Abstract
BackgroundThe goal of this study was to assess the ability of machine artificial intelligence (AI) to quantitatively assess lung ultrasound (LUS) B-line presence using images obtained by learners novice to LUS in patients with acute heart failure (AHF), compared to expert interpretation.MethodsThis was a prospective, multicenter observational study conducted at two urban academic institutions. Learners novice to LUS completed a 30-min training session on lung image acquisition which included lecture and hands-on patient scanning. Learners independently acquired images on patients with suspected AHF. Automatic B-line quantification was obtained offline after completion of the study. Machine AI counted the maximum number of B-lines visualized during a clip. The criterion standard for B-line counts was semi-quantitative analysis by a blinded point-of-care LUS expert reviewer. Image quality was blindly determined by an expert reviewer. A second expert reviewer blindly determined B-line counts and image quality. Intraclass correlation was used to determine agreement between machine AI and expert, and expert to expert.ResultsFifty-one novice learners completed 87 scans on 29 patients. We analyzed data from 611 lung zones. The overall intraclass correlation for agreement between novice learner images post-processed with AI technology and expert review was 0.56 (confidence interval [CI] 0.51–0.62), and 0.82 (CI 0.73–0.91) between experts. Median image quality was 4 (on a 5-point scale), and correlation between experts for quality assessment was 0.65 (CI 0.48–0.82).ConclusionAfter a short training session, novice learners were able to obtain high-quality images. When the AI deep learning algorithm was applied to those images, it quantified B-lines with moderate-to-fair correlation as compared to semi-quantitative analysis by expert review. This data shows promise, but further development is needed before widespread clinical use.
Highlights
The goal of this study was to assess the ability of machine artificial intelligence (AI) to quantitatively assess lung ultrasound (LUS) B-line presence using images obtained by learners novice to LUS in patients with acute heart failure (AHF), compared to expert interpretation
Ultrasound can be used by practitioners across a broad range of expertise to evaluate the lungs for the presence of B-lines, indicating pulmonary edema or Russell et al Ultrasound J (2021) 13:33 loss of lung aeration [2]
Out of 696 lung zones assessed, 611 (88%) images were used in the B-line quantification analysis
Summary
The goal of this study was to assess the ability of machine artificial intelligence (AI) to quantitatively assess lung ultrasound (LUS) B-line presence using images obtained by learners novice to LUS in patients with acute heart failure (AHF), compared to expert interpretation. Lung ultrasound (LUS) for the evaluation of pulmonary edema in acute heart failure (AHF) has become standard care in many emergency departments (ED) and intensive care settings [1]. The workup of AHF has traditionally centered on identifying radiographic and physical exam findings consistent with fluid overload such as pretibial edema, rales, hepatojugular reflux, and pulmonary edema on chest X-ray. Even in AHF without total body fluid overload (e.g., Sympathetic Crashing Acute Pulmonary Edema), identifying pulmonary edema is critical in expediting diagnosis and management [5]. The use of artificial intelligence (AI) software packages embedded in ultrasound systems to identify and quantify B-lines has the potential to offer these same benefits to novice learners without extensive ultrasound training
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
