Age and Sex Estimation Using Artificial Intelligence From Standard 12-Lead ECGs.

BACKGROUND: Sex and age have long been known to affect the ECG. Several biologic variables and anatomic factors may contribute to sex and age-related differences on the ECG. We hypothesized that a convolutional neural network (CNN) could be trained through a process called deep learning to predict a person's age and self-reported sex using only 12-lead ECG signals. We further hypothesized that discrepancies between CNN-predicted age and chronological age may serve as a physiological measure of health. METHODS: We trained CNNs using 10-second samples of 12-lead ECG signals from 499 727 patients to predict sex and age. The networks were tested on a separate cohort of 275 056 patients. Subsequently, 100 randomly selected patients with multiple ECGs over the course of decades were identified to assess within-individual accuracy of CNN age estimation. RESULTS: Of 275 056 patients tested, 52% were males and mean age was 58.6±16.2 years. For sex classification, the model obtained 90.4% classification accuracy with an area under the curve of 0.97 in the independent test data. Age was estimated as a continuous variable with an average error of 6.9±5.6 years (R-squared =0.7). Among 100 patients with multiple ECGs over the course of at least 2 decades of life, most patients (51%) had an average error between real age and CNN-predicted age of <7 years. Major factors seen among patients with a CNN-predicted age that exceeded chronologic age by >7 years included: low ejection fraction, hypertension, and coronary disease (P<0.01). In the 27% of patients where correlation was >0.8 between CNN-predicted and chronologic age, no incident events occurred over follow-up (33±12 years). CONCLUSIONS: Applying artificial intelligence to the ECG allows prediction of patient sex and estimation of age. The ability of an artificial intelligence algorithm to determine physiological age, with further validation, may serve as a measure of overall health.

Screening for cardiac contractile dysfunction using an artificial intelligence-enabled electrocardiogram.

Asymptomatic left ventricular dysfunction (ALVD) is present in 3-6% of the general population, is associated with reduced quality of life and longevity, and is treatable when found1-4. An inexpensive, noninvasive screening tool for ALVD in the doctor's office is not available. We tested the hypothesis that application of artificial intelligence (AI) to the electrocardiogram (ECG), a routine method of measuring the heart's electrical activity, could identify ALVD. Using paired 12-lead ECG and echocardiogram data, including the left ventricular ejection fraction (a measure of contractile function), from 44,959 patients at the Mayo Clinic, we trained a convolutional neural network to identify patients with ventricular dysfunction, defined as ejection fraction ≤35%, using the ECG data alone. When tested on an independent set of 52,870 patients, the network model yielded values for the area under the curve, sensitivity, specificity, and accuracy of 0.93, 86.3%, 85.7%, and 85.7%, respectively. In patients without ventricular dysfunction, those with a positive AI screen were at 4 times the risk (hazard ratio, 4.1; 95% confidence interval, 3.3 to 5.0) of developing future ventricular dysfunction compared with those with a negative screen. Application of AI to the ECG-a ubiquitous, low-cost test-permits the ECG to serve as a powerful screening tool in asymptomatic individuals to identify ALVD.

Feasibility of directional percutaneous epicardial ablation with a partially insulated catheter.

PURPOSE: To demonstrate the feasibility of directional percutaneous epicardial ablation using a partially insulated catheter. METHODS: Partially insulated catheter prototypes were tested in 12 (6 canine, 6 porcine) animal studies in two centers. Prototypes had interspersed windows to enable visualization of epicardial structures with ultrasound. Epicardial unipolar ablation and ablation between two electrodes was performed according to protocol (5-60 W power, 0-60 mls/min irrigation, 78 s mean duration). RESULTS: Of 96 epicardial ablation attempts, unipolar ablation was delivered in 53.1%. Electrogram evidence of ablation, when analyzable, occurred in 75 of 79 (94.9%) therapies. Paired pre/post-ablation pacing threshold (N = 74) showed significant increase in pacing threshold post-ablation (0.9 to 2.6 mA, P < .0001). Arrhythmias occurred in 18 (18.8%) therapies (11 ventricular fibrillation, 7 ventricular tachycardia), mainly in pigs (72.2%). Coronary artery visualization was variably successful. No phrenic nerve injury was noted during or after ablation. Furthermore, there were minimal pericardial changes with ablation. CONCLUSIONS: Epicardial ablation using a partially insulated catheter to confer epicardial directionality and protect the phrenic nerve seems feasible. Iterations with ultrasound windows may enable real-time epicardial surface visualization thus identifying coronary arteries at ablation sites. Further improvements, however, are necessary.

A Novel Defibrillation Tool: Percutaneously Delivered, Partially Insulated Epicardial Defibrillation.

INTRODUCTION: Epicardial defibrillation systems currently require surgical access. We aimed to develop a percutaneous defibrillation system with partially-insulated epicardial coils to focus electrical energy on the myocardium and prevent or minimize extra-cardiac stimulation. METHODS: We tested 2 prototypes created for percutaneous introduction into the pericardial space via a steerable sheath. This included a partially-insulated defibrillation coil and a defibrillation mesh with a urethane balloon acting as an insulator to the face of the mesh not in contact with the epicardium. The average energy associated with a chance of successful defibrillation 75% of the time (ED75) was calculated for each experiment. RESULTS: Of 16 animal experiments, 3 pig experiments had malfunctioning mesh prototypes such that results were unreliable; these were excluded. Therefore, 13 animal experiments were analyzed - 6 canines (29.8±4.0kg); 7 pigs (41.1±4.4kg). The overall ED75 was 12.8±6.7J (10.9±9.1J for canines; 14.4±3.9J in pigs [P=0.37]). The lowest ED75 obtained in canines was 2.5J while in pigs it was 9.5J. The lowest energy resulting in successful defibrillation was 2J in canines and 5J in pigs. There was no evidence of coronary vessel injury or trauma to extra-pericardial structures. CONCLUSION: Percutaneous, epicardial defibrillation using a partially insulated coil is feasible and appears to be associated with low defibrillation thresholds. Focusing insulation may limit extra-cardiac stimulation and potentially lower energy requirements for efficient defibrillation.