Subtle QRS changes are associated with reduced ejection fraction, diastolic dysfunction, and heart failure development and therapy responsiveness: Applications for artificial intelligence to ECG

Abstract

Abstract Background Since the last century, the electrocardiogram (ECG) remains the non‐invasive test, that is, most easily accessible, feasible, and inexpensive for cardiology assessment. In past years, many novel ECG indexes and patterns have been published that allow for a more advanced evaluation of what is currently being done, especially based on subtle QRS changes and patterns. Objective The objective of the study was to provide an update on the evidence and clinical applications of these ECG subtle QRS changes and patterns associated with heart disease. Methods Through the literature review, we will highlight the subtle QRS changes and patterns associated with heart disease, mainly focusing on QRS duration, voltage, morphology, axis, and QT interval. Results Small increases in QRS duration are associated with a reduction in left ventricular ejection fraction (EF), increased cardiac chamber dimensions, and risk for incident heart failure (HF). Moreover, fragmentation of the QRS complex is associated with myocardial fibrosis and is a substrate for developing arrhythmic events. Besides, low amplitude QRS voltage is associated with congestive HF, and an increase in the voltage of the QRS complexes is associated with the effectiveness of diuresis treatment. Furthermore, small increases in QT interval are associated with diastolic dysfunction due to impaired sarcoplasmic reticulum calcium handling as occurs in myocardial ischemia, hypertension, or diabetes. On the other hand, in patients with left ventricular dysfunction, the QRS area is associated with clinical and echocardiographic response to cardiac resynchronization therapy regardless of the type of bundle branch block. In addition, subtle ECG changes and patterns in the left bundle branch block are associated with concomitant right ventricular dilation, mostly based on the QRS axis and voltage. Notwithstanding, to identify these subtle changes in QRS require exact manual measurements that can take time. In this regard, applying artificial intelligence (AI) to the ECG can make a quicker and more complete assessment, as well as provide a low cost when applied to large populations. Conclusion We provided an update on the evidence and clinical applications of these subtle QRS changes and patterns associated with diastolic dysfunction, reduced EF, and HF development and therapy responsiveness, as well as their applications for AI to ECG.

Keywords

• artificial intelligence
• QRS axis
• QRS duration
• QRS fragmentation
• QRS voltage
• QT interval