L. Duckstein et al., FUZZY CLASSIFICATION OF PATIENT STATE WITH APPLICATION TO ELECTRODIAGNOSIS OF PERIPHERAL POLYNEUROPATHY, IEEE transactions on biomedical engineering, 42(8), 1995, pp. 786-792
A methodology which accounts for uncertainty or imprecision in experim
ental observations and both norm and pathology definitions is develope
d on the basis of a distance measure between fuzzy numbers. These fuzz
y numbers may represent, respectively, the measurements, norm, and pat
hology. The distance measure, called normalized fuzzy pathology index
(NFPI), evaluates the difference of distance between observed experime
ntal values for a given patient and norm on the one hand, and patholog
y on the other hand. The NFPI characterizes patient state as a continu
ous index; however, to conform to medical usage, categories of values
are defined. Each of these categories corresponds to a linguistic vari
able. The case study used to illustrate the methodology is the electro
diagnosis of peripheral polyneuropathy in diabetic patients. Here, fou
r initial linguistic categories are defined by a physician, namely: no
rmal state, borderline state, clear-cut, and severe pathology. The NFP
I is calculated in three cases that provide a sensitivity analysis on
measurement fuzziness and distance function weighting. The model is ca
librated using 203 cases and validated using 291 different cases. The
results correspond very closely to the physician's diagnosis. The loss
of information in discretizing the continuous state of patients is di
scussed. Transferring this fuzzy approach to other cases where the con
cept of distance is relevant offers no difficulty.