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

Minimally invasive pancreatectomy with mesentericoportal venous resection: Results from a French national cohort.

HPB : the official journal of the International Hepato Pancreato Biliary Association·2026
Same author

Role of laparoscopy in the management of abdominal trauma.

Journal of visceral surgery·2026
Same author

Enhancing future liver remnant hypertrophy: innovative preoperative strategies and emerging technologies.

Translational gastroenterology and hepatology·2026
Same author

ASO Video Abstract: How to Deal with Median Arcuate Ligament during Pancreaticoduodenectomy? Management Strategies and Impact on Perioperative Outcomes.

Annals of surgical oncology·2026
Same author

FRIES score: predicting conversion in robotic liver surgery.

BJS open·2026
Same author

Predicting Best Performers After Minimally Invasive Left Pancreatectomy: Insights From a National Cohort.

Annals of surgery·2026

Related Experiment Video

Updated: Jul 1, 2026

Application of the En Bloc Concept Combined with Anatomic Resection in Laparoscopic Hepatectomy
04:41

Application of the En Bloc Concept Combined with Anatomic Resection in Laparoscopic Hepatectomy

Published on: March 10, 2023

Deriving Clavien-Dindo Classification from Administrative Data: Development and External Validation in Hepatobiliary

Stylianos Tzedakis1,2, Louis Romengas2,3, Diana Berzan1

  • 1Service de chirurgie digestive, hépatobiliaire et endocrinienne, AP-HP Centre, Groupe Hospitalier Cochin Port Royal, Paris, France.

Annals of Surgery
|May 28, 2026
PubMed
Summary
This summary is machine-generated.

A new algorithm accurately classifies hepatobiliary surgery complications using routine electronic health records, outperforming machine learning models. This tool enables efficient real-time surveillance and health-economic evaluation of postoperative outcomes.

Keywords:
Clavien-Dindo classificationPMSI databaseadministrative dataelectronic health recordshepatobiliary surgeryinternational classification of health interventionsmachine-learningmorbiditymortalitypostoperative complicationsevere complicationsupervised learning

More Related Videos

Laparoscopic Anterior Right Hepatectomy: A Single-Center Experience
09:51

Laparoscopic Anterior Right Hepatectomy: A Single-Center Experience

Published on: December 4, 2023

Intraoperative Strategy under Complex Vascular Adhesion for Laparoscopic Radical Resection of Bismuth-Corlette Type IIIb Perihilar Cholangiocarcinoma
05:22

Intraoperative Strategy under Complex Vascular Adhesion for Laparoscopic Radical Resection of Bismuth-Corlette Type IIIb Perihilar Cholangiocarcinoma

Published on: February 13, 2026

Related Experiment Videos

Last Updated: Jul 1, 2026

Application of the En Bloc Concept Combined with Anatomic Resection in Laparoscopic Hepatectomy
04:41

Application of the En Bloc Concept Combined with Anatomic Resection in Laparoscopic Hepatectomy

Published on: March 10, 2023

Laparoscopic Anterior Right Hepatectomy: A Single-Center Experience
09:51

Laparoscopic Anterior Right Hepatectomy: A Single-Center Experience

Published on: December 4, 2023

Intraoperative Strategy under Complex Vascular Adhesion for Laparoscopic Radical Resection of Bismuth-Corlette Type IIIb Perihilar Cholangiocarcinoma
05:22

Intraoperative Strategy under Complex Vascular Adhesion for Laparoscopic Radical Resection of Bismuth-Corlette Type IIIb Perihilar Cholangiocarcinoma

Published on: February 13, 2026

Area of Science:

  • Hepatobiliary Surgery
  • Health Informatics
  • Medical Algorithm Development

Background:

  • Routine electronic health records (EHR)/administrative data offer potential for efficient, real-time surveillance of postoperative complications.
  • A validated algorithm for classifying hepatobiliary postoperative complications using EHR data is currently lacking.
  • Existing methods lack the efficiency and cost-effectiveness needed for real-time health-economic evaluation.

Purpose of the Study:

  • To develop and externally validate an interpretable, procedure-code-based algorithm for classifying 30-day postoperative complications.
  • To ensure international portability of the developed algorithm.
  • To compare the algorithm's performance against machine learning (ML) approaches.

Main Methods:

  • A retrospective cohort study was conducted in two French hepatobiliary centers (2021-2023).
  • An expert-derived algorithm used 311 procedure codes mapped to International Classification of Health Interventions (ICHI) codes.
  • Machine learning models (RandomForest, ElasticNet, XGBoost) were used as comparators, with performance assessed against gold-standard Clavien-Dindo grades (CDC).

Main Results:

  • The expert algorithm achieved high agreement with gold-standard CDC grading in the validation cohort (macro-F1-score: 0.962, macro-balanced accuracy: 0.974).
  • The algorithm demonstrated strong sensitivity (0.950) and specificity (0.971) for classifying complications.
  • Machine learning approaches underperformed compared to the expert algorithm across all evaluated metrics.

Conclusions:

  • An interpretable, therapeutic-act-based algorithm accurately grades postoperative complications using routine data, outperforming ML models.
  • The use of ICHI mapping facilitates international portability for real-time complication surveillance.
  • The algorithm supports quality benchmarking and policy evaluation in hepatobiliary surgery.