Artificial intelligence-guided image acquisition on patients with implanted electrophysiological devices: Results from a pivotal prospective multi-center clinical trial
ON DEMAND
Speaker:
Session title: Novel Technological Approaches in Echocardiography: What Do They Provide?
Topic: Echocardiography: Technology
Session type: Best ePosters
Available from:

View abstract
Authors

S Surette1 , A Narang2 , R Bae3 , H Hong1 , Y Thomas1 , C Cadieu1 , A Chaudhry1 , R Martin1 , D Rubenson4 , S Goldstein5 , S Little6 , R Lang7 , N Weissman8 , JD Thomas2 , 1Caption Health - Brisbane - United States of America , 2Northwestern University - Chicago - United States of America , 3Minneapolis Heart Institute Foundation - Minneapolis - United States of America , 4Scripps Clinic - La Jolla - United States of America , 5MedStar Washington Hospital Center - Washington - United States of America , 6Houston Methodist - Houston - United States of America , 7The University of Chicago - Chicago - United States of America , 8MedStar Health Research Institute - Washington - United States of America ,

Abstract

Citation: N/A

Background: A novel, recently FDA-authorized software uses deep learning (DL) to provide prescriptive transthoracic echocardiography (TTE) guidance, allowing novices to acquire standard TTE views. The DL model was trained by >5,000,000 observations of the impact of probe motion on image orientation/quality. This study evaluated whether novice-acquired TTE images guided by this software were of diagnostic quality in patients with and without implanted electrophysiological (EP) devices, focusing on RV size and function, which were thought to be sensitive to EP devices. Some aspects of the study have previously been presented.

Methods: 240 patients (61±16 years old, 58% male, 33% BMI >30 kg/m2, 91% with cardiac pathology) were recruited. 8 nurses without echo experience each acquired 10 view TTEs in 30 patients guided by the software. 235 of the patients were also scanned by a trained sonographer without assistance from the software. 5 Level 3 echocardiographers independently assessed the diagnostic quality of the TTEs acquired by the nurses and sonographers to evaluate the effect of EP devices on DL software performance.

Results: Nurses using the AI-guided acquisition software acquired TTEs of sufficient quality to make qualitative assessments of right ventricular (RV) size and function in greater than 80% of cases for patients with and without implanted EP devices (Table). There was no significant difference between nurse- and sonographer-acquired scans.

Conclusion: These results indicate that new DL software can guide novices to obtain TTEs that enable qualitative assessment of RV size even in the presence of implanted EP devices. The results of the comparison to sonographer-acquired exams indicate the software performance is robust to presence of pacemaker/ICD leads visible in the images (Figure).

Pacemaker/ICD Present

Pacemaker/ICD Absent

Total

Number of patients scanned

27

208

235

Visual Qualitative Assessment of RV Size

Nurse n (%) of scans diagnostic

23 (85.2%)

194 (93.3%)

217 (92.3%)

Sonographer n (%) of scans diagnostic

23 (85.2%)

203 (97.6%)

226 (96.2%)

Nurse-Sonographer Percentage Point Difference

0.0%

-4.3%

-3.8%

Visual Qualitative Assessment of RV Function

Nurse n (%) of scans diagnostic

22 (81.5%)

192 (92.3%)

214 (91.1%)

Sonographer n (%) of scans diagnostic

23 (85.2%)

203 (97.6%)

226 (96.2%)

Nurse-Sonographer Percentage Point Difference

-3.7%

-5.3%

-5.1%

Side-by-side comparison of acceptability of nurse-acquired vs. sonographer-acquired TTE for qualitative visual assessment of RV function by presence/absence of pacemakers/ICDs (p = NS for all comparisons)