Assessment and validation of a novel fast fully automated artificial intelligence left ventricular ejection fraction quantification software

Harnessing the Power of AI: A Comprehensive Review of Left Ventricular Ejection Fraction Assessment With Echocardiography

The quantification of left ventricular ejection fraction (LVEF) has important clinical utility in the assessment of cardiac function and is vital for the diagnosis of cardiovascular diseases. A transthoracic echocardiogram serves as the most commonly used tool for LVEF assessment for several reasons, including, its noninvasive nature, great safety profile, real-time image processing ability, portability, and cost-effectiveness. However, transthoracic echocardiogram is highly dependent on the clinical skill of the sonographer and interpreting physician. Moreover, even amongst well-trained clinicians, significant interobserver variability exists in the quantification of LVEF. In search of possible solutions, the usage of artificial intelligence (AI) has been increasingly tested in the clinical setting. While AI-derived ejection fraction is in the preliminary stages of development, it has shown promise in its ability to rapidly quantify LVEF, decrease variability, increase accuracy, and utilize higher-order processing capabilities. This review will delineate the latest advancements of AI in evaluating LVEF through echocardiography and explore the challenges and future trajectory of this emerging domain.

Improved assessment of left ventricular ejection fraction using artificial intelligence in echocardiography: A comparative analysis with cardiac magnetic resonance imaging

BACKGROUND

Left ventricular ejection fraction (LVEF) measurement in echocardiography (Echo) using the recommended modified biplane Simpson (MBS) method is operator-dependent and exhibits variability. We aimed to assess the accuracy of a novel fully automated (Auto) artificial intelligence (AI) in view selection and biplane LVEF calculation compared to MBS-Echo, with cardiac magnetic resonance imaging (CMR) as reference.

METHODS

Each of the 301 consecutive patients underwent CMR and Echo on the same day. LVEF was measured independently by Auto-Echo, MBS-Echo and CMR. Interobserver (n = 40) and test-retest (n = 14) analysis followed.

RESULTS

A total of 229 patients (76%) underwent complete analysis. Auto-Echo and MBS-Echo showed high correlations with CMR (R = 0.89 and 0.89) and with each other (R = 0.93). Auto underestimated LVEF (bias: 2.2%; limits of agreement [LOA]: -13.5 to 17.9%), while MBS overestimated it (bias: -2.2%; LOA: 18.6 to 14.1%). Despite comparable areas under the curves of Auto- and MBS-Echo (0.93 and 0.92), 46% (n = 70) of MBS-Echo misclassified LVEF by ≥5% units in patients with a reduced CMR-LVEF <51%. Although LVEF bias variability across different LV function ranges was significant (p < 0.001), Auto-Echo was closer to CMR for patients with reduced LVEF, wall motion abnormalities, and poor image quality than MBS-Echo. The interobserver correlation coefficient of Auto-Echo was excellent compared to MBS-Echo (1.00 vs. <0.91) for different readers. True test-retest variability was higher for MBS-Echo than for Auto-Echo (7.9% vs. 2.5%).

CONCLUSION

The tested AI has the potential to improve the clinical utility of Echo by reducing user-related variability, providing more accurate and reliable results than MBS.

Artificial Intelligence-Powered Left Ventricular Ejection Fraction Analysis Using the LVivoEF Tool for COVID-19 Patients

We sought to prospectively investigate the accuracy of an artificial intelligence (AI)-based tool for left ventricular ejection fraction (LVEF) assessment using a hand-held ultrasound device (HUD) in COVID-19 patients and to examine whether reduced LVEF predicts the composite endpoint of in-hospital death, advanced ventilatory support, shock, myocardial injury, and acute decompensated heart failure. COVID-19 patients were evaluated with a real-time LVEF assessment using an HUD equipped with an AI-based tool vs. assessment by a blinded fellowship-trained echocardiographer. Among 42 patients, those with LVEF < 50% were older with more comorbidities and unfavorable exam characteristics. An excellent correlation was demonstrated between the AI and the echocardiographer LVEF assessment (0.774, p < 0.001). Substantial agreement was demonstrated between the two assessments (kappa = 0.797, p < 0.001). The sensitivity, specificity, PPV, and NPV of the HUD for this threshold were 72.7% 100%, 100%, and 91.2%, respectively. AI-based LVEF < 50% was associated with worse composite endpoints; unadjusted OR = 11.11 (95% CI 2.25-54.94), p = 0.003; adjusted OR = 6.40 (95% CI 1.07-38.09, p = 0.041). An AI-based algorithm incorporated into an HUD can be utilized reliably as a decision support tool for automatic real-time LVEF assessment among COVID-19 patients and may identify patients at risk for unfavorable outcomes. Future larger cohorts should verify the association with outcomes.

Empowering Medical Students: Harnessing Artificial Intelligence for Precision Point-of-Care Echocardiography Assessment of Left Ventricular Ejection Fraction

Introduction

Point-of-care ultrasound (POCUS) use is now universal among nonexperts. Artificial intelligence (AI) is currently employed by nonexperts in various imaging modalities to assist in diagnosis and decision making.

Aim

To evaluate the diagnostic accuracy of POCUS, operated by medical students with the assistance of an AI-based tool for assessing the left ventricular ejection fraction (LVEF) of patients admitted to a cardiology department.

Methods

Eight students underwent a 6-hour didactic and hands-on training session. Participants used a hand-held ultrasound device (HUD) equipped with an AI-based tool for the automatic evaluation of LVEF. The clips were assessed for LVEF by three methods: visually by the students, by students + the AI-based tool, and by the cardiologists. All LVEF measurements were compared to formal echocardiography completed within 24 hours and were evaluated for LVEF using the Simpson method and eyeballing assessment by expert echocardiographers.

Results

The study included 88 patients (aged 58.3 ± 16.3 years). The AI-based tool measurement was unsuccessful in 6 cases. Comparing LVEF reported by students' visual evaluation and students + AI vs. cardiologists revealed a correlation of 0.51 and 0.83, respectively. Comparing these three evaluation methods with the echocardiographers revealed a moderate/substantial agreement for the students + AI and cardiologists but only a fair agreement for the students' visual evaluation.

Conclusion

Medical students' utilization of an AI-based tool with a HUD for LVEF assessment achieved a level of accuracy similar to that of cardiologists. Furthermore, the use of AI by the students achieved moderate to substantial inter-rater reliability with expert echocardiographers' evaluation.

Validation of American Society of Echocardiography Guideline-Recommended Parameters of Right Ventricular Dysfunction Using Artificial Intelligence Compared With Cardiac Magnetic Resonance Imaging

BACKGROUND

Right ventricular (RV) function is important in the evaluation of cardiac function, but its assessment using standard transthoracic echocardiography (TTE) remains challenging. Cardiac magnetic resonance imaging (CMR) is considered the gold standard. The American Society of Echocardiography recommends surrogate measures of RV function and RV ejection fraction (RVEF) by TTE, including fractional area change (FAC), free wall strain (FWS), and tricuspid annular planar systolic excursion (TAPSE), but they require technical expertise in acquisition and quantification.

METHODS

The aim of this study was to evaluate the sensitivity, specificity, and positive and negative predictive values of FAC, FWS, and TAPSE derived using a rapid, novel artificial intelligence (AI) software (LVivoRV) from a single-plane transthoracic echocardiographic apical four-chamber, RV-focused view without ultrasound-enhancing agents for detecting abnormal RV function compared with CMR-derived RVEF. RV dysfunction was defined as RVEF < 50% and RVEF < 40% on CMR.

RESULTS

TTE and CMR were performed within a median of 10 days (interquartile range, 2-32 days) of each other in 225 consecutive patients without interval procedural or pharmacologic intervention. The sensitivity and negative predictive value to detect CMR-defined RV dysfunction when all three AI-derived parameters (FAC, FWS, and TAPSE) were abnormal were 91% and 96%, while those of expert physician reads were 91% and 97%. Specificity and positive predictive value were lower (50% and 32%) compared with expert physician-read echocardiograms (82% and 56%).

CONCLUSIONS

AI-derived measurements of FAC, FWS, and TAPSE had excellent sensitivity and negative predictive value for ruling out significant RV dysfunction (CMR RVEF < 40%), comparable with that of expert physician readers, but lower specificity. Thus AI, using American Society of Echocardiography guidelines, may serve as a useful screening tool for rapid bedside assessment to exclude significant RV dysfunction.

Single-Site Experience with an Automated Artificial Intelligence Application for Left Ventricular Ejection Fraction Measurement in Echocardiography

Left ventricular ejection fraction (LVEF) is a key parameter in evaluating left ventricular (LV) function using echocardiography (Echo), but its manual measurement by the modified biplane Simpson (MBS) method is time consuming and operator dependent. We investigated the feasibility of a server-based, commercially available and ready-to use-artificial intelligence (AI) application based on convolutional neural network methods that integrate fully automatic view selection and measurement of LVEF from an entire Echo exam into a single workflow. We prospectively enrolled 1083 consecutive patients who had been referred to Echo for diagnostic or therapeutic purposes. LVEF was measured independently using MBS and AI. Test–retest variability was assessed in 40 patients. The reliability, repeatability, and time efficiency of LVEF measurements were compared between the two methods. Overall, 889 Echos were analyzed by cardiologists with the MBS method and by the AI. Over the study period of 10 weeks, the feasibility of both automatic view classification and seamlessly measured LVEF rose to 81% without user involvement. LVEF, LV end-diastolic and end-systolic volumes correlated strongly between MBS and AI (R = 0.87, 0.89 and 0.93, p < 0.001 for all) with a mean bias of +4.5% EF, −12 mL and −11 mL, respectively, due to impaired image quality and the extent of LV function. Repeatability and reliability of LVEF measurement (n = 40, test–retest) by AI was excellent compared to MBS (coefficient of variation: 3.2% vs. 5.9%), although the median analysis time of the AI was longer than that of the operator-dependent MBS method (258 s vs. 171 s). This AI has succeeded in identifying apical LV views and measuring EF in one workflow with comparable results to the MBS method and shows excellent reproducibility. It offers realistic perspectives for fully automated AI-based measurement of LVEF in routine clinical settings.