Deep learning has made many advances in data classification using electrocardiogram (ECG) waveforms. Over the past decade, data science research has focused on developing artificial intelligence (AI) based models that can analyze ECG waveforms to identify and classify abnormal cardiac rhythms accurately. However, the primary drawback of the current AI models is that most of these models are heavy, computationally intensive, and inefficient in terms of cost for real-time implementation. In this review, we first discuss the current state-of-the-art AI models utilized for ECG-based cardiac rhythm classification. Next, we present some of the upcoming modeling methodologies which have the potential to perform real-time implementation of AI-based heart rhythm diagnosis. These models hold significant promise in being lightweight and computationally efficient without compromising the accuracy. Contemporary models predominantly utilize 12-lead ECG for cardiac rhythm classification and cardiovascular status prediction, increasing the computational burden and making real-time implementation challenging. We also summarize research studies evaluating the potential of efficient data setups to reduce the number of ECG leads without affecting classification accuracy. Lastly, we present future perspectives on AI's utility in precision medicine by providing opportunities for accurate prediction and diagnostics of cardiovascular status in patients.

Background: Low‐level tragus stimulation (LLTS) has been shown to significantly reduce atrial fibrillation (AF) burden in patients with paroxysmal AF. P‐wave alternans (PWA) is believed to be generated by the same substrate responsible for AF. Hence, PWA may serve as a marker in guiding LLTS therapy. We investigated the utility of PWA in guiding LLTS therapy in patients with AF. Methods and Results: Twenty‐eight patients with AF were randomized to either active LLTS or sham (earlobe stimulation). LLTS was delivered through a transcutaneous electrical nerve stimulation device (pulse width 200 μs, frequency 20 Hz, amplitude 10–50 mA), for 1 hour daily over a 6‐month period. AF burden over 2‐week periods was assessed by noninvasive continuous ECG monitoring at baseline, 3 months, and 6 months. A 5‐minute control ECG for PWA analysis was recorded during all 3 follow‐up visits. Following the control ECG, an additional 5‐minute ECG was recorded during active LLTS in all patients. At baseline, acute LLTS led to a significant rise in PWA burden. However, active patients receiving chronic LLTS demonstrated a significant reduction in both PWA and AF burden after 6 months ( P <0.05). Active patients who demonstrated an increase in PWA burden with acute LLTS showed a significant drop in AF burden after 6 months of chronic LLTS. Conclusions: Chronic, intermittent LLTS resulted in lower PWA and AF burden than did sham control stimulation. Our results support the use of PWA as a potential marker for guiding LLTS treatment of paroxysmal AF.

Risk stratification at the time of hospital admission is of paramount significance in triaging the patients and providing timely care. In the present study, we aim at predicting multiple clinical outcomes using the data recorded during admission to a cardiac care unit via an optimized machine learning method. This study involves a total of 11,498 patients admitted to a cardiac care unit over two years. Patient demographics, admission type (emergency or outpatient), patient history, lab tests, and comorbidities were used to predict various outcomes. We employed a fully connected neural network architecture and optimized the models for various subsets of input features. Using 10-fold cross-validation, our optimized machine learning model predicted mortality with a mean area under the receiver operating characteristic curve (AUC) of 0.967 (95% confidence interval (CI): 0.963–0.972), heart failure AUC of 0.838 (CI: 0.825–0.851), ST-segment elevation myocardial infarction AUC of 0.832 (CI: 0.821–0.842), pulmonary embolism AUC of 0.802 (CI: 0.764–0.84), and estimated the duration of stay (DOS) with a mean absolute error of 2.543 days (CI: 2.499–2.586) of data with a mean and median DOS of 6.35 and 5.0 days, respectively. Further, we objectively quantified the importance of each feature and its correlation with the clinical assessment of the corresponding outcome. The proposed method accurately predicts various cardiac outcomes and can be used as a clinical decision support system to provide timely care and optimize hospital resources.

Respiratory rate (RR) is a critical vital sign used to assess pulmonary function. Currently, RR estimating instrumentation is specialized and bulky, therefore unsuitable for remote health monitoring. Previously, RR was estimated using proprietary software that extract surface electrocardiogram (ECG) waveform features obtained at several thoracic locations. However, developing a non-proprietary method that uses minimal ECG leads, generally available from mobile cardiac monitors is highly desirable. Here, we introduce an open-source and well-documented Python-based algorithm that estimates RR requiring only single-stream ECG signals. The algorithm was first developed using ECGs from awake, spontaneously breathing adult human subjects. The algorithm-estimated RRs exhibited close linear correlation to the subjects’ true RR values demonstrating an R²of 0.9092 and root mean square error of 2.2 bpm. The algorithm robustness was then tested using ECGs generated by the ischemic hearts of anesthetized, mechanically ventilated sheep. Although the ECG waveforms during ischemia exhibited severe morphologic changes, the algorithm-determined RRs exhibited high fidelity with a resolution of 1 bpm, an absolute error of 0.07 ± 0.07 bpm, and a relative error of 0.67 ± 0.64%. This optimized Python-based RR estimation technique will likely be widely adapted for remote lung function assessment in patients with cardiopulmonary disease.

The measurement of physiologic pressure helps diagnose and prevent associated health complications. From typical conventional methods to more complicated modalities, such as the estimation of intracranial pressures, numerous invasive and noninvasive tools that provide us with insight into daily physiology and aid in understanding pathology are within our grasp. Currently, our standards for estimating vital pressures, including continuous BP measurements, pulmonary capillary wedge pressures, and hepatic portal gradients, involve the use of invasive modalities. As an emerging field in medical technology, artificial intelligence (AI) has been incorporated into analyzing and predicting patterns of physiologic pressures. AI has been used to construct models that have clinical applicability both in hospital settings and at-home settings for ease of use for patients. Studies applying AI to each of these compartmental pressures were searched and shortlisted for thorough assessment and review. There are several AI-based innovations in noninvasive blood pressure estimation based on imaging, auscultation, oscillometry and wearable technology employing biosignals. The purpose of this review is to provide an in-depth assessment of the involved physiologies, prevailing methodologies and emerging technologies incorporating AI in clinical practice for each type of compartmental pressure measurement. We also bring to the forefront AI-based noninvasive estimation techniques for physiologic pressure based on microwave systems that have promising potential for clinical practice.

Repolarization alternans (RA) has been implicated in the pathogenesis of ventricular arrhythmias and sudden cardiac death. We developed a 12-lead, blue-tooth/Smart-Phone (Android) based electrocardiogram (ECG) acquisition and monitoring system (cvrPhone), and an application to estimate RA, in real-time. In in-vivo swine studies (N = 17), 12-lead ECG signals were recorded at baseline and following coronary artery occlusion. RA was estimated using the Fast Fourier Transform (FFT) method using a custom developed algorithm in JAVA. Underlying ischemia was detected using a custom developed ischemic index. RA from each lead showed a significant (p < 0.05) increase within 1 min of occlusion compared to baseline (n = 29). Following myocardial infarction, spontaneous ventricular tachycardia episodes (n = 4) were preceded by significant (p < 0.05) increase of RA prior to the onset of the tachy-arrhythmias. Similarly, the ischemic index exhibited a significant increase following myocardial infarction (p < 0.05) and preceding a tachy-arrhythmic event. In conclusion, RA can be effectively estimated using surface lead electrocardiograms by analyzing beat-to-beat variability in ECG morphology using a smartphone based platform. cvrPhone can be used to detect myocardial ischemia and arrhythmia susceptibility using a user-friendly, clinically acceptable, mobile platform.