A comparison of handheld and standard ultrasound in Swiss medical students

Efficacy of Handheld Ultrasound in Medical Education: A Comprehensive Systematic Review and Narrative Analysis

Miniaturization has made ultrasound (US) technology ultraportable and, in association with their relatively low cost, made handheld devices attractive for medical education training programs. However, performing an ultrasound requires complex skills, and it is unclear whether handheld devices are suitable for the training of novices. Our study aimed to identify to what extent handheld US devices can be employed in medical undergraduates' and residents' education. We selected studies that evaluate the results obtained by students and/or residents who have participated in ultrasound training programs using handheld devices. The studies were included if they reported post-test (pre-test optional) achievements or a comparison with a control group (a group of experts or novices who underwent a different intervention). Twenty-six studies were selected, and their characteristics were summarized. Handheld ultrasound devices were used in training programs to learn echocardiography, abdominal, and/or musculoskeletal ultrasound. Statistically significant progress was noted in the ability of naïve participants to capture and interpret ultrasound images, but training duration influenced the outcomes. While ultrasound training using handheld devices has proven to be feasible for various body regions and purposes (e.g., better understanding of anatomy, clinical applications, etc.), the long-term impacts of handheld education interventions must be considered in addition to the short-term results to outline guidelines for targeted educational needs.

Implementing a Sports Ultrasound Curriculum in Undergraduate Medical Education

ABSTRACT

The utilization of sports ultrasound in the clinical practice of sports medicine physicians is growing rapidly. Simultaneously, ultrasound is being increasingly implemented as a teaching tool in undergraduate medical education. However, a sports ultrasound curriculum for medical students has not been previously described. In this article, we describe methods as well as barriers to implementing a sports ultrasound curriculum at the medical school level. Recommended content for the curriculum also is discussed. While educational goals and resources will vary among institutions, this article may serve as a general roadmap for the creation of a successful curriculum.

Detection of pneumothorax on ultrasound using artificial intelligence

BACKGROUND

Ultrasound (US) for the detection of pneumothorax shows excellent sensitivity in the hands of skilled providers. Artificial intelligence may facilitate the movement of US for pneumothorax into the prehospital setting. The large amount of training data required for conventional neural network methodologies has limited their use in US so far.

METHODS

A limited training database was supplied by Defense Advanced Research Projects Agency of 30 patients, 15 cases with pneumothorax and 15 cases without. There were two US videos per patient, of which we were allowed to choose one to train on, so that a limited set of 30 videos were used. Images were annotated for ribs and pleural interface. The software performed anatomic reconstruction to identify the region of interest bounding the pleura. Three neural networks were created to analyze images on a pixel-by-pixel fashion with direct voting determining the outcome. Independent verification and validation was performed on a data set gathered by the Department of Defense.

RESULTS

Anatomic reconstruction with the identification of ribs and pleura was able to be accomplished on all images. On independent verification and validation against the Department of Defense testing data, our program concurred with the SME 80% of the time and achieved a 86% sensitivity (18/21) for pneumothorax and a 75% specificity for the absence of pneumothorax (18/24). Some of the mistakes by our artificial intelligence can be explained by chest wall motion, hepatization of the underlying lung, or being equivocal cases.

CONCLUSION

Using learning with limited labeling techniques, pneumothorax was identified on US with an accuracy of 80%. Several potential improvements are controlling for chest wall motion and the use of longer videos.

LEVEL OF EVIDENCE

Diagnostic Tests; Level III.