The role of expert focus echocardiography during the COVID-19 pandemic.

BACKGROUND: Focus Echocardiography has routinely been used to offer quick diagnosis in critical care environments, predominantly by clinicians with limited training. During the COVID-19 pandemic, international guidance recommended all echocardiography scans were performed as focus studies to limit operator viral exposure in both inpatient and outpatient settings. The aim of this study was to assess the effectiveness of eFoCUS, a focus scan performed by fully trained echocardiographers following a minimum dataset plus full interrogation of any pathology found. METHODS: All diagnostic echocardiograms, performed by fully trained echocardiographers during an 8-week period during the first UK COVID-19 wave, were included. The number of images acquired was compared in the following categories: admission status, COVID status, image quality, indication, invasive ventilation, pathology found, echocardiographer experience, and whether eFoCUS was deemed adequate to answer the clinical question. RESULTS: In 87.4% of the 698 scans included, the operator considered that the eFOCUS echo protocol, with additional images when needed, was sufficient to answer the clinical question on the request. Echocardiographer experience did not affect the number of images acquired. Less images were acquired in COVID-19 positive patients compared to negative/asymptomatic (38 ± 12 vs. 42 ± 12, p = .001), and more images were required when a valve pathology was identified. CONCLUSION: eFoCUS echocardiography is an effective protocol for use during the COVID-19 pandemic. It provides sufficient diagnostic information to answer the clinical question but differs from standard focus/limited protocols by enabling the identification and interrogation of significant pathology and incidental findings, preventing unnecessary repeat scans and viral exposure of operators.

Automated Left Ventricular Dimension Assessment Using Artificial Intelligence Developed and Validated by a UK-Wide Collaborative.

BACKGROUND: requires training and validation to standards expected of humans. We developed an online platform and established the Unity Collaborative to build a dataset of expertise from 17 hospitals for training, validation, and standardization of such techniques. METHODS: The training dataset consisted of 2056 individual frames drawn at random from 1265 parasternal long-axis video-loops of patients undergoing clinical echocardiography in 2015 to 2016. Nine experts labeled these images using our online platform. From this, we trained a convolutional neural network to identify keypoints. Subsequently, 13 experts labeled a validation dataset of the end-systolic and end-diastolic frame from 100 new video-loops, twice each. The 26-opinion consensus was used as the reference standard. The primary outcome was precision SD, the SD of the differences between AI measurement and expert consensus. RESULTS: In the validation dataset, the AI's precision SD for left ventricular internal dimension was 3.5 mm. For context, precision SD of individual expert measurements against the expert consensus was 4.4 mm. Intraclass correlation coefficient between AI and expert consensus was 0.926 (95% CI, 0.904-0.944), compared with 0.817 (0.778-0.954) between individual experts and expert consensus. For interventricular septum thickness, precision SD was 1.8 mm for AI (intraclass correlation coefficient, 0.809; 0.729-0.967), versus 2.0 mm for individuals (intraclass correlation coefficient, 0.641; 0.568-0.716). For posterior wall thickness, precision SD was 1.4 mm for AI (intraclass correlation coefficient, 0.535 [95% CI, 0.379-0.661]), versus 2.2 mm for individuals (0.366 [0.288-0.462]). We present all images and annotations. This highlights challenging cases, including poor image quality and tapered ventricles. CONCLUSIONS: Experts at multiple institutions successfully cooperated to build a collaborative AI. This performed as well as individual experts. Future echocardiographic AI research should use a consensus of experts as a reference. Our collaborative welcomes new partners who share our commitment to publish all methods, code, annotations, and results openly.