Kati Viikki

Production of diagnostic rules from a neurotologic database with decision trees.

A decision tree is an artificial intelligence program that is adaptive and is closely related to a neural network, but can handle missing or nondecisive data in decision-making. Data on patients with Menieres disease, vestibular schwannoma, traumatic vertigo, sudden deafness, benign paroxysmal positional vertigo, and vestibular neuritis were retrieved from the database of the otoneurologic expert system ONE for the development and testing of the accuracy of decision trees in the diagnostic workup. Decision trees were constructed separately for each disease. The accuracies of the best decision trees were 94%, 95%, 99%, 99%, 100%, and 100% for the respective diseases. The most important questions concerned the presence of vertigo, hearing loss, and tinnitus; duration of vertigo; frequency of vertigo attacks; severity of rotational vertigo; onset and type of hearing loss; and occurrence of head injury in relation to the timing of onset of vertigo. Menieres disease was the most difficult to classify correctly. The validity and structure of the decision trees are easily comprehended and can be used outside the expert system.

Decision tree induction in the diagnosis of otoneurological diseases.

Expert systems have been applied in medicine as diagnostic aids and education tools. The construction of a knowledge base for an expert system may be a difficult task; to automate this task several machine learning methods have been developed. These methods can be also used in the refinement of knowledge bases for removing inconsistencies and redundancies, and for simplifying decision rules. In this study, decision tree induction was employed to acquire diagnostic knowledge for otoneurological diseases and to extract relevant parameters from the database of an otoneurological expert system ONE. The records of patients with benign positional vertigo, Menieres disease, sudden deafness, traumatic vertigo, vestibular neuritis and vestibular schwannoma were retrieved from the database of ONE, and for each disease, decision trees were constructed. The study shows that decision tree induction is a useful technique for acquiring diagnostic knowledge for otoneurological diseases and for extracting relevant parameters from a large set of parameters.

Classification of patients on the basis of otoneurological data by using Kohonen networks

Machine learning methods such as neural networks, decision trees and genetic algorithms can be useful to aid in the classification of patients. We tested Kohonen artificial neural networks, which are known to be effective for classification tasks. Our sample included patients with six different diseases. The Kohonen network algorithm recognized the four largest groups reliably, but the two smallest groups were too small for the method. Neural networks seem to be promising for the computer-aided classification of otoneurological patients provided that the number of patients used is sufficiently large.Machine learning methods such as neural networks, decision trees and genetic algorithms can be useful to aid in the classification of patients. We tested Kohonen artificial neural networks, which are known to be effective for classification tasks. Our sample included patients with six different diseases. The Kohonen network algorithm recognized the four largest groups reliably, but the two smallest groups were too small for the method. Neural networks seem to be promising for the computer-aided classification of otoneurological patients provided that the number of patients used is sufficiently large.

Evaluating Training Data Suitability for Decision Tree Induction

Dcision tree induction, as well as other inductive learning methods, requires training data of high quality to be able to generate accurate and reliable classification models. Example cases should form a representative sample from the application area, and the attributes used to describe example cases should be relevant and adequate for the classification task to be solved. In this paper, measures of the strength of association and an entropy-based approach have been used to assess the quality of the training data. Studied classification tasks related to three otological data sets: a conscript data set, a vertigo data set, and a postoperative nausea and vomiting data set. The pape suggests that the studied approaches give some guidelines about the quality of the training data, but other approaches are also needed to guide training data building.

Neural Network Recognition of Otoneurological Vertigo Diseases with Comparison of Some Other Classification Methods

We have studied computer-aided diagnosis of otoneurological diseases which are difficult, even for experienced specialists, to determine and separate from each other. Since neural networks require plenty of training data, we restricted our research to the commonest otoneurological diseases in our database and to the very most essential parameters used in their diagnostics. According to our results, neural networks can be efficient in the recognition of these diseases provided that we shall be able to add our available cases concerning those diseases which are rare in our database. We compared the results yielded by neural networks to those given by discriminant analysis, genetic algorithms and decision trees.

Generating Decision Trees from Otoneurological Data with a Variable Grouping Method

When medical data sets are modelled by machine learning methods, wealth of variables may be available. This paper deals with variable selection for decision tree induction in the context of two otoneurological data sets: vertigo data, and postoperative nausea and vomiting data. First, a variable grouping method based on measures of association and graph theoretic techniques was used to gain insight into data. Then, representations of learning data were defined using the information from discovered variable groups, and decision trees were generated. The use of variable grouping method was beneficial by revealing interesting associations between variables and enabling generation of accurate and reasonable decision trees that modelled the application areas from different viewpoints.

Impact and Management of Confounding Values and Outliers in a Neurotologic Expert System

We retrieved 728 patients from the database of neurotologic expert system ONE. All patients had filled out a questionnaire concerning their symptoms, earlier diseases, use of alcohol, tobacco, and drugs. This information was combined with results of audiometric and neurotologic tests. Decision trees were applied for data classification and outliers were identified with an informal box plot identification method.

Refining the Knowledge Base 0f an Otoneurological Expert System

This paper deals with the possibilities to refine the knowledge base of an otoneurological expert system ONE with the knowledge learned from data. The augmented knowledge base produces better results for benign positional vertigo, Meni`eres disease, sudden deafness, traumatic vertigo, and vestibular schwannoma. The results of this study suggest that learning from data is useful in refining the knowledge base. However, the knowledge acquired from human experts is also needed.

Application of artificial intelligence in audiology

In this paper, machine learning methods based on artificial intelligence theory are applied to the computer-aided decision making of some otoneurological diseases, for example Me´nie`res disease. Three methods explored are decision trees, genetic algorithms and neural networks. By using such a machine learning method, the decision-making program is trained with a representative training set of cases and tested with another set. The machine learning methods are useful also for our otoneurological expert system, One, which is based on a pattern recognition approach. The methods are able to differentiate most of the cases tested between the six diseases included, provided that a sufficiently large training set is available.