Hallucinations in medical devices
This work addresses the issue of error characterization in medical devices for clinicians and developers, but it is incremental as it builds on existing theoretical and empirical studies.
The paper tackles the problem of defining 'hallucinations' in medical devices, proposing a universal definition for plausible errors that can be impactful or benign, and explores its relation to evaluation methodologies and minimization approaches.
Computer methods in medical devices are frequently imperfect and are known to produce errors in clinical or diagnostic tasks. However, when deep learning and data-based approaches yield output that exhibit errors, the devices are frequently said to hallucinate. Drawing from theoretical developments and empirical studies in multiple medical device areas, we introduce a practical and universal definition that denotes hallucinations as a type of error that is plausible and can be either impactful or benign to the task at hand. The definition aims at facilitating the evaluation of medical devices that suffer from hallucinations across product areas. Using examples from imaging and non-imaging applications, we explore how the proposed definition relates to evaluation methodologies and discuss existing approaches for minimizing the prevalence of hallucinations.