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 Experiment Video

Updated: Jul 3, 2026

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

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

Published on: October 10, 2018

Development and Implementation of a Machine Learning Model for Prediction of Surgical Case Duration.

Jeffrey H Siewerdsen, Niloufar Mirzavand Boroujeni, Aaron C Milhorn

    Joint Commission Journal on Quality and Patient Safety
    |June 26, 2026
    PubMed
    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

    Clinical Performance of Supraglottic Devices in Patients Undergoing Cancer Surgery: A Retrospective Study.

    Anesthesia and analgesia·2026
    Same author

    Reply to: "Beyond Response Rates: Interpreting Long-Term Benefit in CheckMate 743" and "Beyond Statistical Significance: Methodological Fragility and Censoring Bias in the 5-Year Update of CheckMate 743".

    Journal of clinical oncology : official journal of the American Society of Clinical Oncology·2026
    Same author

    Clinical validation of tissue and liquid companion diagnostics for BRAF V600E detection in non-small cell lung cancers from the PHAROS study.

    Cancer research communications·2026
    Same author

    Use of optiflow THRIVE high-flow nasal oxygen system versus a non-rebreather oxygen delivery device in patients with increased risk of airway obstruction in interventional radiology procedures: a randomized pilot study.

    BMC anesthesiology·2026
    Same author

    Flexible Intubation Scope versus Flexible Intubation Scope and Video Laryngoscopy Combination: A Prospective Randomized Clinical Trial.

    Anesthesia and analgesia·2026
    Same author

    Erratum: Five-Year Clinical Outcomes With Nivolumab Plus Ipilimumab Versus Chemotherapy as First-Line Treatment for Unresectable Pleural Mesothelioma in CheckMate 743.

    Journal of clinical oncology : official journal of the American Society of Clinical Oncology·2026

    Accurate surgical case duration estimation (CDE) using machine learning (ML) significantly improves operating room efficiency. Standardizing workflows and software configuration is crucial for reliable CDE, complementing ML advancements.

    Area of Science:

    • Perioperative Medicine
    • Health Informatics
    • Machine Learning in Healthcare

    Background:

    • Accurate surgical case duration estimation (CDE) is vital for operating room efficiency, resource allocation, and patient safety.
    • Traditional CDE methods often result in significant under- or overestimation, causing workflow disruptions and reduced access to care.
    • This study addresses scheduling variability at a high-volume cancer center by developing an ML-based CDE model and analyzing human factors.

    Purpose of the Study:

    • To develop and evaluate a machine learning (ML)-based model for surgical case duration estimation (CDE).
    • To conduct a human-factor analysis to identify contributors to scheduling variability.
    • To compare the ML model's performance against existing scheduling practices and workflow standardization.

    Main Methods:

    Related Experiment Videos

    Last Updated: Jul 3, 2026

    Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
    04:09

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

    Published on: October 10, 2018

    • A gradient-boosted tree model (ORchestra) was trained on 40,656 surgical cases using patient-, procedure-, and surgeon-specific features.
    • Model performance was evaluated against historical averages, Epic's CDE tool, and scheduled durations using MAE, MSE, f30min, and f10% metrics.
    • Human-factor investigations examined scheduling behavior, case duration definitions, and software parameter choices, followed by a silent-trial deployment.

    Main Results:

    • Baseline scheduling practices showed significant underscheduling bias (MSE = -31 min) and low accuracy (MAE = 35.3 min, f30min = 0.52).
    • Workflow standardization (prep/wrap time, Epic settings) improved performance (MAE = 20.1 min, f30min = 0.81).
    • The ORchestra ML model further reduced error (MAE = 19.8 min), eliminated bias (+1.2 min), and enhanced accuracy, particularly in high-variability services.

    Conclusions:

    • Machine learning-based CDE enhances predictive accuracy and reduces scheduling outliers.
    • Effective CDE relies on a combination of ML, standardized workflows, consistent software configuration, and unified operational definitions.
    • Successful implementation requires technical optimization, organizational alignment, governance, and disciplined practice change for sustainable impact.