Association Between Social Isolation With Age-Gap Determined by Artificial Intelligence-Enabled Electrocardiography.

Background: Loneliness and social isolation are associated with poor health outcomes such as an increased risk of cardiovascular diseases. Objectives: The authors aimed to explore the association between social isolation with biological aging which was determined by artificial intelligence-enabled electrocardiography (AI-ECG) as well as the risk of all-cause mortality. Methods: The study included adults aged ≥18 years seen at Mayo Clinic from 2019 to 2022 who respond to a survey for social isolation assessment and had a 12-lead ECG within 1 year of completing the questionnaire. Biological age was determined from ECGs using a previously developed and validated convolutional neural network (AI-ECG age). Age-Gap was defined as AI-ECG age minus chronological age, where positive values reflect an older-than-expected age. The status of social isolation was measured by the previously validated multiple-choice questions based on Social Network Index (SNI) with score ranges between 0 (most isolated) and 4 (least isolated). Results: A total of 280,324 subjects were included (chronological age 59.8 ± 16.4 years, 50.9% female). The mean Age-Gap was -0.2 ± 9.16 years. A higher SNI was associated with a lower Age-Gap (ß of SNI = 4 was -0.11; 95% CI: -0.22 to -0.01; P < 0.001, adjusted to covariates). Cox proportional hazard analysis revealed the association between social connection and all-cause mortality (HR for SNI = 4, 0.47; 95% CI: 0.43-0.5; P < 0.001). Conclusions: Social isolation is associated with accelerating biological aging and all-cause mortality independent of conventional cardiovascular risk factors. This observation underscores the need to address social connection as a health care determinant.

Mortality Risk Stratification Utilizing Artificial Intelligence Electrocardiogram for Hyperkalemia in Cardiac Intensive Care Unit Patients.

Background: Hyperkalemia has been associated with increased mortality in cardiac intensive care unit (CICU) patients. An artificial intelligence (AI) enhanced electrocardiogram (ECG) can predict hyperkalemia, and other AI-ECG algorithms have demonstrated mortality risk-stratification in CICU patients. Objectives: The authors hypothesized that the AI-ECG hyperkalemia algorithm could stratify mortality risk beyond laboratory serum potassium measurement alone. Methods: We included 11,234 unique Mayo Clinic CICU patients admitted from 2007 to 2018 with a 12-lead ECG and blood potassium (K) level obtained at admission with K ≥5 mEq/L defining hyperkalemia. ECGs underwent AI evaluation for the probability of hyperkalemia (probability >0.5 defined as positive). Hospital mortality was analyzed using logistic regression, and survival to 1 year was estimated using Kaplan-Meier and Cox analysis. Results: In the final cohort (n = 11,234), the mean age was 69.6 ± 10.5 years, 37.8% were females, and 92.4% were White. Chronic kidney disease was present in 20.2%. The mean laboratory potassium value for the cohort was 4.2 ± 0.3 mEq/L. The AI-ECG predicted hyperkalemia in 33.9% (n = 3,810) of CICU patients and 12.9% (n = 1,451) of patients had laboratory-confirmed hyperkalemia (K ≥5 mEq/L). In-hospital mortality increased in false-positive, false-negative, and true-positive patients, respectively (P < 0.001), and each of these patient groups had successively lower survival out to 1 year. Conclusions: AI-ECG-based prediction of hyperkalemia, even with a normal laboratory potassium value, was associated with higher in-hospital mortality and lower 1-year survival in CICU patients. This study demonstrated that AI-ECG probability of hyperkalemia may enable rapid individualized risk stratification in critically ill patients beyond laboratory value alone.

Artificial Intelligence-Enhanced Electrocardiography Identifies Patients With Normal Ejection Fraction at Risk of Worse Outcomes.

Background: An artificial intelligence (AI)-based electrocardiogram (ECG) model identifies patients with a higher likelihood of low ejection fraction (EF). Patients with an abnormal AI-ECG score but normal EF (false positives; FP) more often developed future low EF. Objective: The purpose of this study was to evaluate echocardiographic characteristics and all-cause mortality risk in FP patients. Methods: Patients with transthoracic echocardiography and ECG were classified retrospectively into FP, true negatives (TN) (EF ≥50%, normal AI-ECG), true positives (TP) (EF <50%, abnormal AI-ECG), or false negatives (FN) (EF <50%, normal AI-ECG). Echocardiographic abnormalities included systolic and diastolic left ventricular function, valve disease, estimated pulmonary pressures, and right heart parameters. Cox regression was used to assess factors associated with all-cause mortality. Results: Of 100,586 patients (median age 63 years; 45.5% females), 79% were TN, 7% FP, 5% FN, and 8% TP. FPs had more echocardiographic abnormalities than TN but less than FN or TP patients. An echocardiographic abnormality was present in 97% of FPs. Over median 2.7 years, FPs had increased mortality risk (age and sex-adjusted HR: 1.64 [95% CI: 1.55-1.73]) vs TN. Age and sex-adjusted mortality was higher in FP with abnormal echocardiography than FP with normal echocardiography and to TN regardless of echocardiography result; FP with normal echocardiography had comparable mortality risk to TN with abnormal echocardiography. Conclusions: FP patients were more likely than TNs to have echocardiographic abnormalities with 97% of exams showing an abnormality. FP patients had higher mortality rates, especially when their echocardiograms also had an abnormality; the concomitant use of AI ECG and echocardiography helps in stratifying risk in patients with normal LVEF.

Artificial intelligence guided screening for cardiomyopathies in an obstetric population: a pragmatic randomized clinical trial.

Nigeria has the highest reported incidence of peripartum cardiomyopathy worldwide. This open-label, pragmatic clinical trial randomized pregnant and postpartum women to usual care or artificial intelligence (AI)-guided screening to assess its impact on the diagnosis left ventricular systolic dysfunction (LVSD) in the perinatal period. The study intervention included digital stethoscope recordings with point of-care AI predictions and a 12-lead electrocardiogram with asynchronous AI predictions for LVSD. The primary end point was identification of LVSD during the study period. In the intervention arm, the primary end point was defined as the number of identified participants with LVSD as determined by a positive AI screen, confirmed by echocardiography. In the control arm, this was the number of participants with clinical recognition and documentation of LVSD on echocardiography in keeping with current standard of care. Participants in the intervention arm had a confirmatory echocardiogram at baseline for AI model validation. A total of 1,232 (616 in each arm) participants were randomized and 1,195 participants (587 intervention arm and 608 control arm) completed the baseline visit at 6 hospitals in Nigeria between August 2022 and September 2023 with follow-up through May 2024. Using the AI-enabled digital stethoscope, the primary study end point was met with detection of 24 out of 587 (4.1%) versus 12 out of 608 (2.0%) patients with LVSD (intervention versus control odds ratio 2.12, 95% CI 1.05-4.27; P = 0.032). With the 12-lead AI-electrocardiogram model, the primary end point was detected in 20 out of 587 (3.4%) versus 12 out of 608 (2.0%) patients (odds ratio 1.75, 95% CI 0.85-3.62; P = 0.125). A similar direction of effect was observed in prespecified subgroup analysis. There were no serious adverse events related to study participation. In pregnant and postpartum women, AI-guided screening using a digital stethoscope improved the diagnosis of pregnancy-related cardiomyopathy. ClinicalTrials.gov registration: NCT05438576.

Validation of Noninvasive Detection of Hyperkalemia by Artificial Intelligence-Enhanced Electrocardiography in High Acuity Settings.

Background: Artificial intelligence (AI) electrocardiogram (ECG) analysis can enable detection of hyperkalemia. In this validation, we assessed the algorithm's performance in two high acuity settings. Methods: An emergency department (ED) cohort (February to August 2021) and a mixed intensive care unit (ICU) cohort (August 2017 to February 2018) were identified and analyzed separately. For each group, pairs of laboratory-collected potassium and 12 lead ECGs obtained within 4 hours of each other were identified. The previously developed AI ECG algorithm was subsequently applied to leads 1 and 2 of the 12 lead ECGs to screen for hyperkalemia (potassium >6.0 mEq/L). Results: The ED cohort (N=40,128) had a mean age of 60 years, 48% were male, and 1% (N=351) had hyperkalemia. The area under the curve (AUC) of the AI-enhanced ECG (AI-ECG) to detect hyperkalemia was 0.88, with sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and positive likelihood ratio (LR+) of 80%, 80%, 3%, 99.8%, and 4.0, respectively, in the ED cohort. Low-eGFR (<30 ml/min) subanalysis yielded AUC, sensitivity, specificity, PPV, NPV, and LR+ of 0.83, 86%, 60%, 15%, 98%, and 2.2, respectively, in the ED cohort. The ICU cohort (N=2636) had a mean age of 65 years, 60% were male, and 3% (N=87) had hyperkalemia. The AUC for the AI-ECG was 0.88 and yielded sensitivity, specificity, PPV, NPV, and LR+ of 82%, 82%, 14%, 99%, and 4.6, respectively in the ICU cohort. Low-eGFR subanalysis yielded AUC, sensitivity, specificity, PPV, NPV, and LR+ of 0.85, 88%, 67%, 29%, 97%, and 2.7, respectively in the ICU cohort. Conclusions: The AI-ECG algorithm demonstrated a high NPV, suggesting that it is useful for ruling out hyperkalemia, but a low PPV, suggesting that it is insufficient for treating hyperkalemia.

Predictors of mortality by an artificial intelligence enhanced electrocardiogram model for cardiac amyloidosis.

AIMS: We aim to determine if our previously validated, diagnostic artificial intelligence (AI) electrocardiogram (ECG) model is prognostic for survival among patients with cardiac amyloidosis (CA). METHODS: A total of 2533 patients with CA (1834 with light chain amyloidosis (AL), 530 with wild-type transthyretin amyloid protein (ATTRwt) and 169 with hereditary transthyretin amyloid (ATTRv)] were included. An amyloid AI ECG (A2E) score was calculated for each patient reflecting the likelihood of CA. CA stage was calculated using the European modification of the Mayo 2004 criteria for AL and Mayo stage for transthyretin amyloid (ATTR). Risk of death was modelled using Cox proportional hazards, and Kaplan-Meier was used to estimate survival. RESULTS: Median age of the cohort was 67 [inter-quartile ratio (IQR) 59, 74], and 71.6% were male. The median overall survival for the cohort was 35.6 months [95% confidence interval (CI) 32.3, 39.5]. For AL, ATTRwt and ATTRv, respectively, median survival was 22.9 (95% CI 19.2, 28.2), 47.2 (95% CI 43.4, 52.3) and 61.4 (95% CI 48.7, 75.9) months. On univariate analysis, an increasing A2E score was associated with more than a two-fold risk of all-cause death. On multivariable analysis, the A2E score retained its importance with a risk ratio of 2.0 (95% CI 1.58, 2.55) in the AL group and 2.7 (95% CI 1.81, 4.24) in the ATTR group. CONCLUSIONS: Among patients with AL and ATTR amyloidosis, the A2E model helps to stratify risk of CA and adds another dimension of prognostication.

Thirty-Day High-Grade Aortic Valve Block Post-Transcatheter Aortic Valve Replacement in Patients Discharged on Heart Rhythm Monitor.

Background: Conduction disease is an important and common complication post-transcatheter aortic valve replacement (TAVR). Previously, we developed a conduction disease risk stratification and management protocol post-TAVR. This study aims to evaluate high-grade aortic valve block (HAVB) incidence and risk factors in a large cohort undergoing ambulatory cardiac monitoring post-TAVR according to conduction risk grouping. Methods: This single-center, retrospective study evaluated all patients discharged on ambulatory cardiac monitoring between 2016 and 2021 and stratified them into 3 groups based on electrocardiogram predictors of HAVB risk (group 1 [low], group 2 [intermediate], and group 3 [high]). HAVB was defined as ≥2 consecutive nonconducted P waves in sinus rhythm or bradycardia <50 beats/minute with a fixed rate for atrial fibrillation/flutter. Descriptive statistics were used to show the incidence and timeline, while logistic regression was utilized to evaluate predictors of HAVB. Results: Five hundred twenty-eight patients were included (median age 80 years [74-85]; 43.8% female). Forty-one patients (7.8%) developed HAVB during ambulatory monitoring (68% were asymptomatic). Over a median follow-up of 2 years (1.3-2.7), the overall mortality rate was 15.0% (30-day mortality rate of 0.57%, n = 3). Risk factors for HAVB were male sex (odds ratio [OR] = 2.46, p = 0.02, 95% CI = 1.21-5.43), baseline right bundle branch block (OR = 2.80, p = 0.01, 95% CI = 1.17-6.19), and post-TAVR QRS >150 â€‹ms (OR = 2.16, p = 0.03, 95% CI = 1.01-4.40). The negative predictive value for patients in groups 1 and 2 for 30-day HAVB was 95.0 and 93.8%, respectively. Conclusions: The risk of 30-day HAVB post-TAVR on ambulatory monitoring post-TAVR varies according to post-TAVR electrocardiogram findings, and a 3-group algorithm effectively identifies groups with a low negative predictive value for HAVB.

Performance of AI-Enabled Electrocardiogram in the Prediction of Metabolic Dysfunction-Associated Steatotic Liver Disease.

BACKGROUND AND AIMS: Accessible noninvasive screening tools for metabolic dysfunction-associated steatotic liver disease (MASLD) are needed. We aim to explore the performance of a deep learning-based artificial intelligence (AI) model in distinguishing the presence of MASLD using 12-lead electrocardiogram (ECG). METHODS: This is a retrospective study of adults diagnosed with MASLD in Olmsted County, Minnesota, between 1996 and 2019. Both cases and controls had ECGs performed within 6 years before and 1 year after study entry. An AI-based ECG model using a convolutional neural network was trained, validated, and tested in 70%, 10%, and 20% of the cohort, respectively. External validation was performed in an independent cohort from Mayo Clinic Enterprise. The primary outcome was the performance of ECG to identify MASLD, alone or when added to clinical parameters. RESULTS: A total of 3468 MASLD cases and 25,407 controls were identified. The AI-ECG model predicted the presence of MASLD with an area under the curve (AUC) of 0.69 (original cohort) and 0.62 (validation cohort). The performance was similar or superior to age- and sex-adjusted models using body mass index (AUC, 0.71), presence of diabetes, hypertension or hyperlipidemia (AUC, 0.68), or diabetes alone (AUC, 0.66). The model combining ECG, age, sex, body mass index, diabetes, and alanine aminotransferase had the highest AUC: 0.76 (original) and 0.72 (validation). CONCLUSIONS: This is a proof-of-concept study that an AI-based ECG model can detect MASLD with a comparable or superior performance as compared with the models using a single clinical parameter but not superior to the combination of clinical parameters. ECG can serve as another screening tool for MASLD in the nonhepatology space.

Artificial intelligence enabled interpretation of ECG images to predict hematopoietic cell transplantation toxicity.

ABSTRACT: Artificial intelligence (AI)-enabled interpretation of electrocardiogram (ECG) images (AI-ECGs) can identify patterns predictive of future adverse cardiac events. We hypothesized that such an approach would provide prognostic information for the risk of cardiac complications and mortality in patients undergoing hematopoietic cell transplantation (HCT). We retrospectively subjected ECGs obtained before HCT to an externally trained, deep-learning model designed to predict the risk of atrial fibrillation (AF). Included were 1377 patients (849 autologous [auto] HCT and 528 allogeneic [allo] HCT recipients). The median follow-up was 2.9 years. The 3-year cumulative incidence of AF was 9% (95% confidence interval [CI], 7-12) in patients who underwent auto HCT and 13% (10%-16%) in patients who underwent allo HCT. In the entire cohort, pre-HCT AI-ECG estimate of AF risk correlated highly with the development of clinical AF (hazard ratio [HR], 7.37; 95% CI, 3.53-15.4; P < .001), inferior survival (HR, 2.4; 95% CI, 1.3-4.5; P = .004), and greater risk of nonrelapse mortality (NRM; HR, 95% CI, 3.36; 1.39-8.13; P = .007), without increased risk of relapse. Association with mortality was only noted in allo HCT recipients, where the risk of NRM was greater. The use of cyclophosphamide after transplantation resulted in greater 90-day incidence of AF (13% vs 5%; P = .01) compared to calcineurin inhibitor-based graft-versus-host disease prophylaxis, corresponding to temporal changes in AI-ECG AF prediction after HCT. In summary, AI-ECG can inform risk of posttransplant cardiac outcomes and survival in HCT patients and represents a novel strategy for personalized risk assessment.

Artificial intelligence in cardiovascular medicine: clinical applications.

Clinical medicine requires the integration of various forms of patient data including demographics, symptom characteristics, electrocardiogram findings, laboratory values, biomarker levels, and imaging studies. Decision-making on the optimal management should be based on a high probability that the envisaged treatment is appropriate, provides benefit, and bears no or little potential harm. To that end, personalized risk-benefit considerations should guide the management of individual patients to achieve optimal results. These basic clinical tasks have become more and more challenging with the massively growing data now available; artificial intelligence and machine learning (AI/ML) can provide assistance for clinicians by obtaining and comprehensively preparing the history of patients, analysing face and voice and other clinical features, by integrating laboratory results, biomarkers, and imaging. Furthermore, AI/ML can provide a comprehensive risk assessment as a basis of optimal acute and chronic care. The clinical usefulness of AI/ML algorithms should be carefully assessed, validated with confirmation datasets before clinical use, and repeatedly re-evaluated as patient phenotypes change. This review provides an overview of the current data revolution that has changed and will continue to change the face of clinical medicine radically, if properly used, to the benefit of physicians and patients alike.

Artificial intelligence-based screening for cardiomyopathy in an obstetric population: A pilot study.

Background: Cardiomyopathy is a leading cause of pregnancy-related mortality and the number one cause of death in the late postpartum period. Delay in diagnosis is associated with severe adverse outcomes. Objective: To evaluate the performance of an artificial intelligence-enhanced electrocardiogram (AI-ECG) and AI-enabled digital stethoscope to detect left ventricular systolic dysfunction in an obstetric population. Methods: We conducted a single-arm prospective study of pregnant and postpartum women enrolled at 3 sites between October 28, 2021, and October 27, 2022. Study participants completed a standard 12-lead ECG, digital stethoscope ECG and phonocardiogram recordings, and a transthoracic echocardiogram within 24 hours. Diagnostic performance was evaluated using the area under the curve (AUC). Results: One hundred women were included in the final analysis. The median age was 31 years (Q1: 27, Q3: 34). Thirty-eight percent identified as non-Hispanic White, 32% as non-Hispanic Black, and 21% as Hispanic. Five percent and 6% had left ventricular ejection fraction (LVEF) <45% and <50%, respectively. The AI-ECG model had near-perfect classification performance (AUC: 1.0, 100% sensitivity; 99%-100% specificity) for detection of cardiomyopathy at both LVEF categories. The AI-enabled digital stethoscope had an AUC of 0.98 (95% CI: 0.95, 1.00) and 0.97 (95% CI: 0.93, 1.00), for detection of LVEF <45% and <50%, respectively, with 100% sensitivity and 90% specificity. Conclusion: We demonstrate an AI-ECG and AI-enabled digital stethoscope were effective for detecting cardiac dysfunction in an obstetric population. Larger studies, including an evaluation of the impact of screening on clinical outcomes, are essential next steps.

Hypertrophic cardiomyopathy detection with artificial intelligence electrocardiography in international cohorts: an external validation study.

Aims: Recently, deep learning artificial intelligence (AI) models have been trained to detect cardiovascular conditions, including hypertrophic cardiomyopathy (HCM), from the 12-lead electrocardiogram (ECG). In this external validation study, we sought to assess the performance of an AI-ECG algorithm for detecting HCM in diverse international cohorts. Methods and results: A convolutional neural network-based AI-ECG algorithm was developed previously in a single-centre North American HCM cohort (Mayo Clinic). This algorithm was applied to the raw 12-lead ECG data of patients with HCM and non-HCM controls from three external cohorts (Bern, Switzerland; Oxford, UK; and Seoul, South Korea). The algorithm's ability to distinguish HCM vs. non-HCM status from the ECG alone was examined. A total of 773 patients with HCM and 3867 non-HCM controls were included across three sites in the merged external validation cohort. The HCM study sample comprised 54.6% East Asian, 43.2% White, and 2.2% Black patients. Median AI-ECG probabilities of HCM were 85% for patients with HCM and 0.3% for controls (P < 0.001). Overall, the AI-ECG algorithm had an area under the receiver operating characteristic curve (AUC) of 0.922 [95% confidence interval (CI) 0.910-0.934], with diagnostic accuracy 86.9%, sensitivity 82.8%, and specificity 87.7% for HCM detection. In age- and sex-matched analysis (case-control ratio 1:2), the AUC was 0.921 (95% CI 0.909-0.934) with accuracy 88.5%, sensitivity 82.8%, and specificity 90.4%. Conclusion: The AI-ECG algorithm determined HCM status from the 12-lead ECG with high accuracy in diverse international cohorts, providing evidence for external validity. The value of this algorithm in improving HCM detection in clinical practice and screening settings requires prospective evaluation.

Pediatric sex estimation using AI-enabled ECG analysis: influence of pubertal development.

AI-enabled ECGs have previously been shown to accurately predict patient sex in adults and correlate with sex hormone levels. We aimed to test the ability of AI-enabled ECGs to predict sex in the pediatric population and study the influence of pubertal development. AI-enabled ECG models were created using a convolutional neural network trained on pediatric 10-second, 12-lead ECGs. The first model was trained de novo using pediatric data. The second model used transfer learning from a previously validated adult data-derived algorithm. We analyzed the first ECG from 90,133 unique pediatric patients (aged ≤18 years) recorded between 1987-2022, and divided the cohort into training, validation, and testing datasets. Subgroup analysis was performed on prepubertal (0-7 years), peripubertal (8-14 years), and postpubertal (15-18 years) patients. The cohort was 46.7% male, with 21,678 prepubertal, 26,740 peripubertal, and 41,715 postpubertal children. The de novo pediatric model demonstrated 81% accuracy and an area under the curve (AUC) of 0.91. Model sensitivity was 0.79, specificity was 0.83, positive predicted value was 0.84, and the negative predicted value was 0.78, for the entire test cohort. The model's discriminatory ability was highest in postpubertal (AUC = 0.98), lower in the peripubertal age group (AUC = 0.91), and poor in the prepubertal age group (AUC = 0.67). There was no significant performance difference observed between the transfer learning and de novo models. AI-enabled interpretation of ECG can estimate sex in peripubertal and postpubertal children with high accuracy.

An electrocardiogram-based AI algorithm for early detection of pulmonary hypertension.

BACKGROUND: Early diagnosis of pulmonary hypertension (PH) is critical for effective treatment and management. We aimed to develop and externally validate an artificial intelligence algorithm that could serve as a PH screening tool, based on analysis of a standard 12-lead ECG. METHODS: The PH Early Detection Algorithm (PH-EDA) is a convolutional neural network developed using retrospective ECG voltage-time data, with patients classified as "PH-likely" or "PH-unlikely" (controls) based on right heart catheterisation or echocardiography. In total, 39 823 PH-likely patients and 219 404 control patients from Mayo Clinic were randomly split into training (48%), validation (12%) and test (40%) sets. ECGs taken within 1 month of PH diagnosis (diagnostic dataset) were used to train the PH-EDA at Mayo Clinic. Performance was tested on diagnostic ECGs within the test sets from Mayo Clinic (n=16 175/87 998 PH-likely/controls) and Vanderbilt University Medical Center (VUMC; n=6045/24 256 PH-likely/controls). In addition, performance was tested on ECGs taken 6-18 months (pre-emptive dataset), and up to 5 years prior to a PH diagnosis at both sites. RESULTS: Performance testing yielded an area under the receiver operating characteristic curve (AUC) of 0.92 and 0.88 in the diagnostic test sets at Mayo Clinic and VUMC, respectively, and 0.86 and 0.81, respectively, in the pre-emptive test sets. The AUC remained a minimum of 0.79 at Mayo Clinic and 0.73 at VUMC up to 5 years before diagnosis. CONCLUSION: The PH-EDA can detect PH at diagnosis and 6-18 months prior, demonstrating the potential to accelerate diagnosis and management of this debilitating disease.

Ten-Year Trend of Oral Anticoagulation Use in Postoperative and Nonpostoperative Atrial Fibrillation in Routine Clinical Practice.

BACKGROUND: The study aimed to describe the patterns and trends of initiation, discontinuation, and adherence of oral anticoagulation (OAC) in patients with new-onset postoperative atrial fibrillation (POAF), and compare with patients newly diagnosed with non-POAF. METHODS AND RESULTS: This retrospective cohort study identified patients newly diagnosed with atrial fibrillation or flutter between 2012 and 2021 using administrative claims data from OptumLabs Data Warehouse. The POAF cohort included 118 366 patients newly diagnosed with atrial fibrillation or flutter within 30 days after surgery. The non-POAF cohort included the remaining 315 832 patients who were newly diagnosed with atrial fibrillation or flutter but not within 30 days after a surgery. OAC initiation increased from 28.9% to 44.0% from 2012 to 2021 in POAF, and 37.8% to 59.9% in non-POAF; 12-month medication adherence increased from 47.0% to 61.8% in POAF, and 59.7% to 70.4% in non-POAF. The median time to OAC discontinuation was 177 days for POAF, and 242 days for non-POAF. Patients who saw a cardiologist within 90 days of the first atrial fibrillation or flutter diagnosis, regardless of POAF or non-POAF, were more likely to initiate OAC (odds ratio, 2.92 [95% CI, 2.87-2.98]; P <0.0001), adhere to OAC (odds ratio, 1.08 [95% CI, 1.04-1.13]; P <0.0001), and less likely to discontinue (odds ratio, 0.83 [95% CI, 0.82-0.85]; P <0.0001) than patients who saw a surgeon or other specialties. CONCLUSIONS: The use of and adherence to OAC were higher in non-POAF patients than in POAF patients, but they increased over time in both groups. Patients managed by cardiologists were more likely to use and adhere to OAC, regardless of POAF or non-POAF.

Machine learning for prediction of ventricular arrhythmia episodes from intracardiac electrograms of automatic implantable cardioverter-defibrillators.

BACKGROUND: Despite effectiveness of the implantable cardioverter-defibrillator (ICD) in saving patients with life-threatening ventricular arrhythmias (VAs), the temporal occurrence of VA after ICD implantation is unpredictable. OBJECTIVE: The study aimed to apply machine learning (ML) to intracardiac electrograms (IEGMs) recorded by ICDs as a unique biomarker for predicting impending VAs. METHODS: The study included 13,516 patients who received Biotronik ICDs and enrolled in the CERTITUDE registry between January 1, 2010, and December 31, 2020. Database extraction included IEGMs from standard quarterly transmissions and VA event episodes. The processed IEGM data were pulled from device transmissions stored in a centralized Home Monitoring Service Center and reformatted into an analyzable format. Long-range (baseline or first scheduled remote recording), mid-range (scheduled remote recording every 90 days), or short-range predictions (IEGM within 5 seconds before the VA onset) were used to determine whether ML-processed IEGMs predicted impending VA events. Convolutional neural network classifiers using ResNet architecture were employed. RESULTS: Of 13,516 patients (male, 72%; age, 67.5 ± 11.9 years), 301,647 IEGM recordings were collected; 27,845 episodes of sustained ventricular tachycardia or ventricular fibrillation were observed in 4467 patients (33.0%). Neural networks based on convolutional neural networks using ResNet-like architectures on far-field IEGMs yielded an area under the curve of 0.83 with a 95% confidence interval of 0.79-0.87 in the short term, whereas the long-range and mid-range analyses had minimal predictive value for VA events. CONCLUSION: In this study, applying ML to ICD-acquired IEGMs predicted impending ventricular tachycardia or ventricular fibrillation events seconds before they occurred, whereas midterm to long-term predictions were not successful. This could have important implications for future device therapies.