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

Mental health disorders following nephrectomy for renal cell carcinoma: a national study.

BJU international·2026
Same author

Orbitrap Collision Cross Section Measurements Enhance Isomer Annotations in Lipidomics.

bioRxiv : the preprint server for biology·2026
Same author

Sarcopenia is associated with poor survival among patients with non-metastatic renal cell carcinoma and venous tumor thrombus.

World journal of urology·2026
Same author

Metabolite Fraction Libraries for Quantitative NMR Metabolomics.

Analytical chemistry·2026
Same author

<sup>13</sup>C NMR as a foundation for machine learning models of polysaccharides.

Structural dynamics (Melville, N.Y.)·2026
Same author

Local delivery of rhBMP-2 affects systemic metabolic response during healing of critically-sized segmental defects in a rat model.

Bone·2026

Related Experiment Video

Updated: Nov 1, 2025

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

7.1K

Machine Learning-Enabled Renal Cell Carcinoma Status Prediction Using Multiplatform Urine-Based Metabolomics.

Olatomiwa O Bifarin1, David A Gaul2, Samyukta Sah2

  • 1Department of Biochemistry and Molecular Biology, Complex Carbohydrate Research Center, University of Georgia, Athens, Georgia 30602, United States.

Journal of Proteome Research
|June 23, 2021
PubMed
Summary

Developing a noninvasive urine test for renal cell carcinoma (RCC) is crucial. Machine learning analysis of urine metabolomics identified a seven-metabolite panel with high accuracy for detecting RCC.

Keywords:
liquid chromatography mass spectrometrymachine learningmetabolomicsnuclear magnetic resonance spectroscopyrenal cell carcinoma

More Related Videos

Author Spotlight: Engineering Molecular Tools for Disease Detection and Imaging
04:33

Author Spotlight: Engineering Molecular Tools for Disease Detection and Imaging

Published on: December 8, 2023

1.1K
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

8.5K

Related Experiment Videos

Last Updated: Nov 1, 2025

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

7.1K
Author Spotlight: Engineering Molecular Tools for Disease Detection and Imaging
04:33

Author Spotlight: Engineering Molecular Tools for Disease Detection and Imaging

Published on: December 8, 2023

1.1K
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

8.5K

Area of Science:

  • Biochemistry
  • Oncology
  • Data Science

Background:

  • Renal cell carcinoma (RCC) diagnosis relies on invasive and costly methods like imaging and biopsies.
  • Current diagnostic approaches for RCC are prone to errors and patient discomfort.
  • A noninvasive diagnostic assay for RCC is critically needed.

Purpose of the Study:

  • To develop a noninvasive diagnostic assay for renal cell carcinoma (RCC) using urine metabolomic profiling.
  • To identify a panel of urinary metabolites capable of accurately detecting RCC.
  • To leverage machine learning for the discovery of diagnostic biomarkers for RCC.

Main Methods:

  • Collected liquid chromatography-mass spectrometry (LC-MS) and nuclear magnetic resonance (NMR) data from 105 RCC patients and 179 controls.
  • Utilized machine learning (ML) techniques, including univariate, wrapper, and embedded methods, for feature selection.
  • Trained and tuned three distinct ML algorithms to identify predictive metabolomic panels.
  • Validated the diagnostic performance of the selected panel and ML algorithms on a separate test cohort.

Main Results:

  • A panel of seven metabolites was identified as discriminatory for RCC.
  • The seven-metabolite panel achieved 88% accuracy in predicting RCC in the test cohort.
  • The panel demonstrated high sensitivity (94%) and specificity (85%) with an AUC of 0.98.
  • Machine learning algorithms effectively identified and validated the diagnostic potential of the metabolite panel.

Conclusions:

  • Urine metabolomic profiling combined with machine learning offers a promising noninvasive approach for RCC detection.
  • The identified seven-metabolite panel shows significant potential as a diagnostic biomarker for renal cell carcinoma.
  • This study highlights the feasibility of developing accurate, noninvasive diagnostic assays for RCC based on urinary metabolic signatures.