Narrow Results

The purpose of this expert system is to assess a predisposition to bleeding in a patient undergoing a tonsillectomy and/or adenoidectomy, as may occur with patients who have certain blood conditions such as hemophilia, von Willebrand’s disease, and platelet function defects. This objective is achieved by establishing a correlation between the patients’ responses to a medical questionnaire and the relative quantities of blood lost during their operations.

Three major modules constitute the system: the automated questionnaire to be completed by the patient, the expert system proper, and the patient database. The questionnaire is divided into fourteen sections on topics such as the occurrence of bruises and positive familial history. The expert system takes the responses to the questionnaire and determines risk categories for patients undergoing the operations. The patient database contains the patients’ questionnaire responses, personal data and the risk assessments generated by the expert system.

Subsequent to the development of the expert system prototype, inductive learning techniques were examined to automatically classify patients as either normal or abnormal. Specifically, Quinlan’s ID3 induction algorithm was used whereby a training set of patient data generates a classification tree whose leaf nodes correspond to the classification outcomes.

This paper presents the architecture of the hematology expert system, identifies some problems encountered during the knowledge engineering process and presents some statistical data pertaining to the accuracy of its risk assessments. It also offers a comparative review of the expert system and inductive learning methodologies.

A questionnaire, designed to assess bleeding predispositions in tonsillectomy and/or adenoidectomy patients, was administered to 236 otherwise healthy children. For comparative purposes, 114 patients with bleeding disorders were also studied. An unsupervised non-metric clustering technique was used in an attempt to classify bleeders against non-bleeders based solely on the responses to the questionnaire. Non-metric techniques are essential for the classification process because of the large number of missing attribute values in the patient data set. As a benchmark, a supervised inductive machine learning strategy was also used to classify the patients.

Performance results are compared and contrasted between the techniques across different subsets of the patient data. These techniques are also evaluated as a methodology for determining the relative significance of attributes vis-à-vis the reduction of the dimensionality of a large medical data set. In this investigation, the classification rate achieved using the non-metric technique (73%) was only marginally poorer than the rate using the supervised technique (76%). Moreover, these results were obtained with an accompanying 80% reduction in the number of attributes used to perform the analysis.

Reference interval (RIs) were critical to the identification of illness. However, RIs set in one laboratory may not be appropriate for another because of biological, geographical and instrumental factors. Interpretation of clinical data using inappropriate RIs may cause misclassification of results and misdiagnosis that lead to improper treatment. RIs in Taiwan have been mostly referencing from foreign resources, it is desirable to establish one that is closer to the overall conditions in Taiwan (such as breed, climate, diseases, etc.) and to investigate its differences to foreign RIs. The present study used the American Society for Veterinary Clinical Pathology (ASVCP) guidelines to establish in-house RIs for hematological, biochemical and coagulation parameters using dogs in middle Taiwan. The results were also compared to two foreign and one local RIs. The results suggested that the hematological RIs are more comparable to foreign RIs than the biochemical and hemostatic parameters. Differences were found for biochemical parameters including gamma-glutamyl transferase (GGT), lactate dehydrogenase (LDH), lipase, uric acid, bile acid, bilirubin and magnesium; and coagulation parameters including prothrombin time (PT) and activated partial thromboplastin. In all, 18% (7/40) of the all tested parameters were different from the local RI while 38% (18/48) and 41% (19/46) of the parameters were different from the two foreign RIs. The differences in more than 30% RIs and better similarities to local RIs underscore the importance of having own RIs if possible.

The purpose of this expert system is to assess a predisposition to bleeding in a patient undergoing a tonsillectomy and/or adenoidectomy, as may occur with patients who have certain blood conditions such as hemophilia, von Willebrand's disease, and platelet function defects. This objective is achieved by establishing a correlation between the patients' responses to a medical questionnaire and the relative quantities of blood lost during their operations.

Three major modules constitute the system: the automated questionnaire to be completed by the patient, the expert system proper, and the patient database. The questionnaire is divided into fourteen sections on topics such as the occurrence of bruises and positive familial history. The expert system takes the responses to the questionnaire and determines risk categories for patients undergoing the operations. The patient database contains the patients' questionnaire responses, personal data and the risk assessments generated by the expert system.

Subsequent to the development of the expert system prototype, inductive learning techniques were examined to automatically classify patients as either normal or abnormal. Specifically, Quinlan's ID3 induction algorithm was used whereby a training set of patient data generates a classification tree whose leaf nodes correspond to the classification outcomes.

This paper presents the architecture of the hematology expert system, identifies some problems encountered during the knowledge engineering process and presents some statistical data pertaining to the accuracy of its risk assessments. It also offers a comparative review of the expert system and inductive learning methodologies.