Myocardial Infarction Detection using AI
Work
Early diagnosis of heart disease is essential for immediate treatment. I implement an AI model for predicting myocardial infarction by analyzing echocardiogram videos (AP4-views). The project utilizes frame-by-frame analysis instead of single frame, U-NET semantic segmentation, and LSTM model training for enhanced predictive accuracy.
By integrating GLS parameters and LSTM networks, I developed a more accurate and consistent method for predicting MI from echocardiograms. The model achieved 71.5% accuracy with an AUC-ROC score of 0.715 in distinguishing MI from non-MI cases. It demonstrated 72.2% precision and 70.1% sensitivity. While these results are promising, there's room for improvement in future iterations, particularly to enhance sensitivity.
Read More
