Artificial Intelligence for the Detection and Treatment of Atrial Fibrillation.

AF is the most common clinically relevant cardiac arrhythmia associated with multiple comorbidities, cardiovascular complications (e.g. stroke) and increased mortality. As artificial intelligence (AI) continues to transform the practice of medicine, this review article highlights specific applications of AI for the screening, diagnosis and treatment of AF. Routinely used digital devices and diagnostic technology have been significantly enhanced by these AI algorithms, increasing the potential for large-scale population-based screening and improved diagnostic assessments. These technologies have similarly impacted the treatment pathway of AF, identifying patients who may benefit from specific therapeutic interventions. While the application of AI to the diagnostic and therapeutic pathway of AF has been tremendously successful, the pitfalls and limitations of these algorithms must be thoroughly considered. Overall, the multifaceted applications of AI for AF are a hallmark of this emerging era of medicine.

Dual Atrioventricular Nodal Non-Re-Entrant Tachycardia.

A patient presented with symptoms of palpitations. Her standard 12-lead electrocardiogram captured 3 potential causes of her symptoms (premature atrial contractions, junctional rhythm, and narrow complex tachycardia). Further workup uncovered dual atrioventricular node physiology with 1:2 sinus conduction and resultant alternating QRS from a slow and fast conduction pathway. (Level of Difficulty: Intermediate.).

Dramatic elevation of LDL cholesterol from ketogenic-dieting: A Case Series.

High-fat, low carb dieting, also known as the "ketogenic diet," has increased in popularity as a rapid weight-loss tool. Previous studies describe a modest elevation in cholesterol in the average keto-diet participant without specific cardiovascular impact. We hypothesize that patients with a genetic predisposition to cholesterol metabolism dysregulation may have a disproportionate elevation in cholesterol in response to ketogenic dieting.

The Digitization and Decentralization of Clinical Trials.

Now, more than ever, digital technology has made its way into the daily lives of billions across the globe, and the widespread use of this technology has also allowed a digital window into consumers' and patients' daily lives, respectively. In a similar way, the practice of medicine has digitally evolved with the application of electronic health records and development of wearable/portable consumer-based medical devices (eg, Apple Watch ECG and Kardia Mobile by AliveCor). Alongside the increased use of digital technology in clinical care (eg, telehealth and wearable arrhythmia detection), clinical investigators have harnessed this powerful stockpile of data to gain insight into what happens to patients beyond the clinic walls. In this thematic review, we show the impact of digital advancements on the clinical trial process from recruitment and enrollment to interventions and data collection. We also show the pragmatism of this decentralized process and how it will mitigate the limitations of conventional randomized controlled trials. Finally, while pushing the boundaries of tech, we also describe a few limitations of this rapidly growing field to understand better what gaps need to be bridged in the future.

Postdevelopment Performance and Validation of the Artificial Intelligence-Enhanced Electrocardiogram for Detection of Cardiac Amyloidosis.

BACKGROUND: We have previously applied artificial intelligence (AI) to an electrocardiogram (ECG) to detect cardiac amyloidosis (CA). OBJECTIVES: In this validation study, the authors observe the postdevelopment performance of the AI-enhanced ECG to detect CA with respect to multiple potential confounders. METHODS: Amyloid patients diagnosed after algorithm development (June 2019-January 2022) with a 12-lead ECG were identified (n = 440) and were required to have CA. A 15:1 age- and sex-matched control group was identified (n = 6,600). Area under the receiver operating characteristic (AUC) was determined for the cohort and subgroups. RESULTS: The average age was 70.4 ± 10.3 years, 25.0% were female, and most patients were White (91.3%). In this validation, the AI-ECG for amyloidosis had an AUC of 0.84 (95% CI: 0.82-0.86) for the overall cohort and between amyloid subtypes, which is a slight decrease from the original study (AUC 0.91). White, Black, and patients of "other" races had similar algorithm performance (AUC >0.81) with a decreased performance for Hispanic patients (AUC 0.66). Algorithm performance shift over time was not observed. Low ECG voltage and infarct pattern exhibited high AUC (>0.90), while left ventricular hypertrophy and left bundle branch block demonstrated lesser performance (AUC 0.75 and 0.76, respectively). CONCLUSIONS: The AI-ECG for the detection of CA maintained an overall strong performance with respect to patient age, sex, race, and amyloid subtype. Lower performance was noted in left bundle branch block, left ventricular hypertrophy, and ethnically diverse populations emphasizing the need for subgroup-specific validation efforts.

Community-based participatory research application of an artificial intelligence-enhanced electrocardiogram for cardiovascular disease screening: A FAITH! Trial ancillary study.

Objective: With the emergence of artificial intelligence (AI)-based health interventions, systemic racism remains a concern as these advancements are frequently developed without race-specific data analysis or validation. To evaluate the potential utility of an AI-based cardiovascular diseases (CVD) screening tool in an under-resourced African-American cohort, we reviewed the AI-enhanced electrocardiogram (ECG) data of participants enrolled in a community-based clinical trial as a proof-of-concept ancillary study for community-based screening. Methods: Enrollees completed cardiovascular testing including standard 12-lead ECG and a limited echocardiogram (TTE). All ECGs were analyzed using previously published institution-based AI algorithms. AI-ECG predictions were generated for age, sex, and decreased left ventricular ejection fraction (LVEF). Diagnostic accuracy of the AI-ECG for decreased LVEF and sex was quantified using area under the receiver operating characteristic curve (AUC). Correlation between actual age and AI-ECG predicted age was assessed using Pearson correlation coefficients. Results: Fifty-four participants completed both an ECG and TTE (mean age 55 years [range 31-87 years]; 66.7% female). All participants were in sinus rhythm, and the median LVEF of the cohort was 60-65%. The AI-ECG for decreased LVEF demonstrated excellent performance with an AUC of 0.892 (95% confidence interval [CI] 0.708-1); sensitivity=50% (95% CI 9.5-90.5%; n=1/2) and specificity=96% (95% CI 86.8-98.9%; n=49/51). The AI-ECG for participant sex demonstrated similar performance with AUC of 0.944 (95% CI 0.891-0.998); sensitivity=100% (95% CI 82.4-100.0%; n=18/18) and specificity=77.8% (95% CI 61.9-88.3%; n=28/36). The AI-ECG predicted mean age was 55 years (range 26.9-72.6 years) with a strong correlation to actual age (R=0.769; p<0.001). Conclusion: Our analyses of previously developed AI-ECG algorithms for prediction of age, sex, and decreased LVEF demonstrated reliable performance in this community-based, African-American cohort. This novel, community-centric delivery of AI could provide valuable screening resources and appropriate referrals for early detection of highly-morbid CVD for under-resourced patient populations.

Prospective evaluation of smartwatch-enabled detection of left ventricular dysfunction.

Although artificial intelligence (AI) algorithms have been shown to be capable of identifying cardiac dysfunction, defined as ejection fraction (EF) ≤ 40%, from 12-lead electrocardiograms (ECGs), identification of cardiac dysfunction using the single-lead ECG of a smartwatch has yet to be tested. In the present study, a prospective study in which patients of Mayo Clinic were invited by email to download a Mayo Clinic iPhone application that sends watch ECGs to a secure data platform, we examined patient engagement with the study app and the diagnostic utility of the ECGs. We digitally enrolled 2,454 unique patients (mean age 53 ± 15 years, 56% female) from 46 US states and 11 countries, who sent 125,610 ECGs to the data platform between August 2021 and February 2022; 421 participants had at least one watch-classified sinus rhythm ECG within 30 d of an echocardiogram, of whom 16 (3.8%) had an EF ≤ 40%. The AI algorithm detected patients with low EF with an area under the curve of 0.885 (95% confidence interval 0.823-0.946) and 0.881 (0.815-0.947), using the mean prediction within a 30-d window or the closest ECG relative to the echocardiogram that determined the EF, respectively. These findings indicate that consumer watch ECGs, acquired in nonclinical environments, can be used to identify patients with cardiac dysfunction, a potentially life-threatening and often asymptomatic condition.

Real-world performance, long-term efficacy, and absence of bias in the artificial intelligence enhanced electrocardiogram to detect left ventricular systolic dysfunction.

Aims: Some artificial intelligence models applied in medical practice require ongoing retraining, introduce unintended racial bias, or have variable performance among different subgroups of patients. We assessed the real-world performance of the artificial intelligence-enhanced electrocardiogram to detect left ventricular systolic dysfunction with respect to multiple patient and electrocardiogram variables to determine the algorithm's long-term efficacy and potential bias in the absence of retraining. Methods and results: Electrocardiograms acquired in 2019 at Mayo Clinic in Minnesota, Arizona, and Florida with an echocardiogram performed within 14 days were analyzed (n = 44 986 unique patients). The area under the curve (AUC) was calculated to evaluate performance of the algorithm among age groups, racial and ethnic groups, patient encounter location, electrocardiogram features, and over time. The artificial intelligence-enhanced electrocardiogram to detect left ventricular systolic dysfunction had an AUC of 0.903 for the total cohort. Time series analysis of the model validated its temporal stability. Areas under the curve were similar for all racial and ethnic groups (0.90-0.92) with minimal performance difference between sexes. Patients with a 'normal sinus rhythm' electrocardiogram (n = 37 047) exhibited an AUC of 0.91. All other electrocardiogram features had areas under the curve between 0.79 and 0.91, with the lowest performance occurring in the left bundle branch block group (0.79). Conclusion: The artificial intelligence-enhanced electrocardiogram to detect left ventricular systolic dysfunction is stable over time in the absence of retraining and robust with respect to multiple variables including time, patient race, and electrocardiogram features.

Integrating online community support into outpatient breast cancer care: Mayo Clinic Connect online platform.

INTRODUCTION: Mayo Clinic Connect is an online community of over 100,000 members who support each other through sharing lived experience when facing and managing new diagnoses. The community is moderated by Mayo Clinic staff and volunteer patient mentors. METHODS: Mayo Clinic breast clinic patients undergoing evaluation received a binder of support resources including a brochure about Mayo Clinic Connect at visits between January and May of 2019. Surveys were distributed at subsequent visits between May and December of 2019 to assess patient awareness about the online resource, participation frequency, purpose of use, and benefits for members, as well as reasons for not joining (non-members). The primary aim was to assess patient resilience, coping, and self-management after joining the online community. RESULTS: Nine hundred surveys were distributed, and 102 participants completed surveys between May and December 2019. Forty-five percent (n = 46) had heard about Mayo Clinic Connect; 34% (n = 15) through a brochure. The remainder heard about the community from a Mayo Clinic provider (43%; n = 19) or other resources (22%, n = 10; no response n = 2). Twenty percent (n = 20) of survey participants registered as Breast Cancer group members, and most of this subgroup (55%; n = 11) reported understanding diagnosis, treatment plans, and finding peer support as reasons for joining. Seventy-five percent of Mayo Clinic Connect participants (n = 15) reported the community met or exceeded expectations. CONCLUSION: This pilot study reveals the potential positive impact of introducing an online peer support group into clinical care plans for patients coping with a new and anxiety-provoking cancer diagnosis.

Application of artificial intelligence to the electrocardiogram.

Artificial intelligence (AI) has given the electrocardiogram (ECG) and clinicians reading them super-human diagnostic abilities. Trained without hard-coded rules by finding often subclinical patterns in huge datasets, AI transforms the ECG, a ubiquitous, non-invasive cardiac test that is integrated into practice workflows, into a screening tool and predictor of cardiac and non-cardiac diseases, often in asymptomatic individuals. This review describes the mathematical background behind supervised AI algorithms, and discusses selected AI ECG cardiac screening algorithms including those for the detection of left ventricular dysfunction, episodic atrial fibrillation from a tracing recorded during normal sinus rhythm, and other structural and valvular diseases. The ability to learn from big data sets, without the need to understand the biological mechanism, has created opportunities for detecting non-cardiac diseases as COVID-19 and introduced challenges with regards to data privacy. Like all medical tests, the AI ECG must be carefully vetted and validated in real-world clinical environments. Finally, with mobile form factors that allow acquisition of medical-grade ECGs from smartphones and wearables, the use of AI may enable massive scalability to democratize healthcare.

Sex-specific cut-off values for soluble suppression of tumorigenicity 2 (ST2) biomarker increase its cardiovascular prognostic value in the community.

BACKGROUND: Suppression of tumorigenicity 2 (ST2) has important cardiovascular prognostic value in community patients; however, previous analyses have utilized non-sex specific cut-off values. We assessed whether sex-specific ST2 cut-off values would improve the prognostic utility of ST2 in the asymptomatic community. METHODS: A total of 2042 participants underwent clinical assessment and echocardiographic evaluation. Baseline measurements of high sensitivity troponin, natriuretic peptides and ST2 were obtained in 1681 individuals. ST2, cardiac biomarkers and associated co-morbidities were evaluated by sex-specific ST2 quartile analysis. ST2 concentrations were also analysed as dichotomous variables defined as being above the sex-specific cut-off for each the outcomes of heart failure (HF), major adverse cardiac event (MACE) and mortality. RESULTS: Median ST2 concentration was 29.4 ng/mL in male subjects and 24.1 ng/mL in female subjects. Higher ST2 concentrations were associated with incident HF (p<0.001; preserved ejection fraction (EF) p<0.001, reduced EF p=0.23), MACE (p=0.003) and mortality (p<0.001) across sex-specific quartiles. Event-based, hazard ratio (HR) analysis revealed sex-specific ST2 cut-offs were significantly more predictive of incident HF, MACE and mortality compared to non-sex-specific analysis even following adjustment for cardiac co-morbidities and traditional biomarkers. CONCLUSIONS: These data suggest that sex-specific cut-offs, greater than non-sex specific cut-offs, significantly impact the prognostic value of the biomarker ST2 in the asymptomatic community cohort.Clinical SignificanceSuppression of tumorigenicity 2 (ST2) is a biomarker which has known associations with heart failure (HF), major adverse cardiac events (MACEs) and mortality in the general population.Recent data support the concept of sex-specific cut off values and individualized approaches based on sex to predict cardiovascular disease. Given the difference in pathobiology between the sexes, the fact that such approaches improve risk stratification is understandable. Thus, when sex-specific treatments are developed, this may similarly lead to improved outcomes.The use of sex-specific ST2 cut-off values significantly improved the prognostic value in predicting HF, MACE, and mortality in an asymptomatic community. This prognostication was particularly strong for HF with preserved ejection fraction and remained clinically significant following adjustment for cardiac co-morbidities and other traditional cardiac biomarkers (NTproBNP and hscTnI).

Outcomes of orthotopic heart transplantation and left ventricular assist device in patients aged 65 years or more with end-stage heart failure.

Age has traditionally been a limiting factor for advanced heart failure (HF) therapies. Orthotopic heart transplantation (OHT) age guidelines have become less restrictive, and left ventricular assist devices (LVADs) are increasingly utilized as destination therapy for patients ≥65 years. Although indications differ, we assessed outcomes for both modalities in this older population. We reviewed charts of consecutive advanced HF therapy recipients aged ≥65 years at our center from 2012 to 2016. Of 118 patients evaluated, 46 (39%) received an LVAD and 72 (61%) received OHT. Gender, body mass index, and rate of prior sternotomy were similar between groups; OHT recipients were younger, less likely to have diabetes mellitus, and more likely to have HF due to ischemic etiology. Forty-six percent of patients receiving LVADs were urgent need (Interagency Registry for Mechanically Assisted Circulatory Support [INTERMACS] profile 1-2), compared to 29% of patients receiving OHT (United Network for Organ Sharing 1A criteria; P = 0.068). OHT recipients had shorter lengths of stay and better 1-year survival compared to LVAD recipients. Although many centers do not offer advanced HF therapy to patients aged ≥65 years, our results indicate that age alone should not be prohibitive for advanced HF therapy, particularly OHT.