Applying the UTAUT2 framework to patients' attitudes toward healthcare task shifting with artificial intelligence.

BACKGROUND: Increasing patient loads, healthcare inflation and ageing population have put pressure on the healthcare system. Artificial intelligence and machine learning innovations can aid in task shifting to help healthcare systems remain efficient and cost effective. To gain an understanding of patients' acceptance toward such task shifting with the aid of AI, this study adapted the Unified Theory of Acceptance and Use of Technology 2 (UTAUT2), looking at performance and effort expectancy, facilitating conditions, social influence, hedonic motivation and behavioural intention. METHODS: This was a cross-sectional study which took place between September 2021 to June 2022 at the National Heart Centre, Singapore. One hundred patients, aged ≥ 21 years with at least one heart failure symptom (pedal oedema, New York Heart Association II-III effort limitation, orthopnoea, breathlessness), who presented to the cardiac imaging laboratory for physician-ordered clinical echocardiogram, underwent both echocardiogram by skilled sonographers and the experience of echocardiogram by a novice guided by AI technologies. They were then given a survey which looked at the above-mentioned constructs using the UTAUT2 framework. RESULTS: Significant, direct, and positive effects of all constructs on the behavioral intention of accepting the AI-novice combination were found. Facilitating conditions, hedonic motivation and performance expectancy were the top 3 constructs. The analysis of the moderating variables, age, gender and education levels, found no impact on behavioral intention. CONCLUSIONS: These results are important for stakeholders and changemakers such as policymakers, governments, physicians, and insurance companies, as they design adoption strategies to ensure successful patient engagement by focusing on factors affecting the facilitating conditions, hedonic motivation and performance expectancy for AI technologies used in healthcare task shifting.

Predictors of adverse diastolic remodeling in non-diabetic patients presenting with ST-elevation myocardial infarction.

BACKGROUND: Adverse systolic remodeling after ST-elevation myocardial infarction (STEMI) is associated with poor clinical outcomes. However, little is known about diastolic remodeling. The purpose of this study was to identify the factors leading to diastolic remodeling. METHODS: Echocardiography was performed during hospitalization and at 4 months follow-up in 267 non-diabetic STEMI patients from the GIPS-III trial. As parameters of diastolic remodeling we used (1.) the E/e' at 4 months adjusted for the E/e' at hospitalization and (2.) the change in E/e' between hospitalization and 4 months. Multivariable regression models correcting for age and sex were constructed to identify possible association of clinical and angiographic variables as well as biomarkers with diastolic remodeling. RESULTS: Older age, female gender, hypertension, multi vessel disease, higher glucose and higher peak CK were independent predictors of higher E/e' at 4 months in a multivariable model (R2:0.20). After adjustment for E/e' during hospitalization only female gender, multivessel disease and higher glucose remained predictors of E/e' at four months (R2:0.40). Lower myocardial blush grade, AST and NT-proBNP were independent predictors of a higher increase of E/e' between hospitalization and at 4 months in a multivariable model (R2:0.08). CONCLUSIONS: Our data supports the hypothesis that female gender, multivessel coronary artery disease, and microvascular damage are important predictors of adverse diastolic remodeling after STEMI. In addition, our data suggests that older age and hypertension prior to STEMI may have contributed to worse pre-existing diastolic function. TRIAL REGISTRATION: NIH, NCT01217307. Prospectively registered on October 8th 2010, https://clinicaltrials.gov/ct2/show/NCT01217307 .

Effect of isolated ultrafiltration and isovolemic dialysis on myocardial perfusion and left ventricular function assessed with 13N-NH3 positron emission tomography and echocardiography.

Hemodialysis is associated with a fall in myocardial perfusion and may induce regional left ventricular (LV) systolic dysfunction. The pathophysiology of this entity is incompletely understood, and the contribution of ultrafiltration and diffusive dialysis has not been studied. We investigated the effect of isolated ultrafiltration and isovolemic dialysis on myocardial perfusion and LV function. Eight patients (7 male, aged 55 ± 18 yr) underwent 60 min of isolated ultrafiltration and 60 min of isovolemic dialysis in randomized order. Myocardial perfusion was assessed by 13N-NH3 positron emission tomography before and at the end of treatment. LV systolic function was assessed by echocardiography. Regional LV systolic dysfunction was defined as an increase in wall motion score in ≥2 segments. Isolated ultrafiltration (ultrafiltration rate 13.6 ± 3.9 ml·kg-1·h-1) induced hypovolemia, whereas isovolemic dialysis did not (blood volume change -6.4 ± 2.2 vs. +1.3 ± 3.6%). Courses of blood pressure, heart rate, and tympanic temperature were comparable for both treatments. Global and regional myocardial perfusion did not change significantly during either isolated ultrafiltration or isovolemic dialysis and did not differ between treatments. LV ejection fraction and the wall motion score index did not change significantly during either treatment. Regional LV systolic dysfunction developed in one patient during isolated ultrafiltration and in three patients during isovolemic dialysis. In conclusion, global and regional myocardial perfusion was not compromised by 60 min of isolated ultrafiltration or isovolemic dialysis. Regional LV systolic dysfunction developed during isolated ultrafiltration and isovolemic dialysis, suggesting that, besides hypovolemia, dialysis-associated factors may be involved in the pathogenesis of hemodialysis-induced regional LV dysfunction.

Right Heart Dysfunction in Heart Failure With Preserved Ejection Fraction: The Impact of Atrial Fibrillation.

BACKGROUND: Right ventricular (RV) dysfunction and atrial fibrillation (AF) frequently coexist in heart failure with preserved ejection fraction (HFpEF). The mechanisms underlying the association between AF and RV dysfunction are incompletely understood. METHODS AND RESULTS: We identified 102 patients. RV function was assessed with the use of multiple echocardiographic parameters, and dysfunction was present if ≥2 parameters were below the recommended cutoffs. RV function, right atrial (RA) reservoir strain, and RA emptying fraction were compared between AF and sinus rhythm. We included 91 patients with sufficient echocardiographic quality: 45 (50%) had no history of AF, 14 (15%) had earlier AF while in sinus rhythm, and 32 (35%) had current AF. The prevalence of RV dysfunction varied across subgroups (never AF, earlier AF, and current AF: 20%, 43% and 63%, respectively; P = .001). AF was associated with RV dysfunction (odds ratio [OR] 4.70 [95% confidence interval [CI] 1.82-12.1]; P = .001) independently from pulmonary pressures. In patients in sinus rhythm with earlier AF, RA emptying fraction was lower compared with patients without AF history (41 vs 60%; P = .002). Earlier AF was also associated with reduced RA reservoir strain (OR 4.57 [95% CI 1.05-19.9]; P = .04) independently from RV end-diastolic pressure. CONCLUSIONS: Atrial fibrillation is strongly related to reduced RV and RA function in HFpEF independently from pulmonary pressures.

Clinical and Hemodynamic Correlates and Prognostic Value of VE/VCO2 Slope in Patients With Heart Failure With Preserved Ejection Fraction and Pulmonary Hypertension.

BACKGROUND: Impaired exercise capacity is one of the hallmarks of heart failure with preserved ejection fraction (HFpEF), but the clinical and hemodynamic correlates and prognostic value of exercise testing in patients with HFpEF is unknown. METHODS: Patients with HFpEF (left ventricular ejection fraction [LVEF] ≥45%) and pulmonary hypertension underwent cardiopulmonary exercise test (CPX) to measure maximal (peak VO2) and submaximal (ventilatory equivalent for carbon dioxide [VE/VCO2] slope) exercise capacity. In addition, right heart catheterization was performed. Patients were grouped in tertiles based on the VE/VCO2 slope. Univariate and multivariate regression analyses were performed. A Cox regression analysis was performed to determine the mortality during follow-up. RESULTS: We studied 88 patients: mean age 73 ± 9 years, 67% female, mean LVEF 58%, median N-terminal pro-B-type natriuretic peptide (NT-proBNP) 840 (interquartile range 411-1938) ng/L. Patients in the highest VE/VCO2 tertile had the most severe HF, as reflected in higher New York Heart Association functional class and higher NT-proBNP plasma levels (all P < .05 for trend), whereas LVEF was similar between the groups. Multivariable regression analysis with backward elimination on invasive hemodynamic measurements showed that VE/VCO2 slope was independently associated with pulmonary vascular resistance (PVR). Cox regression analysis showed that increased VE/VCO2 slope (but not peak VO2) was independently associated with increased mortality. CONCLUSION: Increased VE/VCO2 slope was associated with more severe disease and higher PVR and was independently associated with increased mortality in patients with HFpEF.

Fibroblast growth factor 23 correlates with volume status in haemodialysis patients and is not reduced by haemodialysis.

BACKGROUND: Recent data suggest a role for fibroblast growth factor 23 (FGF-23) in volume regulation. In haemodialysis patients, a large ultrafiltration volume (UFV) reflects poor volume control, and both FGF-23 and a large UFV are risk factors for mortality in this population. We studied the association between FGF-23 and markers of volume status including UFV, as well as the intradialytic course of FGF-23, in a cohort of haemodialysis patients. METHODS: We carried out observational, post hoc analysis of 109 prevalent haemodialysis patients who underwent a standardized, low-flux, haemodialysis session with constant ultrafiltration rate. We measured UFV, plasma copeptin and echocardiographic parameters including cardiac output, end-diastolic volume and left ventricular mass index at the onset of the haemodialysis session. We measured the intradialytic course of plasma C-terminal FGF-23 (corrected for haemoconcentration) and serum phosphate levels at 0, 1, 3 and 4 h after onset of haemodialysis and analysed changes with linear mixed effect model. RESULTS: Median age was 66 (interquartile range: 51-75) years, 65% were male with a weekly Kt/V 4.3 ± 0.7 and dialysis vintage of 25.4 (8.5-52.5) months. In univariable analysis, pre-dialysis plasma FGF-23 was associated with UFV, end-diastolic volume, cardiac output, early diastolic velocity e' and plasma copeptin. In multivariable regression analysis, UFV correlated with FGF-23 (standardized ß: 0.373, P < 0.001, model R(2): 57%), independent of serum calcium and phosphate. The association between FGF-23 and echocardiographic volume markers was lost for all but cardiac output upon adjustment for UFV. Overall, FGF-23 levels did not change during dialysis [7627 (3300-13 514) to 7503 (3109-14 433) RU/mL; P = 0.98], whereas phosphate decreased (1.71 ± 0.50 to 0.88 ± 0.26 mmol/L; P < 0.001). CONCLUSIONS: FGF-23 was associated with volume status in haemodialysis patients. The strong association with UFV suggests that optimization of volume status, for example by more intensive haemodialysis regimens, may also benefit mineral homeostasis. A single dialysis session did not lower FGF-23 levels.

Effects of sildenafil on invasive haemodynamics and exercise capacity in heart failure patients with preserved ejection fraction and pulmonary hypertension: a randomized controlled trial.

BACKGROUND: Heart failure with preserved ejection fraction (HFpEF), with associated pulmonary hypertension is an increasingly large medical problem. Phosphodiesterase (PDE)-5 inhibition may be of value in this population, but data are scarce and inconclusive. METHODS AND RESULTS: In this single centre, randomized double-blind, placebo-controlled trial, we included 52 patients with pulmonary hypertension [mean pulmonary artery pressure (PAP) >25 mmHg; pulmonary artery wedge pressure (PAWP) >15 mmHg] due to HFpEF [left ventricular ejection fraction (LVEF) ≥45%]. Patients were randomized to the PDE-5 inhibitor sildenafil, titrated to 60 mg three times a day, or placebo for 12 weeks. The primary endpoint was change in mean PAP after 12 weeks. Secondary endpoints were change in mean PAWP, cardiac output, and peak oxygen consumption (peak VO2). Mean age was 74 ± 10 years, 71% was female, LVEF was 58%, median NT-proBNP level was 1087 (535-1945) ng/L. After 12 weeks, change in mean PAP was -2.4 (95% CI -4.5 to -0.3) mmHg in patients who received sildenafil, vs. -4.7 (95% CI -7.1 to -2.3) mmHg in placebo patients (P = 0.14). Sildenafil did not have a favourable effect on PAWP, cardiac output, and peak VO2. Adverse events were overall comparable between groups. CONCLUSION: Treatment with sildenafil did not reduce pulmonary artery pressures and did not improve other invasive haemodynamic or clinical parameters in our study population, characterized by HFpEF patients with predominantly isolated post-capillary pulmonary hypertension. (ClinicalTrials.gov, number NCT01726049).

Long-term cardiac abnormalities after cranial radiotherapy in childhood cancer survivors.

BACKGROUND: Cardiac morbidity is an important late effect in long-term childhood cancer survivors (CCS) treated with cardiotoxic agents or radiotherapy (RT) on the chest. However, there is limited data on the long-term cardiac sequelae in CCS who only received cranial RT. We hypothesized that cranial RT might negatively influence cardiac structure and function. METHODS AND RESULTS: We studied 13 CCS [mean age 30.8 (18.1-39.3) years, 7 males] who received RT only on the head for a cranial tumor and 36 age- and sex-matched healthy sibling controls. Echocardiographic follow-up was performed at median 21.7 (12.6-30.8) years after diagnosis. CCS had lower indexed diastolic LV volumes [56.0 (31.4-68.3) vs. 60.5 (41.9-94.3) mL/m(2), p = 0.024]. CCS also had reduced LV systolic and diastolic function, reflected by lower systolic LV myocardial velocities (5.3 ± 0.9 vs. 7.1 ± 1.7 cm/s, p = 0.001) and longitudinal deformation (- 17.3 ± 3.1 vs. - 20.7 ± 2.0%, p < 0.001), as well as lower diastolic LV myocardial velocities (- 10.7 ± 1.7 vs. - 12.2 ± 1.5 cm/s, p = 0.006) and deformation speed (1.1 ± 0.3 vs. 1.5 ± 0.2 1/s, p = 0.005). Additionally, in CCS insulin-like growth factor levels [15.4 (9.2-34.6) vs. 24.4 (14.8-55.5) nmol/L, p = 0.007] were lower. CONCLUSION: Cranial RT in CCS is associated with smaller cardiac volumes and reduced systolic and diastolic LV function. This off target effect of RT might be related to lower insulin-like growth factor levels.

Hemodialysis-induced regional left ventricular systolic dysfunction and inflammation: a cross-sectional study.

BACKGROUND: Hemodialysis may acutely induce regional left ventricular (LV) systolic dysfunction, which is associated with increased mortality and progressive heart failure. We tested the hypothesis that hemodialysis-induced regional LV systolic dysfunction is associated with inflammation and endothelial injury. Additionally, we studied whether hemodialysis-induced LV systolic dysfunction is associated with an exaggerated bioincompatibility reaction to hemodialysis. STUDY DESIGN: Cross-sectional study. SETTING & PARTICIPANTS: 105 hemodialysis patients on a thrice-weekly dialysis schedule were studied between March 2009 and March 2010. PREDICTORS: Plasma indexes of inflammation (high-sensitivity C-reactive protein, pentraxin 3 [PTX3], interleukin 6 [IL-6], and IL-6:IL-10 ratio), bioincompatibility (leukocytes, neutrophils, complement C3, and myeloperoxidase), and endothelial function (soluble intercellular adhesion molecule 1 [ICAM-1], von Willebrand factor, proendothelin, and endothelin) were measured just before dialysis and at 60, 180, and 240 minutes intradialysis. OUTCOMES: Hemodialysis-induced regional LV systolic function. Wall motion score was measured by echocardiography at 30 minutes predialysis, 60 and 180 minutes intradialysis, and 30 minutes postdialysis. We defined hemodialysis-induced regional LV systolic dysfunction as an increase in wall motion score in 2 or more segments. RESULTS: Patients with hemodialysis-induced regional LV systolic dysfunction (n=29 [27%]) had significantly higher predialysis high-sensitivity C-reactive protein, PTX3, IL-6, and lL-6:IL-10 ratio values. Predialysis levels of bioincompatibility and endothelial markers did not differ between groups. Intradialysis courses of markers of inflammation, bioincompatibility, and endothelial function did not differ in patients with versus without hemodialysis-induced regional LV systolic dysfunction. LIMITATIONS: Coronary angiography or computed tomography for quantification of coronary calcifications in our patients was not performed; therefore, we could not relate markers of inflammation to the extent of atherosclerosis. CONCLUSIONS: Patients with hemodialysis-induced regional LV systolic dysfunction have a proinflammatory cytokine profile. There was no indication of an association with an exaggerated bioincompatibility reaction to hemodialysis.

Artificial intelligence-assisted automated heart failure detection and classification from electronic health records.

AIMS: Electronic health records (EHR) linked to Digital Imaging and Communications in Medicine (DICOM), biological specimens, and deep learning (DL) algorithms could potentially improve patient care through automated case detection and surveillance. We hypothesized that by applying keyword searches to routinely stored EHR, in conjunction with AI-powered automated reading of DICOM echocardiography images and analysing biomarkers from routinely stored plasma samples, we were able to identify heart failure (HF) patients. METHODS AND RESULTS: We used EHR data between 1993 and 2021 from Tayside and Fife (~20% of the Scottish population). We implemented a keyword search strategy complemented by filtering based on International Classification of Diseases (ICD) codes and prescription data to EHR data set. We then applied DL for the automated interpretation of echocardiographic DICOM images. These methods were then integrated with the analysis of routinely stored plasma samples to identify and categorize patients into HF with reduced ejection fraction (HFrEF), HF with preserved ejection fraction (HFpEF), and controls without HF. The final diagnosis was verified through a manual review of medical records, measured natriuretic peptides in stored blood samples, and by comparing clinical outcomes among groups. In our study, we selected the patient cohort through an algorithmic workflow. This process started with 60 850 EHR data and resulted in a final cohort of 578 patients, divided into 186 controls, 236 with HFpEF, and 156 with HFrEF, after excluding individuals with mismatched data or significant valvular heart disease. The analysis of baseline characteristics revealed that compared with controls, patients with HFrEF and HFpEF were generally older, had higher BMI, and showed a greater prevalence of co-morbidities such as diabetes, COPD, and CKD. Echocardiographic analysis, enhanced by DL, provided high coverage, and detailed insights into cardiac function, showing significant differences in parameters such as left ventricular diameter, ejection fraction, and myocardial strain among the groups. Clinical outcomes highlighted a higher risk of hospitalization and mortality for HF patients compared with controls, with particularly elevated risk ratios for both HFrEF and HFpEF groups. The concordance between the algorithmic selection of patients and manual validation demonstrated high accuracy, supporting the effectiveness of our approach in identifying and classifying HF subtypes, which could significantly impact future HF diagnosis and management strategies. CONCLUSIONS: Our study highlights the feasibility of combining keyword searches in EHR, DL automated echocardiographic interpretation, and biobank resources to identify HF subtypes.

Nurse-led home-based detection of cardiac dysfunction by ultrasound: results of the CUMIN pilot study.

Aims: Access to echocardiography is a significant barrier to heart failure (HF) care in many low- and middle-income countries. In this study, we hypothesized that an artificial intelligence (AI)-enhanced point-of-care ultrasound (POCUS) device could enable the detection of cardiac dysfunction by nurses in Tunisia. Methods and results: This CUMIN study was a prospective feasibility pilot assessing the diagnostic accuracy of home-based AI-POCUS for HF conducted by novice nurses compared with conventional clinic-based transthoracic echocardiography (TTE). Seven nurses underwent a one-day training program in AI-POCUS. A total of 94 patients without a previous HF diagnosis received home-based AI-POCUS, POC N-terminal pro-B-type natriuretic peptide (NT-proBNP) testing, and clinic-based TTE. The primary outcome was the sensitivity of AI-POCUS in detecting a left ventricular ejection fraction (LVEF) <50% or left atrial volume index (LAVI) >34 mL/m2, using clinic-based TTE as the reference. Out of seven nurses, five achieved a minimum standard to participate in the study. Out of the 94 patients (60% women, median age 67), 16 (17%) had an LVEF < 50% or LAVI > 34 mL/m2. AI-POCUS provided an interpretable LVEF in 75 (80%) patients and LAVI in 64 (68%). The only significant predictor of an interpretable LVEF or LAVI proportion was the nurse operator. The sensitivity for the primary outcome was 92% [95% confidence interval (CI): 62-99] for AI-POCUS compared with 87% (95% CI: 60-98) for NT-proBNP > 125 pg/mL, with AI-POCUS having a significantly higher area under the curve (P = 0.040). Conclusion: The study demonstrated the feasibility of novice nurse-led home-based detection of cardiac dysfunction using AI-POCUS in HF patients, which could alleviate the burden on under-resourced healthcare systems.

Point-of-care AI-enhanced novice echocardiography for screening heart failure (PANES-HF).

The increasing prevalence of heart failure (HF) in ageing populations drives demand for echocardiography (echo). There is a worldwide shortage of trained sonographers and long waiting times for expert echo. We hypothesised that artificial intelligence (AI)-enhanced point-of-care echo can enable HF screening by novices. The primary endpoint was the accuracy of AI-enhanced novice pathway in detecting reduced LV ejection fraction (LVEF) < 50%. Symptomatic patients with suspected HF (N = 100, mean age 61 ± 15 years, 56% men) were prospectively recruited. Novices with no prior echo experience underwent 2-weeks' training to acquire echo images with AI guidance using the EchoNous Kosmos handheld echo, with AI-automated reporting by Us2.ai (AI-enhanced novice pathway). All patients also had standard echo by trained sonographers interpreted by cardiologists (reference standard). LVEF < 50% by reference standard was present in 27 patients. AI-enhanced novice pathway yielded interpretable results in 96 patients and took a mean of 12 min 51 s per study. The area under the curve (AUC) of the AI novice pathway was 0.880 (95% CI 0.802, 0.958). The sensitivity, specificity, positive predictive and negative predictive values of the AI-enhanced novice pathway in detecting LVEF < 50% were 84.6%, 91.4%, 78.5% and 94.1% respectively. The median absolute deviation of the AI-novice pathway LVEF from the reference standard LVEF was 6.03%. AI-enhanced novice pathway holds potential to task shift echo beyond tertiary centres and improve the HF diagnostic workflow.

An Automated Machine Learning-Based Quantitative Multiparametric Approach for Mitral Regurgitation Severity Grading.

BACKGROUND: Considering the high prevalence of mitral regurgitation (MR) and the highly subjective, variable MR severity reporting, an automated tool that could screen patients for clinically significant MR (≥ moderate) would streamline the diagnostic/therapeutic pathways and ultimately improve patient outcomes. OBJECTIVES: The authors aimed to develop and validate a fully automated machine learning (ML)-based echocardiography workflow for grading MR severity. METHODS: ML algorithms were trained on echocardiograms from 2 observational cohorts and validated in patients from 2 additional independent studies. Multiparametric echocardiography core laboratory MR assessment served as ground truth. The machine was trained to measure 16 MR-related parameters. Multiple ML models were developed to find the optimal parameters and preferred ML model for MR severity grading. RESULTS: The preferred ML model used 9 parameters. Image analysis was feasible in 99.3% of cases and took 80 ± 5 seconds per case. The accuracy for grading MR severity (none to severe) was 0.80, and for significant (moderate or severe) vs nonsignificant MR was 0.97 with a sensitivity of 0.96 and specificity of 0.98. The model performed similarly in cases of eccentric and central MR. Patients graded as having severe MR had higher 1-year mortality (adjusted HR: 5.20 [95% CI: 1.24-21.9]; P = 0.025 compared with mild). CONCLUSIONS: An automated multiparametric ML model for grading MR severity is feasible, fast, highly accurate, and predicts 1-year mortality. Its implementation in clinical practice could improve patient care by facilitating referral to specialized clinics and access to evidence-based therapies while improving quality and efficiency in the echocardiography laboratory.

External validation of a deep learning algorithm for automated echocardiographic strain measurements.

Aims: Echocardiographic strain imaging reflects myocardial deformation and is a sensitive measure of cardiac function and wall-motion abnormalities. Deep learning (DL) algorithms could automate the interpretation of echocardiographic strain imaging. Methods and results: We developed and trained an automated DL-based algorithm for left ventricular (LV) strain measurements in an internal dataset. Global longitudinal strain (GLS) was validated externally in (i) a real-world Taiwanese cohort of participants with and without heart failure (HF), (ii) a core-lab measured dataset from the multinational prevalence of microvascular dysfunction-HF and preserved ejection fraction (PROMIS-HFpEF) study, and regional strain in (iii) the HMC-QU-MI study of patients with suspected myocardial infarction. Outcomes included measures of agreement [bias, mean absolute difference (MAD), root-mean-squared-error (RMSE), and Pearson's correlation (R)] and area under the curve (AUC) to identify HF and regional wall-motion abnormalities. The DL workflow successfully analysed 3741 (89%) studies in the Taiwanese cohort, 176 (96%) in PROMIS-HFpEF, and 158 (98%) in HMC-QU-MI. Automated GLS showed good agreement with manual measurements (mean ± SD): -18.9 ± 4.5% vs. -18.2 ± 4.4%, respectively, bias 0.68 ± 2.52%, MAD 2.0 ± 1.67, RMSE = 2.61, R = 0.84 in the Taiwanese cohort; and -15.4 ± 4.1% vs. -15.9 ± 3.6%, respectively, bias -0.65 ± 2.71%, MAD 2.19 ± 1.71, RMSE = 2.78, R = 0.76 in PROMIS-HFpEF. In the Taiwanese cohort, automated GLS accurately identified patients with HF (AUC = 0.89 for total HF and AUC = 0.98 for HF with reduced ejection fraction). In HMC-QU-MI, automated regional strain identified regional wall-motion abnormalities with an average AUC = 0.80. Conclusion: DL algorithms can interpret echocardiographic strain images with similar accuracy as conventional measurements. These results highlight the potential of DL algorithms to democratize the use of cardiac strain measurements and reduce time-spent and costs for echo labs globally.

Changes in left ventricular diastolic function during hemodialysis sessions.

BACKGROUND: Left ventricular diastolic dysfunction is common in hemodialysis patients and is associated with worse outcome. Previous studies have shown that diastolic function worsens from pre- to post-dialysis session, but this has not been studied during hemodialysis. We studied the evolution of diastolic function parameters early and late during hemodialysis. STUDY DESIGN: Observational study. SETTING & PARTICIPANTS: 109 hemodialysis patients on a thrice-weekly dialysis schedule with a mean age of 62.5 ± 15.6 (SD) years were studied between March 2009 and March 2010. PREDICTOR: Hemodialysis with constant ultrafiltration rate and dialysate conductivity. OUTCOMES: Changes in diastolic function parameters. MEASUREMENTS: Mitral early inflow (E) and tissue Doppler early diastolic velocity (mean e') were evaluated by echocardiography predialysis, at 60 and 180 minutes intradialysis, and postdialysis. Relative blood volume changes were calculated from changes in hematocrit. RESULTS: Predialysis E and mean e' were 0.93 ± 0.24 m/s and 6.6 ± 2.1 cm/s, respectively. E and mean e' values decreased significantly during hemodialysis (P < 0.001). The steepest change occurred at 60 minutes intradialysis (E, -21.4% ± 17.6% and -30.5% ± 19.2% at 60 and 180 minutes, respectively; mean e', -16.0% ± 18.6% and -19.5% ± 21.8% at 60 and 180 minutes, respectively). At 60 minutes intradialysis, changes in relative blood volume and brain natriuretic peptide level were associated significantly with the change in E but not with the change in mean e'. LIMITATIONS: Changes in relative blood volume may not fully reflect central blood volume changes and do not capture the effect of blood loss to the extracorporal circuit. Left atrial volume was not measured. CONCLUSIONS: Left ventricular diastolic function worsens early during a hemodialysis session. The decrease in mean e' at 60 minutes intradialysis was unrelated to changes in relative blood volume. Although this finding does not exclude a role of hypovolemia because of the limitations of the measurement of relative blood volume, it raises the possibility that non-volume-related mechanisms are involved in the early decrease in mean e' during hemodialysis.

Ventricular dysfunction in a family with long QT syndrome type 3.

AIMS: Long QT syndrome (LQTS) type 3 is characterized by prolonged ventricular repolarization due to persistent sodium inward current secondary to a mutation in SCN5a, the gene encoding for the α-subunit of the sodium channel. We speculated that by disrupting calcium homeostasis the persistent inward sodium current in patients with LQTS type 3 might cause derangement of diastolic function. We aimed to identify functional myocardial alterations in a family with a sodium channelopathy with a phenotype of both LQTS type 3 and Brugada syndrome. METHODS AND RESULTS: The study group comprised 12 SCN5a mutation carriers (SCN5a-1795insD), 9 females and 3 males, mean age 35.7 ± 7.3 years, and 12 healthy controls. In addition to conventional echocardiographic measurements, two-dimensional speckle tracking was performed to assess tissue properties. Mean e' was lower in the patients compared with the controls (5.6 ± 0.75 vs. 6.7 ± 0.98 cm/s, P = 0.006). Onset QRS to maximum s' was longer in the patients than in the controls (0.20 ± 0.04 vs. 0.15 ± 0.05 s, P = 0.007), and the number of segments with post-systolic shortening was higher (6.58 ± 2.54 vs. 1.83 ± 1.64, P < 0.001). CONCLUSION: Patients in this family with LQTS type 3 showed post-systolic shortening, as well as both left and right ventricular diastolic dysfunction. The underlying mechanism remains to be elucidated but the persistent sodium inward current leading to calcium overload might play a role, in particular regarding diastolic dysfunction.

Fully Automated Artificial Intelligence Assessment of Aortic Stenosis by Echocardiography.

BACKGROUND: Aortic stenosis (AS) is a common form of valvular heart disease, present in over 12% of the population age 75 years and above. Transthoracic echocardiography (TTE) is the first line of imaging in the adjudication of AS severity but is time-consuming and requires expert sonographic and interpretation capabilities to yield accurate results. Artificial intelligence (AI) technology has emerged as a useful tool to address these limitations but has not yet been applied in a fully hands-off manner to evaluate AS. Here, we correlate artificial neural network measurements of key hemodynamic AS parameters to experienced human reader assessment. METHODS: Two-dimensional and Doppler echocardiographic images from patients with normal aortic valves and all degrees of AS were analyzed by an artificial neural network (Us2.ai) with no human input to measure key variables in AS assessment. Trained echocardiographers blinded to AI data performed manual measurements of these variables, and correlation analyses were performed. RESULTS: Our cohort included 256 patients with an average age of 67.6 ± 9.5 years. Across all AS severities, AI closely matched human measurement of aortic valve peak velocity (r = 0.97, P < .001), mean pressure gradient (r = 0.94, P < .001), aortic valve area by continuity equation (r = 0.88, P < .001), stroke volume index (r = 0.79, P < .001), left ventricular outflow tract velocity-time integral (r = 0.89, P < .001), aortic valve velocity-time integral (r = 0.96, P < .001), and left ventricular outflow tract diameter (r = 0.76, P < .001). CONCLUSIONS: Artificial neural networks have the capacity to closely mimic human measurement of all relevant parameters in the adjudication of AS severity. Application of this AI technology may minimize interscan variability, improve interpretation and diagnosis of AS, and allow for precise and reproducible identification and management of patients with AS.

Optimal Timing of a Physical Exercise Intervention to Improve Cardiorespiratory Fitness: During or After Chemotherapy.

Background: Despite the widely acknowledged benefit of exercise for patients with cancer, little evidence on the optimal timing of exercise on adverse effects of cancer treatment is available. Objectives: The aim of this study was to determine whether an exercise intervention initiated during chemotherapy is superior to an intervention initiated after chemotherapy for improving long-term cardiorespiratory fitness (peak oxygen uptake [VO2peak]). Methods: In this prospective, randomized clinical trial, patients scheduled to receive curative chemotherapy were randomized to a 24-week exercise intervention, initiated either during chemotherapy (group A) or afterward (group B). The primary endpoint was VO2peak 1 year postintervention. Secondary endpoints were VO2peak postintervention, muscle strength, health-related quality of life (HRQoL), fatigue, physical activity, and self-efficacy. Between-group differences were calculated using intention-to-treat linear mixed-models analyses. Results: A total of 266 patients with breast (n = 139), testicular (n = 95), and colon cancer (n = 30) as well as lymphoma (n = 2) were included. VO2peak immediately postintervention and 1 year postintervention did not differ between the 2 groups. Immediately postchemotherapy, patients in group A exhibited significantly lower decreases in VO2peak (3.1 mL/kg/min; 95% CI: 2.2-4.0 mL/kg/min), HRQoL, and muscle strength and reported less fatigue and more physical activity than those in group B. Conclusions: Exercise can be safely performed during chemotherapy and prevents fatigue and decreases in VO2peak, muscle strength, and HRQoL, in addition to hastening the return of function after chemotherapy. Also, if exercise cannot be performed during chemotherapy, a program afterward can enable patients to regain the same level of function, measured 1 year after completion of the intervention. (Optimal Timing of Physical Activity in Cancer Treatment [ACT]; NCT01642680).

Effects of eprosartan on diastolic function and neurohormones in patients with hypertension and diastolic dysfunction.

OBJECTIVE: To compare the effects of an angiotensin receptor blocker(ARB)-based regimen versus a non-ARB based regimen on diastolic function and neurohormones in patients with hypertension and diastolic dysfunction. METHODS: 97 patients with a systolic blood pressure (SBP) > or =140 mmHg, a left ventricular ejection fraction >0.50, and echocardiographic evidence of diastolic dysfunction were randomly assignment to open-label treatment with eprosartan (with other anti-hypertensives; n = 47) or other anti-hypertensives alone (n = 50). Echocardiography, including tissue Doppler imaging (TDI), and neurohormones were done at baseline and after 6 months. RESULTS: Mean age was 65 (+/-10) years and 64% was female. During 6 months of treatment, SBP decreased from 157 +/- 16 to 145 +/- 18 mmHg in the eprosartan group and from 158 +/- 17 to 141 +/- 18 mmHg in the control group (both p < 0.001; p = ns between groups). Diastolic function was unaffected in both groups and there was no correlation between changes in SBP and changes in mean TDI (r = -0.06; p = 0.58). Aldosterone levels decreased in the eprosartan group, but other neurohormones remained largely unchanged. Change in SBP was however related to the change in NT-proBNP (r = 0.26; p = 0.019). CONCLUSION: Lowering blood pressure, either with eprosartan or other anti-hypertensives in hypertensive patients with diastolic dysfunction did not change diastolic function after 6 months of treatment, but was associated with a decrease of NT-proBNP.

Predictive value of tissue Doppler imaging for left ventricular ejection fraction, remodelling, and infarct size after percutaneous coronary intervention for acute myocardial infarction.

AIMS: To investigate in ST-elevation myocardial infarction (STEMI) patients the value of tissue Doppler imaging (TDI) for an early estimation of the extent of myocardial salvage, left ventricular (LV) remodelling, and residual LV ejection fraction (LVEF). METHODS AND RESULTS: In 50 STEMI patients hospitalized for primary percutaneous coronary intervention (PCI), we investigated whether TDI can predict LVEF, infarct size, and LV remodelling as measured by magnetic resonance imaging (MRI) at 4 months post-MI. TDI was assessed within 24 h after MI with colour-coded TDI. Systolic and diastolic velocities from the six basal myocardial segments derived from three standard apical windows were averaged as a measure of global longitudinal velocity (i.e. Sm-6 and Em-6/Am-6, respectively). Sm-6 was shown to be a significant predictor of LVEF at 4 months. In addition, Sm-6 was a significant predictor of infarct size. No significant correlations were found between Sm-6 and LV remodelling. In addition, Sm-6 appeared to be a valuable clinical tool for identification of patients with LVEF > 40% or LVEF < 40% with acceptable positive predictive values. CONCLUSION: Sm-6 is a significant predictor of post-MI LVEF and infarct size as measured by MRI. In contrast, TDI-derived velocities do not predict LV remodelling.