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

The association of different dimensions of anhedonia in the relationship between depressive symptoms and self-harm in adolescents with mood disorders.

Frontiers in psychiatry·2026
Same author

Temperature variability and mortality risk: distinguishing intraday and interday effects and quantifying the attributable mortality burden in Chengdu, Southwest China.

Frontiers in public health·2026
Same author

Hematological biomarkers for predicting pathologic response to neoadjuvant immunochemotherapy and cycle optimization in locally advanced gastric cancer.

Frontiers in immunology·2026
Same author

Return to baseline arsenic concentrations after 1 year on gluten-free diet in children with celiac disease: A prospective cohort study.

JPGN reports·2026
Same author

A physically constrained and interpretable deep learning framework for PM<sub>2.5</sub> inversion under sparse monitoring conditions in arid regions.

Environmental pollution (Barking, Essex : 1987)·2026
Same author

Grading evaluation of haploid fertility restoration traits based on inception-ResNet in maize.

Plant phenomics (Washington, D.C.)·2026

Related Experiment Video

Updated: Jan 14, 2026

Author Spotlight: Advancing Early Detection and Treatment of Gastrointestinal Tumors
03:05

Author Spotlight: Advancing Early Detection and Treatment of Gastrointestinal Tumors

Published on: February 16, 2024

1.5K

Development of a Machine Learning-Based Predictive Model for Anastomotic Leakage Following Gastric Cancer Surgery.

Wenxiang Ma1, Shengbing Zhao2, Nan Du1

  • 1The First School of Clinical Medicine, Lanzhou University, Lanzhou, PR China.

The American Surgeon
|October 23, 2025
PubMed
Summary

An early anastomotic leakage (AL) prediction model using machine learning identifies key risk factors, including postoperative C-reactive protein (CRP), for gastric cancer surgery. This model offers accurate risk assessment to improve patient outcomes.

Keywords:
anastomotic leakagegastric cancermachine learningprediction model

More Related Videos

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

485
Endoscopic Vacuum Therapy for the Treatment of Anastomotic Leakage after Total Gastrectomy with Esophagojejunostomy
04:05

Endoscopic Vacuum Therapy for the Treatment of Anastomotic Leakage after Total Gastrectomy with Esophagojejunostomy

Published on: August 22, 2025

690

Related Experiment Videos

Last Updated: Jan 14, 2026

Author Spotlight: Advancing Early Detection and Treatment of Gastrointestinal Tumors
03:05

Author Spotlight: Advancing Early Detection and Treatment of Gastrointestinal Tumors

Published on: February 16, 2024

1.5K
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

485
Endoscopic Vacuum Therapy for the Treatment of Anastomotic Leakage after Total Gastrectomy with Esophagojejunostomy
04:05

Endoscopic Vacuum Therapy for the Treatment of Anastomotic Leakage after Total Gastrectomy with Esophagojejunostomy

Published on: August 22, 2025

690

Area of Science:

  • Oncology
  • Surgical Gastroenterology
  • Medical Informatics

Background:

  • Anastomotic leakage (AL) after radical gastrectomy for gastric cancer has high mortality (up to 50%) and variable incidence (2.1%-14.6%).
  • Current methods for predicting AL lack accuracy and timeliness.
  • Early and accurate AL risk prediction is crucial for improving patient outcomes.

Purpose of the Study:

  • To develop an early anastomotic leakage (AL) risk prediction model.
  • To integrate multidimensional clinical data using machine learning for AL prediction.
  • To enhance timely risk assessment for patients undergoing radical gastrectomy.

Main Methods:

  • Retrospective enrollment of 1588 patients undergoing radical gastrectomy.
  • Analysis of 36 perioperative features, including dynamic laboratory indicators.
  • Development and validation of five machine learning models using LASSO regression and cross-validation.

Main Results:

  • The LASSO-Logistic model identified key predictors: postoperative C-reactive protein (CRP) within 3 days, age, prior abdominal surgery, and albumin.
  • The model achieved strong external validation performance with an Area Under the Curve (AUC) of 0.871.
  • Sensitivity-optimized mode improved Negative Predictive Value (NPV) to 98.9%.

Conclusions:

  • The LASSO-Logistic model provides precise early warning for anastomotic leakage risk, with postoperative CRP as a core predictor.
  • The model demonstrates moderate generalizability, validated across independent cohorts.
  • Multicenter validation is recommended for broader clinical application.