Double Graph Attention Network for predicting non-alcoholic fatty liver disease in patients with type 2 diabetes

Key Points

• Predictive model accurately identifies non-alcoholic fatty liver disease in patients with type 2 diabetes, enhancing early detection.
• Model achieves an accuracy of 85% in identifying biomarkers related to fatty liver disease in the tested group.
• Analysis employs a double graph attention network to integrate various clinical and biological data sources effectively.
• Potential for improved patient outcomes through early intervention in those identified at risk of fatty liver disease.