Citations

Abstract Background and Aims Artificial intelligence (AI) algorithms in 12-lead electrocardiogram (ECG) provides promising age prediction methods. This study investigated whether the discrepancy between ECG-derived AI-predicted age (AI-ECG age) and chronological age, termed electrocardiographic aging (ECG aging), is associated with atrial fibrillation (AF) risk. Methods An AI-ECG age prediction model was developed using a large-scale dataset (1 533 042 ECGs from 689 639 participants) and validated with six independent and multi-national datasets (737 133 ECGs from 330 794 participants). The AI-ECG age gap was calculated across two South Korean cohorts [mean (standard deviation) follow-up: 4.1 (4.3) years for 111 483 participants and 6.1 (3.8) years for 37 517 participants], one UK cohort [3.0 (1.6) years; 40 973 participants], and one US cohort [12.9 (8.6) years; 90 639 participants]. Participants were classified into two groups: normal group (age gap < 7 years) and ECG-aged group (age gap ≥ 7 years). The predictive capability of ECG aging for new- and early-onset AF risk was assessed. Results The mean AI-ECG ages were 51.9 (16.2), 47.4 (12.5), 68.4 (7.8), and 56.7 (14.6) years with age gaps of .0 (6.8), −.1 (6.0), 4.7 (8.7), and −1.4 (8.9) years in the two South Korean, UK, and US cohorts, respectively. In the ECG-aged group, increased risks of new-onset AF were observed with hazard ratios (95% confidence intervals) of 2.50 (2.24–2.78), 1.89 (1.46–2.43), 1.90 (1.55–2.33), and 1.76 (1.67–1.86) in the two South Korean, UK, and US cohorts, respectively. For early-onset AF, odds ratios were 2.89 (2.47–3.37), 1.94 (1.39–2.70), 1.58 (1.06–2.35), and 1.79 (1.62–1.97) in these cohorts compared with the normal group. Conclusions The AI-derived ECG aging was associated with the risk of new- and early-onset AF, suggesting its potential utility to identify individuals for AF prevention across diverse populations.

Importance Typical cysteine-altering NOTCH3 ( NOTCH3 cys ) variants are highly prevalent (approximately 1 in 300 individuals) and are associated with a broad spectrum of small vessel disease (SVD), ranging from early-onset stroke and dementia (cerebral autosomal dominant arteriopathy with subcortical infarcts and leukoencephalopathy [CADASIL]) to nonpenetrance. A staging system that captures the full NOTCH3 -SVD severity spectrum is needed and currently lacking. Objective To design a simple disease severity staging system that captures the broad clinicoradiological NOTCH3 -SVD severity spectrum. Design, Setting, and Participants A cohort study was performed in which the NOTCH3 -SVD severity staging system was developed using a discovery cohort (2019-2020) and validated in independent international CADASIL cohorts (1999-2023) and the UK Biobank. Clinical and imaging data were collected from participants originating from 23 international CADASIL cohorts and from the UK Biobank. Eligibility criteria were presence of a NOTCH3 cys variant, availability of brain magnetic resonance imaging, and modified Rankin Scale score. The discovery cohort consisted of 195 NOTCH3 cys -positive cases from families with CADASIL; the validation set included 1713 NOTCH3 cys -positive cases from 15 countries. The UK Biobank cohort consisted of 101 NOTCH3 cys -positive individuals. Data from 2-year (2019-2023) and 18-year (1999-2017) follow-up studies were also analyzed. Data analysis was performed from July 2023 to August 2024. Main Outcomes and Measures Percentage of cases following the sequence of events of the NOTCH3 -SVD stages, and the association between the stages and ischemic stroke, intracerebral hemorrhage, global cognition, processing speed, brain volume, brain microstructural damage, and serum neurofilament light chain (NfL) level. Results The NOTCH3 -SVD staging system encompasses 9 disease stages or substages, ranging from stage 0 (premanifest stage) to stage 4B (end stage). Of all 1908 cases, which included 195 in the discovery cohort (mean [SD] age, 52.4 [12.2] years) and 1713 in the validation cohorts (mean [SD] age, 53.1 [13.0] years), 1789 (94%) followed the sequence of events defined by the NOTCH3 -SVD staging system. The NOTCH3 -SVD stages were associated with neuroimaging outcomes in the NOTCH3 cys -positive cases in the CADASIL cohorts and in the UK Biobank and with cognitive outcomes and serum NfL level in cases from the CADASIL cohorts. The NOTCH3 -SVD staging system captured disease progression and was associated with 18-year survival. Conclusions and Relevance The NOTCH3 -SVD staging system captures the full disease spectrum, from asymptomatic individuals with a NOTCH3 cys variant to patients with end-stage disease. The NOTCH3 -SVD staging system is a simple but effective tool for uniform disease staging in the clinic and in research.

Abstract Aims The increasing need for diagnostic echocardiography tests presents challenges in preserving the quality and promptness of reports. While Large Language Models (LLMs) have proven effective in summarizing clinical texts, their application in echo remains underexplored. Methods and results Adult echocardiography studies, conducted at the Mayo Clinic from 1 January 2017 to 31 December 2017, were categorized into two groups: development (all Mayo locations except Arizona) and Arizona validation sets. We adapted open-source LLMs (Llama-2, MedAlpaca, Zephyr, and Flan-T5) using In-Context Learning and Quantized Low-Rank Adaptation fine-tuning (FT) for echo report summarization from ‘Findings’ to ‘Impressions.’ Against cardiologist-generated Impressions, the models’ performance was assessed both quantitatively with automatic metrics and qualitatively by cardiologists. The development dataset included 97 506 reports from 71 717 unique patients, predominantly male (55.4%), with an average age of 64.3 ± 15.8 years. EchoGPT, a fine-tuned Llama-2 model, outperformed other models with win rates ranging from 87% to 99% in various automatic metrics, and produced reports comparable to cardiologists in qualitative review (significantly preferred in conciseness (P < 0.001), with no significant preference in completeness, correctness, and clinical utility). Correlations between automatic and human metrics were fair to modest, with the best being RadGraph F1 scores vs. clinical utility (r = 0.42) and automatic metrics showed insensitivity (0–5% drop) to changes in measurement numbers. Conclusion EchoGPT can generate draft reports for human review and approval, helping to streamline the workflow. However, scalable evaluation approaches dedicated to echo reports remains necessary.

Abstract OBJECTIVES Safety, efficacy and durability are important considerations when selecting a bioprosthesis for aortic valve replacement (AVR). This study assessed 7-year clinical outcomes and haemodynamic performance of the Avalus bioprosthesis. METHODS Patients indicated for surgical AVR were enrolled in this prospective, nonrandomized trial, conducted across 39 sites globally. The primary end-point of this analysis was freedom from surgical explant or percutaneous valve-in-valve reintervention due to structural valve deterioration (SVD) at 7 years of follow-up, determined using Kaplan–Meier (KM) analysis. We also evaluated a composite end-point of SVD and/or severe haemodynamic dysfunction requiring reintervention. Survival, valve-related safety events and haemodynamic performance were assessed. Deaths and safety events were adjudicated by an independent clinical events committee. RESULTS A total of 1132 patients underwent surgical AVR. Mean age was 70 years; 854 patients (75%) were men. The mean STS risk of mortality was 2.0 ± 1.4%, and 659 patients (58%) had a New York Heart Association classification of I/II. One or more concomitant procedures were performed in 577 patients (51%). At 7 years, the Kaplan–Meier rate of freedom from SVD/severe haemodynamic dysfunction requiring reintervention was 1.2% (0.5–2.5%) with no cases adjudicated as SVD. The survival rate was 82.6% (79.5–85.0%). The KM event rate was 5.7% (4.3–7.7%) for reintervention, 6.3% (4.9–8.3%) for endocarditis and 0.4% (0.1–1.1%) for valve thrombosis. Mean aortic gradient, dimensionless velocity index and effective orifice area were 13.8 ± 5.9 mmHg, 0.42 ± 0.09 and 1.99 ± 0.53 cm2, respectively. CONCLUSIONS This analysis demonstrated excellent durability of the Avalus valve with good clinical outcomes and stable haemodynamic performance through 7 years of follow-up.

Background: Our team recently developed an Artificial Intelligence model that enables the identification of increased left ventricular filling pressures using a single-lead electrocardiogram (AI-ECG) with excellent performance (AUC 0.91). However, its ability to predict incident heart failure (HF) in the community is yet to be evaluated. Hypothesis: We tested the hypothesis that the output from the AI-ECG will predict the long-term incidence of heart failure (HF) and HF with preserved ejection fraction (HFpEF), and would refine the HF predictive capabilities of the AHA Predicting Risk of Cardiovascular Disease EVENTs (PREVENT TM ) Equations. Methods: Leveraging the resources of the Rochester Epidemiology Project (REP) we analyzed data from patients who sought primary care in Olmsted County, MN, between 1997-2003 with passive follow-up until April 2024. We included those with a digital ECG at baseline and excluded those who were part of the original algorithm development or history of heart failure. The diagnosis of heart failure was ascertained by using ICD codes (ICD9-428,ICD10-I.50) and a word search for the terms related to heart failure. HFpEF was ascertained using the Ejection Fraction (EF) data closest to the heart failure diagnosis date, using EF more than 40% as the criterion. We tested the association between AI-ECG predicted probabilities and new-onset HF and HFpEF using Cox proportional hazard models. These models were also adjusted for cardiovascular risk factors and were stratified to evaluate the effect of the AI-ECG output on PREVENT TM -predicted HF at 10 years. Results: We included 20,276 subjects, mean age 55±14.03, 52% women, 92% non-Hispanic white. After 18.2±8.5 years of follow-up, 4,008 (19.76%) were diagnosed with HF and 3,812 (18.8%) HFpEF. Risks of HF and HFpEF significantly increased in patients with increased left ventricular filling pressures by AI-ECG, independent of risk factors, all p for trend <0.001, see Fig A-B , respectively. AI-ECG enhanced the prediction capabilities of the PREVENT TM score across all risk groups, see Fig-C. Conclusions: AI-ECG-Derived increased left ventricular filling pressure is associated with new-onset HF and HFpEF in the community and was associated with incidental heart failure at any PREVENT TM risk category. Those results suggest a potential role of AI ECG in predicting heart failure.

Background: Ventricular-arterial coupling (VAC) refers to the ratio of afterload (effective arterial elastance) to contractility (left ventricular (LV) end-systolic elastance) as an integrated marker of cardiac performance. Echocardiography might be used to evaluate VAC through a simple time-efficient bedside evaluation. Hypothesis: VAC is useful for mortality risk stratification in an unselected cardiac intensive care unit (CICU) cohort. Aims: We sought to determine whether the VAC ratio, defined using the ratio of LV end-systolic volume (LVESV) to stroke volume (SV), predicted mortality in the CICU. Methods: Consecutive patients admitted to the Mayo Clinic CICU between 2007 and 2018 were included. The simplified VAC ratio was calculated as the LVESV calculated from 2D measurements using the Teichholz formula divided by the SV calculated from the LV outflow tract pulsed wave Doppler measurement, with values >1 reflecting ventricular-arterial uncoupling. The main outcome was all-cause in-hospital mortality. Results: We included 4685 patients with a median age of 69 (58-79) years; 37% were females. The median VAC ratio was 1.0 (0.7 to 1.8) and 21% of patients had a VAC ratio >2. Most clinical and echocardiographic variables differed in patients with higher VAC ratio, reflecting greater severity of illness with worse cardiac systolic and diastolic function. A total of 329 (7.0%) patients died during hospitalization. An incremental association was observed between a higher VAC and in-hospital mortality (unadjusted OR 1.22, 95% CI 1.16-1.29, p<0.001). Patients with a VAC ratio >1 (unadjusted OR 2.85, 95% CI 2.22-3.69, p <0.001) and especially those with VAC ratio >2 (unadjusted OR 4.28, 95% CI 3.24-5.69, p<0.001) had higher in-hospital mortality overall and in each admission diagnosis subgroup of interest ( Figure ). After multivariable adjustment, patients with a VAC ratio >2 remained at higher risk of in-hospital mortality (adjusted OR 1.63, 95% CI 1.17-2.28, p = 0.01). Conclusions: Ventricular-arterial uncoupling was associated with worse outcomes in an unselected CICU cohort. The echocardiographic VAC ratio is a simple non-invasive bedside measure that can be used for risk prediction in the CICU.

Background: AI-ECG is a cost-effective tool for left ventricular dysfunction (LVD) screening. However, its cost-effectiveness for other forms of structural heart disease (SHD) is unknown. While AI-ECG is inexpensive, a drawback is low positive predictive value (PPV), which leads to high costs from unnecessary follow-up tests. Therefore, strategies to improve the yield of AI-ECG-based screening are needed. Aim: To evaluate the cost savings of a stepwise approach to SHD screening with AI-ECG followed by POCUS compared to AI-ECG alone. Methods: 286 adult outpatients undergoing AI-ECG were selected at random. Participants received same-day POCUS and had a recent TTE (our gold standard for SHD). We evaluated four SHDs: aortic stenosis (AS), cardiac amyloidosis (CA), HCM, and LVD. The costs of AI-ECG ($75) and TTE ($1,305) were obtained from Healthcare Bluebook. The cost of POCUS ($100) was estimated independently. Cost savings were analyzed for simultaneous screening for all forms of SHD and screening for individual SHDs. Results: AI-ECG identified potential SHD in 125 patients, but only 39 were true positives by TTE (31% PPV). In AI-ECG positive patients, POCUS demonstrated findings of SHD in 52/125. Compared to TTE, this stepwise approach yielded 32 true positives and 20 false positives (62% PPV). The cost per patient diagnosed with SHD was $4,733 with AI-ECG alone but decreased to $3,182 with stepwise screening (33% cost savings). Screening for individual SHDs resulted in cost reduction from $18,724 to $6,315 (66% savings) for AS, $21,023 to $12,230 (42% savings) for CA, $9,883 to $6,175 (38% savings) for HCM, and $4,019 to $3,582 (11% savings) for LVD. Conclusions: Stepwise screening for SHD with AI-ECG followed by POCUS significantly reduces costs compared to AI-ECG alone. We also suggest a model for parallel screening for multiple SHDs, which is likely more cost-effective than screening for individual SHDs.

Background: Left ventricular diastolic dysfunction (LVDD) predicts mortality in cardiac intensive care unit (CICU) patients. A novel artificial intelligence enhanced electrocardiogram (AIECG) algorithm can predict LVDD and mortality in general populations but has not been examined in the cardiac intensive care unit (CICU). We aim to assess if LVDD by AI-ECG is associated with in-hospital and one-year mortality in CICU patients. Methods: In this retrospective cohort study, we included consecutive unique adults admitted to the Mayo Clinic CICU from 2007 to 2018 with an admission AIECG, which AI assigned LVDD grade (0 to 3). Medial mitral E/e’ ratio >15 on transthoracic echocardiogram (TTE) defined elevated filling pressures. AIECG and TTE assessment of LVDD were used to assign patients to four groups based on TTE as gold standard: true and false negative, and true and false positive. In-hospital mortality was evaluated using multivariable logistic regression. One-year survival was evaluated using Kaplan-Meier curves and multivariable Cox proportional-hazards. Results: We included 11,868 patients (median age 69.5 years, 37.7% females); 48% had heart failure and 44% had acute coronary syndromes. AIECG LVDD grades were: grade 0 (normal), 33%; grade 1, 7%; grade 2, 39%; grade 3, 21%. In-hospital (adjusted OR) and one-year (adjusted HR) mortality increased in each higher AIECG LVDD grade (Figure A/B), before and after adjustment including TTE measurements. Patients with grade 2-3 LVDD by AIECG and medial mitral E/e’ ratio >15 by TTE (true positive) had the highest in-hospital (adjusted OR 2.5 [1.7-3.9]) and one-year (adjusted HR 1.9 [1.5-2.5]) mortality (Figure C/D), and mortality was elevated similarly in patients with either grade 2-3 LVDD by AIECG (false positive) or medial mitral E/e’ ratio >15 by TTE (false negative). Conclusions: The AIECG LVDD grade was strongly associated with in-hospital and one-year mortality in CICU patients, even after adjusting for clinical variables and TTE measurements. Patients with concordant AIECG and TTE for elevated filling pressures (true positive) were at highest risk.

Abstract Background Heart failure (HF) and atrial fibrillation (AF) are intertwined, sharing common risk factors and influencing each other in a reciprocal manner. While left ventricular diastolic dysfunction (LVDD) stands as a hallmark of HF's hemodynamic profile, its direct correlation with heightened AF risk remains uncertain. Our recent validation of an artificial intelligence-enabled electrocardiogram (AI-ECG) algorithm for LVDD detection has opened new avenues. Yet, whether AI-ECG-detected LVDD correlates with long-term AF risk remains unexplored. Methods We performed a retrospective study among all patients with a comprehensive LVDD assessment from the test population of the AI-ECG LVDD study between September 2001 and June 2022. Patients with prior documented AF according to health records or previous ECG were excluded. Patients were classified by AI-ECG as normal diastolic function (DF), grade 1 (G1), grade 2 (G2), or grade 3 (G3) LVDD. We assessed the risk of AF across AI-ECG LVDD grade, with normal DF as reference, with competing risk models. Results Of 97,023 patients free of AF at baseline, 63,533 (65.4%), 10,776 (11.1%), 18,940 (19.5%), and 3,774 (3.9%) were classified as normal DF, G1-LVDD, G2-LVDD, and G3-LVDD, respectively. Worse AI-ECG LVDD was associated with older age, lower left ventricular ejection fraction (LVEF), and higher rates of HF, diabetes, hypertension, chronic pulmonary disease, renal failure, and cardiovascular disease (p-of-trend&lt;0.001 for all). Over a median follow-up of 4.8 years (interquartile range 1.8-9.2 years), new-onset AF occurred in 6,795 (7.0%) patients. In multivariable survival analysis, adjusted to multiple risk factors including LVEF and clinical HF, G2 and G3 LVDD, representing patients with high filling pressures, were independently associated with a higher AF-risk [G2-LVDD: adjusted hazard ratio (aHR) 1.64 (95% confidence interval (95%CI) 1.52-1.73), G3-LVDD: aHR 2.24 (95%CI 2.02-2.48)]. Conclusion The AI-ECG LVDD algorithm independently predicts long-term AF risk, regardless of LVEF and clinical HF status, highlighting its potential for identifying high-risk populations and guiding proactive monitoring and management.