Otoneurological Expert System

Abstract

An otoneurological expert system was developed to help collect data and diagnose both central and peripheral diseases causing vertigo. Patient history and otoneurological and other examination results are used in the reasoning process. The case history data can be either mandatory or supportive. Mandatory questions are used to confirm a diagnosis, and conflicting answers are used to reject an unlikely disease. Supportive questions support or suppress a diagnosis, but their presence is not obligatory. The reasoning procedure of the otoneurological expert system scores every question independently for different diagnoses, depending on how well they agree with the symptom entity of a disease. Diagnostic criteria are set for each disease. Graphic displays illustrate the linear and nonlinear correlation between the symptoms and diseases. Emphasis is placed on diminishing the possibility of a wrong decision rather than maximizing the likelihood of reaching only one right decision, so that even rare diseases can be taken into consideration.

Evaluation and classification of otoneurological data with new data analysis methods based on machine learning

“…The average sensitivity, specificity and positive predictive value of all the six classes were 85%, 95% and 83%, which are superior (by at least 10%) to the earlier results obtained with the basic perceptron neural network forms and virtually equal to the results computed using principal component analysis [8]. Our expert system [9,10] constructed earlier produced quite similar results on average, although they depended on the disease classes. For instance, it gave an average of sensitivity of 86%.…”

“…Variables (2), (3), (4), and (11) are very important according to the scattering ratios to separate the disease classes. They are the same as the five most important variables jointly with (21) defined earlier [9,10,12,23]. Variables (21) and (22) are known to be important to traumatic vertigo [9,10].…”

“…A combination of the variables measured for a specific patient depends on the clinical investigations performed by physicians. In our earlier research [8][9][10]12], 38 important variables (Table 1) also employed in the present research were determined. In addition, five of them were defined as the most crucial variables by the otoneurologists who gathered the data.…”

“…Our aim is to analyze the influence, and especially its degree, of individual variables that were already known to be influential [8][9][10]23]. By applying our methods it is also possible to investigate the influence of variables on the classification, and, thus, these methods can be used to diminish dimensionality, although we did not perform dimensionality reduction [17,26] in our current work.…”

Disease Profiling for Computerized Peer Support of Ménière's Disease

“…By definition, the expert system is a set of programs that manipulates encoded best knowledge to solve a problem in a specialized domain that normally requires human expertise [35,63]. The program is adaptive and learns during use (ie, a new person’s data updates the database).…”