-
Journal of the American Heart... Jan 2024Identification of children with latent rheumatic heart disease (RHD) by echocardiography, before onset of symptoms, provides an opportunity to initiate secondary...
BACKGROUND
Identification of children with latent rheumatic heart disease (RHD) by echocardiography, before onset of symptoms, provides an opportunity to initiate secondary prophylaxis and prevent disease progression. There have been limited artificial intelligence studies published assessing the potential of machine learning to detect and analyze mitral regurgitation or to detect the presence of RHD on standard portable echocardiograms.
METHODS AND RESULTS
We used 511 echocardiograms in children, focusing on color Doppler images of the mitral valve. Echocardiograms were independently reviewed by an expert adjudication panel. Among 511 cases, 229 were normal, and 282 had RHD. Our automated method included harmonization of echocardiograms to localize the left atrium during systole using convolutional neural networks and RHD detection using mitral regurgitation jet analysis and deep learning models with an attention mechanism. We identified the correct view with an average accuracy of 0.99 and the correct systolic frame with an average accuracy of 0.94 (apical) and 0.93 (parasternal long axis). It localized the left atrium with an average Dice coefficient of 0.88 (apical) and 0.9 (parasternal long axis). Maximum mitral regurgitation jet measurements were similar to expert manual measurements ( value=0.83) and a 9-feature mitral regurgitation analysis showed an area under the receiver operating characteristics curve of 0.93, precision of 0.83, recall of 0.92, and F1 score of 0.87. Our deep learning model showed an area under the receiver operating characteristics curve of 0.84, precision of 0.78, recall of 0.98, and F1 score of 0.87.
CONCLUSIONS
Artificial intelligence has the potential to detect RHD as accurately as expert cardiologists and to improve with more data. These innovative approaches hold promise to scale echocardiography screening for RHD.
Topics: Child; Humans; Mitral Valve Insufficiency; Rheumatic Heart Disease; Artificial Intelligence; Sensitivity and Specificity; Echocardiography
PubMed: 38226515
DOI: 10.1161/JAHA.123.031257 -
Clinical Cardiology Oct 2023The management of chronic heart failure over the past decade has witnessed tremendous strides in medical optimization and device therapy including the use of left... (Review)
Review
The management of chronic heart failure over the past decade has witnessed tremendous strides in medical optimization and device therapy including the use of left ventricular assist devices (LVAD). What we once thought of as irreversible damage to the myocardium is now demonstrating signs of reverse remodeling and recovery. Myocardial recovery on the structural, molecular, and hemodynamic level is necessary for sufficient recovery to withstand explant and achieve sustained recovery post-LVAD. Guideline-directed medical therapy and unloading have been shown to aid in recovery with the potential to successfully explant the LVAD. This review will summarize medical optimization, assessment for recovery, explant methodologies and outcomes post-recovery with explant of durable LVAD.
Topics: Humans; Heart-Assist Devices; Heart Ventricles; Ventricular Remodeling; Heart Failure; Myocardium
PubMed: 37526373
DOI: 10.1002/clc.24094 -
Circulation. Arrhythmia and... Oct 2023The clinical utilization of leadless pacemakers (LPs) as an alternative to traditional transvenous pacemakers is likely to increase with the advent of dual-chamber LP...
BACKGROUND
The clinical utilization of leadless pacemakers (LPs) as an alternative to traditional transvenous pacemakers is likely to increase with the advent of dual-chamber LP systems. Since device retrieval to allow LP upgrade or replacement will become an important capability, the first such dual-chamber, helix-fixation LP system (Aveir DR; Abbott, Abbott Park, IL) was specifically designed to allow catheter-based retrieval. In this study, the preclinical performance and safety of retrieving chronically implanted dual-chamber LPs was evaluated.
METHODS
Atrial and ventricular LPs were implanted in the right atrial appendage and right ventricular apex of 9 healthy ovine subjects. After ≈2 years, the LPs were retrieved using a dedicated transvenous retrieval catheter (Aveir Retrieval Catheter; Abbott) by snaring, docking, and unscrewing from the myocardium. Comprehensive necropsy/histopathology studies were conducted to evaluate device- and procedure-related outcomes.
RESULTS
At a median of 1.9 years postimplant (range, 1.8-2.6), all 18 of 18 (100%) LPs were retrieved from 9 ovine subjects without complications. The median retrieval procedure duration for both LPs, from first-catheter-in to last-catheter-out, was 13.3 minutes (range, 2.5-36.4). Postretrieval, all right atrial, and right ventricular implant sites demonstrated minimal tissue disruption, with intact fibrous tissue limited to the distal device body. No significant device-related trauma, perforation, pericardial effusion, right heart or tricuspid valve injury, or chronic pulmonary thromboembolism were observed at necropsy.
CONCLUSIONS
This preclinical study demonstrated the safe and effective retrieval of chronically implanted, helix-fixation, dual-chamber LP systems, paving the way for clinical studies of LP retrieval.
Topics: Humans; Sheep; Animals; Atrial Fibrillation; Lipopolysaccharides; Pacemaker, Artificial; Sheep, Domestic; Heart Ventricles; Equipment Design
PubMed: 37767710
DOI: 10.1161/CIRCEP.123.012232 -
Open Heart Nov 2023The advent of conversational artificial intelligence (AI) systems employing large language models such as ChatGPT has sparked public, professional and academic debates... (Review)
Review
OBJECTIVES
The advent of conversational artificial intelligence (AI) systems employing large language models such as ChatGPT has sparked public, professional and academic debates on the capabilities of such technologies. This mixed-methods study sets out to review and systematically explore the capabilities of ChatGPT to adequately provide health advice to patients when prompted regarding four topics from the field of cardiovascular diseases.
METHODS
As of 30 May 2023, 528 items on PubMed contained the term ChatGPT in their title and/or abstract, with 258 being classified as journal articles and included in our thematic state-of-the-art review. For the experimental part, we systematically developed and assessed 123 prompts across the four topics based on three classes of users and two languages. Medical and communications experts scored ChatGPT's responses according to the 4Cs of language model evaluation proposed in this article: correct, concise, comprehensive and comprehensible.
RESULTS
The articles reviewed were fairly evenly distributed across discussing how ChatGPT could be used for medical publishing, in clinical practice and for education of medical personnel and/or patients. Quantitatively and qualitatively assessing the capability of ChatGPT on the 123 prompts demonstrated that, while the responses generally received above-average scores, they occupy a spectrum from the concise and correct via the absurd to what only can be described as hazardously incorrect and incomplete. Prompts formulated at higher levels of health literacy generally yielded higher-quality answers. Counterintuitively, responses in a lower-resource language were often of higher quality.
CONCLUSIONS
The results emphasise the relationship between prompt and response quality and hint at potentially concerning futures in personalised medicine. The widespread use of large language models for health advice might amplify existing health inequalities and will increase the pressure on healthcare systems by providing easy access to many seemingly likely differential diagnoses and recommendations for seeing a doctor for even harmless ailments.
Topics: Humans; Artificial Intelligence; Cardiovascular Diseases; Heart; Patients; Referral and Consultation
PubMed: 37945282
DOI: 10.1136/openhrt-2023-002455 -
Scientific Reports Feb 2024As cardiovascular disorders are prevalent, there is a growing demand for reliable and precise diagnostic methods within this domain. Audio signal-based heart disease...
As cardiovascular disorders are prevalent, there is a growing demand for reliable and precise diagnostic methods within this domain. Audio signal-based heart disease detection is a promising area of research that leverages sound signals generated by the heart to identify and diagnose cardiovascular disorders. Machine learning (ML) and deep learning (DL) techniques are pivotal in classifying and identifying heart disease from audio signals. This study investigates ML and DL techniques to detect heart disease by analyzing noisy sound signals. This study employed two subsets of datasets from the PASCAL CHALLENGE having real heart audios. The research process and visually depict signals using spectrograms and Mel-Frequency Cepstral Coefficients (MFCCs). We employ data augmentation to improve the model's performance by introducing synthetic noise to the heart sound signals. In addition, a feature ensembler is developed to integrate various audio feature extraction techniques. Several machine learning and deep learning classifiers are utilized for heart disease detection. Among the numerous models studied and previous study findings, the multilayer perceptron model performed best, with an accuracy rate of 95.65%. This study demonstrates the potential of this methodology in accurately detecting heart disease from sound signals. These findings present promising opportunities for enhancing medical diagnosis and patient care.
Topics: Humans; Artificial Intelligence; Neural Networks, Computer; Heart Diseases; Machine Learning; Heart Sounds; Cardiovascular Diseases
PubMed: 38326488
DOI: 10.1038/s41598-024-53778-7 -
Journal of the American Heart... Dec 2023Temporal trends in the management of acute coronary syndrome complicated with cardiogenic shock after the revision of guideline recommendations for intra-aortic balloon...
Changing Trends in Mechanical Circulatory Support Use and Outcomes in Patients Undergoing Percutaneous Coronary Interventions for Acute Coronary Syndrome Complicated With Cardiogenic Shock: Insights From a Nationwide Registry in Japan.
BACKGROUND
Temporal trends in the management of acute coronary syndrome complicated with cardiogenic shock after the revision of guideline recommendations for intra-aortic balloon pump (IABP) use and the approval of the Impella require further investigation, because their impact remains uncertain.
METHODS AND RESULTS
Using the Japanese Percutaneous Coronary Intervention (J-PCI) registry database from 2019 to 2021, we identified 12 171 patients undergoing percutaneous coronary intervention for acute coronary syndrome complicated with cardiogenic shock under mechanical circulatory support. The patients were stratified into 3 groups: (1) IABP alone, (2) Impella, and (3) venoarterial extracorporeal membrane oxygenation (VA-ECMO); the VA-ECMO group was further stratified into (3a) VA-ECMO alone, (3b) VA-ECMO in combination with IABP, and (3c) VA-ECMO in combination with Impella. The quarterly prevalence and outcomes were reported. The use of IABP alone decreased significantly from 63.5% in the first quarter of 2019 to 58.3% in the fourth quarter of 2021 ( for trend=0.01). Among 4245 patients requiring VA-ECMO, the use of VA-ECMO in combination with IABP decreased significantly from 78.7% to 67.3%, whereas the use of VA-ECMO in combination with Impella increased significantly from 4.2% to 17.0% ( for trend <0.001 for both). After adjusting for the confounders, the risk difference in the fourth quarter of 2021 relative to the first quarter of 2019 for in-hospital mortality was not significant (adjusted odds ratio, 0.84 [95% CI, 0.69-1.01]).
CONCLUSIONS
Our study revealed substantial changes in the use of different mechanical circulatory support modalities in acute coronary syndrome complicated with cardiogenic shock, but they did not significantly improve the outcomes.
Topics: Humans; Shock, Cardiogenic; Acute Coronary Syndrome; Percutaneous Coronary Intervention; Japan; Registries; Intra-Aortic Balloon Pumping; Heart-Assist Devices; Treatment Outcome
PubMed: 38038195
DOI: 10.1161/JAHA.123.031838 -
Methodist DeBakey Cardiovascular Journal 2024Left ventricular assist devices (LVAD) are surgically implanted mechanical support devices utilized with increasing frequency as a bridge to myocardial recovery,...
Left ventricular assist devices (LVAD) are surgically implanted mechanical support devices utilized with increasing frequency as a bridge to myocardial recovery, destination therapy, and heart transplantation. While the use of such devices in patients with advanced heart failure has shown significant survival benefits and improved quality of life, they bear their own risks and complications. Bleeding, infection, pump thrombosis, and stroke are just some of the serious complications associated with LVADs. LVAD-associated pseudoaneurysms are rare, with prior reports of occurrence at the left ventricular apex and at the anastomosis site of the outflow graft to the ascending aorta. Typically, this device-related complication requires surgical repair and, if at all feasible, heart transplantation. However, in cases of difficult anatomy, unfavorable position, and significant comorbidities, surgery may be contraindicated due to high surgical risk. This case portrays a patient suffering from a left ventricular pseudoaneurysm after HeartMate-III implantation that was not amenable to surgical repair due to heightened surgical risk. We document the first pseudoaneurysm associated with the HeartMate-III in available literature and describe a novel management strategy of documented nonoperative course of LVAD-associated pseudoaneurysm, with the patient surviving 56+ months with medical optimization and management.
Topics: Humans; Conservative Treatment; Aneurysm, False; Heart-Assist Devices; Quality of Life; Aorta
PubMed: 38250571
DOI: 10.14797/mdcvj.1301 -
Journal of Cardiology Apr 2024The importance of temporary mechanical circulatory support for treating acute heart failure with cardiogenic shock is increasingly recognized, and Impella (Abiomed,... (Review)
Review
The importance of temporary mechanical circulatory support for treating acute heart failure with cardiogenic shock is increasingly recognized, and Impella (Abiomed, Danvers, MA, USA) has received particular attention in this regard. Impella is an axial flow left ventricular assist device (LVAD) built into the tip of a catheter. It is inserted via a peripheral artery and implanted into the left ventricle. Although the morphology of Impella is different from a typical LVAD, it has similar actions and effects as an LVAD in terms of left ventricular drainage and aortic blood delivery. Impella increases mean arterial pressure (MAP) and systemic blood flow, thereby improving peripheral organ perfusion and promoting recovery from multiple organ failure. In addition, left ventricular unloading with increased MAP increases coronary perfusion and decreases myocardial oxygen demand, thereby promoting myocardial recovery. Impella is also useful as a mechanical vent of the left ventricle in patients supported with veno-arterial extracorporeal membrane oxygenation. Indications for Impella include emergency use for cardiogenic shock and non-emergent use during high-risk percutaneous coronary intervention and ventricular tachycardia ablation. Its intended uses for cardiogenic shock include bridge to recovery, durable device, heart transplantation, and heart surgery. Prophylactic use of Impella in high-risk patients undergoing open heart surgery to prevent postcardiotomy cardiogenic shock is also gaining attention. While there have been many case reports and retrospective studies on the benefits of Impella, there is little evidence based on sufficiently large randomized controlled trials (RCTs). Currently, several RCTs are now ongoing, which are critical to determine when, for whom, and how these devices should be used. In this review, we summarize the principles, physiology, indications, and complications of the Impella support and discuss current issues and future expectations for the device.
Topics: Humans; Shock, Cardiogenic; Heart-Assist Devices; Motivation; Heart Failure; Cardiac Surgical Procedures; Retrospective Studies; Treatment Outcome
PubMed: 37926367
DOI: 10.1016/j.jjcc.2023.10.008 -
The Canadian Journal of Cardiology Jun 2024This manuscript reviews the application of artificial intelligence (AI) in acute cardiac care, highlighting its potential to transform patient outcomes in the face of... (Review)
Review
This manuscript reviews the application of artificial intelligence (AI) in acute cardiac care, highlighting its potential to transform patient outcomes in the face of the global burden of cardiovascular diseases. It explores how AI algorithms can rapidly and accurately process data for the prediction and diagnosis of acute cardiac conditions. The paper examines AI's impact on patient health across various diagnostic tools such as echocardiography, electrocardiography, coronary angiography, cardiac CT, and MRI and discusses the regulatory landscape for AI in healthcare, categorizes AI algorithms by their risk levels. Furthermore, it addresses the challenges of data quality, generalizability, bias, transparency, and regulatory considerations, underscoring the necessity for inclusive data and robust validation processes. The review concludes with future perspectives on integrating AI into clinical workflows and the ongoing need for research, regulation, and innovation to harness AI's full potential in improving acute cardiac care.
PubMed: 38901544
DOI: 10.1016/j.cjca.2024.06.011 -
The Canadian Journal of Cardiology Apr 2024Adopting artificial intelligence in medicine may improve speed and accuracy in patient diagnosis. We sought to develop an artificial intelligence (AI) algorithm to...
BACKGROUND
Adopting artificial intelligence in medicine may improve speed and accuracy in patient diagnosis. We sought to develop an artificial intelligence (AI) algorithm to interpret wide complex tachycardia (WCT) electrocardiograms (ECG) and compare its diagnostic accuracy to cardiologists.
METHODS
Using 3330 WCT ECGs (2906 SVT and 424 VT), we created a training/validation (3131) and test set (199 ECGs). A convolutional neural network (CNN) structure using a modification of differentiable architecture search (DARTS), ZeroLess-DARTS, was developed to differentiate between SVT and VT.
RESULTS
The mean accuracy of electrophysiology (EP) cardiologists was 92.5% with a sensitivity of 91.7%, specificity of 93.4%, positive predictive value of 93.7%, negative predictive value of 91.7%. NonEP cardiologists had an accuracy of 73.2 ± 14.4% with a sensitivity, specificity, positive and negative predictive value of 59.8 ± 18.2%, 93.8 ± 3.7%, 93.6 ± 2.3%, and 73.2 ± 14.4%, respectively. AI had superior sensitivity and accuracy (91.9% and 93.0%, respectively) than NonEP cardiologists, and had similar performance of EP cardiologists. Mean time to interpret each ECG varied between 10.1-13.8 seconds for EP cardiologists and 3.1 -16.6 seconds for NonEP cardiologists. Conversely AI required a mean of 0.0092 ± 0.0035 seconds for each ECG interpretation.
CONCLUSIONS
AI appears to diagnose WCT with superior accuracy than Cardiologists and similar to those of Electrophysiologists. Using AI to assist with ECG interpretations may improve patient care.
PubMed: 38588794
DOI: 10.1016/j.cjca.2024.03.027