Citations

Importance Timely identification of aortic stenosis (AS) is essential for appropriate clinical management, yet screening remains limited by dependence on comprehensive echocardiography and trained imaging personnel. Objective To develop and validate a deep learning algorithm for detection of moderate or greater AS and prospectively evaluate its performance using artificial intelligence (AI)–guided focused cardiac ultrasound (FoCUS) acquired by novice operators. Design, Setting, and Participants This diagnostic study included retrospective algorithm development and validation and prospective evaluation of AI-guided FoCUS across Mayo Clinic sites in the Midwest, Arizona, and Florida. The model was developed using 6753 patients and evaluated in internal validation (n = 852), internal test (n = 844), and validation (n = 1912) cohorts. Performance was assessed on FoCUS acquired by experienced sonographers (n = 602) and prospectively by novice operators (n = 1302). The retrospective model development and validation cohorts comprised studies performed from January 2005 through September 2022. Prospective study was conducted in 2 enrollment periods from June to August 2024 and from June to September 2025. Participants from both periods were combined to comprise the final prospective cohort. Exposure AI-guided FoCUS acquisition and automated deep learning–based assessment for detection of moderate or greater AS. Main Outcomes and Measures Detection of moderate or greater AS. Performance was assessed using area under the receiver operating characteristic curve (AUROC), sensitivity, specificity, and positive predictive value. Results The model demonstrated excellent discrimination in the internal test cohort (AUROC, 0.99; 95% CI, 0.98-1.00) and geographically distinct validation cohorts in Arizona (AUROC, 0.99; 95% CI, 0.97-1.00) and Florida (AUROC, 0.99; 95% CI, 0.96-1.00). Among FoCUS examinations acquired by experienced sonographers, sensitivity was 95% (95% CI, 82-99) and specificity was 97% (95% CI, 95-98). In the prospective novice-operator cohort, 1258 of 1302 examinations (96.6%) were suitable for automated analysis. Sensitivity was 93% (95% CI, 82-99) and specificity was 96% (95% CI, 95-97). Expert review of AI-positive and uninterpretable examinations increased the positive predictive value from 49.4% to 91.1%, with sensitivity of 85.4%. Conclusions and Relevance A deep learning algorithm accurately detected moderate or greater AS across validation cohorts in this study. In prospective evaluation, novice operators were able to acquire AI-guided FoCUS examinations that enabled accurate detection of moderate or greater AS. These findings support a scalable strategy that may expand access to AS detection in settings with limited echocardiography resources.

Background Transcatheter edge‐to‐edge repair (TEER) and replacement (TTVR) have emerged as new modalities to treat patients with symptomatic significant tricuspid regurgitation. This study aimed to compare invasive hemodynamic and right ventricular (RV) changes and symptom improvement over 1 year. Methods Patients who underwent TEER/TTVR at Mayo Clinic (Rochester, MN, 2017–2024) were included. Hemodynamic profiles were described before and immediately after intervention, in addition to RV enlargement/dysfunction ≥moderate at 30 days and change in symptoms over time. Results Of 100 patients included (50 per group, median age 81 versus 80 years and female 62% versus 42%, in TTVR and TEER, respectively), all had ≥ moderate–severe symptomatic tricuspid regurgitation. Post intervention, mean right atrial pressure decreased in TEER (16 to 14 mm Hg, P <0.001), V wave decreased in both groups (to 16 mm Hg, P <0.001). RV enlargement was less prevalent in both cohorts at 30 days (60%–40% in TEER, P =0.01, and 72 to 58% in TTVR, P =0.07), yet prevalence of RV dysfunction decreased only in TEER (26 to 15%, P =0.17) as opposed to TTVR (31 to 44%, P =0.13). TTVR resulted in a higher stroke volume index and more complete tricuspid regurgitation elimination at 30 days. Both groups resulted in similar improvements in New York Heart Association class, with overall similar survival. Conclusions TEER was associated with a greater reduction in right atrial pressure and more favorable RV remodeling at 30 days, as opposed to TTVR, which achieved more complete and sustained elimination of tricuspid regurgitation with higher forward stroke volume.

Abstract Aims Heart failure is prevalent; however, there is no cost-effective screening option. Against formal echocardiography, we assessed the diagnostic performance of focused cardiac ultrasound (FoCUS), performed by novice users guided and interpreted by artificial intelligence (AI) for the assessment of left ventricular ejection fraction (LVEF). Methods and results We prospectively enrolled 496 adults referred for diagnostic echocardiography. Novice operators (without clinical or imaging experience) underwent a 4-h imaging workshop, then performed FoCUS using a point-of-care device (Philips Lumify) utilizing real-time AI-image guidance (UltraSight). Images were assessed by AI-image interpretation software (Mayo Clinic), and two expert blinded echocardiologists. Median age was 67, 39% female, and body mass index range 17–56 kg/m2. Forty-one subjects (8.3%) exhibited moderate or greater LV dilatation and 28 (5.6%) had LVEF &lt;40%. The median scan time was 4 min (IQR 3–5). Adequate views were achieved in 95.0% and 97.4% of subjects for AI interpretation and expert analysis, respectively. A two-step diagnostic screening process for low EF in which only abnormal AI reads or uninterpretable scans were reviewed by experts (15.1%) had a sensitivity 96.2%, specificity 95.4%, PPV 54.3%, and NPV 99.8%. A subsequent prospective validation study of 344 subjects demonstrated similar results (sensitivity 100%, specificity 99.4%). Conclusion In this early feasibility investigation, AI-guidance technology embedded on a handheld device, enabled novice users without clinical or imaging experience to acquire sufficient quality images to accurately assess LVEF with minimal training. The technology evaluated in this study may hold promise for AI-guidance and interpretation to facilitate low-cost screening for cardiac dysfunction.

Abstract Background Right ventricular (RV) systolic function is an independent predictor of outcome, but a robust automated method of quantitation is lacking. Purpose To develop and validate a deep learning model for quantifying RV systolic function from 2D echo clips and assess its prognostic value in various loading states and left-heart disease. Methods A deep learning convolutional neural network (CNN) was developed to quantitate RV systolic function using all available apical 4 chamber (A4C) views from 13,039 patients (61,187 A4C video clips) in a US institution. Videos were converted to frames of 256x256 grayscale pixels, with graphics, including the ECG, removed. The model used the S3D architecture, a 3D-CNN with many of the spatial and temporal convolutions separated. RV free wall longitudinal strain (RVFWLS) was used to define RV function: normal (≤-25%); mild (-20% to –24%); moderate (-15% to –19%) and severe RV dysfunction (0% to –14%). The AI-estimate was the average of multiple 32-frame segments for each clip identified as an A4C, including both standard and RV-focused variations. The model was validated in four distinct clinical cohorts from independent data sources: 1) 1365 patients referred to an external diagnostic echocardiography lab in a different US state; 2) 569 patients recruited prospectively with known or suspected pulmonary hypertension (PH); 3) 416 patients with moderate or greater tricuspid valve regurgitation (TR); 4) 872 patients imaged at an Eastern European University with left-sided cardiac diseases (valvular disease, cardiomyopathies, etc.), athletes, or healthy volunteers. Results Model output was strongly correlated with the presence of RV dysfunction by manual measurement [AUC 0.907 (95% CI: 0.888-0.926)] in the internal validation set. Results were similar in an external validation US cohort [N=1365; AUC 0.919 (95% CI: 0.899-0.939)]. When the model was applied to 569 patients with known or suspected PH, presence and severity of the AI measures of RV dysfunction were strongly associated with functional class, 6 min walk distance, NT-proBNP levels and right heart failure (p&lt;0.001). The presence and severity of RV dysfunction (as categorized by the AI model) was strongly associated with all-cause mortality in patients with PH (Figure 1A) and in patients with significant TR (Figure 1B). The European cohort was a geographically and institutionally distinct cohort with a low prevalence of &gt;mild TR (10.8%) or PH (6.4%). In this cohort the AI model predicted a reduced RVEF (&lt; 45%) with an AUC of 0.864 (95% CI: 0.831-0.898) and associated with both all-cause mortality (Figure 2A) and a composite endpoint of heart failure hospitalization or death (Figure 2B). Conclusions A fully automated, AI-based assessment of RV systolic function, using 2D apical 4 chamber echo views alone, is highly feasible and can accurately categorize disease severity and predict outcome across a wide spectrum of cardiovascular conditions.Figure 1 Figure 2

Background Artificial intelligence (AI)–enabled electrocardiography has emerged as a tool for detecting cardiac dysfunction. The prognostic relevance of AI‐enabled electrocardiography–derived diastolic dysfunction (DD) in patients undergoing transcatheter aortic valve replacement had not been assessed. Methods We analyzed 3197 patients undergoing transcatheter aortic valve replacement for severe aortic stenosis between 2010 and 2023 with baseline 12‐lead ECGs processed by a validated AI model to classify diastolic function (grades 0–3). Multivariable Cox models and nested model comparisons assessed associations with all‐cause mortality, including a prespecified analysis in patients with indeterminate echocardiographic grading. Trajectories were defined by change in AI‐enabled electrocardiography DD grade (<2 versus ≥2) from baseline to 30‐day or 1‐year follow‐up. Results At baseline, 21% had grade 3, 57% had grade 2, 8% had grade 1, and 14% had grade 0 AI‐enabled electrocardiography DD. Higher grades were associated with adverse cardiac remodeling and comorbidities. Over a median follow‐up of 3.4 years, grade 3 AI‐enabled electrocardiography DD independently predicted mortality (hazard ratio [HR], 1.80 [95% CI, 1.47–2.20]; P <0.001). AI‐enabled electrocardiography DD improved prognostic discrimination beyond clinical and echocardiographic measures (ΔHarrell concordance statistic, 0.016; Δ χ 2 =57; P <0.001). Among 1259 patients with indeterminate echocardiographic grading, AI‐enabled electrocardiography added prognostic value (ΔHarrell concordance statistic, 0.02; Δ χ 2 =13; P =0.006). Worsening or persistently high‐risk trajectories were associated with increased mortality (HRs, 1.45–1.80; all P <0.05). Conclusions AI‐enabled electrocardiography–derived DD independently predicts mortality after transcatheter aortic valve replacement, adds value beyond echocardiographic grading, and enables dynamic risk stratification through longitudinal tracking.

Abstract Aims Coronary angiography might contain clinically relevant information, beyond its traditional role in delineating coronary artery disease. We sought to explore the role of deep learning (DL) in detecting right ventricular dysfunction from routinely acquired cine images during coronary angiography. Methods and results 3D-convolutional neural networks (CNN) were trained to identify right ventricle (RV) dysfunction from diagnostic angiography of the right coronary artery (RCA). The model’s input was two cine angiograms from LAO and RAO projections. The model’s output was normal vs. abnormal RV function. Ground truth on RV function was obtained from the nearest transthoracic echocardiogram to the coronary angiogram. Two analyses were performed to identify (i) any RV dysfunction (≥mild) and (ii) significant RV dysfunction (≥mild–moderate). A total of 10 336 coronary angiograms from 9849 patients (mean age 66, 36% women) were included. The cohort was split into training (70%), validation (15%), and testing (15%) sets. In the testing sets, the models attained an area under the ROC curve (AUC), sensitivity, and specificity of 0.82 (95% CI: 0.80–0.84), 0.75, and 0.74, for detecting any RV dysfunction, and 0.83 (95% CI: 0.80–0.86), 0.82, and 0.70 for detecting significant (≥mild–moderate) RV dysfunction. Combining an ECG-driven AI model with the angio-driven model improved the AUC values to 0.83 and 0.87 for detecting any or advanced RV dysfunction, respectively. Conclusion A novel deep learning algorithm yielded acceptable classification accuracy in detecting RV dysfunction from routine cine angiography of the RCA. The model’s performance improved further by adding ECG to its inputs.

Background The natural history of asymptomatic moderate or severe aortic regurgitation (AR) remains uncertain, with conflicting reports about its progression and surgical timing. We aimed to quantify adverse outcomes under conservative management and evaluate the association of aortic valve replacement/repair (AVR) with mortality. Methods Systematic searches (inception–July 2025) identified cohort studies of asymptomatic moderate/severe AR. Random-effects models estimated pooled incidence rates of adverse events; fixed-effects models were used for hazard ratios (HRs) of AVR vs conservative management. Results Twenty-seven studies (4720 patients; mean age 49 years; mean follow-up 3.9 years) were included. Pooled incidence rates per 100 person-years were 1.75 (95% CI 1.27 to 2.41) for all-cause mortality, 1.29 for cardiac death, 0.29 for sudden death, 4.30 for new symptoms and 7.01 for AVR. Asymptomatic low left ventricular ejection fraction occurred in only 0.9 per 100 person-years. Mortality rates were more than double those of the general population across age groups—2.45 (1.90 to 3.18) per 100 person-years for cohorts with mean age ≥50 years versus 0.59 (0.29 to 1.21) for younger cohorts. Early AVR was associated with lower mortality (pooled HR 0.33; 95% CI 0.30 to 0.37). Conclusion Asymptomatic moderate/severe AR carries significant excess mortality irrespective of age, contradicting its historically benign reputation. Given the rarity of asymptomatic LV dysfunction, earlier intervention guided by more sensitive markers of LV damage may improve outcomes, although heterogeneity and study quality warrant cautious interpretation. PROSPERO registration number CRD42024522683.

Background: Tricuspid regurgitation (TR) is associated with significant morbidity, but individualized treatment and timing of intervention are yet to be defined. We previously proposed and validated artificial intelligence electrocardiography (AI-ECG) scores for various diseases. Whether incorporating AI-ECG information adds to risk stratification above and beyond classical clinical parameters is unknown. Objectives: To identify AI-ECG scores independently associated with all-cause mortality in chronic TR and to create a composite AI-ECG risk score. Methods: Patients with a first echocardiographic diagnosis of ≥moderate TR between 2005-2016 and an ECG within ±15 days were included. The Tricuspid Regurgitation Impact on Outcome (TRIO) score was calculated as previously described based on 8 simple parameters (age, sex, severe TR, heart failure, lung disease, heart rate, creatinine and AST). AI-ECG probabilities of low ejection fraction, aortic stenosis, amyloid, cirrhosis, atrial fibrillation and hypertrophic cardiomyopathy were estimated by existing algorithms; the first 4 were associated with all-cause mortality and a composite AI-ECG risk score was calculated (0-4; 1 point for each AI-ECG above specific threshold). Results: A total of 12,377 pts were included (age 72±13 yrs, 55% women). Over a median follow-up of 1.3 yrs (IQR 0.1 to 4.4), 7,121 pts (58%) died. Mortality risk increased significantly with higher composite AI-ECG risk score (Fig. 1A). On multivariable analysis (proportional hazards method), the composite AI-ECG risk score remained independently associated with death, even after adjusting for age, sex, high NT-proBNP levels (>2,500 pg/mL), right ventricular systolic pressure (RVSP), diuretic use and TRIO risk score category (Fig. 1B). Conclusions: Patients with ≥moderate TR show progressively worse survival with increasing composite AI-ECG risk score. Incorporating AI-derived information from a simple and inexpensive ECG may identify patients with the highest risk of mortality beyond clinical risk scores as TRIO or classical clinical, laboratory and echocardiographic parameters. Prospective validation of this approach needs to be tested in future trials.

Background Tricuspid valve surgery is recommended for severe isolated tricuspid regurgitation (TR) if symptoms persist despite optimal medical therapy. The definition of optimal therapy for TR is unclear beyond managing underlying conditions. Diuretics are the primary treatment for volume retention in TR, but it is unknown whether a “safe diuretic dose” exists for conservative management. We sought to evaluate the association between diuretic dose and outcomes. Methods Adult patients with ≥moderate–severe isolated TR were retrospectively identified from echocardiographic reports. Clinical and echocardiographic data were extracted from electronic medical records and manually reviewed. The primary end point was all‐cause mortality. Loop diuretic doses were converted to furosemide equivalent and categorized into 4 groups: <40 mg, 40 to 79 mg, 80 to 159 mg, and ≥160 mg daily. Results Of 1302 patients (age 72±13 years, 60% female), 565 (43%) had moderate–severe TR and 737 (57%) had severe TR. Median follow‐up was 8.7 (1.4, 14.0) years. Comorbidities increased with higher diuretic doses. A linear relationship between diuretic dose and mortality was observed in spline‐curve analysis. Hazard ratios (and CIs) for mortality adjusted for age, sex, coronary disease, chronic kidney disease, mild pulmonary hypertension, and New York Heart Association III/IV symptoms were 1.21 (0.96–1.53) ( P =0.12) for <40 mg, 1.50 (1.23–1.82) ( P <0.001) for 40 to 79 mg, 1.86 (1.46–2.37) ( P <0.001) for 80 to 159 mg, and 2.90 (2.18–3.88) ( P <0.001) for ≥160 mg furosemide equivalent. Any diuretic dose was associated with significant symptoms (New York Heart Association III–IV), with more patients experiencing symptoms at higher doses. Conclusion A daily loop diuretic dose ≥40 mg furosemide equivalent is associated with increased mortality and greater symptom severity in patients with TR.

Abstract Aims Tricuspid valve regurgitation (TR) is common and associated with increased mortality. The interaction between the pulmonary artery (PA) circulation and the right ventricle (RV) and association with outcomes is incompletely understood. The effective PA elastance (PA Ea) is a composite measure of RV afterload that refers to the pulmonary vascular load that the RV must overcome to eject blood. Whether PA Ea discriminates mortality risk in unselected patients with significant TR is unknown. Methods and results In consecutive patients with ≥moderate TR, we compared all-cause mortality at 5 years based on the PA Ea (defined as the RV systolic pressure/stroke volume as measured by transthoracic echocardiography). In a total of 12 682 patients, the median PA Ea was 0.7 mm Hg/mL (interquartile range 0.5, 0.9). Increasing levels of PA Ea were associated with heart failure, liver and kidney disease, and clinical markers of risk such as the Tricuspid Regurgitation Impact on Outcomes score. Increasing levels of PA Ea were associated with larger RVs, worse RV systolic function, higher N-terminal pro-brain natriuretic peptide levels, and greater degrees of right heart failure. After adjusting for age and sex, PA Ea was associated with higher risk of death (hazard ratio 1.55 per 0.5 mm Hg/mL change of PA Ea; 95% confidence intervals 1.51–1.60; P &lt; 0.0001). In multivariable modelling incorporating available clinical variables, PA Ea was independently predictive of outcome compared with other indexes of RV–PA coupling. Conclusion In patients with significant TR, 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 risk.