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: Apr 16, 2026

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
05:47

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

1.9K

Explainability Challenges in Medical AI: The Conceptual Hidden Cost of Machine Learning Preprocessing.

Ahmed M Salih1,2,3,4

  • 1Department of Population Health Sciences University of Leicester Leicester UK.

Health Science Reports
|April 15, 2026
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

Issues And Trends In Healthcare Delivery System01:29

Issues And Trends In Healthcare Delivery System

6.5K
The issues and trends in healthcare delivery are constantly changing. The COVID-19 pandemic is one recent issue that wreaked havoc on healthcare systems, causing a shortage of healthcare workers, high demand for medicines and supplies, and increased medical expenditure due to a lack of insurance. Other issues include rising healthcare costs and care fragmentation.
Cost Containment
Payment for healthcare services has historically promoted adoption of costly and often unnecessary or inefficient...
6.5K

You might also read

Related Articles

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

Sort by
Same author

Clinical Phenotypes in Hypertension: A Data-Driven Approach to Risk Stratification.

Hypertension (Dallas, Tex. : 1979)·2025
Same author

Artificial intelligence in cardiovascular imaging: risks, mitigations and the path to safe implementation.

Heart (British Cardiac Society)·2025
Same author

Bone mineral density and cardiovascular diseases: a two-sample Mendelian randomization study.

JBMR plus·2025
Same author

Explainable Artificial Intelligence in Paediatric: Challenges for the Future.

Health science reports·2024
Same author

Leukocyte Telomere Length and Cardiac Structure and Function: A Mendelian Randomization Study.

Journal of the American Heart Association·2024
Same author

Genome-Wide Association Study of Pericardial Fat Area in 28 161 UK Biobank Participants.

Journal of the American Heart Association·2023
Same journal

Factors Influencing Timing of First Antenatal Care Visit Among Bangladeshi Women: Application of Accelerated Failure Time Models Using Demographic Health Survey 2022.

Health science reports·2026
Same journal

Turnaround Time and Patients' Perceptions of Clinical Laboratory Services at a Tertiary Hospital in Pakistan: A Cross-Sectional Study.

Health science reports·2026
Same journal

Organizational Culture Patterns and Safety-Relevant Dimensions in Teaching Hospitals: A Cross-Sectional Study.

Health science reports·2026
Same journal

Clinical Significance of Tumor Invasion Gene Profiling in Early-Stage Hormone Receptor-Positive Breast Cancer: A Cross-Sectional Study.

Health science reports·2026
Same journal

Association Between Neutrophil to High-Density Lipoprotein Cholesterol Ratio and Heart Failure: A Cross-Sectional Analysis.

Health science reports·2026
Same journal

Knowledge, Attitudes, and Practices Regarding Typhoid Fever Among University Students in Bangladesh: A Cross-Sectional Study.

Health science reports·2026
See all related articles

Data preprocessing in medical machine learning enhances model performance but can reduce explainability. Careful consideration of preprocessing steps is crucial to avoid bias and maintain clinical trust in AI systems.

Area of Science:

  • Medical Machine Learning
  • Healthcare Artificial Intelligence

Background:

  • Data preprocessing is essential for optimizing machine learning model performance and efficiency.
  • Common preprocessing techniques include handling missing values, outlier removal, data augmentation, dimensionality reduction, and managing confounding variables.

Purpose of the Study:

  • To explore common data preprocessing steps in medical machine learning.
  • To highlight the conceptual trade-offs, particularly reduced model explainability and clinical interpretability, associated with these preprocessing decisions.

Main Methods:

  • A literature review was conducted to examine data preprocessing techniques in machine learning.

Main Results:

  • Preprocessing improves model accuracy but can obscure new findings and hinder model explainability if not carefully implemented.
Keywords:
MedicineXAIpreprocessing

Related Experiment Videos

Last Updated: Apr 16, 2026

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
05:47

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

1.9K
  • Key risks identified include the introduction of bias and oversimplification, with proposed mitigation strategies.

    • Conclusions:

    • Preprocessing practices in medical AI can pose challenges to explainability.
    • Balancing model performance with explainability is vital for reliable predictions and clinical trust in healthcare AI systems.