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

A scalable framework for UAV-based point cloud reconstruction and organ segmentation of field-grown cotton in complex field environments.

Frontiers in plant science·2026
Same author

Explainable machine learning for the early differentiation of pediatric bronchopneumonia using routine laboratory parameters.

PloS one·2026
Same author

Day-Long Persistent Luminescence in Intrinsically Integrated Donor-Acceptor Carbon Dots Enabled by Defect-Mediated Charge Trapping.

Angewandte Chemie (International ed. in English)·2026
Same author

Dietary Fat and Fiber Divergently Control Intestinal Nanoplastic Bioaccumulation through Gut Motility and Barrier Pathways.

Environmental science & technology·2026
Same author

Ecotype-Specific Drilosphere Microbiome Reprogramming Influencing Microplastic Impacts on Soil Carbon-Nitrogen Characteristics and Earthworm Health.

Environmental science & technology·2026
Same author

Shoot-root hormonal coordination and cross-sphere microbiome assembly underpin nanomaterial-induced resistance to rare earth elements in lettuce.

Journal of hazardous materials·2026

Related Experiment Video

Updated: Jul 5, 2026

Development of Compendium for Esophageal Squamous Cell Carcinoma
03:36

Development of Compendium for Esophageal Squamous Cell Carcinoma

Published on: April 12, 2024

Development and Validation of an Interpretable Machine Learning Model Based on Peripheral Blood Biomarkers for

Qingkai Wang1, Liran Shen1, Weibing Qiu2

  • 1Department of Medical Laboratory Centre, Shanxian Central Hospital, Heze, 274330, People's Republic of China.

International Journal of General Medicine
|July 1, 2026
PubMed
Summary

Machine learning models using blood biomarkers can effectively prescreen for esophageal cancer (EC). An explainable random forest model achieved high accuracy, identifying creatinine and SIRI as key indicators for EC risk.

Keywords:
SHAPesophageal cancermachine learningrisk predictionroutine laboratory biomarkerssystemic inflammation

More Related Videos

Establishment and Evaluation of a Risk Prediction Model for Pathological Escalation of Gastric Low-Grade Intraepithelial Neoplasia
03:05

Establishment and Evaluation of a Risk Prediction Model for Pathological Escalation of Gastric Low-Grade Intraepithelial Neoplasia

Published on: February 16, 2024

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

Related Experiment Videos

Last Updated: Jul 5, 2026

Development of Compendium for Esophageal Squamous Cell Carcinoma
03:36

Development of Compendium for Esophageal Squamous Cell Carcinoma

Published on: April 12, 2024

Establishment and Evaluation of a Risk Prediction Model for Pathological Escalation of Gastric Low-Grade Intraepithelial Neoplasia
03:05

Establishment and Evaluation of a Risk Prediction Model for Pathological Escalation of Gastric Low-Grade Intraepithelial Neoplasia

Published on: February 16, 2024

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

Area of Science:

  • Oncology
  • Biomarkers
  • Machine Learning

Background:

  • Esophageal cancer (EC) requires improved noninvasive prescreening methods for risk stratification.
  • Routine peripheral blood biomarkers can be utilized for developing cost-effective prescreening tools.

Purpose of the Study:

  • To develop and validate explainable machine learning (ML) models for esophageal cancer (EC) prescreening.
  • To identify key blood biomarkers for predicting EC risk.

Main Methods:

  • A dual-center retrospective case-control study included 454 participants (198 EC cases, 256 controls).
  • LASSO regression identified nine features, and seven ML algorithms were trained and validated.
  • Shapley additive explanations (SHAP) were used for model interpretability.

Main Results:

  • The random forest (RF) model demonstrated superior performance (AUC=0.973, accuracy=0.926) in the validation set.
  • SHAP analysis highlighted creatinine and SIRI as the most influential biomarkers, with lower creatinine and higher SIRI associated with increased EC risk.
  • The model showed excellent discrimination and good calibration.

Conclusions:

  • An explainable RF model using blood biomarkers shows promise as a noninvasive prescreening tool for esophageal cancer.
  • The model can aid in guiding endoscopic referrals but requires prospective validation before clinical implementation.