Publications
712 results found
Alajrami E, Ng T, Jevsikov J, et al., 2024, Active learning for left ventricle segmentation in echocardiography., Comput Methods Programs Biomed, Vol: 248
BACKGROUND AND OBJECTIVE: Training deep learning models for medical image segmentation require large annotated datasets, which can be expensive and time-consuming to create. Active learning is a promising approach to reduce this burden by strategically selecting the most informative samples for segmentation. This study investigates the use of active learning for efficient left ventricle segmentation in echocardiography with sparse expert annotations. METHODS: We adapt and evaluate various sampling techniques, demonstrating their effectiveness in judiciously selecting samples for segmentation. Additionally, we introduce a novel strategy, Optimised Representativeness Sampling, which combines feature-based outliers with the most representative samples to enhance annotation efficiency. RESULTS: Our findings demonstrate a substantial reduction in annotation costs, achieving a remarkable 99% upper bound performance while utilising only 20% of the labelled data. This equates to a reduction of 1680 images needing annotation within our dataset. When applied to a publicly available dataset, our approach yielded a remarkable 70% reduction in required annotation efforts, representing a significant advancement compared to baseline active learning strategies, which achieved only a 50% reduction. Our experiments highlight the nuanced performance of diverse sampling strategies across datasets within the same domain. CONCLUSIONS: The study provides a cost-effective approach to tackle the challenges of limited expert annotations in echocardiography. By introducing a distinct dataset, made publicly available for research purposes, our work contributes to the field's understanding of efficient annotation strategies in medical image segmentation.
Jevsikov J, Ng T, Lane ES, et al., 2024, Automated mitral inflow Doppler peak velocity measurement using deep learning., Comput Biol Med, Vol: 171
Doppler echocardiography is a widely utilised non-invasive imaging modality for assessing the functionality of heart valves, including the mitral valve. Manual assessments of Doppler traces by clinicians introduce variability, prompting the need for automated solutions. This study introduces an innovative deep learning model for automated detection of peak velocity measurements from mitral inflow Doppler images, independent from Electrocardiogram information. A dataset of Doppler images annotated by multiple expert cardiologists was established, serving as a robust benchmark. The model leverages heatmap regression networks, achieving 96% detection accuracy. The model discrepancy with the expert consensus falls comfortably within the range of inter- and intra-observer variability in measuring Doppler peak velocities. The dataset and models are open-source, fostering further research and clinical application.
Foley MJ, Rajkumar CA, Ahmed-Jushuf F, et al., 2024, A double-blind, randomised, placebo-controlled trial of the coronary sinus Reducer in refractory angina: design and rationale of the ORBITA-COSMIC trial., EuroIntervention, Vol: 20, Pages: e216-e223
The coronary sinus Reducer (CSR) is an hourglass-shaped device which creates an artificial stenosis in the coronary sinus. Whilst placebo-controlled data show an improvement in angina, these results are unreplicated and are the subject of further confirmatory research. The mechanism of action of this unintuitive therapy is unknown. The Coronary Sinus Reducer Objective Impact on Symptoms, MRI Ischaemia, and Microvascular Resistance (ORBITA-COSMIC) trial is a randomised, placebo-controlled, double-blind trial investigating the efficacy of the CSR. Patients with (i) established epicardial coronary artery disease, (ii) angina on maximally tolerated antianginal medication, (iii) evidence of myocardial ischaemia and (iv) no further options for percutaneous coronary intervention or coronary artery bypass grafting will be enrolled. Upon enrolment, angina and quality-of-life questionnaires, treadmill exercise testing and quantitative stress perfusion cardiac magnetic resonance (CMR) imaging will be performed. Participants will record their symptoms daily on a smartphone application throughout the trial. After a 2-week symptom assessment phase, participants will be randomised in the cardiac catheterisation laboratory to CSR or a placebo procedure. After 6 months of blinded follow-up, all prerandomisation tests will be repeated. A prespecified subgroup will undergo invasive coronary physiology assessment at prerandomisation and follow-up. The primary outcome is stress myocardial blood flow on CMR. Secondary outcomes include angina frequency, quality of life and treadmill exercise time. (ClinicalTrials.gov: NCT04892537).
Foley M, Rajkumar CA, Ahmed-Jushuf F, et al., 2024, The ability of contemporary cardiologists to judge the ischemic impact of a coronary lesion visually., Cardiovasc Revasc Med, Vol: 59, Pages: 60-66
BACKGROUND: Landmark trials showed that invasive pressure measurement (Fractional Flow Reserve, FFR) was a better guide to coronary stenting than visual assessment. However, present-day interventionists have benefited from extensive research and personal experience of mapping anatomy to hemodynamics. AIMS: To determine if visual assessment of the angiogram performs as well as invasive measurement of coronary physiology. METHODS: 25 interventional cardiologists independently visually assessed the single vessel coronary disease of 200 randomized participants in The Objective Randomized Blinded Investigation with optimal medical Therapy of Angioplasty in stable angina trial (ORBITA). They gave a visual prediction of the FFR and Instantaneous Wave-free Ratio (iFR), denoted vFFR and viFR respectively. Each judged each lesion on 2 occasions, so that every lesion had 50 vFFR, and 50 viFR assessments. The group consensus visual estimates (vFFR-group and viFR-group) and individual cardiologists' visual estimates (vFFR-individual and viFR-individual) were tested alongside invasively measured FFR and iFR for their ability to predict the placebo-controlled reduction in stress echo ischemia with stenting. RESULTS: Placebo-controlled ischemia improvement with stenting was predicted by vFFR-group (p < 0.0001) and viFR-group (p < 0.0001), vFFR-individual (p < 0.0001) and viFR-individual (p < 0.0001). There were no significant differences between the predictive performance of the group visual estimates and their invasive counterparts: p = 0.53 for vFFR vs FFR and p = 0.56 for viFR vs iFR. CONCLUSION: Visual assessment of the angiogram by contemporary experts, provides significant additional information on the amount of ischaemia which can be relieved by placebo-controlled stenting in single vessel coronary artery disease.
Stowell CC, Kallassy V, Lane B, et al., 2024, Automated echocardiographic left ventricular dimension assessment in dogs using artificial intelligence: Development and validation., J Vet Intern Med, Vol: 38, Pages: 922-930
BACKGROUND: Artificial intelligence (AI) could improve accuracy and reproducibility of echocardiographic measurements in dogs. HYPOTHESIS: A neural network can be trained to measure echocardiographic left ventricular (LV) linear dimensions in dogs. ANIMALS: Training dataset: 1398 frames from 461 canine echocardiograms from a single specialist center. VALIDATION: 50 additional echocardiograms from the same center. METHODS: Training dataset: a right parasternal 4-chamber long axis frame from each study, labeled by 1 of 18 echocardiographers, marking anterior and posterior points of the septum and free wall. VALIDATION DATASET: End-diastolic and end-systolic frames from 50 studies, annotated twice (blindly) by 13 experts, producing 26 measurements of each site from each frame. The neural network also made these measurements. We quantified its accuracy as the deviation from the expert consensus, using the individual-expert deviation from consensus as context for acceptable variation. The deviation of the AI measurement away from the expert consensus was assessed on each individual frame and compared with the root-mean-square-variation of the individual expert opinions away from that consensus. RESULTS: For the septum in end-diastole, individual expert opinions deviated by 0.12 cm from the consensus, while the AI deviated by 0.11 cm (P = .61). For LVD, the corresponding values were 0.20 cm for experts and 0.13 cm for AI (P = .65); for the free wall, experts 0.20 cm, AI 0.13 cm (P < .01). In end-systole, there were no differences between individual expert and AI performances. CONCLUSIONS AND CLINICAL IMPORTANCE: An artificial intelligence network can be trained to adequately measure linear LV dimensions, with performance indistinguishable from that of experts.
Rajkumar CA, Foley MJ, Ahmed-Jushuf F, et al., 2023, A Placebo-Controlled Trial of Percutaneous Coronary Intervention for Stable Angina., N Engl J Med, Vol: 389, Pages: 2319-2330
BACKGROUND: Percutaneous coronary intervention (PCI) is frequently performed to reduce the symptoms of stable angina. Whether PCI relieves angina more than a placebo procedure in patients who are not receiving antianginal medication remains unknown. METHODS: We conducted a double-blind, randomized, placebo-controlled trial of PCI in patients with stable angina. Patients stopped all antianginal medications and underwent a 2-week symptom assessment phase before randomization. Patients were then randomly assigned in a 1:1 ratio to undergo PCI or a placebo procedure and were followed for 12 weeks. The primary end point was the angina symptom score, which was calculated daily on the basis of the number of angina episodes that occurred on a given day, the number of antianginal medications prescribed on that day, and clinical events, including the occurrence of unblinding owing to unacceptable angina or acute coronary syndrome or death. Scores range from 0 to 79, with higher scores indicating worse health status with respect to angina. RESULTS: A total of 301 patients underwent randomization: 151 to the PCI group and 150 to the placebo group. The mean (±SD) age was 64±9 years, and 79% were men. Ischemia was present in one cardiac territory in 242 patients (80%), in two territories in 52 patients (17%), and in three territories in 7 patients (2%). In the target vessels, the median fractional flow reserve was 0.63 (interquartile range, 0.49 to 0.75), and the median instantaneous wave-free ratio was 0.78 (interquartile range, 0.55 to 0.87). At the 12-week follow-up, the mean angina symptom score was 2.9 in the PCI group and 5.6 in the placebo group (odds ratio, 2.21; 95% confidence interval, 1.41 to 3.47; P<0.001). One patient in the placebo group had unacceptable angina leading to unblinding. Acute coronary syndromes occurred in 4 patients in the PCI group and in 6 patients in the placebo group. CONCLUSIONS: Among patients with stable angina who were receivi
Ali N, Saqi K, Arnold AD, et al., 2023, Left bundle branch pacing with and without anodal capture: impact on ventricular activation pattern and acute haemodynamics., Europace, Vol: 25
AIMS: Left bundle branch pacing (LBBP) can deliver physiological left ventricular activation, but typically at the cost of delayed right ventricular (RV) activation. Right ventricular activation can be advanced through anodal capture, but there is uncertainty regarding the mechanism by which this is achieved, and it is not known whether this produces haemodynamic benefit. METHODS AND RESULTS: We recruited patients with LBBP leads in whom anodal capture eliminated the terminal R-wave in lead V1. Ventricular activation pattern, timing, and high-precision acute haemodynamic response were studied during LBBP with and without anodal capture. We recruited 21 patients with a mean age of 67 years, of whom 14 were males. We measured electrocardiogram timings and haemodynamics in all patients, and in 16, we also performed non-invasive mapping. Ventricular epicardial propagation maps demonstrated that RV septal myocardial capture, rather than right bundle capture, was the mechanism for earlier RV activation. With anodal capture, QRS duration and total ventricular activation times were shorter (116 ± 12 vs. 129 ± 14 ms, P < 0.01 and 83 ± 18 vs. 90 ± 15 ms, P = 0.01). This required higher outputs (3.6 ± 1.9 vs. 0.6 ± 0.2 V, P < 0.01) but without additional haemodynamic benefit (mean difference -0.2 ± 3.8 mmHg compared with pacing without anodal capture, P = 0.2). CONCLUSION: Left bundle branch pacing with anodal capture advances RV activation by stimulating the RV septal myocardium. However, this requires higher outputs and does not improve acute haemodynamics. Aiming for anodal capture may therefore not be necessary.
Krishnathasan K, Dimopoulos K, Duncan N, et al., 2023, Advanced heart failure in adult congenital heart disease: the role of renal dysfunction in management and outcomes, European Journal of Preventive Cardiology, Vol: 30, Pages: 1335-1342, ISSN: 2047-4873
AimsPrevious studies in adult congenital heart disease (CHD) have demonstrated a link between renal dysfunction and mortality. However, the prognostic significance of renal dysfunction in CHD and decompensated heart failure (HF) remains unclear. We sought to assess the association between renal dysfunction and outcomes in adults with CHD presenting to our centre with acute HF between 2010 and 2021.Methods and resultsThis retrospective analysis focused on the association between renal dysfunction, pre-existing and on admission, and outcomes during and after the index hospitalization. Chronic kidney disease (CKD) was defined as an estimated glomerular filtration rate <60 mL/min/1.73 m2. Cox regression analysis was used to identify the predictors of death post-discharge. In total, 176 HF admissions were included (mean age 47.7 ± 14.5 years, 43.2% females). One-half of patients had a CHD of great complexity, 22.2% had a systemic right ventricle, and 18.8% had Eisenmenger syndrome. Chronic kidney disease was present in one-quarter of patients. The median length of intravenous diuretic therapy was 7 (4–12) days, with a maximum dose of 120 (80–160) mg furosemide equivalents/day, and 15.3% required inotropic support. The in-hospital mortality rate was 4.5%. The 1- and 5-year survival rates free of transplant or ventricular assist device (VAD) post-discharge were 75.4% [95% confidence interval (CI): 69.2–82.3%] and 43.3% (95% CI: 36–52%), respectively. On multivariable Cox analysis, CKD was the strongest predictor of mortality or transplantation/VAD. Highly complex CHD and inpatient requirement of inotropes also remained predictive of an adverse outcome.ConclusionAdult patients with CHD admitted with acute HF are a high-risk cohort. CKD is common and triples the risk of death/transplantation/VAD. An expert multidisciplinary approach is essential for optimizing outcomes.
Ali N, Arnold AD, Miyazawa AA, et al., 2023, Septal scar as a barrier to left bundle branch area pacing, PACE-PACING AND CLINICAL ELECTROPHYSIOLOGY, Vol: 46, Pages: 1077-1084, ISSN: 0147-8389
Tindale A, Cretu I, Haynes R, et al., 2023, How robust are recommended waiting times to pacing after cardiac surgery that are derived from observational data?, Europace, Vol: 25, Pages: 1-9, ISSN: 1099-5129
AIMS: For bradycardic patients after cardiac surgery, it is unknown how long to wait before implanting a permanent pacemaker (PPM). Current recommendations vary and are based on observational studies. This study aims to examine why this variation may exist. METHODS AND RESULTS: We conducted first a study of patients in our institution and second a systematic review of studies examining conduction disturbance and pacing after cardiac surgery. Of 5849 operations over a 6-year period, 103 (1.8%) patients required PPM implantation. Only pacing dependence at implant and time from surgery to implant were associated with 30-day pacing dependence. The only predictor of regression of pacing dependence was time from surgery to implant. We then applied the conventional procedure of receiver operating characteristic (ROC) analysis, seeking an optimal time point for decision-making. This suggested the optimal waiting time was 12.5 days for predicting pacing dependence at 30 days for all patients (area under the ROC curve (AUC) 0.620, P = 0.031) and for predicting regression of pacing dependence in patients who were pacing-dependent at implant (AUC 0.769, P < 0.001). However, our systematic review showed that recommended optimal decision-making time points were strongly correlated with the average implant time point of those individual studies (R = 0.96, P < 0.001). We further conducted modelling which revealed that in any such study, the ROC method is strongly biased to indicate a value near to the median time to implant as optimal. CONCLUSION: When commonly used automated statistical methods are applied to observational data with the aim of defining the optimal time to pacing after cardiac surgery, the suggested answer is likely to be similar to the average time to pacing in that cohort.
Kanagaratnam P, Francis DP, Chamie D, et al., 2023, A randomised controlled trial to investigate the use of acute coronary syndrome therapy in patients hospitalised with COVID-19: the C19-ACS trial, Journal of Thrombosis and Haemostasis, Vol: 21, Pages: 2213-2222, ISSN: 1538-7836
BACKGROUND: Patients hospitalised with COVID-19 suffer thrombotic complications. Risk factors for poor outcomes are shared with coronary artery disease. OBJECTIVES: To investigate efficacy of an acute coronary syndrome regimen in patients hospitalised with COVID-19 and coronary disease risk factors. PATIENTS/METHODS: A randomised controlled open-label trial across acute hospitals (UK and Brazil) added aspirin, clopidogrel, low-dose rivaroxaban, atorvastatin, and omeprazole to standard care for 28-days. Primary efficacy and safety outcomes were 30-day mortality and bleeding. The key secondary outcome was a daily clinical status (at home, in hospital, on intensive therapy unit admission, death). RESULTS: 320 patients from 9 centres were randomised. The trial terminated early due to low recruitment. At 30 days there was no significant difference in mortality (intervention: 11.5% vs control: 15%, unadjusted OR 0.73, 95%CI 0.38 to 1.41, p=0.355). Significant bleeds were infrequent and not significantly different between the arms (intervention: 1.9% vs control 1.9%, p>0.999). Using a Bayesian Markov longitudinal ordinal model, it was 93% probable that intervention arm participants were more likely to transition to a better clinical state each day (OR 1.46, 95% CrI 0.88 to 2.37, Pr(Beta>0)=93%; adjusted OR 1.50, 95% CrI 0.91 to 2.45, Pr(Beta>0)=95%) and median time to discharge home was two days shorter (95% CrI -4 to 0, 2% probability that it was worse). CONCLUSIONS: Acute coronary syndrome treatment regimen was associated with a reduction in the length of hospital stay without an excess in major bleeding. A larger trial is needed to evaluate mortality.
Seligman H, Patel SB, Alloula A, et al., 2023, Development of artificial intelligence tools for invasive Doppler-based coronary microvascular assessment., Eur Heart J Digit Health, Vol: 4, Pages: 291-301
AIMS: Coronary flow reserve (CFR) assessment has proven clinical utility, but Doppler-based methods are sensitive to noise and operator bias, limiting their clinical applicability. The objective of the study is to expand the adoption of invasive Doppler CFR, through the development of artificial intelligence (AI) algorithms to automatically quantify coronary Doppler quality and track flow velocity. METHODS AND RESULTS: A neural network was trained on images extracted from coronary Doppler flow recordings to score signal quality and derive values for coronary flow velocity and CFR. The outputs were independently validated against expert consensus. Artificial intelligence successfully quantified Doppler signal quality, with high agreement with expert consensus (Spearman's rho: 0.94), and within individual experts. Artificial intelligence automatically tracked flow velocity with superior numerical agreement against experts, when compared with the current console algorithm [AI flow vs. expert flow bias -1.68 cm/s, 95% confidence interval (CI) -2.13 to -1.23 cm/s, P < 0.001 with limits of agreement (LOA) -4.03 to 0.68 cm/s; console flow vs. expert flow bias -2.63 cm/s, 95% CI -3.74 to -1.52, P < 0.001, 95% LOA -8.45 to -3.19 cm/s]. Artificial intelligence yielded more precise CFR values [median absolute difference (MAD) against expert CFR: 4.0% for AI and 7.4% for console]. Artificial intelligence tracked lower-quality Doppler signals with lower variability (MAD against expert CFR 8.3% for AI and 16.7% for console). CONCLUSION: An AI-based system, trained by experts and independently validated, could assign a quality score to Doppler traces and derive coronary flow velocity and CFR. By making Doppler CFR more automated, precise, and operator-independent, AI could expand the clinical applicability of coronary microvascular assessment.
Butcher CJT, Cantor E, Sohaib A, et al., 2023, Variation in optimal hemodynamic atrio-ventricular delay of biventricular pacing with different endocardial left ventricular lead locations using precision hemodynamics, JOURNAL OF CARDIOVASCULAR ELECTROPHYSIOLOGY, Vol: 34, Pages: 1431-1440, ISSN: 1045-3873
Zaman S, Vimalesvaran K, Howard JP, et al., 2023, Efficient labelling for efficient deep learning: the benefit of a multiple-image-ranking method to generate high volume training data applied to ventricular slice level classification in cardiac MRI, Journal of Medical Artificial Intelligence, Vol: 6, ISSN: 2617-2496
BACKGROUND: Getting the most value from expert clinicians' limited labelling time is a major challenge for artificial intelligence (AI) development in clinical imaging. We present a novel method for ground-truth labelling of cardiac magnetic resonance imaging (CMR) image data by leveraging multiple clinician experts ranking multiple images on a single ordinal axis, rather than manual labelling of one image at a time. We apply this strategy to train a deep learning (DL) model to classify the anatomical position of CMR images. This allows the automated removal of slices that do not contain the left ventricular (LV) myocardium. METHODS: Anonymised LV short-axis slices from 300 random scans (3,552 individual images) were extracted. Each image's anatomical position relative to the LV was labelled using two different strategies performed for 5 hours each: (I) 'one-image-at-a-time': each image labelled according to its position: 'too basal', 'LV', or 'too apical' individually by one of three experts; and (II) 'multiple-image-ranking': three independent experts ordered slices according to their relative position from 'most-basal' to 'most apical' in batches of eight until each image had been viewed at least 3 times. Two convolutional neural networks were trained for a three-way classification task (each model using data from one labelling strategy). The models' performance was evaluated by accuracy, F1-score, and area under the receiver operating characteristics curve (ROC AUC). RESULTS: After excluding images with artefact, 3,323 images were labelled by both strategies. The model trained using labels from the 'multiple-image-ranking strategy' performed better than the model using the 'one-image-at-a-time' labelling strategy (accuracy 86% vs. 72%, P=0.02; F1-score 0.86 vs. 0.75; ROC AUC 0.95 vs. 0.86). For expert clinicians performing this task manually the intra-observer variability was low (Cohen's κ=0.90), but the inter-observer variability was higher (Cohen's &kap
Al Saikhan L, Park C, Tillin T, et al., 2023, Sex-differences in associations of LV structure and function measured by echocardiography with long-term risk of mortality and cardiovascular morbidity, FRONTIERS IN CARDIOVASCULAR MEDICINE, Vol: 10, ISSN: 2297-055X
Chow J-J, Leong KMW, Shun-Shin MJ, et al., 2023, Ventricular conduction stability noninvasively identifies an arrhythmic substrate in survivors of idiopathic ventricular fibrillation, Journal of the American Heart Association, Vol: 12, Pages: 1-24, ISSN: 2047-9980
Background Idiopathic ventricular fibrillation (VF) is a diagnosis of exclusion following normal cardiac investigations. We sought to determine if exercise-induced changes in electrical substrate could distinguish patient groups with various ventricular arrhythmic pathophysiological conditions and identify patients susceptible to VF. Methods and Results Computed tomography and exercise testing in patients wearing a 252-electrode vest were combined to determine ventricular conduction stability between rest and peak exercise, as previously described. Using ventricular conduction stability, conduction heterogeneity in idiopathic VF survivors (n=14) was compared with those surviving VF during acute ischemia with preserved ventricular function following full revascularization (n=10), patients with benign ventricular ectopy (n=11), and patients with normal hearts, no arrhythmic history, and negative Ajmaline challenge during Brugada family screening (Brugada syndrome relatives; n=11). Activation patterns in normal subjects (Brugada syndrome relatives) are preserved following exercise, with mean ventricular conduction stability of 99.2±0.9%. Increased heterogeneity of activation occurred in the idiopathic VF survivors (ventricular conduction stability: 96.9±2.3%) compared with the other groups combined (versus 98.8±1.6%; P=0.001). All groups demonstrated periodic variation in activation heterogeneity (frequency, 0.3-1 Hz), but magnitude was greater in idiopathic VF survivors than Brugada syndrome relatives or patients with ventricular ectopy (7.6±4.1%, 2.9±2.9%, and 2.8±1.2%, respectively). The cause of this periodicity is unknown and was not replicable by introducing exercise-induced noise at comparable frequencies. Conclusions In normal subjects, ventricular activation patterns change little with exercise. In contrast, patients with susceptibility to VF experience activation heterogeneity following exercise that requires f
Kaza N, Htun V, Miyazawa A, et al., 2023, Upgrading right ventricular pacemakers to biventricular pacing or conduction system pacing: a systematic review and meta-analysis, EUROPACE, Vol: 25, Pages: 1077-1086, ISSN: 1099-5129
- Author Web Link
- Cite
- Citations: 3
Ali N, Arnold AD, Miyazawa AA, et al., 2023, Comparison of methods for delivering cardiac resynchronization therapy: an acute electrical and haemodynamic within-patient comparison of left bundle branch area, His bundle, and biventricular pacing, EP Europace, Vol: 25, Pages: 1060-1067, ISSN: 1099-5129
AimsLeft bundle branch area pacing (LBBAP) is a promising method for delivering cardiac resynchronization therapy (CRT), but its relative physiological effectiveness compared with His bundle pacing (HBP) is unknown. We conducted a within-patient comparison of HBP, LBBAP, and biventricular pacing (BVP).Methods and resultsPatients referred for CRT were recruited. We assessed electrical response using non-invasive mapping, and acute haemodynamic response using a high-precision haemodynamic protocol. Nineteen patients were recruited: 14 male, mean LVEF of 30%. Twelve had time for BVP measurements. All three modalities reduced total ventricular activation time (TVAT), (ΔTVATHBP -43 ± 14 ms and ΔTVATLBBAP −35 ± 20 ms vs. ΔTVATBVP −19 ± 30 ms, P = 0.03 and P = 0.1, respectively). HBP produced a significantly greater reduction in TVAT compared with LBBAP in all 19 patients (−46 ± 15 ms, −36 ± 17 ms, P = 0.03). His bundle pacing and LBBAP reduced left ventricular activation time (LVAT) more than BVP (ΔLVATHBP −43 ± 16 ms, P < 0.01 vs. BVP, ΔLVATLBBAP −45 ± 17 ms, P < 0.01 vs. BVP, ΔLVATBVP −13 ± 36 ms), with no difference between HBP and LBBAP (P = 0.65). Acute systolic blood pressure was increased by all three modalities. In the 12 with BVP, greater improvement was seen with HBP and LBBAP (6.4 ± 3.8 mmHg BVP, 8.1 ± 3.8 mmHg HBP, P = 0.02 vs. BVP and 8.4 ± 8.2 mmHg for LBBAP, P = 0.3 vs. BVP), with no difference between HBP and LBBAP (P = 0.8).ConclusionHBP delivered better ventricular resynchronization than LBBAP because right ventricular activation was slower during LBBAP. But LBBAP was not inferior to HBP with respect to LV electrical resynchronization and acute haemodynamic response.
Simader FA, Howard JP, Ahmad Y, et al., 2023, Catheter ablation improves cardiovascular outcomes in patients with atrial fibrillation and heart failure: a meta-analysis of randomized controlled trials, EUROPACE, Vol: 25, Pages: 341-350, ISSN: 1099-5129
- Author Web Link
- Cite
- Citations: 10
Whinnett ZI, Shun-Shin MJ, Tanner M, et al., 2023, Effects of haemodynamically atrio-ventricular optimized His bundle pacing on heart failure symptoms and exercise capacity: the His Optimized Pacing Evaluated for Heart Failure (HOPE-HF) randomized, double-blind, cross-over trial, EUROPEAN JOURNAL OF HEART FAILURE, Vol: 25, Pages: 274-283, ISSN: 1388-9842
- Author Web Link
- Cite
- Citations: 3
Lane ES, Jevsikov J, Shun-shin MJ, et al., 2023, Automated multi-beat tissue Doppler echocardiography analysis using deep neural networks, MEDICAL & BIOLOGICAL ENGINEERING & COMPUTING, ISSN: 0140-0118
Alajrami E, Naidoo P, Jevsikov J, et al., 2023, Deep Active Learning for Left Ventricle Segmentation in Echocardiography, Pages: 283-291, ISSN: 0302-9743
The training of advanced deep learning algorithms for medical image interpretation requires precisely annotated datasets, which is laborious and expensive. Therefore, this research investigates state-of-the-art active learning methods for utilising limited annotations when performing automated left ventricle segmentation in echocardiography. Our experiments reveal that the performance of different sampling strategies varies between datasets from the same domain. Further, an optimised method for representativeness sampling is introduced, combining images from feature-based outliers to the most representative samples for label acquisition. The proposed method significantly outperforms the current literature and demonstrates convergence with minimal annotations. We demonstrate that careful selection of images can reduce the number of images needed to be annotated by up to 70%. This research can therefore present a cost-effective approach to handling datasets with limited expert annotations in echocardiography.
Jevsikov J, Lane ES, Alajrami E, et al., 2023, Automated Analysis of Mitral Inflow Doppler Using Deep Neural Networks, Pages: 394-402, ISSN: 0302-9743
Doppler echocardiography is a widely applied modality for the functional assessment of heart valves, such as the mitral valve. Currently, Doppler echocardiography analysis is manually performed by human experts. This process is not only expensive and time-consuming, but often suffers from intra- and inter-observer variability. An automated analysis tool for non-invasive evaluation of cardiac hemodynamic has potential to improve accuracy, patient outcomes, and save valuable resources for health services. Here, a robust algorithm is presented for automatic Doppler Mitral Inflow peak velocity detection utilising state-of-the-art deep learning techniques. The proposed framework consists of a multi-stage convolutional neural network which can process Doppler images spanning arbitrary number of heartbeats, independent from the electrocardiogram signal and any human intervention. Automated measurements are compared to Ground-truth annotations obtained manually by human experts. Results show the proposed model can efficiently detect peak mitral inflow velocity achieving an average F1 score of 0.88 for both E- and A-peaks across the entire test set.
Arnold AD, Shun-Shin MJ, Ali N, et al., 2023, Contributions of Atrioventricular Delay Shortening and Ventricular Resynchronization to Hemodynamic Benefits of Biventricular Pacing, JACC-CLINICAL ELECTROPHYSIOLOGY, Vol: 9, Pages: 117-119, ISSN: 2405-500X
- Author Web Link
- Cite
- Citations: 3
Reddy RK, Howard JP, Ahmad Y, et al., 2023, Catheter Ablation for Ventricular Tachycardia After MI: A Reconstructed Individual Patient Data Meta-analysis of Randomised Controlled Trials., Arrhythm Electrophysiol Rev, Vol: 12, ISSN: 2050-3369
BACKGROUND: The prognostic impact of ventricular tachycardia (VT) catheter ablation is an important outstanding research question. We undertook a reconstructed individual patient data meta-analysis of randomised controlled trials comparing ablation to medical therapy in patients developing VT after MI. METHODS: We systematically identified all trials comparing catheter ablation to medical therapy in patients with VT and prior MI. The prespecified primary endpoint was reconstructed individual patient assessment of all-cause mortality. Prespecified secondary endpoints included trial-level assessment of all-cause mortality, VT recurrence or defibrillator shocks and all-cause hospitalisations. Prespecified subgroup analysis was performed for ablation approaches involving only substrate modification without VT activation mapping. Sensitivity analyses were performed depending on the proportion of patients with prior MI included. RESULTS: Eight trials, recruiting a total of 874 patients, were included. Of these 874 patients, 430 were randomised to catheter ablation and 444 were randomised to medical therapy. Catheter ablation reduced all-cause mortality compared with medical therapy when synthesising individual patient data (HR 0.63; 95% CI [0.41-0.96]; p=0.03), but not in trial-level analysis (RR 0.91; 95% CI [0.67-1.23]; p=0.53; I2=0%). Catheter ablation significantly reduced VT recurrence, defibrillator shocks and hospitalisations compared with medical therapy. Sensitivity analyses were consistent with the primary analyses. CONCLUSION: In patients with postinfarct VT, catheter ablation reduces mortality.
Ganesananthan S, Rajkumar CA, Foley M, et al., 2022, Remote digital smart device follow-up in prospective clinical trials: early insights from ORBITA-2, ORBITA-COSMIC, and ORBITA-STAR, EUROPEAN HEART JOURNAL SUPPLEMENTS, Vol: 24, Pages: H32-H42, ISSN: 1520-765X
Asaria P, Bennett J, Elliott P, et al., 2022, Contributions of event rates, pre-hospital deaths and hospital case fatality to variations in myocardial infarction mortality in 326 districts in England: spatial analysis of linked hospitalisation and mortality data, The Lancet Public Health, Vol: 7, Pages: e813-e824, ISSN: 2468-2667
Background: Myocardial infarction (MI) mortality varies substantially within high-income countries. There is limited guidance on what interventions – primary and secondary prevention and/or improving care pathways and quality – can reduce and equalise MI mortality. Our aimwas to understand the contribution of incidence (event rate), pre-hospital deaths and hospital case-fatality, to how MI mortality varies within England.Methods: We used linked data on hospitalisation and deaths from 2015-2018 with geographical identifiers to estimate MI death and event rates, pre-hospital deaths and hospital case fatality for men and women aged 45 years and older in 326 districts in England. Data were analysed in a Bayesian spatial model that accounted for similarities and differences inspatial patterns of fatal and non-fatal MI. Results: The 99th to 1st percentile ratio of age-standardised MI death rate was 2.63 (95% credible interval 2.45-2.83) in women and 2.56 (2.37-2.76) in men across districts, with death rate highest in north of England. The main contributor to this variation was MI event rate, with a 99th to 1st percentile ratio of 2.55 (2.39-2.72) (women) and 2.17 (2.08-2.27) (men) across districts. Pre-hospital mortality was greater than hospital case fatality in every district. Prehospital mortality had a 99th to 1st percentile ratio 1.60 (1.50-1.70) in women and 1.75 (1.66-1.86) in men across districts and made a greater contribution to case-fatality variation thanhospital case fatality which had a 99th to 1st percentile ratio of 1.39 (1.29-1.49) (women) and1.49 (1.39-1.60) (men). The contribution of case fatality to variation in deaths across districtswas largest in middle ages. Pre-hospital mortality was slightly higher in men than women inmost districts and age groups, whereas hospital case fatality was higher in women in virtuallyall districts at ages up to and including 65-74 years; after this age, it became similar betweenthe sexes.3Interpretation: Mos
Nowbar AN, Francis DP, Al-Lamee RK, 2022, Quality of Life Assessment in Trials of Revascularization for Chronic Stable Angina: Insights from ORBITA and the Implications of Blinding, CARDIOVASCULAR DRUGS AND THERAPY, Vol: 36, Pages: 1011-1018, ISSN: 0920-3206
- Author Web Link
- Cite
- Citations: 1
Sedlacek K, Polasek R, Jansova H, et al., 2022, Inadvertent QRS prolongation by an optimization device-based algorithm in patients with cardiac resynchronization therapy, PLOS ONE, Vol: 17, ISSN: 1932-6203
Ganesananthan S, Rajkumar C, Foley M, et al., 2022, Cardiopulmonary exercise testing and efficacy of percutaneous coronary intervention: A substudy of the ORBITA trial, European Heart Journal, Vol: 43, Pages: 3132-3145, ISSN: 0195-668X
AimsOxygen-pulse morphology and gas exchange analysis measured during cardiopulmonary exercise testing (CPET) has been associated with myocardial ischaemia. We examine the relationship between CPET parameters, myocardial ischaemia and anginal symptoms in patients with chronic coronary syndrome. We also determine the ability of these parameters to predict the placebo-controlled response to percutaneous coronary intervention (PCI).Methods and resultsPatients with severe single vessel coronary artery disease were randomised 1:1 to PCI or placebo in the ORBITA trial. Subjects underwent pre-randomisation treadmill CPET, dobutamine stress-echocardiography (DSE) and symptom assessment. These assessments were repeated at the end of a 6-week blinded follow-up period. 195 patients with CPET data were randomised (102 PCI, 93 placebo). Patients in whom an oxygen-pulse plateau was observed during CPET had higher (more ischaemic) DSE score (+0.82 segments; 95%CI, 0.40 to 1.25, P=0.0068) and lower FFR (-0.07; -0.12 to -0.02, P=0.011) compared to those without. At lower (more abnormal) oxygen-pulse slopes, there was a larger improvement of the placebo-controlled effect of PCI on DSE score (oxygen-pulse plateau presence [Pinteraction=0.026] and oxygen-pulse gradient [Pinteraction=0.023]) and Seattle angina physical-limitation score (oxygen-pulse plateau presence [Pinteraction=0.037]). Impaired peak VO2, VE/VCO2 slope, peak oxygen-pulse and oxygen-uptake efficacy slope was significantly associated with higher symptom burden but did not relate to severity of ischaemia or predict response to PCI.ConclusionAlthough selected CPET parameters relate to severity of angina symptoms and quality of life, only an oxygen-pulse plateau detects the severity of myocardial ischaemia and predicts the placebo-controlled efficacy of PCI in patients with single-vessel coronary artery disease.
This data is extracted from the Web of Science and reproduced under a licence from Thomson Reuters. You may not copy or re-distribute this data in whole or in part without the written consent of the Science business of Thomson Reuters.