Researchers developed a deep learning-driven MASLD classification system for precision risk management.
Key Details
- 1Study analyzed 1,111 liver biopsies to train a deep LASSO model using six clinical indicators.
- 2Algorithm defined four MASLD subtypes with distinct risk profiles for hepatic and extrahepatic complications.
- 3External validation performed in cohorts of 6,172 and 7,406 adults; clustering was consistent.
- 4Cluster 4 displayed highest risk for combined cardiovascular, liver, and kidney complications, and high frequency of PNPLA3 risk alleles.
- 5The classification intends to tailor interventions, such as prioritizing fibrosis screening or cardiorenal protection, by subtype.
Why It Matters
The use of advanced AI/machine learning in clinical stratification sets a precedent for data-driven, precision approaches in metabolic and cardiometabolic disease management. Implications exist for integration with imaging biomarkers and improving targeted clinical decision-making in radiology and hepatology.
Source
EurekAlert
Related News
•EurekAlert
AI-Powered OCT Enables Rapid 'Optical Biopsy' for Early Endometrial Cancer Detection
A team at Washington University has developed a catheter-based 3D OCT system with AI to quickly and noninvasively detect early endometrial cancers.
•EurekAlert
AI Clinical Reasoning in Diagnostics and Digital Fatigue in Healthcare
Recent JMIR features explore large language models in clinical diagnostics and digital fatigue among healthcare professionals.
•EurekAlert
KAIST, MIT, Microsoft Develop Efficient AI Image Upsampling for Robotics
KAIST, MIT, and Microsoft have created 'Upsample Anything,' a training-free AI method to restore high-resolution visual data from compressed images with up to 16x improved GPU memory efficiency.