AI-enhanced guidance demonstrated improvement in novices' Apical-4-chamber and Apical-5-chamber views.

INTRODUCTION

Artificial Intelligence (AI) modules might simplify the complexities of cardiac ultrasound (US) training by offering real-time, step-by-step guidance on probe manipulation for high-quality diagnostic imaging. This study investigates real-time AI-based guidance tool in facilitating cardiac US training and its impact on novice users' proficiency.

METHODS

This independent, prospective randomized controlled trial enrolled participants who completed a six-hour cardiac US course, followed by a designated cardiac US proficiency exam. Both groups received in-person guided training using the same devices, with the AI-enhanced group receiving additional real-time AI feedback on probe navigation and image quality during both training and testing, while the non-AI group relied solely on the instructor's guidance.

RESULTS

Data were collected from 44 participants: 21 in the AI-enhanced group and 23 in the non-AI group. Improvement was observed in the assessment of the AI-enhanced group compared to the non-AI in acquiring the Apical-4-chamber and the Apical-5- chamber views [mean 88% (± SD 10%) vs. mean 76% (± SD 17%), respectively; p = 0.016]. On the other hand, a slower time to complete the echocardiography exam was observed by the AI-enhanced group [mean 401 s (± SD 51) vs. 348 s (± SD 81) respectively; p = 0.038].

DISCUSSION

The addition of real-time, AI-based feedback demonstrated benefits in the cardiac POCUS teaching process for the more challenging echocardiography four- and five- chamber views. It also has the potential to surpass challenges related to in-person POCUS training. Additional studies are required to explore the long-term effect of this training approach.

CLINICAL TRIAL NUMBER

Not applicable.