Health information technology (IT) will be used more frequently by healthcare providers to acquire, manage, analyze, and disseminate healthcare information and knowledge for better patient care in the coming years. Computerized Clinical Decision Support (CDS) systems, a part of health IT applications, have been shown to improve the quality, safety, and value of healthcare. However, due to the lack of understanding of the complexities surrounding decision tasks, system design in medicine does not support a higher level of reasoning in decision support. Therefore, to guide the design of high-level reasoning in CDS systems, it is imperative to understand the complex decision-making patterns and the factors that contribute to decision task complexity. Despite substantial prior research on task complexity in other domains, less is known about complex clinical decision tasks. In response to this pressing gap, the objective of our research is to increase the understanding of complexity in clinical decision tasks. Task complexity is well defined in other successful areas of system design including defense, the humanities, engineering, business and the social sciences. We will utilize successful models from other fields for task complexity to understand the factors necessary for innovative design of CDS systems. To achieve this goal, we will characterize the decision-making patterns of clinical experts through clinical incident interviews (Aim 1);identify factors that contribute to complex decision tasks through clinician observations (Aim 2);and utilize these findings to design and evaluate a prototypical CDSS that uses visual and population analytics to improve decision quality (Aim 3). This application responds to the AHRQ SEN (NOT-HS-13-011) with emphasis on the system "Design" research area. The research will be conducted in the domain of Infectious Diseases (ID) due to its dynamic complexity and importance in the public health domain.
This project addresses potential gaps in health IT system design. This includes the understanding of complex clinical decision tasks. We anticipate that improved understanding of task complexity in clinical decisions will enhance the design of future innovative Clinical Decision Support (CDS) interventions that will increase the effectiveness of delivery for better patient and population care. The complexity contributing factors related to clinical decision tasks once identified, can then be used to establish functional requirements, as well as develop and test system specifications and designs in all areas of medicine. The results of the proposed research will help guide the design of future innovative CDS systems that support a high-level reasoning in complex decision tasks. Thus, we will be able to identify these crucial health IT design factors for future system design and increase the effectiveness of health IT. An intelligently designed health IT can improve the quality, safety, efficiency, and effectiveness of healthcare.
|Roosan, Don; Del Fiol, Guilherme; Butler, Jorie et al. (2016) Feasibility of Population Health Analytics and Data Visualization for Decision Support in the Infectious Diseases Domain: A pilot study. Appl Clin Inform 7:604-23|
|Islam, R; Weir, C; Del Fiol, G (2016) Clinical Complexity in Medicine: A Measurement Model of Task and Patient Complexity. Methods Inf Med 55:14-22|
|Roosan, Don; Samore, Matthew; Jones, Makoto et al. (2016) Big-Data Based Decision-Support Systems to Improve Clinicians' Cognition. IEEE Int Conf Healthc Inform 2016:285-288|
|Islam, Roosan; Mayer, Jeanmarie; Clutter, Justin (2016) Supporting novice clinicians cognitive strategies: System design perspective. IEEE EMBS Int Conf Biomed Health Inform 2016:509-512|
|Islam, Roosan; Weir, Charlene R; Jones, Makoto et al. (2015) Understanding complex clinical reasoning in infectious diseases for improving clinical decision support design. BMC Med Inform Decis Mak 15:101|
|Islam, Roosan; Weir, Charlene; Del Fiol, Guilherme (2014) Heuristics in Managing Complex Clinical Decision Tasks in Experts' Decision Making. IEEE Int Conf Healthc Inform 2014:186-193|