Oh, Jae K.

Abstract Aims To develop a deep learning model that: (i) utilizes transthoracic echocardiography (TTE) clips to detect left ventricular (LV) enlargement without being provided information regarding a patient’s sex and body size; and (ii) can be accurately applied to clips acquired using either standard comprehensive TTE or handheld cardiac ultrasound (HCU). Methods and results Using retrospective TTE data (training: 8722 patients; internal validation: 468 patients), we developed a deep learning model that estimates a patient’s end-diastolic LV volume (indexed to body surface area and normalized across the sexes), and then thresholds this estimate to perform the following classifications: (1) normally sized LV vs. ≥ mild LV enlargement; (2) normal/mildly enlarged LV vs. ≥ moderate LV enlargement. For retrospective datasets, the model showed strong performance in TTE across three geographically distinct locations (Minnesota and Wisconsin: 1082 patients, AUC = 0.925 and 0.953 for classifications 1 and 2, respectively; Arizona: 1475 patients, AUC = 0.935 and 0.969; and Florida: 1481 patients, AUC = 0.934 and 0.970). Additionally, performance was strong for both TTE and HCU clips collected from a prospective cohort of 410 patients who underwent HCU immediately following TTE (TTE: AUC = 0.925 and 0.971; HCU: AUC = 0.874 and 0.902, for classifications 1 and 2, respectively). Conclusion An automated deep learning model applied to TTE or HCU images accurately categorizes LV volumes. These results lay a foundation for future work aimed at optimizing clinical outcomes for heart failure patients by enabling early detection of LV enlargement across various point-of-care settings.

ABSTRACT Background The assessment of aortic stenosis (AS) severity remains a challenge in some patients, and hemodynamic exercise testing has been proposed as a diagnostic tool in this population. However, the current understanding of exercise hemodynamics in AS is limited. Methods Retrospective review of 34 adults (aged ≥ 18 years) with ≥ moderate AS and preserved left ventricular ejection fraction (LVEF) undergoing exercise invasive hemodynamics (supine cycle protocol) with simultaneous measurement of aortic and left ventricular pressures. Results Age was 77.1 (IQR 68.6; 84.1) years, and 50% were female. LVEF was 62.1 ± 6.6%. All patients were symptomatic. Resting aortic valve area (AVA) was 1.0 ± 0.2 cm 2 and aortic valve (AV) systolic mean gradient 22.0 ± 7.3 mmHg. At peak exercise (40 [IQR 30; 60] W), AV systolic mean gradient (Δ3 [0.6; 7] mmHg, p < 0.001) and AVA (Δ0.2 [0; 0.6] cm 2 , p = 0.002) significantly increased, while stroke volume (SV) did not (Δ6.8 ± 19.4 ml; p = 0.07). Exercise‐induced changes in AV systolic mean gradient were directly related to changes in cardiac output ( r = 0.53, p = 0.003), being inversely related to exercise systemic vascular resistance ( r = −0.60, p = 0.002). Elevated pulmonary artery wedge pressure was present in 41.2% at rest (≥ 15 mmHg) and 69.7% during exercise (≥ 25 mmHg). Conclusions Symptomatic patients with ≥ moderate AS and preserved LVEF experience small increases in AV mean gradient with exercise, and unlike the normal physiological response to exercise, there was no significant increase in SV. In most patients, AVA rose during exercise. Exercise‐induced elevation in filling pressures was highly prevalent.

Background Left ventricular diastolic dysfunction (LVDD) predicts mortality in patients in cardiac intensive care units. An artificial intelligence enhanced ECG (AIECG) algorithm can predict LVDD and mortality in general populations but has not been examined in cardiac intensive care units. Methods This historical cohort study included consecutive adults admitted to Mayo Clinic cardiac intensive care unit from 2007 to 2018 with an admission AIECG. The AIECG assigned the LVDD grade (0–3). Medial mitral E/e' ratio >15 on transthoracic echocardiogram (TTE) defined elevated filling pressures. In‐hospital and 1‐year mortality was evaluated, before and after multivariable adjustment. Results We included 11 868 patients (median age 69.5 years, 37.7% female); 48% had heart failure and 44% had acute coronary syndromes. AIECG LVDD grade was 0 (normal), 33%; 1, 7%; 2, 39%; and 3, 21%. In‐hospital and 1‐year mortality increased in each higher AIECG LVDD grade. After adjustment, each higher AIECG LVDD grade was associated with higher in‐hospital (adjusted odds ratio [OR], 1.22 [95% CI, 1.13–1.32]) and 1‐year mortality (adjusted hazard ratio [HR], 1.23 [95% CI, 1.19–1.29]); this persisted after adjustment for TTE measurements. Patients with grade 2 or 3 LVDD by AIECG and medial mitral E/e' ratio >15 by TTE had the highest in‐hospital (adjusted OR, 2.54 [95% CI, 1.69–3.88]) and 1‐year (adjusted HR, 2.03 [95% CI, 1.65–2.48]) mortality, whereas patients meeting either of these criteria had similar, elevated mortality. Conclusions The AIECG LVDD grade was strongly associated with in‐hospital and 1‐year mortality in patients in cardiac intensive care units, even after adjusting for clinical variables and TTE measurements. Patients with concordant AIECG and TTE for elevated filling pressures were at highest risk.

Abstract Background Moderate-severe mitral annulus calcification (MAC) and left ventricular (LV) diastolic dysfunction are both linked to increased risks of heart failure and mortality. Assessing LV diastolic function (LVDF) in moderate-severe-MAC by echocardiography is frequently challenging and unreliable. We recently validated an AI-ECG model for LVDF. We aimed to determine if this tool can predict long-term mortality in patients with moderate-severe-MAC and whether it can help establish MAC-specific echocardiographic LVDF parameter cutoffs. Methods This retrospective study included all patients from the AI-ECG LVDF study test cohort who underwent comprehensive transthoracic echocardiography confirming moderate-severe-MAC and ECG within fourteen days of each other at Mayo Clinic between 09/2001 and 06/2022. AI-ECG LVDF was determined based on the index ECG. Patients were categorized based on AI-ECG into groups representing normal/grade-1 LVDF, grade-2 LVDF, or grade-3 LVDG (DF-1, DF-2, and DF-3, respectively). Results Of 2,506 patients with moderate-severe-MAC [mean age 77, 64.1% females], 709 (28.3%), 1,510 (60.3%), and 287 (11.5%) were classified as DF-1, DF-2, and DF-3, respectively. Worse LVDF grade was associated with older age, male sex, lower LV ejection fraction, and higher rates of noncardiovascular and cardiovascular comorbidities. Over a median follow-up of 2.8 years, 1,059 (42.3%) patients died. In multivariable survival analysis, DF-2 [adjusted hazard ratio (aHR) 1.43, 95% confidence interval (95%CI) 1.21-1.68] and DF-3 (aHR 1.54, 95%CI 1.22-1.93) were independently associated with a higher risk of death (figure). Findings were also consistent after adjusting to mitral inflow gradients. When comparing LVDF echocardiographic parameters in controls without MAC matched by age, sex, left ventricular ejection fraction, and AI-ECG DF grade, significant differences were observed. Patients with moderate to severe MAC generally exhibited lower e' velocities, higher TR velocities, elevated E/e' ratios, and increased LAVi. Interestingly, the E/A ratio between MAC patients and their matched controls across AI-ECG LVDF grades remained consistent. Conclusion AI-ECG LVDF predicts mortality risk in patients with moderate-severe-MAC, regardless of mitral inflow gradients. Utilizing AI-ECG LVDF might aid in the risk stratification of patients with significant MAC.

Abstract Background AI-enhanced electrocardiogram (AI-ECG) is a cost-effective tool for left ventricular dysfunction screening. However, its cost-effectiveness for other forms of structural heart disease (SHD) is unknown. While AI-ECG is inexpensive, the relatively low positive predictive value (PPV) of many models can lead to high costs from unnecessary follow-up tests like transthoracic echocardiography (TTE). Therefore, strategies to improve the yield of AI-ECG-based screening are needed. Purpose To evaluate the cost savings of a stepwise approach to SHD screening using AI-ECG followed by point-of-care ultrasound (POCUS) compared to AI-ECG alone. Methods 286 adult outpatients undergoing AI-ECG were randomly selected to undergo same-day POCUS. All participants were required to have a recent TTE, our gold standard for SHD diagnosis, for comparison purposes. We evaluated four SHDs: aortic stenosis, cardiac amyloidosis, hypertrophic cardiomyopathy, and left ventricular dysfunction (defined as left ventricular ejection fraction &lt;50%). The costs of AI-ECG ($75/test) and TTE ($1,305/test) were sourced from Healthcare Bluebook, while the cost of POCUS ($100/test) was independently estimated. We compared the costs of screening with AI-ECG alone to stepwise screening with AI-ECG followed by POCUS. Costs were analyzed for two paradigms: screening for all forms of SHD in parallel and screening for each SHD individually. Results AI-ECG alone identified potential SHD in 125 out of 286 patients. When compared to TTE, only 39 out of 125 were true positives (31% PPV). Among the AI-ECG-positive patients, POCUS demonstrated findings of SHD in 52 out of 125 cases. When compared to TTE, this stepwise approach yielded 32 true positives and 20 false positives (62% PPV). In the parallel screening paradigm, the cost per patient diagnosed with SHD was $4,733 with AI-ECG alone, which decreased to $3,182 with stepwise screening (33% cost savings). For the individual SHD screening paradigm, cost reductions were as follows: aortic stenosis ($18,724 to $6,315, 66% savings), cardiac amyloidosis ($21,023 to $12,230, 42% savings), hypertrophic cardiomyopathy ($9,883 to $6,175, 38% savings), and left ventricular dysfunction ($4,019 to $3,582, 11% savings). Conclusions Stepwise SDH screening with AI-ECG followed by POCUS markedly reduces costs compared to AI-ECG alone. The greatest cost savings for individual SHD screening were observed for aortic stenosis and cardiac amyloidosis, conditions where AI-ECG models have lower PPVs. Parallel screening for multiple SHDs is also less costly than screening for any individual SHD alone. Therefore, a parallel screening approach may maximize SHD detection while minimizing screening costs. Stepwise Screening Approach for SHD SDH Screening Costs

ABSTRACTBackgroundThe self‐expanding, supra‐annular Evolut valve is an established platform for Transcatheter Aortic Valve Implantation (TAVI). Evolut PRO introduced an outer sealing wrap to mitigate paravalvular leakage. We evaluated the 3‐year clinical outcomes and valve performance of the Evolut PRO in standard clinical practice for severe aortic stenosis (AS) patients at intermediate or higher risk for surgery.MethodsThe FORWARD PRO prospective, single‐arm, multicentre, post‐market clinical study enrolled 638 patients with native aortic valve stenosis or failed surgical bioprosthetic aortic valve undergoing TAVI, at intermediate or high risk, with the Evolut PRO valve. Clinical and serial echocardiographic outcomes were followed‐up for 3 years.ResultsTAVI using Evolut PRO was attempted in 629 AS patients (implanted in 97%) (mean age 81.7 years; STS PROM score, 4.7%). At 3 years all‐cause mortality was 25.0%, disabling stroke 6.5% (all‐cause mortality or disabling stroke, 28.5%) and rate of new permanent pacemaker implantation 24.7%. Excellent valve haemodynamics were maintained (mean gradient 8.8 ± 4.7 mm Hg; mean effective orifice area 2.0 ± 0.5 cm2) at 3 years. In a paired analysis of patients with ≥ mild paravalvular leakage (PVL) at discharge, more than two‐thirds demonstrated improved PVL at 3 years. Patients with ≥ mild PVL at discharge had higher median total calcium volume than those with no/trace PVL (p < 0.001).ConclusionsIn clinical practice TAVI with the Evolut PRO valve is associated with favorable clinical outcomes and excellent haemodynamic performance out to 3 years. The observation of improvements in PVL over time warrants further research.

Abstract Aims Cardiogenic shock (CS) is a critical manifestation of severe cardiac dysfunction, necessitating precise evaluation of left ventricular (LV) function by transthoracic echocardiography. The prognostic value of global longitudinal strain (GLS) has not been examined in patients with CS. Therefore, we aimed to assess the prognostic significance of GLS in patients with CS. Methods and results This was a retrospective study of patients with CS from 2007 to 2018 who had a transthoracic echocardiography performed within 24 h of admission. GLS was measured, and conventional parameters were obtained. LV dysfunction was categorized by GLS: &gt; 9.7% (Quartile 1), 7.0% &lt; GLS ≤ 9.7% (Quartile 2), 5.0% &lt; GLS ≤ 7.0% (Quartile 3), and ≤5.0% (Quartile 4). Outcomes included in-hospital and 1-year all-cause mortality. Among 623 patients with CS with the median LVEF of 31% [inter-quartile range (IQR): 24–41%] and the median GLS of 7.0% (IQR: 5.0–9.7%), in-hospital mortality was 29%. Mortality increased across GLS quartiles: Quartile 1: 17%; Quartile 2: 22%; Quartile 3: 35%; and Quartile 4: 42%. GLS remained the only independent echocardiographic predictor of in-hospital mortality after adjusting for clinical covariates (adjusted odds ratio: 1.23 per 1% decrease, 95% confidence interval: 1.04–1.46, P = 0.015). GLS independently predicted 1-year all-cause mortality (P &lt; 0.001). The prognostic value of GLS was superior in cases with acute coronary syndrome. A classification and regression tree analysis identified GLS as the most important echocardiographic variable for predicting in-hospital mortality. Conclusion GLS independently predicted short- and long-term mortality in patients with CS, surpassing conventional echocardiographic parameters in prognostic value, supporting its potential role in risk stratification in this population.

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 &lt; 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.