Bird, Jared

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 <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 Aims Early detection of structural heart disease (SHD) improves patient outcomes. However, population-based screening is not recommended due to the lack of accurate and cost-effective tools. We evaluated the costs of artificial intelligence–enabled electrocardiogram (AI-ECG) alone vs. AI-ECG followed by handheld cardiac ultrasound (HCU) for SHD screening. Methods and results We performed a model-based cost analysis using data from 286 adult patients who underwent ECG and same-day HCU performed by a novice operator. Transthoracic echocardiogram (TTE) was the reference standard. We compared two screening strategies: (i) AI-ECG alone and (ii) a stepwise approach (AI-ECG followed by HCU). We assessed costs per diagnosis of aortic stenosis (AS), increased left ventricular wall thickness (ILVWT), and left ventricular systolic dysfunction (LVSD). Sensitivity analyses were conducted for varying disease prevalence. The stepwise approach decreased the cost per diagnosis of AS from $6386 (AI-ECG alone) to $2746 (57.0% savings), ILVWT from $4448 to $2895 (34.9% savings), and LVSD from $1469 to $1296 (11.8% savings). Overall, the cost per diagnosis for all SHDs combined decreased from $1940 to $1570 (19.1% savings). Sensitivity analysis demonstrated that cost savings were inversely proportional to disease prevalence. Nevertheless, stepwise screening remained cost-saving compared with AI-ECG alone until prevalence exceeded ∼55.9% for AS, 28.9% for ILVWT, 20.7% for LVSD, and 40.8% for all SHDs combined. Conclusion A stepwise screening strategy incorporating HCU after a positive AI-ECG reduces the immediate costs of SHD detection by minimizing unnecessary TTEs. This approach may enhance the feasibility of population-based SHD screening, particularly in lower-prevalence settings.

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 < 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.

INTRODUCTION: Cardiovascular disease is a leading cause of maternal mortality. Our aim was to evaluate the feasibility and quality of artificial intelligence (AI)-guided focused cardiac ultrasound (FoCUS) by novice scanners to screen for left ventricular (LV) systolic dysfunction in pregnant individuals. METHODS: Patients were prospectively enrolled during routine obstetric appointments. FoCUS images were acquired by individuals without scanning or clinical experience using AI-guided image acquisition software (UltraSight) on a Philips Lumify device. Standard two-dimensional imaging views were attempted: parasternal long axis (PSLA), parasternal short axis mid-level (PSSA Mid), apical four chamber (A4C), three chamber (A3C), and two chamber (A2C). Two experienced cardiologists reviewed all images and graded diagnostic quality: poor, adequate, good, excellent. RESULTS: A total of 101 pregnant participants were enrolled; median age was 32 (interquartile range [IQR], 29, 35) years. The median gestational age was 23 (IQR, 16, 31) weeks; 16% first trimester, 45% second, and 39% third. The most feasible views were the PSLA and PSSA Mid, 98% and 97% with adequate or greater image quality, respectively. A3C and A2C were least feasible, acquired in 34% and 40% with adequate or greater image quality in 28% and 35%, respectively. Average scan time was 6 minutes, 46 seconds ± 0.2. The LV ejection fraction could be determined for the entire cohort and was normal (50–75%) for all. CONCLUSIONS/IMPLICATIONS: Implementation of AI-guided FoCUS in pregnant individuals is feasible, even in the absence of an experienced sonographer. This approach could allow for low-cost screening and early diagnosis of LV systolic dysfunction during pregnancy.

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 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

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: Enlargement or dilation of the left ventricle (LV) is associated with increased cardiovascular morbidity and mortality, and is an established precursor of ventricular dysfunction and heart failure in almost all major cardiovascular conditions. Although there are existing artificial intelligence frameworks that make use of deep learning to detect LV enlargement, many entail LV segmentation, which can be error-prone especially for point-of-care ultrasound (POCUS) images. Goal: To develop a fully end-to-end deep learning framework that takes as input either transthoracic echocardiographic (TTE) or POCUS 2D image clips, and classifies directly (i.e., without first segmenting the LV) whether a patient has an enlarged LV. Methods: Using a sample of retrospective TTE data enriched for LV enlargement (out of 13,868 patients total, 3,351 had an enlarged LV defined using sex-specific guideline-directed criteria), we trained a classifier that takes as input apical 2-chamber and parasternal long axis videos, and provides as output a binary label denoting whether a patient has an enlarged LV. Then, we evaluated the trained model using a holdout testing dataset of retrospective TTE data (2,087 patients) as well as data from a prospective cohort of 428 patients from whom TTE and POCUS were collected simultaneously. Results: For the retrospective TTE testing dataset, the AUC was 0.851 (95% confidence interval (CI) of 0.830-871). For the prospective cohort, the model performed comparably for both TTE and POCUS video clips (TTE: AUC of 0.865, 95% CI of 0.823-0.906; POCUS: AUC of 0.840, 95% CI of 0.797-0.883). Conclusions: The current deep learning model performed comparably well for both TTE and POCUS echocardiograms. We regard these results as a proof-of-concept of the potential utility of this model in helping point-of-care clinicians make decisions regarding whether patients should receive further evaluation for LV enlargement and associated conditions.

Background: Recently, our team developed an end-to-end artificial intelligence (AI) framework that can successfully estimate left ventricular ejection fraction (LVEF) from echocardiogram videos. However, this framework requires specific views (A2C and PLAX), and cannot estimate LVEF for studies from which these views are missing. Goal: To develop a deep learning model to estimate LVEF from any type and number of echocardiogram video(s). Methods: We built a deep learning model for B-mode echocardiogram videos of the left ventricle (A2C, A3C, A4C, or PLAX views), using retrospective transthoracic echocardiography (TTE) data. The model was evaluated with two test datasets: one with random valid (i.e., showing the left ventricle) views, and one with preselected views (both having 433 patients). Later, the model was tested with a prospective patient cohort that had both TTE and point-of-care ultrasound (POCUS) data collected simultaneously (393 patients). Results: On the retrospective TTE test set, we observed excellent performance (five random valid views per study: RMSE of 6.87% and Pearson correlation (PC) of 0.82 on LVEF estimation, and an AUC of 0.96 (95% CI: of 0.94-0.98) on low LVEF classification (<=40%); preselected views: RMSE of 6.75%, PC of 0.83, and an AUC of 0.96 (95% CI: 0.94-0.98)). For both TTE and POCUS data from the prospective cohort, we also observed strong performance (TTE: RMSE of 5.62%, PC of 0.87, and an AUC of 0.97; POCUS: RMSE of 6.12%, PC of 0.84, and an AUC of 0.96). For the prospective test sets as well as for the retrospective TTE test set with preselected views, results reflect the estimated LVEF average of A2C, A3C, A4C, and PLAX videos from each patient. Conclusions: For both TTE and POCUS data, the current model showed strong performance which was comparable to that of our previously established view-specific model. Alongside this comparable performance, the current model surpasses our previous model in terms of flexibility, as it isn't dependent on view classification and allows a broader selection in terms of the number and types of videos per study or patient. This innovative approach could prove particularly beneficial in point-of-care situations in which it may not be feasible to obtain high-quality, view-specific videos.