Effect of changes in body weight and serum albumin levels on electrocardiographic QRS amplitudes

Artificial Intelligence-Enabled Electrocardiography Detects Hypoalbuminemia and Identifies the Mechanism of Hepatorenal and Cardiovascular Events

Background

Albumin, an important component of fluid balance, is associated with kidney, liver, nutritional, and cardiovascular diseases (CVD) and is measured by blood tests. Since fluid balance is associated with electrocardiography (ECG) changes, we established a deep learning model (DLM) to estimate albumin via ECG.

Objective

This study aimed to develop a DLM to estimate albumin via ECG and explored its contribution to future complications.

Materials and Methods

A DLM was trained for estimating ECG-based albumin (ECG-Alb) using 155,078 ECGs corresponding to albumin from 79,111 patients, and another independent 13,335 patients from an academic medical center and 11,370 patients from a community hospital were used for internal and external validation. The primary analysis focused on distinguishing patients with mild to severe hypoalbuminemia, and the secondary analysis aimed to provide additional prognostic value from ECG-Alb for future complications, which included mortality, new-onset hypoalbuminemia, chronic kidney disease (CKD), new onset hepatitis, CVD mortality, new-onset acute myocardial infarction (AMI), new-onset stroke (STK), new-onset coronary artery disease (CAD), new-onset heart failure (HF), and new-onset atrial fibrillation (Afib).

Results

The AUC to identify hypoalbuminemia was 0.8771 with a sensitivity of 56.0% and a specificity of 90.7% in the internal validation set, and the Pearson correlation coefficient was 0.69 in the continuous analysis. The most important ECG features contributing to ECG-Alb were ordered in terms of heart rate, corrected QT interval, T wave axis, sinus rhythm, P wave axis, etc. The group with severely low ECG-Alb had a higher risk of all-cause mortality [hazard ratio (HR): 2.45, 95% CI: 1.81-3.33] and the other hepatorenal and cardiovascular events in the internal validation set. The external validation set yielded similar results.

Conclusion

Hypoalbuminemia and its complications can be predicted using ECG-Alb as a novel biomarker, which may be a non-invasive tool to warn asymptomatic patients.

Electrocardiogram voltage attenuation and shortening of the duration of P-waves, QRS complexes, and QT intervals

Multiple pathologies in concert may lead to attenuation of the electrocardiogram (ECG) voltage. A case of a patient illustrating the above is presented, who showed marked attenuation of the ECG voltage. Automated values of the amplitude of the ECG QRS complexes, P-waves, and T-waves (in mm), duration of the QRS complexes, P-waves, and QT intervals (in ms), in 2 ECGs were compared. The patient was a 64-year-old woman who developed in the setting of a fatal illness, pleural and pericardial effusions, pneumomediastinum, pneumoperitoneum, subcutaneous emphysema in the neck and chest, peripheral edema with weight gain of 43.4 lbs, marked hypoalbuminemia, abnormal liver tests, and renal failure. All the above pathologies led to a marked attenuation of the ECG voltage, and shortening of the mean P-wave, QRS complexes, and QTc interval durations. The postulated mechanism of the observed ECG phenomena is discussed.

Attenuation of ECG voltage in cirrhotic patients

Two patients with cirrhosis (CIR), ascites (ASC), and peripheral oedema (PEROD) are presented. They were followed for many years, had multiple hospital admissions and clinic evaluations, had repeated laboratory testing, and many ECGs recorded. As their condition worsened, they developed attenuation of the ECG voltage (ATTECGV), which was more pronounced during intervals of increased fluid overload. Attenuation of the ECG voltage was decreased at times of successful diuresis and amelioration of PEROD, while abdominal paracenteses for ASC did not have any influence on the ATTECGV, suggesting that ATTECGV in patients with CIR is due to the associated PEROD, and not to ASC.

Variations of intrathoracic amount of blood as a reason of ECG voltage changes

BACKGROUND

It is known that electroconduction of intrathoracic organs and tissues significantly influences the ECG voltage. It changes during therapy or exercise test due to redistribution and/or volume variations of blood and body fluids and their electroconductivity variations. This fact must be taken into consideration during interpretation of corresponding ECG. But there are no quantitative estimations of this influence on human ECG. The goals of this study were to estimate the influence of variations of thoracic electroconduction, and heart volume on QRS voltage in humans, due to gravity change.

METHODS

ECGs of 26 healthy volunteers were analyzed in upright and supine position. Experimental conditions-acute change of gravity--are created in a special aircraft flying on Kepler's parabola trajectory. Each parabola includes phases of normo-, hypergravity (blood shifts in caudal direction), and microgravity (blood redistributes in cranial direction). Amplitude of QRS in Frank leads in all phases has been analyzed. 2-D echo studies for six subjects were used for estimation of heart volume change.

RESULTS

In an upright position during hypergravity the amplitude of R wave in Z increases in 95% of cases (mean 0.19 mV). During microgravity amplitude of R wave in Z decreases in 95% (mean 0.24 mV). In supine position changes of QRS voltage are not significantly.

CONCLUSION

Blood redistribution during gravity change leads to changes of QRS voltage, which is more expressed and steady on R in Z lead: an average near 0.2 mV. It is due to the balance between two factors: (a). changes of degree of short circuiting by variations in the amount of blood in thorax (b). changes of distance between heart and electrodes as a result of change in the position, form, and volume of the heart.

Diminution of QRS complexes caused by anasarca after an acute myocardial infarction: a case report and a discussion of the plausible underlying pathophysiological mechanisms

We describe the case of an 81-year-old man with an acute anterior myocardial infarction (MI), complicated by anoxic encephalopathy, respiratory, and acute renal failure, who developed gradually marked reduction in the QRS complexes of his electrocardiogram (ECG) in the process of gaining 44 pounds, due to anasarca. Such ECG pattern has been recently associated with marked peripheral edema in the context of critical illness of varying etiologies. Our patient did not have a pericardial effusion, and his gradually increasing weight values correlated strongly with the corresponding sums of the amplitudes of the QRS complexes of the 12-lead ECGs (r =.92, P =.0029). The mechanism of this ECG phenomenon is attributed to a reduction of the overall transfer impedance of the conducting volume surrounding the heart, which leads to an attenuation of the potentials recorded on the body surface, due to a shunting effect of the edematous subcutaneous connective tissues. This reduction of the composite transfer impedance of the conducting medium is being mediated by the low resistivity of the water of the retained anasarca fluid.