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 Videos

A Multi-Phase Protocol for Developing and Validating an Explainable AI Framework for Continuous Monitoring, Risk

Basile Njei1, Ulrick Sidney Kanmounye2

  • 1Euclid University, Avenue de France, Campus ENAM BP 157 Bangui, Central African Republic, Bangui, CF.

JMIR Research Protocols
|May 25, 2026
PubMed
Summary

Related Concept Videos

Chronic Pancreatitis II: Collaborative Care01:29

Chronic Pancreatitis II: Collaborative Care

The management of chronic pancreatitis is multifaceted, involving a comprehensive approach that includes thorough assessment, diagnostic testing, and a variety of management strategies.
Assessment:
Chronic Pancreatitis I: Introduction01:25

Chronic Pancreatitis I: Introduction

Chronic pancreatitis is a long-standing, relapsing inflammation of the pancreas, characterized by irreversible damage to the gland. It results in progressive destruction of the pancreatic parenchyma, fibrosis, and eventual loss of both exocrine and endocrine function. The disease may evolve gradually after multiple episodes of acute pancreatitis or develop independently.EtiologyChronic pancreatitis can arise from a variety of causes:Alcohol use is the leading cause, accounting for 70–80% of...

You might also read

Related Articles

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

Sort by
Same author

Increased Risk of Alzheimer Disease-Associated Mortality in Nonobese vs Obese Metabolic Dysfunction-Associated Steatotic Liver Disease: A 30-Year National Cohort Study.

Gastro hep advances·2026
Same author

Response to Jamalinia and Lonardo.

Clinical and translational gastroenterology·2026
Same author

An Explainable AI Framework for Continuous Monitoring, Risk Stratification, and Clinical Decision Support in Primary Biliary Cholangitis: Protocol for a Multiphase Development and Validation Study.

JMIR research protocols·2026
Same author

A conceptual agentic AI architecture for MASLD-associated significant fibrosis in primary care.

PLOS digital health·2026
Same author

FibroX: a machine learning model for detecting and prognosticating advanced fibrosis in metabolic dysfunction-associated steatotic liver disease.

Translational gastroenterology and hepatology·2026
Same author

National and state-level trends in digestive diseases in the United States, 1990 to 2021.

Proceedings (Baylor University. Medical Center)·2026

This study introduces AIm-PBC, an explainable AI framework for primary biliary cholangitis (PBC) management. It aims to improve disease monitoring, predict complications, and support clinical decisions for better patient outcomes.

Area of Science:

  • Hepatology and Artificial Intelligence
  • Clinical Decision Support Systems
  • Biomedical Informatics

Background:

  • Current primary biliary cholangitis (PBC) management relies on static markers and fragmented symptom assessment.
  • Inadequate risk stratification for clinically significant portal hypertension (CSPH) hinders effective patient care.
  • Existing tools lack integration of longitudinal data, elastography, and patient-reported outcomes.

Purpose of the Study:

  • Develop and validate an explainable AI framework, AIm-PBC, for continuous PBC disease monitoring.
  • Enable early prediction of CSPH complications and provide guideline-based clinical decision support.
  • Bridge the gap between disease monitoring, risk prediction, and clinical action in PBC management.

Main Methods:

Related Experiment Videos

  • Multi-phase study involving retrospective and prospective data from at least 600 PBC patients.
  • AI framework integrates biochemical markers, elastography, and patient-reported outcomes using gradient-boosted models with SHapley Additive Explanations.
  • Deployment via an EHR clinical decision support tool and evaluation through simulation and pilot studies.

    • Main Results:

    • Primary outcomes focus on the calibration and responsiveness of the AI-generated disease activity index.
    • Evaluation of the CSPH prediction model's discriminatory performance against established criteria.
    • Assessment of the decision support tool's effectiveness in improving guideline-concordant care and usability.

    Conclusions:

    • The AIm-PBC framework offers a scalable, explainable AI solution for PBC management.
    • Potential to enhance early complication detection and improve symptom management in PBC patients.
    • Aims to support equitable, evidence-based care delivery in routine hepatology practice.