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.

Artificial Intelligence Electrocardiography to Predict Atrial Fibrillation in Patients With Chronic Lymphocytic Leukemia.

Background: The use of an artificial intelligence electrocardiography (AI-ECG) algorithm has demonstrated its reliability in predicting the risk of atrial fibrillation (AF) within the general population. Objectives: This study aimed to determine the effectiveness of the AI-ECG score in identifying patients with chronic lymphocytic leukemia (CLL) who are at high risk of developing AF. Methods: We estimated the probability of AF based on AI-ECG among patients with CLL extracted from the Mayo Clinic CLL database. Additionally, we computed the Mayo Clinic CLL AF risk score and determined its ability to predict AF. Results: Among 754 newly diagnosed patients with CLL, 71.4% were male (median age = 69 years). The median baseline AI-ECG score was 0.02 (range = 0-0.93), with a value ≥0.1 indicating high risk. Over a median follow-up of 5.8 years, the estimated 10-year cumulative risk of AF was 26.1%. Patients with an AI-ECG score of ≥0.1 had a significantly higher risk of AF (HR: 3.9; 95% CI: 2.6-5.7; P < 0.001). This heightened risk remained significant (HR: 2.5; 95% CI: 1.6-3.9; P < 0.001) even after adjusting for the Mayo CLL AF risk score, heart failure, chronic kidney disease, and CLL therapy. In a second cohort of CLL patients treated with a Bruton tyrosine kinase inhibitor (n = 220), a pretreatment AI-ECG score ≥0.1 showed a nonsignificant increase in the risk of AF (HR: 1.7; 95% CI: 0.8-3.6; P = 0.19). Conclusions: An AI-ECG algorithm, in conjunction with the Mayo CLL AF risk score, can predict the risk of AF in patients with newly diagnosed CLL. Additional studies are needed to determine the role of AI-ECG in predicting AF risk in CLL patients treated with a Bruton tyrosine kinase inhibitor.

Rationale and design of the NODE-303 study: evaluating the safety of symptom-prompted, self-administered etripamil for paroxysmal supraventricular tachycardia episodes in real-world settings.

BACKGROUND: Paroxysmal supraventricular tachycardia (PSVT) is a common episodic arrhythmia characterized by unpredictable onset and burdensome symptoms including palpitations, dizziness, chest pain, distress, and shortness of breath. Treatment of acute episodes of PSVT in the clinical setting consists of intravenous adenosine, beta-blockers, and calcium channel blockers (CCBs). Etripamil is an intranasally self-administered L-type CCB in development for acute treatment of AV-nodal dependent PSVT in a nonmedical supervised setting. METHODS: This paper summarizes the rationale and study design of NODE-303 that will assess the efficacy and safety of etripamil. In the randomized, double-blinded, placebo-controlled, Phase 3 RAPID trial, etripamil was superior to placebo in the conversion of single PSVT episodes by 30 minutes post initial dose when administered in the nonhealthcare setting; this study required a mandatory and observed test dosing prior to randomization. The primary objective of NODE-303 is to evaluate the safety of symptom-prompted, self-administered etripamil for multiple PSVT episodes in real-world settings, without the need for test dosing prior to first use during PSVT. Secondary endpoints include efficacy and disease burden. Upon perceiving a PSVT episode, the patient applies an electrocardiographic monitor, performs a vagal maneuver, and, if the vagal maneuver is unsuccessful, self-administers etripamil 70 mg, with an optional repeat dose if symptoms do not resolve within 10 minutes after the first dose. A patient may treat up to four PSVT episodes during the study. Adverse events are recorded as treatment-emergent if they occur within 24 hours after the administration of etripamil. RESULTS: Efficacy endpoints include time to conversion to sinus rhythm within 30 and 60 minutes after etripamil administration, and the proportion of patients who convert at 3, 5, 10, 20, 30, and 60 minutes. Patient-reported outcomes are captured by the Brief Illness Perception Questionnaire, the Cardiac Anxiety Questionnaire, the Short Form Health Survey 36, the Treatment Satisfaction Questionnaire for Medication and a PSVT survey. CONCLUSIONS: Overall, these data will support the development of a potentially paradigm-changing long-term management strategy for recurrent PSVT.

Incidence, risk factors, and outcomes of atrial functional mitral regurgitation in patients with atrial fibrillation or sinus rhythm.

AIMS: Atrial functional mitral regurgitation (AFMR) has been associated with atrial fibrillation (AF) and heart failure with preserved ejection fraction. However, data on incident AFMR are scarce. We aimed to study the incidence, risk factors, and clinical significance of AFMR in AF or sinus rhythm (SR). METHODS AND RESULTS: Adults with new diagnosis of AF and adults in SR were identified. Patients with >mild MR at baseline, primary mitral disease, cardiomyopathy, left-sided valve disease, previous cardiac surgery, or with no follow-up echocardiogram were excluded. Diastolic dysfunction (DD) was indicated by ≥2/4 abnormal diastolic function parameters [mitral medial e', mitral medial E/e', tricuspid regurgitation velocity, left atrial volume index (LAVI)]. Overall, 1747 patients with AF and 29 623 in SR were included. Incidence rate of >mild AFMR was 2.6 per 100 person-year in new-onset AF and 0.7 per 100 person-year in SR, P < 0.001. AF remained associated with AFMR in a propensity score-matched analysis based on age, sex, and comorbidities between AF and SR [hazard ratio: 3.80 (95% confidence interval 3.04-4.76)]. Independent risk factors associated with incident AFMR were age ≥65 years, female sex, LAVI, and DD in both AF and SR, in addition to rate (vs. rhythm) control in AF. Incident AFMR was independently associated with all-cause death in both groups (both P < 0.001). CONCLUSIONS: AF conferred a three-fold increase in the risk of incident AFMR. DD, older age, left atrial size, and female sex were independent risk factors in both SR and AF, while rhythm control was protective. AFMR was universally associated with worse mortality.

Non-invasive detection of cardiac allograft rejection among heart transplant recipients using an electrocardiogram based deep learning model.

Aims: Current non-invasive screening methods for cardiac allograft rejection have shown limited discrimination and are yet to be broadly integrated into heart transplant care. Given electrocardiogram (ECG) changes have been reported with severe cardiac allograft rejection, this study aimed to develop a deep-learning model, a form of artificial intelligence, to detect allograft rejection using the 12-lead ECG (AI-ECG). Methods and results: Heart transplant recipients were identified across three Mayo Clinic sites between 1998 and 2021. Twelve-lead digital ECG data and endomyocardial biopsy results were extracted from medical records. Allograft rejection was defined as moderate or severe acute cellular rejection (ACR) based on International Society for Heart and Lung Transplantation guidelines. The extracted data (7590 unique ECG-biopsy pairs, belonging to 1427 patients) was partitioned into training (80%), validation (10%), and test sets (10%) such that each patient was included in only one partition. Model performance metrics were based on the test set (n = 140 patients; 758 ECG-biopsy pairs). The AI-ECG detected ACR with an area under the receiver operating curve (AUC) of 0.84 [95% confidence interval (CI): 0.78-0.90] and 95% (19/20; 95% CI: 75-100%) sensitivity. A prospective proof-of-concept screening study (n = 56; 97 ECG-biopsy pairs) showed the AI-ECG detected ACR with AUC = 0.78 (95% CI: 0.61-0.96) and 100% (2/2; 95% CI: 16-100%) sensitivity. Conclusion: An AI-ECG model is effective for detection of moderate-to-severe ACR in heart transplant recipients. Our findings could improve transplant care by providing a rapid, non-invasive, and potentially remote screening option for cardiac allograft function.

Artificial Intelligence-Augmented Electrocardiogram in Determining Sex: Correlation with Sex Hormone Levels.

OBJECTIVE: To study the relationship between the sex probability derived from the artificial intelligence (AI)-augmented electrocardiogram (ECG) and sex hormone levels. PATIENTS AND METHODS: Adult patients with total testosterone (TT; ng/dL) or estradiol (E2; pg/mL) levels (January 1, 2000, to December 31, 2020) with ECGs obtained within 6 months of the blood sample were identified. The closest ECG to the blood test was used. The AI-ECG model output ranges from 0.0 to 1.0, with higher numbers indicating high probability of being male. Low male probability was defined as ≤0.3, intermediate as 0.31 to 0.69, and high as ≥0.7. Continuous variables are expressed as median (interquartile range). RESULTS: Paired TT-ECGs were available in 58,084 male subjects and 11,190 female subjects. Paired E2-ECGs were available in 2835 male patients and 18,228 female patients. TT levels had moderate positive correlation with AI-ECG male sex probability (r=0.46, P<.001). Male subjects with low AI-ECG male sex probability had lower TT and higher E2 levels compared with men with high probability (TT: 303 [129-474] vs 381 [264-523], P <.001; E2: 35 [21-49] vs 32 [22-38], P=.05). Female subjects with high AI-ECG male sex probability had higher TT and lower E2 levels compared with those who had low male probability (TT: ≤50 years of age: 31 [18-55] vs 26 [16-39], P<.001; >50 years of age: 27 [12-68] vs 20 [12-34], P<.001; E2: ≤50 years of age: 58 [30-124] vs 47 [25-87], P=.001; >50 years of age: 30 [10-55] vs 21 [10-41], P=.006). CONCLUSION: In this study, TT levels were lower and E2 levels higher with decreasing AI-ECG male probability in both sexes. Male and female patients with discordant AI-ECG sex probability had significantly different TT or E2 levels. This suggests that the ECG could be used as a biomarker of hormone status.

Association Between Coffee Consumption and Incident Atrial Fibrillation (from the Multi-Ethnic Study of Atherosclerosis [MESA]).

This study aimed to elucidate a potential dose-dependent relation between coffee intake and atrial fibrillation (AF) incidence in a multi-ethnic setting. Previous studies were comprised mainly of White populations, and an exploration of dose dependency is limited. To address these gaps, we analyzed the Multi-Ethnic Study of Atherosclerosis data, a prospective cohort study. In the primary analysis, we crudely divided patients into 3 groups: nonconsumers, 1 to 3 cups/month, and ≥1 cup/week. For the secondary analysis, we stratified the cohort into 9 groups of gradual increments for coffee consumption. A multivariable cox proportional hazards regression model was adjusted for 6 potential confounders: age, gender, smoking, hypertension, diabetes mellitus, and alcohol. Subjects who drank ≥1 cup of coffee/week had a higher incidence of AF (adjusted hazard ratio 1.40, p = 0.015) than nonconsumers. Furthermore, in the secondary analysis, there was an overall trend, albeit not consistent, of increasing adjusted hazard ratio with progressively increasing doses of coffee in the following groups: 1 to 3 cups/month, 2 to 4 cups/week, 2 to 3 cups/day and ≥6 cups/day. Notably, AF incidence was highest (9.8%) for the group consuming the most coffee, that is, ≥6 cups/day (p = 0.02). Stratification by race/ethnicity suggested the results may be driven by White and Hispanic rather than Black or Chinese-American subgroups. In conclusion, the findings suggest an association between coffee consumption and incident AF in contrast to most previous studies.

Advances in Cardiac Electrophysiology.

Despite the global COVID-19 pandemic, during the past 2 years, there have been numerous advances in our understanding of arrhythmia mechanisms and diagnosis and in new therapies. We increased our understanding of risk factors and mechanisms of atrial arrhythmias, the prediction of atrial arrhythmias, response to treatment, and outcomes using machine learning and artificial intelligence. There have been new technologies and techniques for atrial fibrillation ablation, including pulsed field ablation. There have been new randomized trials in atrial fibrillation ablation, giving insight about rhythm control, and long-term outcomes. There have been advances in our understanding of treatment of inherited disorders such as catecholaminergic polymorphic ventricular tachycardia. We have gained new insights into the recurrence of ventricular arrhythmias in the setting of various conditions such as myocarditis and inherited cardiomyopathic disorders. Novel computational approaches may help predict occurrence of ventricular arrhythmias and localize arrhythmias to guide ablation. There are further advances in our understanding of noninvasive radiotherapy. We have increased our understanding of the role of His bundle pacing and left bundle branch area pacing to maintain synchronous ventricular activation. There have also been significant advances in the defibrillators, cardiac resynchronization therapy, remote monitoring, and infection prevention. There have been advances in our understanding of the pathways and mechanisms involved in atrial and ventricular arrhythmogenesis.

Artificial intelligence-guided screening for atrial fibrillation using electrocardiogram during sinus rhythm: a prospective non-randomised interventional trial.

BACKGROUND: Previous atrial fibrillation screening trials have highlighted the need for more targeted approaches. We did a pragmatic study to evaluate the effectiveness of an artificial intelligence (AI) algorithm-guided targeted screening approach for identifying previously unrecognised atrial fibrillation. METHODS: For this non-randomised interventional trial, we prospectively recruited patients with stroke risk factors but with no known atrial fibrillation who had an electrocardiogram (ECG) done in routine practice. Participants wore a continuous ambulatory heart rhythm monitor for up to 30 days, with the data transmitted in near real time through a cellular connection. The AI algorithm was applied to the ECGs to divide patients into high-risk or low-risk groups. The primary outcome was newly diagnosed atrial fibrillation. In a secondary analysis, trial participants were propensity-score matched (1:1) to individuals from the eligible but unenrolled population who served as real-world controls. This study is registered with ClinicalTrials.gov, NCT04208971. FINDINGS: 1003 patients with a mean age of 74 years (SD 8·8) from 40 US states completed the study. Over a mean 22·3 days of continuous monitoring, atrial fibrillation was detected in six (1·6%) of 370 patients with low risk and 48 (7·6%) of 633 with high risk (odds ratio 4·98, 95% CI 2·11-11·75, p=0·0002). Compared with usual care, AI-guided screening was associated with increased detection of atrial fibrillation (high-risk group: 3·6% [95% CI 2·3-5·4] with usual care vs 10·6% [8·3-13·2] with AI-guided screening, p<0·0001; low-risk group: 0·9% vs 2·4%, p=0·12) over a median follow-up of 9·9 months (IQR 7·1-11·0). INTERPRETATION: An AI-guided targeted screening approach that leverages existing clinical data increased the yield for atrial fibrillation detection and could improve the effectiveness of atrial fibrillation screening. FUNDING: Mayo Clinic Robert D and Patricia E Kern Center for the Science of Health Care Delivery.

Associations of Atrial Fibrillation After Noncardiac Surgery With Stroke, Subsequent Arrhythmia, and Death : A Cohort Study.

BACKGROUND: Postoperative atrial fibrillation (AF) after noncardiac surgery confers increased risks for ischemic stroke and transient ischemic attack (TIA). How outcomes for postoperative AF after noncardiac surgery compare with those for AF occurring outside of the operative setting is unknown. OBJECTIVE: To compare the risks for ischemic stroke or TIA and other outcomes in patients with postoperative AF versus those with incident AF not associated with surgery. DESIGN: Cohort study. SETTING: Olmsted County, Minnesota. PARTICIPANTS: Patients with incident AF between 2000 and 2013. MEASUREMENTS: Patients were categorized as having AF occurring within 30 days of a noncardiac surgery (postoperative AF) or having AF unrelated to surgery (nonoperative AF). RESULTS: Of 4231 patients with incident AF, 550 (13%) had postoperative AF as their first-ever documented AF presentation. Over a mean follow-up of 6.3 years, 486 patients had an ischemic stroke or TIA and 2462 had subsequent AF; a total of 2565 deaths occurred. The risk for stroke or TIA was similar between those with postoperative AF and nonoperative AF (absolute risk difference [ARD] at 5 years, 0.1% [95% CI, -2.9% to 3.1%]; hazard ratio [HR], 1.01 [CI, 0.77 to 1.32]). A lower risk for subsequent AF was seen for patients with postoperative AF (ARD at 5 years, -13.4% [CI, -17.8% to -9.0%]; HR, 0.68 [CI, 0.60 to 0.77]). Finally, no difference was seen for cardiovascular death or all-cause death between patients with postoperative AF and nonoperative AF. LIMITATION: The population consisted predominantly of White patients; caution should be used when extrapolating the results to more racially diverse populations. CONCLUSION: Postoperative AF after noncardiac surgery is associated with similar risk for thromboembolism compared with nonoperative AF. Our findings have potentially important implications for the early postsurgical and subsequent management of postoperative AF. PRIMARY FUNDING SOURCE: National Institute on Aging.

Cardiac resynchronization therapy response in cardiac sarcoidosis.

INTRODUCTION: Cardiac sarcoidosis (CS) is a nonischemic cardiomyopathy (NICM) characterized by infiltration of noncaseating granulomas involving the heart with highly variable clinical manifestations that can include conduction abnormalities and systolic heart failure. Cardiac resynchronization therapy (CRT) has shown significant promise in NICM, though little is known about its efficacy in patients with CS. OBJECTIVE: To determine if CRT improved cardiac remodeling in patients with CS. METHODS: We retrospectively reviewed all patients with a clinical or histological diagnosis of CS who underwent CRT implantation at the Mayo Clinic enterprise from 2000 to 2021. Baseline characteristics, imaging parameters, heart failure hospitalizations and need for advanced therapies, and major adverse cardiac events (MACE) were assessed. RESULTS: Our cohort was comprised of 55 patients with 61.8% male and a mean age of 58.7 ± 10.9 years. Eighteen (32.7%) patients had definite CS, 21 (38.2%) had probable CS, while 16 (29.1%) had presumed CS, and 26 (47.3%) with extracardiac sarcoidosis. The majority underwent CRT-D implantation (n = 52, 94.5%) and 3 (5.5%) underwent CRT-P implantation with 67.3% of implanted devices being upgrades from prior pacemakers or implantable cardioverter defibrillators. At 6 months postimplantation there was no significant improvement in ejection fraction (34.8 ± 10.9% vs. 37.7 ± 14.2%, p = .331) or left ventricular end-diastolic diameter (58.5 ± 10.2 vs. 57.5 ± 8.1 mm, p = .236), though mild improvement in left ventricular end systolic diameter (49.1 ± 9.9 vs. 45.7± 9.9 mm, p < .0001). Within the first 6 months postimplantation, 5 (9.1%) patients sustained a heart failure hospitalization. At a mean follow-up of 4.1± 3.7 years, 14 (25.5%) patients experienced a heart failure hospitalization, 11 (20.0%) underwent cardiac transplantation, 1 (1.8%) underwent left ventricular assist device implantation and 7 (12.7%) patients died. CONCLUSIONS: Our findings suggest variable response to CRT in patients with CS with no overall improvement in ventricular function within 6 months and a substantial proportion of patients progressing to advanced heart failure therapies.

Artificial intelligence opportunities in cardio-oncology: Overview with spotlight on electrocardiography.

Cardiovascular disease is a leading cause of death among cancer survivors, second only to cancer recurrence or development of new tumors. Cardio-oncology has therefore emerged as a relatively new specialty focused on prevention and management of cardiovascular consequences of cancer therapies. Yet challenges remain regarding precision and accuracy with predicting individuals at highest risk for cardiotoxicity. Barriers such as access to care also limit screening and early diagnosis to improve prognosis. Thus, developing innovative approaches for prediction and early detection of cardiovascular illness in this population is critical. In this review, we provide an overview of the present state of machine learning applications in cardio-oncology. We begin by outlining some factors that should be considered while utilizing machine learning algorithms. We then examine research in which machine learning has been applied to improve prediction of cardiac dysfunction in cancer survivors. We also highlight the use of artificial intelligence (AI) in conjunction with electrocardiogram (ECG) to predict cardiac malfunction and also atrial fibrillation (AF), and we discuss the potential role of wearables. Additionally, the article summarizes future prospects and critical takeaways for the application of machine learning in cardio-oncology. This study is the first in a series on artificial intelligence in cardio-oncology, and complements our manuscript on echocardiography and other forms of imaging relevant to cancer survivors cared for in cardiology clinical practice.

Cardiovascular Disease Screening in Women: Leveraging Artificial Intelligence and Digital Tools.

Cardiovascular disease remains the leading cause of death in women. Given accumulating evidence on sex- and gender-based differences in cardiovascular disease development and outcomes, the need for more effective approaches to screening for risk factors and phenotypes in women is ever urgent. Public health surveillance and health care delivery systems now continuously generate massive amounts of data that could be leveraged to enable both screening of cardiovascular risk and implementation of tailored preventive interventions across a woman's life span. However, health care providers, clinical guidelines committees, and health policy experts are not yet sufficiently equipped to optimize the collection of data on women, use or interpret these data, or develop approaches to targeting interventions. Therefore, we provide a broad overview of the key opportunities for cardiovascular screening in women while highlighting the potential applications of artificial intelligence along with digital technologies and tools.

Electrocardiographic biosignals to predict atrial fibrillation: Are we there yet?

The prevalence of atrial fibrillation (AF) continues to grow in an aging population, and its impact on both patients and the health care system has has made it a global burden. There are limited available options to detect individuals at risk of AF that may benefit from prevention and treatment strategies. The ECG may be an effective tool do so. In this work, we discuss the latest work by Hayiroglu and colleagues related to this work and the use of novel ECG prediction tools to identify individuals individuals that could benefit from early and proactive screening, surveillance, and management strategies.

Outcomes of Direct Oral Anticoagulants Co-Prescribed with Common Interacting Medications.

Direct oral anticoagulants (DOACs) can potentially interact with multiple prescription medications. We examined the prevalence of co-prescription of DOACs with interacting medications and its impact on outcomes in patients with atrial fibrillation (AF). Patients with AF treated with a DOAC from 2010 to 2017 at the Mayo Clinic and co-prescribed medications that are inhibitors or inducers of the P-glycoprotein and/or Cytochrome P450 3A4 pathways were identified. The outcomes of stroke, transient ischemic attack, or systemic embolism, major bleeding, and minor bleeds were compared between patients with and without an enzyme inducer. Cox proportional hazards model was used to assess the association between interacting medications and outcomes. Of 8,576 patients with AF (mean age 70 ± 12 years, 35% female) prescribed a DOAC (38.6% apixaban, 35.8% rivaroxaban, 25.6% dabigatran), 2,610 (30.4%) were on at least 1 interacting agent: the majority were on an enzyme inhibitor (n = 2,592). Prescribed medications included non-dihydropyridine calcium channel blocker (n = 1,412; 16.5%), antiarrhythmic medication (n = 790; 9.2%), antidepressant (n = 659; 7.7%), antibiotic/antifungal (n = 77; 0.90%), antiepileptics (n = 17; 0.2%) and immunosuppressant medications (n = 19; 0.2%). Patients on an interacting medication were more likely to receive a lower dose of DOAC than indicated by the manufacturer's labeling (15.0% vs 11.4%, p <0.0001). In multivariable analysis, co-prescription of an enzyme inhibitor was not associated with risk of any bleeding (hazard ratio 0.87 [0.71 to 1.05], p = 0.15) or stroke, transient ischemic attack, or systemic embolism (hazard ratio 0.82 [0.51 to 1.31], p = 0.39). In conclusion, DOACs are co-prescribed with medications with potential interactions in 30.4% of patients with AF. Co-prescription of DOACs and these drugs are not associated with increased risk of adverse embolic or bleeding outcomes in our cohort.

Tandem deep learning and logistic regression models to optimize hypertrophic cardiomyopathy detection in routine clinical practice.

Background: An electrocardiogram (ECG)-based artificial intelligence (AI) algorithm has shown good performance in detecting hypertrophic cardiomyopathy (HCM). However, its application in routine clinical practice may be challenging owing to the low disease prevalence and potentially high false-positive rates. Objective: Identify clinical characteristics associated with true- and false-positive HCM AI-ECG results to improve its clinical application. Methods: We reviewed the records of the 200 patients with highest HCM AI-ECG scores in January 2021 at our institution. Logistic regression was used to create a clinical variable-based "Candidacy for HCM Detection (HCM-DETECT)" score, differentiating true-positive from false-positive AI-ECG results. We validated the HCM-DETECT score in an independent cohort of 200 patients with the highest AI-ECG scores from January 2022. Results: In the 2021 cohort (median age 71 [interquartile range 58-80] years, 48% female), the rates of true-positive, false-positive, and indeterminate AI-ECG results for HCM detection were 36%, 48%, and 16%, respectively. In the 2022 cohort, the rates were 26%, 47%, and 27%, respectively. The HCM-DETECT score included age, coronary artery disease, prior pacemaker, and prior cardiac valve surgery, and had an area under the receiver operating characteristic curve of 0.81 (95% confidence interval 0.73-0.87) for differentiating true- vs false-positive AI results. When the 2022 cohort was limited to HCM detection candidates identified with the HCM-DETECT score, the false-positive AI-ECG rate was reduced from 47% to 13.5%. Conclusion: Application of a clinical score (HCM-DETECT) in tandem with an AI-ECG model improved HCM detection yield, reducing the false-positive rate of AI-ECG more than 3-fold.

Electrocardiography-Based Artificial Intelligence Algorithm Aids in Prediction of Long-term Mortality After Cardiac Surgery.

OBJECTIVE: To assess whether an electrocardiography-based artificial intelligence (AI) algorithm developed to detect severe ventricular dysfunction (left ventricular ejection fraction [LVEF] of 35% or below) independently predicts long-term mortality after cardiac surgery among patients without severe ventricular dysfunction (LVEF>35%). METHODS: Patients who underwent valve or coronary bypass surgery at Mayo Clinic (1993-2019) and had documented LVEF above 35% on baseline electrocardiography were included. We compared patients with an abnormal vs a normal AI-enhanced electrocardiogram (AI-ECG) screen for LVEF of 35% or below on preoperative electrocardiography. The primary end point was all-cause mortality. RESULTS: A total of 20,627 patients were included, of whom 17,125 (83.0%) had a normal AI-ECG screen and 3502 (17.0%) had an abnormal AI-ECG screen. Patients with an abnormal AI-ECG screen were older and had more comorbidities. Probability of survival at 5 and 10 years was 86.2% and 68.2% in patients with a normal AI-ECG screen vs 71.4% and 45.1% in those with an abnormal screen (log-rank, P<.01). In the multivariate Cox survival analysis, the abnormal AI-ECG screen was independently associated with a higher all-cause mortality overall (hazard ratio [HR], 1.31; 95% CI, 1.24 to 1.37) and in subgroups of isolated valve surgery (HR, 1.30; 95% CI, 1.18 to 1.42), isolated coronary artery bypass grafting (HR, 1.29; 95% CI, 1.20 to 1.39), and combined coronary artery bypass grafting and valve surgery (HR, 1.19; 95% CI, 1.08 to 1.32). In a subgroup analysis, the association between abnormal AI-ECG screen and mortality was consistent in patients with LVEF of 35% to 55% and among those with LVEF above 55%. CONCLUSION: A novel electrocardiography-based AI algorithm that predicts severe ventricular dysfunction can predict long-term mortality among patients with LVEF above 35% undergoing valve and/or coronary bypass surgery.

Detection of hypertrophic cardiomyopathy by an artificial intelligence electrocardiogram in children and adolescents.

BACKGROUND: There is no established screening approach for hypertrophic cardiomyopathy (HCM). We recently developed an artificial intelligence (AI) model for the detection of HCM based on the 12­lead electrocardiogram (AI-ECG) in adults. Here, we aimed to validate this approach of ECG-based HCM detection in pediatric patients (age ≤ 18 years). METHODS: We identified a cohort of 300 children and adolescents with HCM (mean age 12.5 ± 4.6 years, male 68%) who had an ECG and echocardiogram at our institution. Patients were age- and sex-matched to 18,439 non-HCM controls. Diagnostic performance of the AI-ECG model for the detection of HCM was estimated using the previously identified optimal diagnostic threshold of 11% (the probability output derived by the model above which an ECG is considered to belong to an HCM patient). RESULTS: Mean AI-ECG probabilities of HCM were 92% and 5% in the case and control groups, respectively. The area under the receiver operating characteristic curve (AUC) of the AI-ECG model for HCM detection was 0.98 (95% CI 0.98-0.99) with corresponding sensitivity 92% and specificity 95%. The positive and negative predictive values were 22% and 99%, respectively. The model performed similarly in males and females and in genotype-positive and genotype-negative HCM patients. Performance tended to be superior with increasing age. In the age subgroup <5 years, the test's AUC was 0.93. In comparison, the AUC was 0.99 in the age subgroup 15-18 years. CONCLUSIONS: A deep-learning, AI model can detect pediatric HCM with high accuracy from the standard 12­lead ECG.