Researchers create an AI model integrating genetic, clinical, and transcriptomic data to identify individuals at risk for thrombosis.
Key Details
- 1A new AI tool analyzes over 12,900 genes alongside clinical and genetic data to model thrombosis risk.
- 2Study involved 790 individuals from families with a history of venous thrombosis, including 70 with idiopathic thrombosis.
- 3494 genes, including many noncoding RNAs, were identified as associated with thrombosis risk.
- 4Adding transcriptomic data improved patient classification: those classified 'high-risk' without thrombosis dropped from 43% to 23%.
- 5The research was published in the Journal of Thrombosis and Haemostasis and still requires external validation.
Why It Matters
The study highlights how integrating genomic and transcriptomic profiles via AI can provide more precise risk stratification than clinical factors alone, pointing toward more personalized and data-driven approaches in disease prevention—relevant as similar data integration strategies emerge in radiology and imaging AI.
Source
EurekAlert
Related News
•EurekAlert
AI-Enhanced Imaging Breaks Barriers in Complex Media for Biomedical Use
Researchers developed a physics-based machine learning imaging system that enhances visibility through complex media, holding promise for biomedical imaging.
•EurekAlert
AI Model Accelerates Accurate Dose Prediction for CyberKnife Radiotherapy
A physics- and spatially informed diffusion model accelerates Monte Carlo–level dose estimation for CyberKnife radiotherapy using planning CT and anatomical data.
•EurekAlert
New G-AUDIT Tool Detects Hidden Bias in Medical AI Training Data
Johns Hopkins and FDA researchers unveil G-AUDIT, a tool to identify hidden biases in medical AI datasets before model training.