An intelligent system based on fuzzy probabilities for medical diagnosis – a study in aphasia diagnosis

Background: aphasia diagnosis is particularly challenging due to the linguistic uncertainty and vagueness, inconsistenciesin the definition of aphasic syndromes, large number of measurements with imprecision, natural diversity andsubjectivity in test objects as well as in opinions of experts who diagnose the disease.methods: fuzzy probability is proposed here as the basic framework for handling the uncertainties in medical diagnosisand particularly aphasia diagnosis. to efficiently construct this fuzzy probabilistic mapping, statistical analysis isperformed that constructs input membership functions as well as determines an effective set of input features.results: considering the high sensitivity of performance measures to different distribution of testing/training sets, astatistical t-test of significance is applied to compare fuzzy approach results with nn results as well as author’s earlierwork using fuzzy logic. the proposed fuzzy probability estimator approach clearly provides better diagnosis for bothclasses of data sets. specifically, for the first and second type of fuzzy probability classifiers, i.e. spontaneous speechand comprehensive model, p-values are 2.24e-08 and 0.0059, respectively, strongly rejecting the null hypothesis.conclusions: the technique is applied and compared on both comprehensive and spontaneous speech test data fordiagnosis of four aphasia types: anomic, broca, global and wernicke. statistical analysis confirms that the proposedapproach can significantly improve accuracy using fewer aphasia features.