Researchers have developed an AI model that uses electrocardiogram (ECG) data to predict the outcomes of coronary CT angiography. The model was tested in multiple cohorts and showed promising results, including improved risk stratification and clinical triage. It identified specific ECG patterns associated with high-risk predictions. While the study suggests potential for this tool, further validation is needed in broader clinical settings. --- Why it matters: This matters to AI researchers because it demonstrates a practical application of fine-tuning pre-existing models on new data, improving their performance and utility in real-world scenarios. Source: https://arxiv.org/abs/2512.05136