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
Light-Driven Random Number Generators Boost Image Security at Hardware Level
Researchers at Hanyang University developed a light-driven true random number generator for embedding secure signatures into images and detecting tampering.
•EurekAlert
AI Accelerates Radiopharmaceuticals, Boosts Personalized Dosimetry in Cancer
Machine learning is driving advancements in radiopharmaceutical drug discovery and optimizing patient-specific dosimetry for precision cancer therapy.
•EurekAlert
Physicians Overly Trust Erroneous AI, Ignore Contradictory Evidence
Physicians tend to trust incorrect AI advice, even when evidence contradicts it, suggesting risks in clinical decision-making with AI tools.