Future Guidelines for Artificial Intelligence in Echocardiography

New ultrasound techniques. Present and future

The present study highlights the advances in ultrasound, especially regarding its clinical applications to critically ill patients. Artificial intelligence (AI) is crucial in automating image interpretation, improving accuracy and efficiency. Software has been developed to make it easier to perform accurate bedside ultrasound examinations, even by professionals lacking prior experience, with automatic image optimization. In addition, some applications identify cardiac structures, perform planimetry of the Doppler wave, and measure the size of vessels, which is especially useful in hemodynamic monitoring and continuous recording. The "strain" and "strain rate" parameters evaluate ventricular function, while "auto strain" automates its calculation from bedside images. These advances, and the automatic determination of ventricular volume, make ultrasound monitoring more precise and faster. The next step is continuous monitoring using gel devices attached to the skin.

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.

Automated and reference methods for the calculation of left ventricular outflow tract velocity time integral or ejection fraction by non-cardiologists: a systematic review on the agreement of the two methods

Echocardiography is crucial for evaluating patients at risk of clinical deterioration. Left ventricular ejection fraction (LVEF) and velocity time integral (VTI) aid in diagnosing shock, but bedside calculations can be time-consuming and prone to variability. Artificial intelligence technology shows promise in providing assistance to clinicians performing point-of-care echocardiography. We conducted a systematic review, utilizing a comprehensive literature search on PubMed, to evaluate the interchangeability of LVEF and/or VTI measurements obtained through automated mode as compared to the echocardiographic reference methods in non-cardiology settings, e.g., Simpson´s method (LVEF) or manual trace (VTI). Eight studies were included, four studying automated-LVEF, three automated-VTI, and one both. When reported, the feasibility of automated measurements ranged from 78.4 to 93.3%. The automated-LVEF had a mean bias ranging from 0 to 2.9% for experienced operators and from 0% to -10.2% for non-experienced ones, but in both cases, with wide limits of agreement (LoA). For the automated-VTI, the mean bias ranged between - 1.7 cm and - 1.9 cm. The correlation between automated and reference methods for automated-LVEF ranged between 0.63 and 0.86 for experienced and between 0.56 and 0.81 for non-experienced operators. Only one study reported a correlation between automated-VTI and manual VTI (0.86 for experienced and 0.79 for non-experienced operators). We found limited studies reporting the interchangeability of automated LVEF or VTI measurements versus a reference approach. The accuracy and precision of these automated methods should be considered within the clinical context and decision-making. Such variability could be acceptable, especially in the hands of trained operators. PROSPERO number CRD42024564868.

Overview and Clinical Applications of Artificial Intelligence and Machine Learning in Cardiac Anesthesiology

Artificial intelligence- (AI) and machine learning (ML)-based applications are becoming increasingly pervasive in the healthcare setting. This has in turn challenged clinicians, hospital administrators, and health policymakers to understand such technologies and develop frameworks for safe and sustained clinical implementation. Within cardiac anesthesiology, challenges and opportunities for AI/ML to support patient care are presented by the vast amounts of electronic health data, which are collected rapidly, interpreted, and acted upon within the periprocedural area. To address such challenges and opportunities, in this article, the authors review 3 recent applications relevant to cardiac anesthesiology, including depth of anesthesia monitoring, operating room resource optimization, and transthoracic/transesophageal echocardiography, as conceptual examples to explore strengths and limitations of AI/ML within healthcare, and characterize this evolving landscape. Through reviewing such applications, the authors introduce basic AI/ML concepts and methodologies, as well as practical considerations and ethical concerns for initiating and maintaining safe clinical implementation of AI/ML-based algorithms for cardiac anesthesia patient care.

Deep learning evaluation of echocardiograms to identify occult atrial fibrillation

Atrial fibrillation (AF) often escapes detection, given its frequent paroxysmal and asymptomatic presentation. Deep learning of transthoracic echocardiograms (TTEs), which have structural information, could help identify occult AF. We created a two-stage deep learning algorithm using a video-based convolutional neural network model that (1) distinguished whether TTEs were in sinus rhythm or AF and then (2) predicted which of the TTEs in sinus rhythm were in patients who had experienced AF within 90 days. Our model, trained on 111,319 TTE videos, distinguished TTEs in AF from those in sinus rhythm with high accuracy in a held-out test cohort (AUC 0.96 (0.95-0.96), AUPRC 0.91 (0.90-0.92)). Among TTEs in sinus rhythm, the model predicted the presence of concurrent paroxysmal AF (AUC 0.74 (0.71-0.77), AUPRC 0.19 (0.16-0.23)). Model discrimination remained similar in an external cohort of 10,203 TTEs (AUC of 0.69 (0.67-0.70), AUPRC 0.34 (0.31-0.36)). Performance held across patients who were women (AUC 0.76 (0.72-0.81)), older than 65 years (0.73 (0.69-0.76)), or had a CHA2DS2VASc ≥2 (0.73 (0.79-0.77)). The model performed better than using clinical risk factors (AUC 0.64 (0.62-0.67)), TTE measurements (0.64 (0.62-0.67)), left atrial size (0.63 (0.62-0.64)), or CHA2DS2VASc (0.61 (0.60-0.62)). An ensemble model in a cohort subset combining the TTE model with an electrocardiogram (ECGs) deep learning model performed better than using the ECG model alone (AUC 0.81 vs. 0.79, p = 0.01). Deep learning using TTEs can predict patients with active or occult AF and could be used for opportunistic AF screening that could lead to earlier treatment.

Development of artificial intelligence-based slow-motion echocardiography and clinical usefulness for evaluating regional wall motion abnormalities

The diagnostic accuracy of exercise stress echocardiography (ESE) for myocardial ischemia requires improvement, given that it currently depends on the physicians' experience and image quality. To address this issue, we aimed to develop artificial intelligence (AI)-based slow-motion echocardiography using inter-image interpolation. The clinical usefulness of this method was evaluated for detecting regional wall-motion abnormalities (RWMAs). In this study, an AI-based echocardiographic image-interpolation pipeline was developed using optical flow calculation and prediction for in-between images. The accuracy for detecting RWMAs and image readability among 25 patients with RWMA and 25 healthy volunteers was compared between four cardiologists using slow-motion and conventional ESE. Slow-motion echocardiography was successfully developed for arbitrary time-steps (e.g., 0.125×, and 0.5×) using 1,334 videos. The RWMA detection accuracy showed a numerical improvement, but it was not statistically significant (87.5% in slow-motion echocardiography vs. 81.0% in conventional ESE; odds ratio: 1.43 [95% CI: 0.78-2.62], p = 0.25). Interreader agreement analysis (Fleiss's Kappa) for detecting RWMAs among the four cardiologists were 0.66 (95%CI: 0.55-0.77) for slow-motion ESE and 0.53 (95%CI: 0.42-0.65) for conventional ESE. Additionally, subjective evaluations of image readability using a four-point scale showed a significant improvement for slow-motion echocardiography (2.11 ± 0.73 vs. 1.70 ± 0.78, p < 0.001).In conclusion, we successfully developed slow-motion echocardiography using in-between echocardiographic image interpolation. Although the accuracy for detecting RWMAs did not show a significant improvement with this method, we observed enhanced image readability and interreader agreement. This AI-based approach holds promise in supporting physicians' evaluations.

Optimizing outcomes in heart failure: 2022 and beyond

Although the development of therapies and tools for the improved management of heart failure (HF) continues apace, day-to-day management in clinical practice is often far from ideal. A Cardiovascular Round Table workshop was convened by the European Society of Cardiology (ESC) to identify barriers to the optimal implementation of therapies and guidelines and to consider mitigation strategies to improve patient outcomes in the future. Key challenges identified included the complexity of HF itself and its treatment, financial constraints and the perception of HF treatments as costly, failure to meet the needs of patients, suboptimal outpatient management, and the fragmented nature of healthcare systems. It was discussed that ongoing initiatives may help to address some of these barriers, such as changes incorporated into the 2021 ESC HF guideline, ESC Heart Failure Association quality indicators, quality improvement registries (e.g. EuroHeart), new ESC guidelines for patients, and the universal definition of HF. Additional priority action points discussed to promote further improvements included revised definitions of HF 'phenotypes' based on trial data, the development of implementation strategies, improved affordability, greater regulator/payer involvement, increased patient education, further development of patient-reported outcomes, better incorporation of guidelines into primary care systems, and targeted education for primary care practitioners. Finally, it was concluded that overarching changes are needed to improve current HF care models, such as the development of a standardized pathway, with a common adaptable digital backbone, decision-making support, and data integration, to ensure that the model 'learns' as the management of HF continues to evolve.

The Emerging Role of Artificial Intelligence in Valvular Heart Disease

Valvular heart disease (VHD) is a morbid condition in which timely identification and evidence-based treatments can lead to improved outcomes. Artificial intelligence broadly refers to the ability for computers to perform tasks and problem solve like the human mind. Studies applying AI to VHD have used a variety of structured (eg, sociodemographic, clinical) and unstructured (eg, electrocardiogram, phonocardiogram, and echocardiograms) and machine learning modeling approaches. Additional researches in diverse populations, including prospective clinical trials, are needed to evaluate the effectiveness and value of AI-enabled medical technologies in clinical care for patients with VHD.

Current role and future perspectives of artificial intelligence in echocardiography

Echocardiography is an essential tool in diagnostic cardiology and is fundamental to clinical care. Artificial intelligence (AI) can help health care providers serving as a valuable diagnostic tool for physicians in the field of echocardiography specially on the automation of measurements and interpretation of results. In addition, it can help expand the capabilities of research and discover alternative pathways in medical management specially on prognostication. In this review article, we describe the current role and future perspectives of AI in echocardiography.

Machine learning prediction of progressive subclinical myocardial dysfunction in moderate aortic stenosis

Background

Moderate severity aortic stenosis (AS) is poorly understood, is associated with subclinical myocardial dysfunction, and can lead to adverse outcome rates that are comparable to severe AS. Factors associated with progressive myocardial dysfunction in moderate AS are not well described. Artificial neural networks (ANNs) can identify patterns, inform clinical risk, and identify features of importance in clinical datasets.

Methods

We conducted ANN analyses on longitudinal echocardiographic data collected from 66 individuals with moderate AS who underwent serial echocardiography at our institution. Image phenotyping involved left ventricular global longitudinal strain (GLS) and valve stenosis severity (including energetics) analysis. ANNs were constructed using two multilayer perceptron models. The first model was developed to predict change in GLS from baseline echocardiography alone and the second to predict change in GLS using data from baseline and serial echocardiography. ANNs used a single hidden layer architecture and a 70%:30% training/testing split.

Results

Over a median follow-up interval of 1.3 years, change in GLS (≤ or >median change) could be predicted with accuracy rates of 95% in training and 93% in testing using ANN with inputs from baseline echocardiogram data alone (AUC: 0.997). The four most important predictive baseline features (reported as normalized % importance relative to most important feature) were peak gradient (100%), energy loss (93%), GLS (80%), and DI < 0.25 (50%). When a further model was run including inputs from both baseline and serial echocardiography (AUC 0.844), the top four features of importance were change in dimensionless index between index and follow-up studies (100%), baseline peak gradient (79%), baseline energy loss (72%), and baseline GLS (63%).

Conclusions

Artificial neural networks can predict progressive subclinical myocardial dysfunction with high accuracy in moderate AS and identify features of importance. Key features associated with classifying progression in subclinical myocardial dysfunction included peak gradient, dimensionless index, GLS, and hydraulic load (energy loss), suggesting that these features should be closely evaluated and monitored in AS.