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 Experiment Video

Updated: Jun 21, 2026

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

ML-BUSMetab: Machine Learning-Based Metabolomic Profiling for Predicting Aspirin Response in Colorectal Cancer

Abdulvahap Pınar1,2, Ahmet Kadir Arslan1, Cemil Çolak1

  • 1Department of Biostatistics and Medical Informatics, Faculty of Medicine, İnönü University, 44280 Malatya, Turkey.

Journal of Clinical Medicine
|June 12, 2026
PubMed
Summary

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

Fecal Extracellular Vesicle Metabolomics as a Non-Invasive Biomarker Source in Colorectal Cancer: TPOT AutoML Superiority over Tree-Based Models with SHAP and LIME Clinical Interpretability.

International journal of molecular sciences·2026
Same author

Evaluation of vinpocetine in an acute doxorubicin-induced cardiotoxicity model in rats.

Scientific reports·2026
Same author

CMT-BUSNet: Adaptive Fusion-Based Triple-Branch Hybrid Architecture for Explainable Breast Ultrasound Tumor Segmentation.

Diagnostics (Basel, Switzerland)·2026
Same author

Evaluation of the Efficacy of Plasma Shower and 585 Nm Q-Switched Laser in the Treatment of Mild to Moderate Acne Vulgaris.

Journal of cosmetic dermatology·2026
Same author

The Toxic Effects of Hydrated Cement, Autoclaved Aerated Concrete, and Demolition Dusts on the Respiratory System in Rats.

Toxics·2026
Same author

Forecasting Stone-Free Status Following Percutaneous Nephrolithotomy Utilizing Explainable Machine Learning.

Journal of clinical medicine·2026
This summary is machine-generated.

Machine learning models can identify aspirin use through plasma metabolomics, paving the way for personalized colorectal cancer chemoprevention. Further validation is needed to address batch effects for clinical translation.

Area of Science:

  • Metabolomics
  • Machine Learning
  • Personalized Medicine

Background:

  • Aspirin chemoprevention for colorectal cancer (CRC) shows variable efficacy.
  • Developing personalized strategies requires understanding individual responses.

Purpose of the Study:

  • To create and validate machine learning (ML) models distinguishing aspirin users from placebo based on plasma metabolomic profiles.
  • To characterize the metabolomic signature of aspirin administration.

Main Methods:

  • Utilized datasets from the Aspirin/Folate Polyp Prevention Study (AFPPS) for training and external validation.
  • Applied multi-method consensus feature selection to reduce 19,433 features to 300.
  • Benchmarked 16 ML and deep learning (DL) architectures using nested cross-validation.
Keywords:
batch effect correctioncolorectal cancer chemopreventionexplainable artificial intelligencegradient boostingmetabolomics

More Related Videos

Identification and Quantification of Deranged Metabolites in Critically Ill Patients Using NMR-Based Metabolomics
11:02

Identification and Quantification of Deranged Metabolites in Critically Ill Patients Using NMR-Based Metabolomics

Published on: November 29, 2024

Related Experiment Videos

Last Updated: Jun 21, 2026

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

Identification and Quantification of Deranged Metabolites in Critically Ill Patients Using NMR-Based Metabolomics
11:02

Identification and Quantification of Deranged Metabolites in Critically Ill Patients Using NMR-Based Metabolomics

Published on: November 29, 2024

Main Results:

  • GBM_sklearn achieved a high cross-validation PR-AUC of 0.945; ensemble stacking offered superior calibration.
  • Deep learning models underperformed traditional ML due to smaller sample sizes.
  • Metabolite m/z 196.0604 was identified as a key biomarker, linked to glycerophospholipid pathways; external validation performance dropped significantly due to batch effects.

Conclusions:

  • Metabolomics-driven personalized chemoprevention is feasible.
  • High feature-to-sample ratios and batch effects necessitate harmonization and feature reduction for clinical translation.