Artificial intelligence cloud platform improves arrhythmia detection from insertable cardiac monitors to 25 cardiac rhythm patterns through multi-label classification.

BACKGROUND: Electrocardiogram (ECG) is the gold standard for the diagnosis of cardiac arrhythmias and other heart diseases. Insertable cardiac monitors (ICMs) have been developed to continuously monitor cardiac activity over long periods of time and to detect 4 cardiac patterns (atrial tachyarrhythmias, ventricular tachycardia, bradycardia, and pause). However, interpretation of ECG or ICM subcutaneous ECG (sECG) is time-consuming for clinicians. Artificial intelligence (AI) classifies ECG and sECG with high accuracy in short times. OBJECTIVE: To demonstrate whether an AI algorithm can expand ICM arrhythmia recognition from 4 to many cardiac patterns. METHODS: We performed an exploratory retrospective study with sECG raw data coming from 20 patients wearing a Confirm Rx™ (Abbott, Sylmar, USA) ICM. The sECG data were recorded in standard conditions and then analyzed by AI (Willem™, IDOVEN, Madrid, Spain) and cardiologists, in parallel. RESULTS: In nineteen patients, ICMs recorded 2261 sECGs in an average follow-up of 23 months. Within these 2261 sECG episodes, AI identified 7882 events and classified them according to 25 different cardiac rhythm patterns with a pondered global accuracy of 88%. Global positive predictive value, sensitivity, and F1-score were 86.77%, 83.89%, and 85.52% respectively. AI was especially sensitive for bradycardias, pauses, rS complexes, premature atrial contractions, and inverted T waves, reducing the median time spent to classify each sECG compared to cardiologists. CONCLUSION: AI can process sECG raw data coming from ICMs without previous training, extending the performance of these devices and saving cardiologists' time in reviewing cardiac rhythm patterns detection.

Avoiding unnecessary ventricular pacing is associated with reduced incidence of heart failure hospitalizations and persistent atrial fibrillation in pacemaker patients.

AIMS: In bradycardia patients treated with dual-chamber pacing, we aimed to evaluate whether pacing with atrioventricular (AV) delay management [AV hysteresis (AVH)], compared with standard pacing with fixed AV delays, reduces unnecessary ventricular pacing percentage (VPP) and is associated with better clinical outcomes. Main study endpoints were the incidence of heart failure hospitalizations (HFH), persistent atrial fibrillation (AF), and cardiac death. METHODS AND RESULTS: Data from two identical prospective observational studies, BRADYCARE I in the USA and BRADYCARE II in Europe, Africa, and Asia, were pooled. Overall, 2592 patients (75 ± 10 years, 45.1% female, 50% with AVH) had complete clinical and device data at 1-year follow-up and were analysed. Primary pacing indication was sinus node disease (SND) in 1177 (45.4%), AV block (AVB) in 974 (37.6%), and other indications in 441 (17.0%) patients. Pacing with AVH, compared with standard pacing, was associated with a lower 1-year incidence of HFH [1.3% vs. 3.1%, relative risk reduction (RRR) 57.5%, P = 0.002] and of persistent AF (5.3% vs. 7.7%, RRR = 31.1%, P = 0.028). Cardiac mortality was not different between groups (1.0% vs. 1.4%, RRR = 27.8%, P = 0.366). Pacing with AVH, compared with standard pacing, was associated with a lower (P < 0.001) median VPP in all patients (7% vs. 75%), in SND (3% vs. 44%), in AVB (25% vs. 98%), and in patients with other pacing indications (3% vs. 47%). CONCLUSION: Cardiac pacing with AV delay management via AVH is associated with reduced 1-year incidence of HFH and persistent AF, most likely due to a reduction in VPP compared to standard pacing.

Artificial intelligence augments detection accuracy of cardiac insertable cardiac monitors: Results from a pilot prospective observational study.

Background: Insertable cardiac monitors (ICMs) are indicated for long-term monitoring of patients with unexplained syncope or who are at risk for cardiac arrhythmias. The volume of ICM-transmitted information may result in long data review times to identify true and clinically relevant arrhythmias. Objective: The purpose of this study was to evaluate whether artificial intelligence (AI) may improve ICM detection accuracy. Methods: We performed a retrospective analysis of consecutive patients implanted with the Confirm RxTM ICM (Abbott) and followed in a prospective observational study. This device continuously monitors subcutaneous electrocardiograms (SECGs) and transmits to clinicians information about detected arrhythmias and patient-activated symptomatic episodes. All SECGs were classified by expert electrophysiologists and by the WillemTM AI algorithm (IDOVEN). Results: During mean follow-up of 23 months, of 20 ICM patients (mean age 68 ± 12 years; 50% women), 19 had 2261 SECGs recordings associated with cardiac arrhythmia detections or patient symptoms. True arrhythmias occurred in 11 patients: asystoles in 2, bradycardias in 3, ventricular tachycardias in 4, and atrial tachyarrhythmias (atrial tachycardia/atrial fibrillation [AT/AF]) in 10; with 6 patients having >1 arrhythmia type. AI algorithm overall accuracy for arrhythmia classification was 95.4%, with 97.19% sensitivity, 94.52% specificity, 89.74% positive predictive value, and 98.55% negative predictive value. Application of AI would have reduced the number of false-positive results by 98.0% overall: 94.0% for AT/AF, 87.5% for ventricular tachycardia, 99.5% for bradycardia, and 98.8% for asystole. Conclusion: Application of AI to ICM-detected episodes is associated with high classification accuracy and may significantly reduce health care staff workload by triaging ICM data.

A new interpretation of nonpulmonary vein substrates of the left atrium in patients with atrial fibrillation.

BACKGROUND: Substrate analysis of the left atrium in patients undergoing atrial fibrillation ablation has limitations when performed by means of simple bipolar acquisition. OBJECTIVE: To evaluate the incidence of low-voltage zones (LVZs) through maps constructed by means of various catheters: multipolar (MC), omnipolar (OC), and circular catheters (CMCs) with the 3D electro-anatomical systems (3d-S) CARTO3 and EnSite Precision. METHODS: To assess LVZs, we acquired maps by means of CMC and MC in the voltage range 0.05-0.5 mV in 70 consecutive patients in sinus rhythm. In the case of OC only, we made an intra-patient comparison of bipolar maps constructed by means of the along and across, and HD-Wave configurations of the EnSite 3d-S in the ranges of 0.05-0.5 and 0.5-1.0 mV. On the basis of this comparison, we chose the range that best identified LVZs as a set of different colors (SDC) compatible with patchy fibrosis (qualitative analysis). Subsequently, we detected the voltage values corresponding to purple and gray points, close to SDC, and the value inside corresponding to blue, green, and red colors, and we evaluated the color change in other voltage ranges. Finally, we performed a quantitative analysis of LVZs by applying the qualitative characteristics described above. RESULTS: On the basis of our settings, for OC, the optimal range identifying LVZs was 0.3-0.6 mV. OC revealed smaller LVZs than MC (P < .05 or P < .001), except in the lateral wall. No significant differences were observed between CMCs. CONCLUSIONS: In our experience, OC does not present the limits of bipolar HD maps, though further studies are needed in order to confirm that 0.3-0.6 mV is the optimal voltage range within which to identify LVZs.

Efficacy and safety of catheter ablation of atrioventricular nodal re-entrant tachycardia by means of flexible-tip irrigated catheters.

PURPOSE: Irrigated-tip ablation catheters increase safety and efficacy of ablation procedures, but their use in atrioventricular nodal re-entrant tachycardia (AVNRT) ablation has not been systematically evaluated. The aim of this study is to evaluate the safety and efficacy of radiofrequency (RF) catheter ablation of AVNRT by means of the novel flexible-tip open-irrigated catheter FlexAbility™ and a 3D electroanatomic mapping (EAM) system. METHODS: This is a single-center and single-operator study on 80 patients referred for AVNRT catheter ablation. Outcome included acute and long-term procedural success as well as complications reported over a median follow-up of 19 months (interquartile range 6-24 months). RESULTS: Acute success was achieved in all 80 patients. One procedure-related major complication, involving the vascular access, occurred. Mean fluoroscopy time was 106 ± 71 s. One patient (1.2%) suffered long-term AVNRT recurrence. Five patients (6.2%) underwent ablation for AVNRT combined with ablation for other clinical arrhythmias. CONCLUSIONS: Irrigated RF ablation of AVNRT by means of the novel flexible-tip open-irrigated catheter associated to 3D EAM system is effective and safe. Success rates are comparable to those of other techniques. Complication rate is very low.

Economic analysis of remote monitoring of cardiac implantable electronic devices: Results of the Health Economics Evaluation Registry for Remote Follow-up (TARIFF) study.

BACKGROUND: Remote monitoring (RM) of cardiac implantable electronic devices has been demonstrated to improve outpatient clinic workflow and patient management. However, few data are available on the socioeconomic impact of RM. OBJECTIVE: The aim of this study was to assess the costs and benefits of RM compared with standard care (SC). METHODS: We used 12-month patient data from the Health Economics Evaluation Registry for Remote Follow-up (TARIFF) study (N = 209; RM: n = 102 (48.81%); SC: n = 107 (51.19%)). Cost comparison was made from 2 perspectives: the health care system (HCS) and patients. The use of health care resources was defined on the basis of hospital clinical folders. Out-of-pocket expenses were reported directly by patients. RESULTS: HCS perspective: The overall mean annual cost per patient in the SC group (€1044.89 ± €1990.47) was significantly higher than in the RM group (€482.87 ± €2488.10) (P < .0001), with a reduction of 53.87% being achieved in the RM group. The primary driver of cost reduction was the cost of cardiovascular hospitalizations (SC: €`886.67 ± €1979.13 vs RM: €432.34 ± €2488.10; P = .0030). Patient and caregiver perspective: The annual cost incurred by patients was significantly higher in the SC group than in the RM group (SC: €169.49 ± €189.50 vs RM: €56.87 ± €80.22; P < .0001). Patients' quality-adjusted life-years were not significantly different between the groups. Provider perspective: The total number of inhospital device follow-up visits was reduced by 58.78% in the RM group. CONCLUSION: RM of patients with cardiac implantable electronic devices (CIEDs) is cost saving from the perspectives of the HCS, patients, and caregivers. Introducing appropriate reimbursements will make RM sustainable even for the provider, i.e. the hospitals which provide the service and encourage widespread adoption of RM.

Hospitalization rates and associated cost analysis of cardiac resynchronization therapy with an implantable defibrillator and quadripolar vs. bipolar left ventricular leads: a comparative effectiveness study.

AIMS: This study compares, from a prospective, observational, non-randomized registry, the post-implant hospitalization rates and associated healthcare resource utilization of cardiac resynchronization therapy-defibrillator (CRT-D) patients with quadripolar (QUAD) vs. bipolar (BIP) left ventricular (LV) leads. METHODS AND RESULTS: Between January 2009 and December 2012, 193 consecutive patients receiving de novo CRT-D implants with either a QUAD (n = 116) or a BIP (n = 77) LV lead were enrolled at implant and followed until July 2013 at a single-centre, university hospital. Post-implant hospitalizations related to heart failure (HF) or LV lead surgical revision and associated payer costs were identified using ICD-9-CM diagnosis and procedure codes. Italian national reimbursement rates were determined. Propensity scores were estimated using a logistic regression model based upon 11 pre-implant baseline characteristics and were used to derive a 1 : 1 matched cohort of QUAD (n = 77) and BIP (n = 77) patients. Hospitalization rates for the two groups were compared using negative binomial regression and associated payer costs were compared using non-parametric bootstrapping (×10 000) and one-sided hypothesis test. Hospitalization rates of the QUAD group [0.15/ patient (pt)-year] were lower than those of the BIP group (0.32/ pt-year); the incidence rate ratio was 0.46, P = 0.04. The hospitalization costs for the QUAD group (434 ± 128 €/pt-year) were lower than those for the BIP group (1136 ± 362 €/pt-year). The average difference was 718 €/pt-year, P = 0.016. CONCLUSIONS: In this comparative effectiveness assessment of well-matched groups of CRT-D patients with quadripolar and bipolar LV leads, QUAD patients experienced a lower rate of hospitalizations for HF and LV lead surgical revision, and a lower cost burden. This has important implications for LV pacing lead choice.

Impact of in-clinic follow-up visits in patients with implantable cardioverter defibrillators: demographic and socioeconomic analysis of the TARIFF study population.

PURPOSE: Remote monitoring of cardiac implantable electronic devices has been demonstrated to safely reduce frequency of hospital visits. Limited studies are available evaluating the economic impact. The aim of this article is to highlight the social impact and costs for the patients associated with hospital visits for routine device follow-up at the enrollment visit for the TARIFF study (NCT01075516). METHODS: TARIFF is a prospective, cohort, observational study designed to compare the costs and impact on quality of life between clinic-based and remote care device follow-up strategies. RESULTS: Two hundred nine patients (85.2 % males) were enrolled in the study; 153 patients (73.2 %) were retired, 36 (17.2 %) were active workers, 18 (8.6 %) were housewives, and 2 (1.0 %) were looking for a job. Among active workers, 63.9 % required time off from work to attend the hospital visit, while 67.0 % of all patients had to interrupt daily activities. The majority of patients spent half a day or more attending the visit. A carer accompanied 77 % of patients. Among carers, 36.6 % required time off from work, and 77.6 % had to interrupt daily activities. Median distance traveled was 36 km. The average cost of travel was 10 euros with 25 % of patients spending more than 30 euros. CONCLUSIONS: Data from patients enrolled in the TARIFF registry confirm that there are social and economic impacts to patients attending routine device checks in hospital which can be significantly reduced by using a remote monitoring strategy.

Rationale and design of the health economics evaluation registry for remote follow-up: TARIFF.

AIMS: The aims of the study are to develop a cost-minimization analysis from the hospital perspective and a cost-effectiveness analysis from the third payer standpoint, based on direct estimates of costs and QOL associated with remote follow-ups, using Merlin@home and Merlin.net, compared with standard ambulatory follow-ups, in the management of ICD and CRT-D recipients. METHODS AND RESULTS: Remote monitoring systems can replace ambulatory follow-ups, sparing human and economic resources, and increasing patient safety. TARIFF is a prospective, controlled, observational study aimed at measuring the direct and indirect costs and quality of life (QOL) of all participants by a 1-year economic evaluation. A detailed set of hospitalized and ambulatory healthcare costs and losses of productivity that could be directly influenced by the different means of follow-ups will be collected. The study consists of two phases, each including 100 patients, to measure the economic resources consumed during the first phase, associated with standard ambulatory follow-ups, vs. the second phase, associated with remote follow-ups. CONCLUSION: Remote monitoring systems enable caregivers to better ensure patient safety and the healthcare to limit costs. TARIFF will allow defining the economic value of remote ICD follow-ups for Italian hospitals, third payers, and patients. The TARIFF study, based on a cost-minimization analysis, directly comparing remote follow-up with standard ambulatory visits, will validate the cost effectiveness of the Merlin.net technology, and define a proper reimbursement schedule applicable for the Italian healthcare system. TRIAL REGISTRATION: NCT01075516.