From vagueness in medical thought to the foundations of fuzzy reasoning in medical diagnosis
Artificial Intelligence in Medicine
IPMU'10 Proceedings of the Computational intelligence for knowledge-based systems design, and 13th international conference on Information processing and management of uncertainty
Artificial Intelligence in Medicine
Hi-index | 0.00 |
This paper examines the role of imprecision in the interpretation of verbal symptom intensities (e.g., high fever) depending on the level of medical expertise. In a contrastive study we compare low, medium and high level experts (medical students vs. physicians with M = 5.3 vs. M = 24.9 years of experience) concerning their interpretation of symptom intensities. For obtaining and modeling of empirical data a fuzzy approach was used. The resulting fuzzy membership functions (MF) reflect the meanings of the verbal symptom intensities. The two main findings are: (1) with increasing expertise the precision of the MF increase such that low level experts have very vague concepts compared to high level experts and (2) the precision depends on the symptom (e.g., intensities of fever are more precise than pain intensities).