Search

The primary diagnosis of Tuberculosis (TB) is usually carried out by looking at the various signs and symptoms of a patient. However, these signs and symptoms cannot be measured with 100 % certainty since they are associated with various types of uncertainties such as vagueness, imprecision, randomness, ignorance and incompleteness. Consequently, traditional primary diagnosis, based on these signs and symptoms, which is carried out by the physicians, cannot deliver reliable results. Therefore, this article presents the design, development and applications of a Belief Rule Based Expert System (BRBES) with the ability to handle various types of uncertainties to diagnose TB. The knowledge base of this system is constructed by taking experts' suggestions and by analyzing historical data of TB patients. The experiments, carried out, by taking the data of 100 patients demonstrate that the BRBES's generated results are more reliable than that of human expert as well as fuzzy rule based expert system. [ABSTRACT FROM AUTHOR]

The article presents a study which predicted the intensity of low back pain (LBP) through the use of artificial neural network (ANN) and the adaptive neuro-fuzzy inference system (ANFIS). Also cited are the skin resistance and visual analog scale (VAS) values as input variables for ANN and ANFIS, and the Dumlupinar University Hospital in Turkey as the site of the study.

The article presents a study which aimed to enhance the accuracy of a fuzzy expert decision making system by improving the parameters of type-2 sigmoid membership functions of fuzzy input variables and identifying the most appropriate type-1 membership function. Among the data collected are body mass index, creatinine, and systolic and diastolic blood pressure. The accuracy of the system is verified in a medical diagnostic decision making system for renal diagnostic applications.

The article discusses the intelligence fuzzy rule-based expert system used to assess the severity of asthma. Also cited are the scores used in the system like the Hargreave score, the Canadian Asthma Consensus Report Score (CACRS), and the Prediction of Control State of Asthma Score (PCSAS), and the five modules of the system like respiratory symptoms, bronchial obstruction, and asthma instability.

The article presents a three-stage expert system based on a hybrid support vector machines (SVM) technique for the diagnosis of thyroid disease. The system is compared to the SVM based on the grid search technique (Grid-SVM) and the SVM based on Grid search and principle component analysis (PCA-Grid-SVM), and the use of particle swarm optimization (PSO) to optimize the parameters of an optimal predictor model.

Of late, there has been an increase in hearing impairment cases and to provide the most advantageous solutions to them is an uphill task for audiologists. Significant difficulty faced by the audiologists is in effective programming of hearing aids to provide enhanced satisfaction to the users. The main aim of our study was to develop a software intelligent system (SIS): (i) to perform the required audiological investigations for finding the degree and type of hearing loss, and (ii) to suggest appropriate values of hearing aid parameters for enhancing the speech intelligibility and the satisfaction level among the hearing aid users. In this paper, we present a Neuro-Fuzzy based SIS to automatically predict and suggest the hearing-aid parameters such as gain values, compression ratio and threshold knee point, which are needed to be fixed for different octave frequencies of sound inputs during the hearing-aid trial. The test signals for audiological investigations are generated through the standard hardware present in a personal computer system and with the aid of a software algorithm. The proposed system was validated with 243 subjects’ data collected at the Government General Hospital, Chennai, India. The calculated sensitivity, specificity and accuracy of the proposed audiometer incorporated in the SIS were 98.6%, 96.4 and 98.2%, respectively, by comparing its interpretations with those of the ‘gold standard’ audiometers. Furthermore, 91% (221 of 243) of the hearing impaired subjects attained satisfaction in the first hearing aid trials itself with the gain values as recommended by the improved SIS. The proposed system reduced around 75% of the ‘trial and error’ time spent by audiologists for enhancing satisfactory usage of the hearing aid. Hence, the proposed SIS could be used to find the degree and type of hearing loss and to recommend hearing aid parameters to provide optimal solutions to the hearing aid users. [ABSTRACT FROM AUTHOR]

At the University of Miyazaki Hospital (UMH), we have accumulated and semantically structured a vast amount of medical information since the activation of the electronic health record system approximately 10 years ago. With this medical information, we have decided to develop an alert system for aiding in medical treatment. The purpose of this investigation is to not only to integrate an alert framework into the electronic heath record system, but also to formulate a modeling method of this knowledge. A trial alert framework was developed for the staff in various occupational categories at the UMH. Based on findings of subsequent interviews, a more detailed and upgraded alert framework was constructed, resulting in the final model. Based on our current findings, an alert framework was developed with four major items. Based on the analysis of the medical practices from the trial model, it has been concluded that there are four major risk patterns that trigger the alert. Furthermore, the current alert framework contains detailed definitions which are easily substituted into the database, leading to easy implementation of the electronic health records. [ABSTRACT FROM AUTHOR]