Kane, Garvan C.

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/Introduction Close monitoring of aortic stenosis (AS) by follow-up echocardiography is recommended by all Cardiology and Imaging Societies’ guidelines. Whether these guidelines are strictly followed is unknown. Purpose We aimed to describe our institution’s practice patterns for echocardiographic monitoring in patients with aortic sclerosis (AScl) and AS of any severity. Methods Adult patients residing in our institution’s county with an echocardiographic diagnosis of AScl or AS between 01/2005-01/2022 were identified and classified into 4 groups: AScl, mild AS, moderate AS, or severe AS, at each echocardiogram during the study timeframe. Kaplan Meier analyses were used to evaluate the composite outcome, the occurrence of follow-up echocardiogram or death. Patients were censored at the time of aortic valve replacement/repair, heart transplant, or last clinical follow-up. Guideline follow-up was considered appropriate when the primary outcome occurred by 5 years (AScl/mild AS), 2 years (moderate AS), and 1 year (severe AS). Results A total of 23,726 echocardiograms from 9,578 unique patients were included. At index echocardiogram, median patient age was 74 years (IQR 65-82) and 4,806 (50.2%) were women. AScl was observed in 7,358 (76.8%) cases, mild AS in 1,442 (15.1%) cases, moderate AS in 479 (5%), and severe AS in 301 (3.1%) cases. Rates of composite outcome achievement by the end of the guideline-recommended interval were 81%, 90%, 80%, and 72% in AScl, mild, moderate, and severe AS, respectively. Rates for men were 83%, 92%, 82%, and 75% in these groups, while rates for women were 78%, 88%, 78%, and 68%, respectively (Figure 1). Follow-up rates were similar before and after 2012 (when transcatheter aortic valve replacement was approved for treatment of severe AS in high-risk surgical patients in the USA). Follow-up rates were higher in patients managed by cardiovascular providers compared to non-cardiovascular providers (Figure 2). Conclusion Depending on disease severity, between one fourth and one tenth of patients remained alive and unfollowed at the end of their guideline-recommended surveillance interval. There is significant variability in echocardiogram monitoring based on sex and referring provider specialty. Figure 1 Figure 2

Abstract Background Transthoracic echocardiography is the primary modality used for the assessment of the pericardial space. Guidelines recommend semi-qualitative assessment of the size of a pericardial effusion with characterization as trace, small, moderate or large. The reproducibility and association of this characterization is variable. Whether simple 2D-based quantitative measures of effusion size better associate with pericardial volumes is unclear. An accurate measure of pericardial volume would be helpful for tracking patients over time. Purpose To test whether 2D-based measures of the pericardial space could accurately predict pericardial volumes. Methods We retrospectively assessed a series of echos performed immediately prior to pericardiocentesis. 2D-based area tracings from the parasternal long and short axis at the papillary muscle level as well as 2D volumetric tracings from the apical 4 chamber view using the Simpson's method were tested with the operator blinded to the true pericardial volume (recorded at pericardiocentesis). Patients who underwent pericardiocentesis in setting of acute perforation were excluded as were patients where pericardiocentesis was unsuccessful or incomplete. Pericardial fluid area or volume was calculated by taking the difference between the measures obtained by tracing the epicardial border of the heart and pericardium (figure 1). Results The median pericardiocentesis (n=118) fluid volume was 500 mL (IQR 350 – 750 mL) with a range, 95–2300 mL. The pericardial fluid was serous (22%), sero-sanguineous (37%) and sanguineous in 41%. The effusion was malignant in 24 cases and due to inflammation in 42 cases. Pericardial area traces from either the parasternal short (r=0.56, p<.0001) or long axis (r=0.62, p<.0001) correlated modestly with measured pericardial volume. The average volume estimated echocardiographically by the Simpson’s method was 580 ± 359 mL (range, 85.8–2419 mL). There was stronger linear correlation between echocardiographic (apical 4-chamber measurement) and pericardiocentesis-derived volumes (r=0.92, p < 0.0001; figure 2A). Etiology of the pericardial effusion was not associated with estimates of pericardial volumes. There was a large overlap in pericardial volume amongst the reading physician qualitative grading of effusion size (figure 2B). Categorization of pericardial effusion size was improved when based on volumetric estimates (Kappa 0.65) rather than physician estimates (Kappa 0.32; Figure 2B). Variation between measured pericardial volume and actual pericardial volume was most related to the quality of the image and the likely extent to which the pericardial fluid was not entirely captured in the image window. Conclusion Two-dimensional transthoracic echocardiography using biplane Simpson’s method of disks can simply and reasonably accurately estimate the pericardial effusion volume. This technique may add value in the serial assessment of pericardial effusions. Figure 2

Abstract Background Catheter ablation for atrial fibrillation (AF) improves quality of life and lowers cardiovascular adverse events. However, AF recurrence rates remain high - thus the need for better or improved predictors of AF recurrence. The role of left atrial (LA) stiffness remains unclear, as prior findings were controversial. Purpose To explore the relationship between a noninvasive LA stiffness index (LAstiffn) and AF recurrence after catheter ablation. Methods We analyzed a prospectively recruited cohort of patients who underwent catheter ablation for AF, were in sinus rhythm at 3 months post-ablation, had no significant (< moderate) valvular disease, and had LA volumes and LA diastolic function prospectively measured. LAStiffn was calculated as (E/e’)/LA emptying fraction (LAEF) ratio (abnormal defined as >15/45≈0.3). Outcome endpoint was the first documented AF/atrial flutter episode, lasting >30s, beyond 3 months post ablation (end of blanking period). Results A total of 589 patients were studied (mean age 60±10 years; 75% men; 50% with persistent AF; Table 1). At 3 months post-ablation, mean LAVI(Left atrial volume index) was 36±10 mL/m2 and LAstiffn 0.32±0.22. LAstiffn tended to be higher in older patients, in females, and patients with persistent AF and comorbidities (hypertension, congestive heart failure, coronary artery disease, CHA2DS2-VASc score ≥2, etc). At multivariable regression analysis, LAstiffn correlated with LV size and mass, degree of mitral/tricuspid regurgitation, and right ventricular systolic pressure. At 1 year, 3 years, and 8 years follow up, AF recurred in 118, 191, and 347 patients, respectively. At univariate Cox proportional hazards regression analysis, LAstiffn index >0.3 was significantly associated with AF recurrence at 1 year (log-rank P=.0005), 3 years (P=.0002), and 8 years follow up (P<.0001; Figure). In multivariate analysis including all clinical and laboratory factors with P<.10 in univariate analysis, LAstiffn >0.3 remained an independent factor for AF recurrence only at 3-years (adjusted HR 1.40 [1.03-1.91], P=.03) and 8 years follow up (adjusted HR 1.65 [1.29-2.13], P<.0001) after adjustment for age, sex, type of AF (persistent/paroxysmal), LA volume index (LAVi), obstructive sleep apnea, and prior pacemaker/ICD implantation (best independent factors); P=.14 at 1 year follow up. In ROC analysis, LAstiffn (AUC 0.61, P=.001) performed slightly better than LA deformation LAEF (AUC 0.59, P=.002) or E/e’ (AUC 0.58, P=.03), though with modest sensitivity/specificity (58%/62%). Conclusions LAstiffn may reflect LA myopathy that is likely due to the cumulative effects of comorbidities, diastolic dysfunction, and intrinsic LA tissue remodeling. LA stiffening may be a substrate facilitating redevelopment of AF, thus patients with increased LAstiffn may need more frequent monitoring to prevent/treat AF recurrence earlier.

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 <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

Abstract Background/Introduction Tricuspid valve regurgitation (TR) is a common valvular disease associated with increased mortality. There is a need for tools to assess the interaction between the pulmonary artery (PA) circulation and the right ventricle (RV) in patients with TR and to investigate their association with outcomes. Various echo parameters have emerged that assess RV-PA coupling, including the ratio of TAPSE to RV systolic pressure (RVSP) and the PA pulsatility index (PAPi). The effective PA elastance (PA Ea) is a composite measure of RV afterload that refers to the measure of the pulmonary vascular load that the RV must overcome to eject blood into the PA. PA Ea is simple to estimate by echo and found to be an independent haemodynamic risk measure in various left heart and pulmonary hypertension (PH) diseases. Whether PA Ea discriminates risk in unselected patients with significant TR and how it compares to other measures of RV-PA coupling is untested. Purpose To ascertain the prognostic value of PA Ea in patients with TR. Methods In consecutive patients with a first diagnosis of ≥ moderate TR (regardless of aetiology), we compared all-cause mortality at five years based on the PA Ea (defined as the RVSP/stroke volume as measured by transthoracic echocardiography). As stroke volume was measured by Doppler at the left ventricular (LV) outflow tract, patients with > moderate aortic valve regurgitation were excluded. The Tricuspid Regurgitation Impact on Outcomes (TRIO) score was calculated as previously described. PA Ea was separated into 4 groups for comparison based on the separation of quartiles of PA Ea rounded to one decimal place. Results In the 13,608 patients studied, PA Ea could be calculated in 12,682 patients (94.4%). The median PA Ea was 0.68 mmHg/mL (IQR 0.50, 0.92). Increasing levels of PA Ea were associated with clinical comorbidities including heart failure, liver and kidney disease and clinical markers of risk such as the TRIO score. Increasing levels of PA Ea were also associated with larger RVs, worse RV systolic function, higher NT-pro BNP levels, and greater degrees of right heart failure (Table). Each quartile of PA Ea was associated with a significant increase in all-cause mortality (Figure). After adjusting for age and sex, PA Ea was associated with higher risk of death (HR 2.41 (2.28-2.56); p<.0001). While worsening degrees of PA Ea correlated with both declining levels of TAPSE/PASP and PAPi (Table), PA Ea was independently predictive of outcome in a combined model: PA Ea HR 1.65 (1.51-1.80, Chi-squ 120, p<.0001); PAPi HR 0.84 (0.80-0.89, Chi-squ 48, p<.0001) and TAPSE/PASP HR 0.32 (017-0.60, Chi-squ 12, p=.0004). Conclusion(s) In patients with significant TR, PA Ea is highly feasible and higher PA Ea is progressively associated with RV dysfunction, right heart failure, and worse survival. Incorporating PA Ea into the routine echo assessment may help stratify disease severity in patients with significant TR. Table Assoc. of PA Ea with mortality in TR

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.

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.