Seeing Around the Corner: AI Predicts Liver Cirrhosis Years Before Diagnosis
A new machine learning approach leveraging routine health data can forecast the development of liver cirrhosis up to three years in advance, offering opportunities for early intervention.



![The system classifies Parkinson’s disease by fusing information from MRI cortical thickness, clinical assessments, MRI volumetric data, and demographic features, employing modality-specific encoding followed by symmetric cross-attention between cortical and clinical data, then sparse attention-gated multimodal fusion weighted by learnable parameters [latex]\alpha_{1}-\alpha_{4}[/latex] to generate a representation [latex]\mathbf{H}[/latex] for predicting disease probability.](https://arxiv.org/html/2601.00519v1/x2.png)
