Biomedical subjects

G Del Fiol

Publications and source records attributed to G Del Fiol.

3 recordsLinked to original sources

PubMed2006

Modeling end-users' acceptance of a knowledge authoring tool.

OBJECTIVES: Knowledge bases comprise a vital component in the classic medical expert system model, yet the knowledge acquisition process by which they are created has been characterized as highly iterative and labor-intensive. The difficulty of this process underscores the importance of knowledge authoring tools that satisfy the demands of end-users. The authors hypothesize that the acceptability of a knowledge authoring tool for the creation of medical knowledge base content can be predicted by an accepted model in the information technology (IT) field, specifically the Technology Acceptance Model (TAM). METHODS: An online survey was conducted amongst knowledge base authors who had previously established experience with the authoring tool software. The Likert-based questions in the survey were patterned directly after accepted TAM constructs with minor modifications to particularize them to the software being used. The results were analyzed using structural equation modeling. RESULTS: The TAM performed well in predicting endusers' behavioral intentions to use the knowledge authoring tool. Five out of seven goodness-of-fit statistics indicate that the model represents the behavioral intentions of the authors well. All but one of the hypothesized relationships specified by the TAM were significant with p values less than 0.05. CONCLUSIONS: The TAM provides an adequate means by which development teams can anticipate and better understand what aspects of a knowledge authoring tool are most important to their target audience. Further research involving other behavioral models and an expanded user base will be necessary to better understand the scope of issues that factor into acceptability.

Attitude↗

PubMed2000

Comparison of two knowledge bases on the detection of drug-drug interactions.

This paper describes a drug ordering decision support system that helps with the prevention of adverse drug events by detecting drug-drug interactions in drug orders. The architecture of the system was devised in order to facilitate its use attached to physician order entry systems. The described model focuses in issues related to knowledge base maintenance and integration with external systems. Finally, a retrospective study was performed. Two knowledge bases, developed by different academic centers, were used to detect drug-drug interactions in a dataset with 37,237 drug prescriptions. The study concludes that the proposed knowledge base architecture enables content from other knowledge sources to be easily transferred and adapted to its structure. The study also suggests a method that can be used on the evaluation and refinement of the content of drug knowledge bases.

Artificial Intelligence↗

PubMed2000

Design, implementation and evaluation of a clinical decision support system to prevent adverse drug events.

Adverse drug events are known to be a major health problem worldwide. It is estimated that the annual costs related to these events in the United States are greater than the total costs with cardiovascular disease care. Decision support systems that assist drug ordering have demonstrated to be a powerful tool to prevent prescription errors and adverse drug events. On the other hand, some issues related to the development, implementation, configuration, and evaluation of these decision support systems still need further research. This paper presents the development and evaluation of a decision support system prototype that helps with the prevention of adverse drug events by detecting drug-drug interactions in drug orders. The structure of the system tries to solve some of the problems described by the literature, such as integration with hospital information systems, adaptability to local needs, and knowledge base maintenance. The proposed model has shown to be an effective method for representing drug-drug interactions. The prototype was evaluated by a retrospective study using a dataset with 37.237 prescriptions. The system was able to detect 10.044 (27.0%) orders containing one or more drug-drug interactions. Among these interactions, 6.4% had high severity. In a future study, it is intended to apply the developed system in a real-time on-line environment, evaluating the benefits achieved in terms of improvement in medical practice and patient outcomes.

Adverse Drug Reaction Reporting Systems↗