systems (F1=0.70 vs. F1=0.43).
The optimal system achieved a precision of 0.38 at 0.9 recall, demonstrating effective SSI surveillance capabilities.

Conclusions:

Automated surveillance systems, especially those employing deep learning, combined with multimodal EHR data, enhance infection surveillance efficiency.
This advanced approach can increase the volume of SSI surveillance data available for guiding interventions.
The findings highlight the potential for data-driven strategies to reduce SSI rates effectively.