OBJECTIVE: The contents of microbial information are complicated because of being hierarchical, duplicated as well as their changes are continuous and various. Much of time and cost are required for maintaining, expanding the information after representing them into a relational database. The relational database is not adequate to make the information sharable via Internet. In addition, user's meta-knowledge is insufficient to use the information via Internet and users may not be able to cope with the continuous changes of microbial information through the static web interface. Therefor, this study is conducted to develop an active microbial web database for resolving those problems. METHODS: To solve these problems, object-oriented database, which was able to represent the complicated contents and knowledge, was used, and intelligent agents were implemented to cope with the continuous evolution of microbial information. Also, they were incorporated into user interface to assist users in an interactive environment, who want to use information via Internet. RESULTS: The implemented system have shown advantages of solving difficulties arising from hierarchical and duplicated microbial data. It showed the possibility to share and manage the complex microbial data via Internet. It helped the system to be implemented as the active database, information stored in the object-oriented database. CONCLUSION: This study indicates that a similar approach may lead to develop an expert system based on the web and active database, which is able to be evolved, and to develop intelligent interface, using the agent.
Expert Systems ; Internet

Aiming at the dilemma of expensive and difficult maintenance, lack of technical data and insufficient maintenance force for modern medical equipment, an intelligent fault diagnosis expert system of multi-parameter monitor based on fault tree was proposed in this study. Firstly, the fault tree of multi-parameter monitor was established and analyzed qualitatively and quantitatively, then based on the analysis results of fault tree, the expert system knowledge base and inference engine were constructed and the overall framework of the system was determined, finally the intelligent fault diagnosis expert system for multi-parameter monitor was developed by using the page hypertext preprocessor (PHP) language, with an accuracy rate of 80% in fault diagnosis. The results showed that technology fusion on the basis of fault tree and expert system can effectively realize intelligent fault diagnosis of multi-parameter monitors and provide troubleshooting suggestions, which can not only provide experience accumulation for fault diagnosis of multi-parameter monitors, but also provide a new idea and technical support for fault diagnosis of medical equipment.
Expert Systems ; Monitoring, Physiologic

BACKGROUND: Demands for complicated and long-term administration clinical trials have been increased since investigators actively involved in early stage clinical trials including first-in-human (FIH) trials. Research wards in our clinical trial center were mainly used for phase 1 trials. In order to perform several clinical trials simultaneously during a short period with a minimum number of rooms, beds, and equipment, staffs have to spend a lot of time for efficient operation of limited numbers of facilities. In this study, automated bed-allocation system was developed for efficient scheduling of the research ward based on clinical trial condition and status like experts. METHODS: The system was developed based on clinical trial design, schedule, and the information on research bed and availability stored and updated in database (DB). Automatic assignment system was designed to find an optimal schedule according to the given information using expert rules and algorithms. The optimal solution can be visualized on Gantt chart using C# and Chart FX API. RESULTS: The system was developed to demonstrate the schedule on color chart. It turned out to be well-designed to find an optimal schedule for bed allocation. The system also allows automatic updating of the schedule and information in the DB. CONCLUSION: Automated bed-allocation system developed in this study could save time and improve the efficiency for using space and equipment in clinical trial center. The system can be also applied to similar works or tasks in other fields.
Appointments and Schedules ; Expert Systems ; Humans ; Research Personnel

This study was conducted to develop the NutriSonic Web Expert System for Meal Management and Nutrition Counseling with Analysis of User's Nutritive Changes of selected days and food exchange information with easy data transition. This program manipulates a food, menu and meal and search database that has been developed. Also, the system provides a function to check the user's nutritive change of selected days. Users can select a recommended general and therapeutic menu using this system. NutriSonic can analyze nutrients and e-food exchange ("e" means the food exchange data base calculated by a computer program) in menus and meals. The expert can insert and store a meal database and generate the synthetic information of age, sex and therapeutic purpose of disease. With investigation and analysis of the user's needs, the meal planning program on the internet has been continuously developed. Users are able to follow up their nutritive changes with nutrient information and ratio of 3 major energy nutrients. Also, users can download another data format like Excel files (.xls) for analysis and verify their nutrient time-series analysis. The results of analysis are presented quickly and accurately. Therefore it can be used by not only usual people, but also by dietitians and nutritionists who take charge of making a menu and experts in the field of food and nutrition. It is expected that the NutriSonic Web Expert System can be useful for nutrition education, nutrition counseling and expert meal management.
Counseling ; Expert Systems ; Fees and Charges ; Follow-Up Studies ; Internet ; Meals

BACKGROUND: Determination of antibody specificity using antigram spread sheet requires experience and knowledge on in vitro characteristics of red cell antibodies, time-consuming, and still subjective to human error. A computer-based antibody identification system was developed to overcome these disadvantages. METHODS: Decision support system program for antibody identification was designed using Visual Basic 5.0 for Dade Data-cyte Plus. This system integrates the reaction patterns of saline, 37degrees C albumin, antiglobulin, 4degrees C saline enzyme treated and user-defined phases and lists the antibodies according to the probability. 115 irregular antibodies previously confirmed by standard manual method reanalyzed with this program. RESULTS: In 111 of 115 cases (96.5%), this system produced the same results with the manual identification. In two cases, of not matched 4 cases the computer program suggested additional antibodies and in one case, the computer program detected previous human error. In the other case, antibody identification was possible only after further tests including selective adsorption of multiple antibodies. CONCLUSION: The decision support system was rapid and easy and showed good concordance rate when compared with manual antibody identificaion results. In addition, human error could be reduced. Decision support system for antibody identification could be used in small blood banks by less experienced staffs.
Adsorption ; Antibodies ; Antibody Specificity ; Blood Banks ; Expert Systems ; Humans

In order to increase the performance of automatic sleep stage scoring, we propose a hybrid neural-network and rule-based expert system taking advantages of each system. The suggesting hybrid system comprises signal cleaning. feature extraction, event detection, rule-based sleep scoring and neural network classification. We selected segment based EEG features. the state of EOG. and EMG tone as a major feature set. With the extracted features, the rule-based expert system classities the sleep stages by symbolic reasoning. The scoring process of rule-based expert system comprises the single epoch reasoning based on the typical events and the multi-epoch adjusting when no events are detected. If the decision of rule-based expert system is uncertain, then these features are fed into the neural network. We used a two hidden layer feed forward network using error hack propagation algorithm. The agreement rate between human scorer and automatic algorithm were evaluated. The neural network supplements the shortcomings of rule-based system by dealing with exceptions of rules. The result shows that the compuational ol computational and symbolic intelligence is promising approach sleep signal anal) sis.
Classification ; Electroencephalography ; Electrooculography ; Expert Systems ; Humans ; Intelligence ; Sleep Stages*

BACKGROUND: Rapid and accurate diagnosis of multiple acid-base disorders is not so easy. The authors evaluated a need of a computer-aided diagnosis program for acid-base disorders through the questions of 25 cases with acid-base disorders in 105 physicians. METHODS: For 39 college graduated students and 66 housestaffs, we asked them to diagnose 25 sample cases of acid-base disorders, which were selected from the published 36 cases (Horn et. al. 1992, Halperin and Goldstein 1994, Walmsley and White 1988). The 25 questions consisted of 15 cases with single disorder, 8 cases with double disorder and 2 cases with triple disorder. RESULTS: The 39 college graduated students diagnosed correctly in 55.4%; 79.6% in single disorders, 23.7% in double disorders and 0.0% in triple disorders. The 36 housestaffs (answer rate: 55.4%) diagnosed correctly in 61.7%; 82.4% in single disorders, 38.2% in double disorders and 0.0% in triple disorders. CONCLUSIONS: The data suggest that the physicians can't diagnose acid-base disorders well and that they needs a computer-aided expert system to diagnose the acid-base disorders and to ensure uniform quality of patient care.
Acidosis ; Alkalosis ; Diagnosis* ; Expert Systems* ; Humans ; Patient Care

This study aims to apply a new expert system to design removable partial denture (RPD) framework. The RPD design is completed in three steps, namely, "selecting missing teeth", "selecting abutment condition", and "selecting personalized clasp". The system can help auxiliary dentists develop personalized treatment plans to reduce their clinical workload. It can also generate a dental preparation guideline for clinical preparation, which can prevent tooth preparation mistakes. By generating the standard electronic drawings of the framework design, the system can reduce the inconvenience caused by manual drawing, thereby facilitating dentist-technician communication and reducing the rate of remade.
Dental Abutments ; Denture Design ; Denture, Partial, Removable ; Expert Systems ; Tooth

OBJECTIVES: The usability of clinical information systems (CISs) is known to be an essential consideration in ensuring patient safety as well as integrating clinical flow. This study aimed to determine how usability and safety guidelines of CIS consider clinical workflow through a systematic review in terms of the target systems, methodology, and guideline components of relevant articles. METHODS: A literature search was conducted for articles published from 2000 to 2015 in PubMed, Cochrane, EMBASE, Web of Science, and CINAHL. The Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) statement method was employed. Articles containing recommendations, principles, and evaluation items for CIS usability and safety were included. The selected articles were classified according to article type, methodology, and target systems. Taking clinical workflow into consideration, the components of guidelines were extracted and classified. RESULTS: A total of 7,401 articles were identified by keyword search. From the 76 articles remaining after abstract screening, 15 were selected through full-text review. Literature review (n = 7) was the most common methodology, followed by expert opinions (n = 6). Computerized physician order entry (n = 6) was the most frequent system. Four articles considered the entire process of clinical tasks, and two articles considered the principles of the entire process of user interface affecting clinical workflow. Only two articles performed heuristic evaluations of CISs. CONCLUSIONS: The usability and safety guidelines of CISs need improvement in guideline development methodology and with consideration of clinical workflow.
Expert Testimony ; Heuristics ; Hospital Information Systems ; Information Systems* ; Mass Screening ; Medical Order Entry Systems ; Methods ; Patient Safety ; User-Computer Interface

The purpose of this study is to design push-pull osmotic pump (PPOP) tablets of famotidine using the expert system for the formulation design of osmotic pump of poor water-soluble drug which had been established by the authors. Firstly, the parameters which were requisite of the system input were obtained from literatures and experimental tests. Then the parameters were input into the system, and the program was run. The system displayed the designed formulations sequential. Finally, famotidine PPOP was prepared according to the designed formulations and the in vitro dissolution was carried out. It was found out that the target formulation of famotidine PPOP which could release for 24 hours was obtained in a very short period. Meanwhile, the practicability of the established expert system was proved.
Delayed-Action Preparations ; Drug Delivery Systems ; methods ; Excipients ; chemistry ; Expert Systems ; Famotidine ; administration & dosage ; chemistry ; Osmosis ; Solubility ; Tablets ; Water