Case-based learning is a common approach used by educators to provide students with the opportunity to apply theory to real-life clinical scenarios in a controlled setting, effectively enhancing students’ learning engagement. We have developed a platform containing case scenarios focused on the radiographic positioning of lines and tubes, such as endotracheal tubes and central venous catheters. These medical devices are commonly encountered in emergency, intensive care, medical, and surgical units, and their correct placement is essential for patient safety and effective treatment. Each case scenario is developed using a framework designed to augment radiology education beyond passive learning of image interpretation. Under this framework, students are guided through cases using a series of questions on an electronic platform, consisting of 1) multiple-choice questions targeting image interpretation, which feature clinical images that enable students to review and enhance their understanding of clinical knowledge, and 2) more advanced, free response questions on choice of intervention and patient care designed to stimulate discussion. The platform encompasses a custom large language model (LLM) chatbot pre-trained with knowledge of relevant medical guidelines and evaluation rubrics that students can interact with in place of the course instructor to enable personalized and interactive learning on the go. Students’ clinical decision-making abilities are evaluated through the case, and areas of improvement are identified with instant feedback. Through the cases, students learn about recognizing the position and common complications associated with lines and tubes placements. By simulating real-life clinical scenarios, this work allows students to improve their technical skills in image interpretation, as well as develop an understanding of how imaging is incorporated into clinical care and patient management in the acute setting.

Keywords: Technology, artificial intelligence, undergraduate learning.