부산대학교 도서관

With the recent development of Software as a Medical Device (SaMD), the significance of reducing use errors inmedical devices is increasing. In this study, we conducted a formative evaluation of Artificial Intelligence (AI)-based software forophthalmic image detection and diagnosis. The software automatically displays the presence or absence of neovascular age-relatedmacular degeneration using fundus images to assist medical personnel in making diagnostic decisions. We aimed to find ways toreduce the number of use errors in formative evaluations. For this purpose, we conducted usability testing by performing tasksbased on use scenarios for usability formative evaluations with intended users in their intended use environments, and thenmodified the user interface to reduce use errors. The initial formative evaluation revealed errors in utilizing the capture and dragand-drop functions for uploading fundus images, checking analysis results, and perform logout procedures. To reduce use errors,we improved the function by relocating the capture icon, displaying a hand-shaped cursor during dragging, inserting a fundusposition guide, and eliminating the drag-and-drop function. We have also enhanced the design to present analytics results in amore intuitive manner and added a separate logout button to reduce the risk of use error. As a result, the number of use errorsin the formative evaluation decreased from six to one in the summative evaluation. The development of ophthalmic imagedetection and diagnosis assistant software that reflects these improvements is expected to enhance user safety, usability, andreduce use errors.