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

Association for Academic Surgery Presidential Address - Hidden Figures: They Are all Around Us.

The Journal of surgical research·2026
Same author

ASO Author Reflections: Trials and Tribulations of Managing Recurrent Uterine Leiomyosarcoma.

Annals of surgical oncology·2026
Same author

ASO Visual Abstract: Efficacy and Safety of Cytoreductive Surgery with Hyperthermic Intraperitoneal Chemotherapy for Recurrent Uterine Leiomyosarcoma: Results of a Phase 2 Study.

Annals of surgical oncology·2026
Same author

A Pan-Cancer Single-Cell Atlas to Evaluate Tumor Identity, Cell Line Concordance, and Dependency Mapping.

bioRxiv : the preprint server for biology·2026
Same author

Association for Academic Surgery Founder's Lecture - Addressing the Surgical Workforce Crisis: Retention Strategies for a Thriving Future.

The Journal of surgical research·2026
Same author

Efficacy and Safety of Cytoreductive Surgery with Hyperthermic Intraperitoneal Chemotherapy for Recurrent Uterine Leiomyosarcoma: Results of a Phase 2 Study.

Annals of surgical oncology·2026

Related Experiment Video

Updated: Sep 22, 2025

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
07:13

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

204

Development and Validation of an Explainable Machine Learning Model for Major Complications After Cytoreductive

Huiyu Deng1, Zahra Eftekhari1, Cameron Carlin1

  • 1City of Hope National Medical Center, Duarte, California.

JAMA Network Open
|May 25, 2022
PubMed
Summary

Machine learning models can predict major complications after cytoreductive surgery (CRS) better than traditional methods. This approach identified six distinct patient risk groups, improving surgical oncology risk assessment.

More Related Videos

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

8.4K
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

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

Published on: August 16, 2020

6.9K

Related Experiment Videos

Last Updated: Sep 22, 2025

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
07:13

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

204
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

8.4K
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

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

Published on: August 16, 2020

6.9K

Area of Science:

  • Surgical Oncology
  • Artificial Intelligence in Medicine
  • Predictive Analytics

Background:

  • Cytoreductive surgery (CRS) is a complex oncologic operation with significant morbidity.
  • Improved risk prediction tools are essential for optimizing patient outcomes.
  • Traditional logistic regression models have limitations in predicting complex surgical risks.

Purpose of the Study:

  • To develop and validate an explainable machine learning (ML) model for predicting major postoperative complications in patients undergoing CRS.
  • To compare the performance of the ML model against traditional multiple logistic regression (MLR) models.
  • To identify novel surgical risk phenotypes using AI-driven interpretation.

Main Methods:

  • A prognostic study utilizing data from 2372 patients undergoing CRS between 1998 and 2018.
  • An ensemble-based gradient-boosting ML model was developed and validated.
  • The SHAP (Shapley additive explanations) method was employed for model interpretation and risk phenotype identification.

Main Results:

  • The optimized ML model demonstrated superior predictive performance (AUROC: 0.74, AUPRC: 0.42) compared to MLR models (AUROC: 0.54, AUPRC: 0.18).
  • Key predictors for major complications included estimated blood loss, pelvic peritonectomy, and operative time.
  • SHAP analysis revealed complex interactions between predictors and identified 6 distinct surgical risk phenotypes.

Conclusions:

  • An explainable ML model significantly improves the prediction of major complications in CRS patients compared to traditional methods.
  • The identification of distinct surgical risk phenotypes provides a novel framework for personalized risk assessment.
  • This AI-driven approach enhances understanding of complex surgical risks in oncology.