Artificial Intelligence Interpretation of the Electrocardiogram: A State-of-the-Art Review.

PURPOSE OF REVIEW: Artificial intelligence (AI) is transforming electrocardiography (ECG) interpretation. AI diagnostics can reach beyond human capabilities, facilitate automated access to nuanced ECG interpretation, and expand the scope of cardiovascular screening in the population. AI can be applied to the standard 12-lead resting ECG and single-lead ECGs in external monitors, implantable devices, and direct-to-consumer smart devices. We summarize the current state of the literature on AI-ECG. RECENT FINDINGS: Rhythm classification was the first application of AI-ECG. Subsequently, AI-ECG models have been developed for screening structural heart disease including hypertrophic cardiomyopathy, cardiac amyloidosis, aortic stenosis, pulmonary hypertension, and left ventricular systolic dysfunction. Further, AI models can predict future events like development of systolic heart failure and atrial fibrillation. AI-ECG exhibits potential in acute cardiac events and non-cardiac applications, including acute pulmonary embolism, electrolyte abnormalities, monitoring drugs therapy, sleep apnea, and predicting all-cause mortality. Many AI models in the domain of cardiac monitors and smart watches have received Food and Drug Administration (FDA) clearance for rhythm classification, while others for identification of cardiac amyloidosis, pulmonary hypertension and left ventricular dysfunction have received breakthrough device designation. As AI-ECG models continue to be developed, in addition to regulatory oversight and monetization challenges, thoughtful clinical implementation to streamline workflows, avoiding information overload and overwhelming of healthcare systems with false positive results is necessary. Research to demonstrate and validate improvement in healthcare efficiency and improved patient outcomes would be required before widespread adoption of any AI-ECG model.

Phase I/II Trial of Electrophysiology-Guided Noninvasive Cardiac Radioablation for Ventricular Tachycardia.

BACKGROUND: Case studies have suggested the efficacy of catheter-free, electrophysiology-guided noninvasive cardiac radioablation for ventricular tachycardia (VT) using stereotactic body radiation therapy, although prospective data are lacking. METHODS: We conducted a prospective phase I/II trial of noninvasive cardiac radioablation in adults with treatment-refractory episodes of VT or cardiomyopathy related to premature ventricular contractions (PVCs). Arrhythmogenic scar regions were targeted by combining noninvasive anatomic and electric cardiac imaging with a standard stereotactic body radiation therapy workflow followed by delivery of a single fraction of 25 Gy to the target. The primary safety end point was treatment-related serious adverse events in the first 90 days. The primary efficacy end point was any reduction in VT episodes (tracked by indwelling implantable cardioverter defibrillators) or any reduction in PVC burden (as measured by a 24-hour Holter monitor) comparing the 6 months before and after treatment (with a 6-week blanking window after treatment). Health-related quality of life was assessed using the Short Form-36 questionnaire. RESULTS: Nineteen patients were enrolled (17 for VT, 2 for PVC cardiomyopathy). Median noninvasive ablation time was 15.3 minutes (range, 5.4-32.3). In the first 90 days, 2/19 patients (10.5%) developed a treatment-related serious adverse event. The median number of VT episodes was reduced from 119 (range, 4-292) to 3 (range, 0-31; P<0.001). Reduction was observed for both implantable cardioverter defibrillator shocks and antitachycardia pacing. VT episodes or PVC burden were reduced in 17/18 evaluable patients (94%). The frequency of VT episodes or PVC burden was reduced by 75% in 89% of patients. Overall survival was 89% at 6 months and 72% at 12 months. Use of dual antiarrhythmic medications decreased from 59% to 12% ( P=0.008). Quality of life improved in 5 of 9 Short Form-36 domains at 6 months. CONCLUSIONS: Noninvasive electrophysiology-guided cardiac radioablation is associated with markedly reduced ventricular arrhythmia burden with modest short-term risks, reduction in antiarrhythmic drug use, and improvement in quality of life. CLINICAL TRIAL REGISTRATION: URL: https://www.clinicaltrials.gov/ . Unique identifier: NCT02919618.

Single-site ventricular pacing via the coronary sinus in patients with tricuspid valve disease.

Aims: To evaluate coronary sinus single-site (CSSS) left ventricular pacing in adult patients with normal left ventricular ejection fraction (LVEF) when traditional right ventricular lead implantation is not feasible or is contraindicated. Methods and results: We performed a retrospective analysis of 23 patients with tricuspid valve surgery/disease who received a CSSS ventricular pacing lead to avoid crossing the tricuspid valve. Two matched control populations were obtained from patients receiving (i) conventional right ventricular single-site (RVSS) leads and (ii) coronary sinus leads for cardiac resynchronization therapy (CSCRT). Main outcomes of interest were lead stability, electrical lead parameters and change in LVEF during long-term follow-up. Successful CSSS pacing was accomplished in all 23 patients without any procedural complications. During the 5.3 ± 2.8-year follow-up 22/23 (95.7%) leads were functional with stable pacing and sensing parameters, and 1/23 (4.3%) was extracted for unrelated reasons. Compared to CSSS leads, the lead revision/abandonment was similar with RVSS leads (Hazard ratio (HR) 0.87, 95% confidence interval (CI) 0.03, 22.0), but was higher with CSCRT leads (HR 7.41, 95% CI 1.30, 139.0). There was no difference in change in LVEF between CSSS and RVSS groups (-2.4 ± 11.0 vs. 1.5 ± 12.8, P = 0.76), but LVEF improved in CSCRT group (11.2 ± 16.5%, P = 0.002). Fluoroscopy times were longer during implantation of CSSS compared to RVSS leads (25.6 ± 24.6 min vs. 12.3 ± 18.6 min, P = 0.049). Conclusion: In patients with normal LVEF, single-site ventricular pacing via the coronary sinus is a feasible, safe and reliable alternative to right ventricular pacing.

Management of cardiac implantable electronic devices during interventional pulmonology procedures.

An increasing number of patients are receiving cardiac implantable electronic devices (CIED) now. Many of them need pulmonary procedures for various indications including, but not limited to, lung cancer and benign endobronchial lesions. Over the last two decades, interventional pulmonology (IP) has expanded its scope to include various modalities that use heat and electrical energy and in the process, create electromagnetic field in the vicinity. This raises concerns for electromagnetic interference (EMI) causing abnormal behavior in the CIEDs. While guidelines and recommendations on the peri-procedural management of CIEDs do exist, none of them directly address the pulmonary procedures. In this paper, we strive to review the available literature pertaining to the management of CIEDs in the context of EMI caused by the various IP procedures.

Noninvasive Cardiac Radiation for Ablation of Ventricular Tachycardia.

BACKGROUND: Recent advances have enabled noninvasive mapping of cardiac arrhythmias with electrocardiographic imaging and noninvasive delivery of precise ablative radiation with stereotactic body radiation therapy (SBRT). We combined these techniques to perform catheter-free, electrophysiology-guided, noninvasive cardiac radioablation for ventricular tachycardia. METHODS: We targeted arrhythmogenic scar regions by combining anatomical imaging with noninvasive electrocardiographic imaging during ventricular tachycardia that was induced by means of an implantable cardioverter-defibrillator (ICD). SBRT simulation, planning, and treatments were performed with the use of standard techniques. Patients were treated with a single fraction of 25 Gy while awake. Efficacy was assessed by counting episodes of ventricular tachycardia, as recorded by ICDs. Safety was assessed by means of serial cardiac and thoracic imaging. RESULTS: From April through November 2015, five patients with high-risk, refractory ventricular tachycardia underwent treatment. The mean noninvasive ablation time was 14 minutes (range, 11 to 18). During the 3 months before treatment, the patients had a combined history of 6577 episodes of ventricular tachycardia. During a 6-week postablation "blanking period" (when arrhythmias may occur owing to postablation inflammation), there were 680 episodes of ventricular tachycardia. After the 6-week blanking period, there were 4 episodes of ventricular tachycardia over the next 46 patient-months, for a reduction from baseline of 99.9%. A reduction in episodes of ventricular tachycardia occurred in all five patients. The mean left ventricular ejection fraction did not decrease with treatment. At 3 months, adjacent lung showed opacities consistent with mild inflammatory changes, which had resolved by 1 year. CONCLUSIONS: In five patients with refractory ventricular tachycardia, noninvasive treatment with electrophysiology-guided cardiac radioablation markedly reduced the burden of ventricular tachycardia. (Funded by Barnes-Jewish Hospital Foundation and others.).

Pulmonary embolism in patients with transvenous cardiac implantable electronic device leads.

BACKGROUND: Cardiac implantable electronic devices (CIEDs) are commonly associated with transvenous lead-related thrombi that can cause pulmonary embolism (PE). METHODS AND RESULTS: We retrospectively evaluated all patients with transvenous CIED leads implanted at Mayo Clinic Rochester between 1 January 2000, and 25 October 2010. Pulmonary embolism outcomes during follow-up were screened using diagnosis codes and confirmed with imaging study reports. Of 5646 CIED patients (age 67.3 ± 16.3 years, 64% men, mean follow-up 4.69 years) 88 developed PE (1.6%), incidence 3.32 [95% confidence interval (CI) 2.68-4.07] per 1000 person-years [men: 3.04 (95% CI 2.29-3.96) per 1000 person-years; women: 3.81 (95% CI 2.72-5.20) per 1000 person-years]. Other than transvenous CIED lead(s), 84% had another established risk factor for PE such as deep vein thrombosis (28%), recent surgery (27%), malignancy (25%), or prior history of venous thromboembolism (15%). At the time of PE, 22% had been hospitalized for ≥ 48 h, and 59% had been hospitalized in the preceding 30 days. Pulmonary embolism occurred in 22% despite being on systemic anticoagulation therapy. Out of 88 patients with PE, 45 subsequently died, mortality rate 93 (95% CI 67-123) per 1000 person-years (hazard ratio 2.0, 95% CI 1.5-2.7, P < 0.0001). CONCLUSIONS: Though lead-related thrombus is commonly seen in patients with transvenous CIED leads, clinical PE occurs with a low incidence. It is possible that embolism of lead thrombus is uncommon or emboli are too small to cause consequential pulmonary infarction.

Trends in Use and Adverse Outcomes Associated with Transvenous Lead Removal in the United States.

BACKGROUND: Transvenous lead removal (TLR) has made significant progress with respect to innovation, efficacy, and safety. However, limited data exist regarding trends in use and adverse outcomes outside the centers of considerable experience for TLR. The aim of our study was to examine use patterns, frequency of adverse events, and influence of hospital volume on complications. METHODS AND RESULTS: Using the Nationwide Inpatient Sample, we identified 91 890 TLR procedures. We investigated common complications including pericardial complications (hemopericardium, cardiac tamponade, or pericardiocentesis), pneumothorax, stroke, vascular complications (consisting of hemorrhage/hematoma, incidents requiring surgical repair, and accidental arterial puncture), and in-hospital deaths described with TLR, defining them by the validated International Classification of Diseases, Ninth Revision, Clinical Modification diagnosis code. We specifically assessed in-hospital death (2.2%), hemorrhage requiring transfusion (2.6%), vascular complications (2.0%), pericardial complications (1.4%), open heart surgery (0.2%), and postoperative respiratory failure (2.4%). Independent predictors of complications were female sex and device infections. Hospital volume was not independently associated with higher complications. There was a significant rise in overall complication rates over the study period. CONCLUSIONS: The overall complication rate in patients undergoing TLR was higher than previously reported. Female sex and device infections are associated with higher complications. Hospital volume was not associated with higher complication rates. The number of adverse events in the literature likely underestimates the actual number of complications associated with TLR.

Effects on repolarization using dynamic QT interval monitoring in long-QT patients following left cardiac sympathetic denervation.

BACKGROUND: Videoscopic left cardiac sympathetic denervation (LCSD) is an adjunct therapy for reduction of arrhythmia-induced events in patients with long-QT syndrome (LQTS). LCSD reduces LQTS-triggered breakthrough cardiac events. The temporal effects of QTc changes post-LCSD have not been studied. METHODS: We utilized continuous QTc monitoring on 72 patients with LQTS. We evaluated acute and long-term QTc changes in comparison to 12-lead ECG-derived QTc values prior to surgery, 24 hours postsurgery, and at follow up ≥3 months. RESULTS: Seventy-two patients underwent LCSD at our institution (46% male, mean age at LCSD was 14 ± 10 years). The mean baseline, pre-LCSD QTc was 505 ± 56 ms, which had decreased significantly at ≥3 months post-LCSD to 491 ± 40 ms (P = 0.001). QTc monitoring revealed that the majority of the cohort (53/72; 74%) had a transient increase >30 ms in QTc from baseline, with an average maximum increase of 72 ± 30 ms. Resolution within 10 ms of baseline or less occurred in 57% (30/53) at 24 hours post-LCSD. CONCLUSIONS: Although LQTS patients may have a paradoxically increased QTc post-LCSD, the effects are transient in most patients. Importantly, no patients experienced any arrhythmias in the postoperative setting related to this transient rise in QTc.

Decreased postoperative atrial fibrillation following cardiac transplantation: the significance of autonomic denervation.

BACKGROUND: Endocardial ablation approaches targeting the retroatrial cardiac ganglia to treat atrial fibrillation (AF) have been proposed. However, the potential value using this approach is unknown. Disruption of the autonomic inputs with orthotropic heart transplant (OHT) provides a unique opportunity to study the effects of autonomic innervation on AF genesis and maintenance. We hypothesized that due to denervation, the risk of postoperative AF would be lower following OHT compared to surgical maze even though both groups get isolation of the pulmonary veins. METHODS AND RESULTS: We reviewed 155 OHTs (mean age 52 ± 11 years, 72% males) and used 1:1 age-, sex-, and date-of-surgery-matched two control groups from patients undergoing surgical maze or only coronary artery bypass grafting (CABG). Using conditional logistic regression we compared the odds of AF within 2 weeks following OHT versus controls. Postoperative AF occurred in 10/155 (6.5%) OHT patients. The conditional odds of postoperative AF were lower for OHT as compared to controls (vs maze: odds ratio [OR] 0.27 [95% confidence interval (CI) 0.13-0.57], vs CABG: OR 0.38 [0.17-0.81], P = 0.003; and on additional adjustment for left atrial enlargement, vs maze: OR 0.28 [0.13-0.60], vs CABG: OR 0.14 [0.04-0.47], P = 0.0009). CONCLUSIONS: Risk of postoperative AF is significantly lower with OHT as in comparison to surgical maze. As both surgeries entail isolation of the pulmonary veins but only OHT causes disruption of autonomic innervation, this observation supports a mechanistic role of autonomic nervous system in AF. The benefit of targeting the cardiac autonomic system to treat AF needs further investigation.

Impact of radiocontrast use during left ventricular pacemaker lead implantation for cardiac resynchronization therapy.

AIMS: The risk of contrast-induced nephropathy (CIN) with radiocontrast use during left ventricular (LV) lead placement for cardiac resynchronization therapy (CRT) is unknown. It is unclear as to whether minimizing contrast use impacts adequacy of LV lead placement. METHODS AND RESULTS: A retrospective analysis was performed of all LV leads placed for CRT at Mayo Clinic, Rochester, MN from 16 March 2001 to 1 April 2009. The primary goal was to assess risk of CIN and adequacy of lead placement depending on the amount of contrast administered during CRT placement. Contrast-induced nephropathy was defined as a ≥25% increase in serum creatinine ≥48 h post-procedurally. Adequacy of lead placement was assessed in a blinded fashion by review of procedural fluoroscopic and post-procedural radiographic images. Eight hundred and twenty-two subjects were divided based on the amount of procedural contrast used into tertile 1 (<55 mL, 257 patients), tertile 2 (55-94 mL, 261 patients), and tertile 3 (≥95 mL, 304 patients). Contrast-induced nephropathy occurred in 5.4% of patients in tertile 1, 5.4% in tertile 2 and 11.8% in tertile 3 (P = 0.004). Among the tertiles, lead positioning was optimal in 95, 80 and 66%, respectively (P < 0.0001). Fluoroscopic time was 34 ± 23, 42 ± 26, and 48 ± 30 min in tertiles 1, 2, and 3 (P < 0.0001). CONCLUSION: Risk of CIN with CRT implantations was substantial. Increased volume of radiocontrast used for LV lead placement was associated with substantially increased risk of CIN. Minimal contrast use was associated with decreased procedural times without adverse impact on adequacy of lead placement.

Embolic strokes after peripherally inserted central catheter placement.

Peripherally inserted central catheters (PICCs) have become popular for a range of indications in both inpatient and outpatient settings. Though PICCs are generally safe, they can be associated with a variety of complications. We present here a case with embolic strokes due to inadvertent arterial placement of PICC, an uncommon but potentially life-threatening complication. A high clinical suspicion with critical evaluation of radiographs is indispensable for suspecting misplaced PICCs.

Association of serum osteoprotegerin with left ventricular mass in African American adults with hypertension.

BACKGROUND: African-Americans with hypertension are susceptible to left ventricular hypertrophy (LVH). Serum osteoprotegerin level has been reported to be associated with LVH. We investigated the association of osteoprotegerin with LV mass (LVM) in 898 African-Americans with hypertension (mean age 65 years, 71% women). METHODS: Osteoprotegerin levels were measured in serum by an immunoassay and log-transformed for analyses. LVM index (LVMi; LVM/height(2.7)) was estimated using M-mode echocardiography. Linear regression analyses using generalized estimating equations were used to assess the association of osteoprotegerin with LVMi. RESULTS: Serum osteoprotegerin was correlated with LVMi (r = 0.21; P < 0.0001), an estimated increase in LVMi of 5.05 (95% confidence interval 2.93, 7.17) g/m(2.7) in the highest compared to the lowest osteoprotegerin quartile. This association remained statistically significant after adjustment for conventional cardiovascular risk factors (age, sex, body mass index (BMI), history of smoking, diabetes, systolic blood pressure (BP), total and high-density lipoprotein cholesterol), estimated renal function, history of myocardial infarction and stroke, lifestyle factors (physical activity score, years of education, amount of alcohol consumption), medications (aspirin, antihypertensives, statins, estrogens), and C-reactive protein (CRP) (P = 0.02). Additionally, osteoprotegerin was correlated with early/atrial (E/A) ratio (r = -0.16; P < 0.0001), LV mean wall thickness (r = 0.17; P < 0.0001) and relative wall thickness (r = 0.14; P < 0.0001) but not ejection fraction (r = 0.04; P = 0.24) or internal end-diastolic dimension (r = 0.02; P = 0.60). CONCLUSION: In African-Americans with hypertension, a higher serum osteoprotegerin level is weakly but independently associated with a higher LVM.