Waks, Jonathan W.

Background: Pulmonary hypertension (PH) is a life-threatening disease affecting up to 1% of the global population. Diagnosis can be challenging and is often delayed due to the need for advanced imaging and invasive procedures. The use of artificial intelligence applied to ECGs (ECG-AI) has been shown to detect subtle patterns in voltage-time data and may be a valuable tool for the early detection of PH. Hypothesis and Purpose: To evaluate the performance of a previously trained, ECG-AI algorithm to detect PH (ECG-AI PH) using real-world data (RWD) collected in a multicenter, validation study. A joint primary hypothesis required sensitivity (Sn), specificity (Sp), positive predictive value (PPV), and negative predictive value (NPV) to exceed the null values of 76%, 70%, 10% and 90%. Study Design and Methods: This retrospective validation study was conducted at 5 geographically diverse U.S. health systems. Adult subjects were eligible for inclusion if they had a 12-lead ECG paired with an echocardiogram (Echo) in which tricuspid regurgitation velocity (TRV) was recorded, following presentation with dyspnea. Patients were classified according to echocardiographic criteria as either PH (PH+, TRV >3.4 m/s) or controls (PH-, TRV ≤2.8 m/s) to simulate the real-world use of ECG-AI, where a positive result could lead to a follow-up Echo. The study database was locked before processing the digital ECGs with ECG-AI PH. Performance was also estimated in a subset of subjects that later had a right heart catheterization using mPAP ≥ 20mmHg as the definition of PH. Results: A total of 14281 subjects (53% female, 63% aged 50+ years) met the inclusion criteria, including 3019 PH+ cases and 11262 PH- controls (Figure). Sn and Sp were 84.0% (95% CI: 82.6%, 85.3%) and 71.7% (95% CI: 70.9%, 72.6%), respectively. The positive and negative predictive values were 18.9% (95% CI: 18.4%, 19.4%) and 98.3% (95% CI: 98.1%, 98.4%), respectively, at 7.3% prevalence. Each endpoint met pre-defined performance criteria. In the subset of 1683 subjects with a follow up RHC, performance remained robust (Sn 85% (1155/1358); Sp 46% (151/325)). Conclusion: While ECG-AI PH was first developed as an investigational tool to detect PH, continued development as software as a medical device for clinical use demonstrated that the algorithm retained strong performance to detect PH in diverse, non-overlapping clinical settings and patient populations.

AbstractBackgroundRecipients of implantable cardioverter defibrillator (ICD) generator replacement with multiple medical comorbidities may be at higher risk of adverse outcomes that attenuate the benefit of ICD replacement. The aim of this investigation was to study the association between the Charlson comorbidity index (CCI) and outcomes after ICD generator replacement.MethodsAll patients undergoing first ICD generator replacement at Mayo Clinic, Rochester and Beth Israel Deaconess Medical Center, Boston between 2001 and 2011 were identified. Outcomes included: (a) all‐cause mortality, (b) appropriate ICD therapy, and (c) death prior to appropriate therapy. Multivariable Cox regression analysis was performed to assess association between CCI and outcomes.ResultsWe identified 1421 patients with mean age of 69.6 ± 12.1 years, 81% male and median (range) CCI of 3 (0‐18). During a mean follow‐up of 3.9 ± 3 years, 52% of patients died, 30.6% experienced an appropriate therapy, and 23.6% died without experiencing an appropriate therapy. In multivariable analysis, higher CCI score was associated with increased all‐cause mortality (Hazard ratio, HR 1.10 [1.06‐1.13] per 1 point increase in CCI, P < .001), death without prior appropriate therapy (HR 1.11 [1.07‐1.15], P < .0001), but not associated with appropriate therapy (HR 1.01 [0.97‐1.05], P = .53). Patients with CCI ≥5 had an annual risk of death of 12.2% compared to 8.7% annual rate of appropriate therapy.ConclusionsCCI is predictive of mortality following ICD generator replacement. The benefit of ICD replacement in patients with CCI score ≥5 should be investigated in prospective studies.

Background— The effectiveness of implantable cardioverter-defibrillators (ICDs) for primary prevention of sudden death in patients with an ejection fraction (EF) ≤35% and clinical heart failure is well established. However, outcomes after replacement of the ICD generator in patients with recovery of EF to >35% and no previous therapies are not well characterized. Methods and Results— Between 2001 and 2011, generator replacement was performed at 2 tertiary medical centers in 253 patients (mean age, 68.3±12.7 years; 82% men) who had previously undergone ICD placement for primary prevention but subsequently never received appropriate ICD therapy. EF had recovered to >35% in 72 of 253 (28%) patients at generator replacement. During median (quartiles) follow-up of 3.3 (1.8–5.3) years after generator replacement, 68 of 253 (27%) experienced appropriate ICD therapy. Patients with EF ≤35% were more likely to experience ICD therapy compared with those with EF >35% (12% versus 5% per year; hazard ratio, 3.57; P =0.001). On multivariable analysis, low EF predicted appropriate ICD therapy after generator replacement (hazard ratio, 1.96 [1.35–2.87] per 10% decrement; P =0.001). Death occurred in 25% of patients 5 years after generator replacement. Mortality was similar in patients with EF ≤35% and >35% (7% versus 5% per year; hazard ratio, 1.10; P =0.68). Atrial fibrillation (3.24 [1.63–6.43]; P <0.001) and higher blood urea nitrogen (1.28 [1.14–1.45] per increase of 10 mg/dL; P <0.001) were associated with mortality. Conclusions— Although approximately one fourth of patients with a primary prevention ICD and no previous therapy have EF >35% at the time of generator replacement, these patients continue to be at significant risk for appropriate ICD therapy (5% per year). These data may inform decisions on ICD replacement.

Background The decision to initially implant an implantable cardioverter-defibrillator (ICD) is informed by robust randomized controlled trials, but no such data exist to guide the decision to replace an ICD generator. In this study, we aimed to determine outcomes after ICD generator replacement. Methods All patients with ischemic or nonischemic cardiomyopathy who underwent ICD generator replacement from 2001 to 2011 at Mayo Clinic, MN, or Beth Israel Deaconess Medical Center, MA, were included. Outcomes included (1) appropriate therapy after generator replacement and (2) death before appropriate therapy after generator replacement. Cox proportional hazards modeling was used to determine the associations between patient characteristics and outcomes. Results In 1421 patients undergoing ICD generator replacement (mean±SD age 69.6±12.1 years, 81% male), appropriate therapy occurred after replacement in 435 patients (30.6%) over a mean follow-up of 2.7±2.6 years. Associated factors included lower left ventricular ejection fraction and history of appropriate therapy before generator replacement. Death before appropriate ICD therapy occurred in 336 (23.7%) patients. Older age, lower left ventricular ejection fraction, and noncardiac comorbidities, including diabetes mellitus, chronic lung disease, peripheral vascular disease, lower hemoglobin, and lower glomerular filtration rate, were associated with greater risk of death before appropriate therapy. A progressive increase in mortality was observed with aggregation of these noncardiac comorbidities. Conclusions The decision to replace the ICD should take into consideration not only left ventricular ejection fraction and history of ventricular arrhythmias, but also comorbid illnesses that may impact the duration and the quality of life.