Jove
Visualize
Contact Us

Related Concept Videos

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
  1. Home
  3. Establishment Of Two Pathomic-based Machine Learning Models To Predict Clca1 Expression In Colon Adenocarcinoma.
  1. Home
  3. Establishment Of Two Pathomic-based Machine Learning Models To Predict Clca1 Expression In Colon Adenocarcinoma.

Related Experiment Video

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

199

Establishment of two pathomic-based machine learning models to predict CLCA1 expression in colon adenocarcinoma.

Caiyun Yao1, Maotong Hu1, Lingxia Zhou1

  • 1Pathology Department, Yiwu Central Hospital, Jinhua, Zhejiang, China.

Plos One
|July 21, 2025

View abstract on PubMed

Summary
This summary is machine-generated.

This study developed pathomics models to predict Chloride channel accessory 1 (CLCA1) expression in colon adenocarcinoma (COAD) from H&E images. The models revealed CLCA1

More Related Videos

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

1.2K
Author Spotlight: Liujunzi Decoction as a Traditional Chinese Treatment for Coloproctitis Cancer
06:24

Author Spotlight: Liujunzi Decoction as a Traditional Chinese Treatment for Coloproctitis Cancer

Published on: October 13, 2023

1.1K

Related Experiment 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

199
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

1.2K
Author Spotlight: Liujunzi Decoction as a Traditional Chinese Treatment for Coloproctitis Cancer
06:24

Author Spotlight: Liujunzi Decoction as a Traditional Chinese Treatment for Coloproctitis Cancer

Published on: October 13, 2023

1.1K

Area of Science:

  • Computational pathology and bioinformatics
  • Oncology and cancer research
  • Biomarker discovery and validation

Background:

  • Chloride channel accessory 1 (CLCA1) is a potential prognostic biomarker in colon adenocarcinoma (COAD).
  • Predicting CLCA1 expression from histopathological images can offer valuable prognostic insights.
  • Integrating pathomics with transcriptomics can elucidate underlying biological mechanisms in COAD.

Purpose of the Study:

  • To develop and validate pathomics models for predicting CLCA1 expression in COAD using H&E stained images.
  • To investigate the prognostic value of CLCA1 and its associated pathomics features in COAD.
  • To explore the biological mechanisms linked to CLCA1 expression and pathomics via transcriptomic analysis.

Main Methods:

  • Development of two pathomics models (Random Forest and XGBoost) to predict CLCA1 expression from H&E images.
  • Assessment of CLCA1 prognostic value using gene transcriptome expression data and Cox regression analysis.
  • Exploration of biological mechanisms using Gene Set Variation Analysis (GSVA), immune infiltration, and somatic mutation analysis.

    • Main Results:

    • The Random Forest pathomics model achieved high predictive performance (AUC 0.846 training, 0.776 validation).
    • Downregulated CLCA1 expression in COAD was associated with a poor prognosis (P=0.008).
    • Low-risk score groups showed enrichment in pathways like epithelial-mesenchymal transition and VEGF signaling.

    Conclusions:

    • Pathomics-based machine learning models can effectively predict CLCA1 expression from H&E images in COAD.
    • CLCA1 expression and its pathomics signature hold prognostic value for overall survival in COAD patients.
    • This integrated approach provides a theoretical basis for understanding COAD pathogenesis and facilitates further research.