Studies indicate that about 3-7% of school-age children have attention deficit hyperactivity disorder (ADHD). If these disorders are not diagnosed and treated early, its consequences can harshly impair the adult life of the individual. In this context, early diagnosis is critical. Clinical reasoning is a key contributor to the quality of health care. Clinical decisions at the policy level are made within a stochastic domain; decisions for individuals are usually more qualitative. In both cases, poor reasoning can result in an undesirable outcome. Clinical decisions are most typically communicated in a document through free text. Text has significant limitations (particularly ambiguity and poor structuring) whether used for analysis, or to explain the decision-making process. In safety engineering, similar problems are faced in conveying safety arguments to support certification. As a result, approaches have been developed to conveying arguments in ways which improve communication and which are more amenable to analysis. The Goal Structuring Notation (GSN) - a graphical argumentation notation for safety - was developed for those reasons. It has evolved to be one of the most widely used techniques for representing safety arguments. The use of text-mining techniques is another approach in the process of achieving or suggesting a diagnosis to the physician. This paper investigates the relative feasibility of these two approaches and discuss their complementation. Based on a case example, the benefts and problems of adopting GSN and ontology approach in clinical decision-making for ADHD are discussed and illustrated.
|Number of pages
|International Journal of Healthcare Information Systems and Informatics
|Published - 2013