Related Experiment Video
Updated: Jul 12, 2026
10:03
Characterization of Electrode Materials for Lithium Ion and Sodium Ion Batteries Using Synchrotron Radiation Techniques
Published on: November 11, 2013
Using artificial intelligence to identify characteristics associated with clinical and economic outcomes in MASH
Kamal Kant Mangla1, Semiu O Gbadamosi2, Daniel Semeniuta3
1Novo Nordisk Service Centre India Pvt. Ltd., Bengaluru, KA 560066, India.
Therapeutic Advances in Gastroenterology
|July 11, 2026
Summary
Artificial intelligence (AI) phenotyping identified factors linked to rapid fibrosis progression, adverse outcomes, and high costs in metabolic dysfunction-associated steatohepatitis (MASH). This approach aids in identifying MASH patients needing closer monitoring and management.
Area of Science:
- Hepatology and data science applications in clinical research.
- Utilizing artificial intelligence for patient stratification in liver disease.
Background:
- Metabolic dysfunction-associated steatohepatitis (MASH) exhibits heterogeneous disease characteristics, hindering identification of patients with high unmet needs.
- Challenges in stratifying MASH patients due to disease variability.
Purpose of the Study:
- To employ artificial intelligence (AI) phenotyping to identify factors associated with rapid fibrosis progression in MASH.
- To determine predictors of long-term clinical outcomes and high healthcare costs in MASH patients.
- To leverage AI for improved identification of MASH patients requiring intensive management.
Main Methods:
- Retrospective cohort study analyzing electronic health records and claims data from January 2013 to September 2022.
- Machine learning applied to group patient characteristics (diagnoses, procedures, medications) into phenotypic signals.
- Iterative refinement and evaluation of phenotypic signals for association with rapid fibrosis progression, clinical outcomes, and healthcare costs.
Main Results:
- Rapid fibrosis progression in MASH was associated with anemia, thrombocytopenia, and cardiovascular diagnoses.
- Long-term liver and cardiovascular outcomes were linked to chronic diseases, kidney and cardiac diagnoses, medications, lab tests, and injuries.
- High healthcare costs in MASH patients correlated with heart failure procedures, cardiac diagnoses/testing, hospitalization codes, kidney diagnoses, gastrointestinal diagnoses, and abdominal imaging.
Conclusions:
- AI phenotyping effectively analyzes multidimensional real-world data for MASH patient stratification.
- This AI-driven approach can facilitate proactive identification of MASH patients needing enhanced monitoring and clinical management.
- Demonstrates the potential of AI in uncovering complex associations within large patient datasets for clinical decision support.
