Henkel Maurice, Belfi Lily
Department of Radiology, University Hospital Basel, Basel, Switzerland (M.H.).
Department of Radiology, Weill Cornell Medicine, New York, New York (L.B.).
Acad Radiol. 2024 Feb;31(2):724-735. doi: 10.1016/j.acra.2023.05.021. Epub 2023 Jun 16.
Learning analytics is a rapidly advancing scientific field that enables data-driven insights and personalized learning experiences. However, traditional methods for teaching and assessing radiology skills do not provide the data needed to leverage this technology in radiology education.
In this paper, we implemented rapmed.net, an interactive radiology e-learning platform designed to utilize learning analytics tools in radiology education. Second-year medical students' pattern recognition skills were evaluated using time to solve a case, dice score, and consensus score, while their interpretation abilities were assessed through multiple-choice questions (MCQs). Assessments were conducted before and after a pulmonary radiology block to examine the learning progress.
Our results show that a comprehensive assessment of students' radiological skills using consensus maps, dice scores, time metrics, and MCQs revealed shortcomings traditional MCQs would not have detected. Learning analytics tools allow for a better understanding of students' radiology skills and pave the way for a data-driven educational approach in radiology.
As one of the most important skills for physicians across all disciplines, improving radiology education will contribute to better healthcare outcomes.
学习分析是一个迅速发展的科学领域，它能实现数据驱动的见解和个性化学习体验。然而，传统的放射学技能教学和评估方法无法提供在放射学教育中利用这项技术所需的数据。
在本文中，我们实施了rapmed.net，这是一个交互式放射学电子学习平台，旨在在放射学教育中利用学习分析工具。通过解决病例的时间、骰子分数和一致性分数来评估二年级医学生的模式识别技能，同时通过多项选择题（MCQ）来评估他们的解读能力。在肺部放射学课程前后进行评估，以检查学习进展。
我们的结果表明，使用一致性图、骰子分数、时间指标和MCQ对学生的放射学技能进行全面评估，揭示了传统MCQ无法检测到的不足之处。学习分析工具能够更好地理解学生的放射学技能，并为放射学中数据驱动的教育方法铺平道路。
作为所有学科医生最重要的技能之一，改善放射学教育将有助于提高医疗保健效果。
