Instantaneous detection of acute myocardial infarction and ischaemia from a single carotid pressure waveform in rats

Abstract

Background Myocardial infarction (MI) is one of the leading causes of death worldwide. It is well-accepted that early diagnosis followed by early reperfusion therapy significantly increases the MI survival. Diagnosis of acute MI is traditionally based on the presence of chest pain and ECG criteria. However, around 50% of the MIs are without chest pain, and ECG is neither completely specific nor definitive. Therefore, there is an unmet need for methods that allow detection of acute MI or ischemia without using ECG. Our hypothesis is that a hybrid physics-based machine learning (ML) method can detect occurrence of acute MI or ischemia from a single carotid pressure waveform. Methods We used a standard occlusion/reperfusion rat model. Physics-based ML classifiers were developed using intrinsic frequency (IF) parameters extracted from carotid pressure waveforms. ML models were trained, validated, and generalized using data from 32 rats. The final ML models were tested on an external stratified blind dataset from additional 13 rats. Results When tested on blind data, the best ML model showed specificity = 0.92 and sensitivity = 0.92 for detecting acute MI. The best model’s specificity and sensitivity for ischemia detection were 0.85 and 0.92, respectively. Conclusions We demonstrated that a hybrid physics-based machine learning approach can detect occurrence of acute myocardial infarction and ischemia from carotid pressure waveform in rats. Since carotid pressure waveforms can be measured noninvasively, this proof-of-concept preclinical study can potentially be expanded in future studies for noninvasive detection of MI or myocardial ischemia.