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

Pharmacokinetics in Pediatric Patients: Drug Metabolism01:24

Pharmacokinetics in Pediatric Patients: Drug Metabolism

179
In pediatric care, understanding the nuances of hepatic drug metabolism is crucial, as it significantly differs from that of adults. This divergence is primarily due to the developmental stage of drug-metabolizing enzymes, which affects how medications are processed in the body. In neonates, for instance, the activity of Phase I enzymes—critical for the initial breakdown of drugs—is markedly reduced, functioning at just 20–40% of the levels seen in adults. This reduction poses...
179

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

A Robustness-Oriented Quantum-Classical Hybrid Machine Learning Pipeline for Breast Cancer Diagnosis: External Validation, Explainability, and Rigorous Benchmarking in the NISQ Era.

Diagnostics (Basel, Switzerland)·2026
Same author

Metabolomic Classification of Myalgic Encephalomyelitis/Chronic Fatigue Syndrome via Explainable Ensemble Learning and Pareto-Guided Feature Selection.

International journal of molecular sciences·2026
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

The relationship between depression, falls, dizziness, and physical activity in geriatric individuals with BPPV.

BMC geriatrics·2026
Same author

ML-BUSMetab: Machine Learning-Based Metabolomic Profiling for Predicting Aspirin Response in Colorectal Cancer Chemoprevention: A Multi-Model Explainable Artificial Intelligence Approach with External Validation.

Journal of clinical medicine·2026
Same author

Explainable Boosting Machine in Sepsis Prediction Using Platelet Metabolomics: An Interpretable Machine Learning Approach.

Diagnostics (Basel, Switzerland)·2026

Related Experiment Video

Updated: Jan 10, 2026

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

1.0K

Machine Learning-Integrated Explainable Artificial Intelligence Approach for Predicting Steroid Resistance in

Fatma Hilal Yagin1,2, Feyza Inceoglu1, Cemil Colak3

  • 1Department of Biostatistics, Faculty of Medicine, Malatya Turgut Ozal University, 44280 Malatya, Türkiye.

Pharmaceuticals (Basel, Switzerland)
|November 27, 2025
PubMed
Summary

Machine learning models can predict steroid-resistant nephrotic syndrome (SRNS) using metabolomic data. Key biomarkers like glucose and creatine levels help identify patients needing alternative treatments early.

Keywords:
explainable artificial intelligencemetabolomic biomarker discoverypediatric nephrotic syndromesteroid resistance prediction

More Related Videos

Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis
09:16

Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis

Published on: June 18, 2020

7.3K

Related Experiment Videos

Last Updated: Jan 10, 2026

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

1.0K
Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis
09:16

Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis

Published on: June 18, 2020

7.3K

Area of Science:

  • Nephrology
  • Metabolomics
  • Machine Learning

Background:

  • Nephrotic syndrome (NS) is a heterogeneous glomerular disorder with significant treatment resistance.
  • Steroid-resistant nephrotic syndrome (SRNS) leads to higher morbidity and renal function decline compared to steroid-sensitive nephrotic syndrome (SSNS).
  • Current treatments are limited for SRNS, necessitating early identification and alternative therapeutic strategies.

Purpose of the Study:

  • To develop a machine learning (ML) model integrated with explainable artificial intelligence (XAI) to distinguish SRNS from SSNS.
  • To identify key metabolomic biomarkers predictive of steroid resistance in NS.
  • To enhance clinical transparency and interpretability in predicting SRNS.

Main Methods:

  • Proton nuclear magnetic resonance (1H NMR) metabolomics was performed on plasma samples from 41 NS patients (27 SSNS, 14 SRNS).
  • ML models (XGBoost, LightGBM, AdaBoost, Random Forest) were trained and evaluated using cross-validation on preprocessed metabolomic data.
  • XAI techniques (SHAP, LIME) were employed for feature importance and individual patient-level explanations.

Main Results:

  • The Random Forest model achieved the highest performance: accuracy (0.87 ± 0.12), sensitivity (0.90 ± 0.18), and AUC (0.92 ± 0.09).
  • Key predictive metabolomic biomarkers identified include glucose, creatine, 1-methylhistidine, homocysteine, and acetone.
  • Low glucose and creatine levels were associated with increased SRNS risk, while higher propylene glycol and carnitine concentrations indicated higher SRNS probability.

Conclusions:

  • The study successfully developed an accurate and interpretable ML model for predicting SRNS using metabolomic signatures.
  • Candidate metabolomic biomarkers were identified for early prediction of SRNS, aiding in treatment decisions.
  • The findings elucidate potential molecular mechanisms underlying steroid resistance in nephrotic syndrome.