Real-Time Artificial Intelligence-Based Guidance of Echocardiographic Imaging by Novices: Image Quality and Suitability for Diagnostic Interpretation and Quantitative Analysis.

BACKGROUND: We aimed to assess in a prospective multicenter study the quality of echocardiographic exams performed by inexperienced users guided by a new artificial intelligence software and evaluate their suitability for diagnostic interpretation of basic cardiac pathology and quantitative analysis of cardiac chamber and function. METHODS: The software (UltraSight, Ltd) was embedded into a handheld imaging device (Lumify; Philips). Six nurses and 3 medical residents, who underwent minimal training, scanned 240 patients (61±16 years; 63% with cardiac pathology) in 10 standard views. All patients were also scanned by expert sonographers using the same device without artificial intelligence guidance. Studies were reviewed by 5 certified echocardiographers blinded to the imager's identity, who evaluated the ability to assess left and right ventricular size and function, pericardial effusion, valve morphology, and left atrial and inferior vena cava sizes. Finally, apical 4-chamber images of adequate quality, acquired by novices and sonographers in 100 patients, were analyzed to measure left ventricular volumes, ejection fraction, and global longitudinal strain by an expert reader using conventional methodology. Measurements were compared between novices' and experts' images. RESULTS: Of the 240 studies acquired by novices, 99.2%, 99.6%, 92.9%, and 100% had sufficient quality to assess left ventricular size and function, right ventricular size, and pericardial effusion, respectively. Valve morphology, right ventricular function, and left atrial and inferior vena cava size were visualized in 67% to 98% exams. Images obtained by novices and sonographers yielded concordant diagnostic interpretation in 83% to 96% studies. Quantitative analysis was feasible in 83% images acquired by novices and resulted in high correlations (r≥0.74) and small biases, compared with those obtained by sonographers. CONCLUSIONS: After minimal training with the real-time guidance software, novice users can acquire images of diagnostic quality approaching that of expert sonographers in most patients. This technology may increase adoption and improve accuracy of point-of-care cardiac ultrasound.

Seroprevalence of SARS-CoV-2 Antibody in Echocardiography and Stress Laboratory.

PURPOSE: Transesophageal echocardiography is an aerosol-generating procedure, and exercise stress testing is a potentially aerosol-generating activity. Concern has been raised about heightened risk of transmission of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) among health care personnel participating in these procedures. We aimed to investigate the prevalence of past coronavirus disease 2019 (COVID-19) infection in echocardiography and stress laboratory staff. METHODS: All staff who worked in the echocardiography and stress laboratories of one high-traffic urban hospital from March 15, 2020, to June 15, 2020, were asked to voluntarily participate. Those willing to participate were consented, and past COVID-19 infection was confirmed by a SARS-CoV-2 IgG antibody test (ARCHITECT, Abbott Laboratories) from June 15, 2020, to July 3, 2020. Clinical data were collected from the electronic medical record, and self-reported symptoms were documented with a participant survey. RESULTS: A total of 43 staff members (86.0% of 50 total laboratory staff) participated. A majority of participants were less than 40 years old (69.8%), were White (86.0%), and were women (79.1%); mean body mass index was 24.9 ± 4.7 kg/m2. Of the 43 staff members tested for past COVID-19 infection, 3 (7.0%) had a positive SARS-CoV-2 IgG antibody result. There were no unique features in the 3 SARS-CoV-2 antibody-positive subjects; of these, 2 had known prior COVID-19 infection and 1 was asymptomatic. CONCLUSIONS: This study provides clinical data on the seroprevalence of SARS-CoV-2 antibody in echocardiography and stress laboratory staff who regularly participate in a variety of procedures that are or may be aerosol-generating.

Diagnostic accuracy of bicuspid aortic valve by echocardiography.

BACKGROUND: Echocardiography is regarded as the gold standard for diagnosis of bicuspid aortic valve (BAV), yet diagnostic accuracy has been evaluated previously only in single-center studies. We systematically evaluated the accuracy of BAV diagnosis in a large healthcare system of multiple echocardiography laboratories. METHODS AND RESULTS: Aurora Health Care is a multihospital, multi-clinic system across the state of Wisconsin encompassing 33 inpatient and outpatient echocardiography laboratories with 39 cardiologist readers and 72 sonographers. As all laboratories store echocardiograms in one database, we queried all patients with "bicuspid aortic valve" diagnosis on echocardiography. Echocardiograms were classified as "BAV" or "possible BAV" based on initial reader confidence. An expert review panel categorized each as BAV, no BAV, or Indeterminate. Of the 745 cases identified, 589 (79.1%, initial reader interpretation: n = 494 "BAV," n = 95 "possible") were BAV. A high level of agreement (84%) was present in BAV diagnosis. There were 156 (20.9%) echocardiograms that were no BAV (8.4%) or Indeterminate (12.4%). We identified three common reasons for misdiagnosis: poor image quality (n = 70, 44.9%), leaflet calcium (n = 44, 28.2%), and oblique axis imaging (n = 33, 21.1%). A clear reason for misclassification was not elucidated in nine cases (n = 9, 5.7%). CONCLUSIONS: This is the first study to evaluate BAV accuracy across a community health system with multiple echocardiography laboratories and a heterogeneous group of readers and sonographers. We establish a high degree of accuracy of echocardiography in BAV diagnosis and draw attention to common echocardiographic pitfalls that lead to BAV misclassification, highlighting opportunities for education and quality improvement.

Transthoracic echocardiography is adequate for intraprocedural guidance of transcatheter aortic valve implantation.

BACKGROUND: While transcatheter aortic valve implantation (TAVI) has traditionally been supported intraprocedurally by transoesophageal echocardiography (TOE), transthoracic echocardiography (TTE) is increasingly being used. We evaluated echocardiographic imaging characteristics and clinical outcomes in patients who underwent TTE during TAVI (TTE-TAVI). METHODS AND RESULTS: A select team of dedicated sonographers and interventional echocardiographers performed TTE-TAVI in 278 patients, all of whom underwent TAVI through transfemoral access. We implanted the Medtronic EVOLUT R valve in 258 patients (92.8%). TTE images were acquired immediately pre-procedure by a dedicated sonographer in the cardiac catheterization laboratory with the patient in the supine position. TTE was then performed post deployment of TAVI. In the procedure, TTE image quality was fair or better in 249 (89.6%) cases. Color-flow Doppler was adequate or better in 275 (98.9%) cases. In 2 cases, paravalvular regurgitation (PVL) could not be assessed confidently by echocardiography due to poor image quality; in those cases, PVL was assessed by fluoroscopy, aortic root injection and invasive hemodynamics. Both TTE and invasive hemodynamics were used in the assessment of need for post-deployment stent ballooning (n = 23, 8.3%). TTE adequately recognized new pericardial effusion in 3 cases. No case required TOE conversion for image quality. There was only 1 case of intraprocedural TTE failing to recognize moderate PVL, without clinical implication. In 99% of patients, TTE-TAVI adequately assessed PVL compared with 24-h and 1-month follow-up TTE. CONCLUSIONS: With the current generation of TAVI, TTE-TAVI is adequate intraprocedurally when performed by specialized sonographers and dedicated cardiologists in a highly experienced TAVI center.