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

RNA-Seq and XAI Can be Used as Tools to Aid Pathologists in the Process of Cancer Diagnosis.

Methods in molecular biology (Clifton, N.J.)·2026
Same author

New Strategies to Uncover Genes Involved in the Development of Prostate Cancer in Families with Multiple Cases.

Methods in molecular biology (Clifton, N.J.)·2026
Same author

The impact of vasectomy on the seminal microbiome: possible implications and source of microbes.

Human reproduction open·2026
Same author

MiRInter-Trans: a transformer-based framework for microRNA interaction prediction.

Bioinformatics advances·2026
Same author

Early life social and environmental exposures and all-cause hospital visits among children under five in southern Mozambique.

Environment international·2026
Same author

Probabilistic health risk assessment of exposure to bisphenol A in a Spanish population cohort.

Environmental toxicology and pharmacology·2026

Related Experiment Video

Updated: Jul 23, 2025

Detection and Isolation of Cancer in Prostate Biopsies Using Stimulated Raman Histology and Artificial Intelligence
08:08

Detection and Isolation of Cancer in Prostate Biopsies Using Stimulated Raman Histology and Artificial Intelligence

Published on: June 10, 2025

101

Explainable artificial intelligence to predict and identify prostate cancer tissue by gene expression.

Alberto Ramírez-Mena1, Eduardo Andrés-León2, Maria Jesus Alvarez-Cubero3

  • 1GENYO, Centre for Genomics and Oncological Research: Pfizer -University of Granada - Andalusian Regional Government, Granada, 18016, Spain.

Computer Methods and Programs in Biomedicine
|July 15, 2023
PubMed
Summary

This study introduces a novel machine learning classifier for prostate cancer (PCa) detection using gene expression data. The developed model offers accurate predictions and explanations, potentially improving early diagnosis and clinical decision-making.

Keywords:
Biomedical informaticsClinical decision supportExplainable artificial intelligenceMachine learningMolecular biologyProstate cancer

More Related Videos

Microarray-based Identification of Individual HERV Loci Expression: Application to Biomarker Discovery in Prostate Cancer
13:19

Microarray-based Identification of Individual HERV Loci Expression: Application to Biomarker Discovery in Prostate Cancer

Published on: November 2, 2013

16.6K
Quantitation of Protein Expression and Co-localization Using Multiplexed Immuno-histochemical Staining and Multispectral Imaging
08:40

Quantitation of Protein Expression and Co-localization Using Multiplexed Immuno-histochemical Staining and Multispectral Imaging

Published on: April 8, 2016

12.9K

Related Experiment Videos

Last Updated: Jul 23, 2025

Detection and Isolation of Cancer in Prostate Biopsies Using Stimulated Raman Histology and Artificial Intelligence
08:08

Detection and Isolation of Cancer in Prostate Biopsies Using Stimulated Raman Histology and Artificial Intelligence

Published on: June 10, 2025

101
Microarray-based Identification of Individual HERV Loci Expression: Application to Biomarker Discovery in Prostate Cancer
13:19

Microarray-based Identification of Individual HERV Loci Expression: Application to Biomarker Discovery in Prostate Cancer

Published on: November 2, 2013

16.6K
Quantitation of Protein Expression and Co-localization Using Multiplexed Immuno-histochemical Staining and Multispectral Imaging
08:40

Quantitation of Protein Expression and Co-localization Using Multiplexed Immuno-histochemical Staining and Multispectral Imaging

Published on: April 8, 2016

12.9K

Area of Science:

  • Genomics
  • Bioinformatics
  • Machine Learning in Oncology

Background:

  • Prostate cancer (PCa) is a leading cancer in men globally, with current screening methods like PSA tests lacking specificity and digital rectal exams often being inconclusive.
  • There's a critical need for reliable diagnostic tools to aid pathologists and improve PCa detection accuracy in clinical practice.
  • Existing research has identified potential biomarkers, but few have translated into routine diagnostic applications or decision-support tools for clinicians.

Purpose of the Study:

  • To develop and validate an explainable artificial intelligence (XAI) based classifier for predicting prostate cancer occurrence.
  • To provide physicians with accurate diagnostic predictions and understandable explanations for clinical decision support.
  • To identify key genes contributing to PCa diagnosis through machine learning analysis.

Main Methods:

  • A panel of 47 genes was selected based on differential expression, gene ontology, and literature review.
  • Machine learning models, utilizing eXplainable AI, were trained on gene expression data from 550 The Cancer Genome Atlas samples.
  • The model was validated across four independent external cohorts (463 samples) and employed SHapley Additive exPlanations (SHAP) for interpretability.

Main Results:

  • The Random Forest algorithm with majority class downsampling demonstrated superior performance, achieving an average sensitivity of 0.90, specificity of 0.8, and AUC of 0.84.
  • The study highlighted the diagnostic relevance of genes DLX1, MYL9, FGFR, CAV2, and MYLK for prostate cancer screening.
  • The developed classifier showed robust statistical significance and consistent performance across diverse ancestral cohorts.

Conclusions:

  • The proposed machine learning model exhibits strong performance and generalizability across independent cohorts of varying ancestries.
  • The provided explanations are consistent with existing literature, supporting the model's potential for clinical integration.
  • Future applications may involve integrating this model with liquid biopsy techniques for enhanced prostate cancer screening.