Clinical Decision Support Systems (CDSS) are software designed to help clinicians to make decisions about patient diagnosis using technical devices such as desktops, laptops and iPads, and mobile devices, to obtain medical information and set up alert systems to monitor medication. A Clinical Decision Support System has been suggested by many as a key to a solution for improving patient safety together with Physician Based Computer Order Entry. This technology could prove to be very important in conditions such as chronic diseases where health outlay is high and where self-efficacy can affect health outcomes. However, the success of CDSS relies on technology, training and ongoing support. This chapter includes a historical overview and practical application of CDSS in medicine, and discusses challenges involved with implementation of such systems. It discusses new frontiers of CDSS and implications of self-management using social computing technologies, in particular in the management of chronic disease.
TopIntroduction
Clinical Decision Support Systems are software applying “active knowledge systems which use two or more items of patient data to generate case-specific advice” (Wyatt & Spiegelhalter, 1991, p. 3). CDSS are information systems designed to improve clinical decision making ‘at the point in time that decisions are made’ (Berner, 2007, p. 3). The systems use technical devices such as desktops, laptops, iPads and mobile devices to derive medical information from data repositories to support the decision making process in a health organization. Patient characteristics are matched to knowledge database sets, and software algorithms generate patient-specific recommendations (Garg et al., 2010), as well-designed clinical decision support systems have been shown to improve the quality of health care with the use of clinical guidelines (Lamy et al., 2008).
The notion of using CDSS has been around for more than 50 years (Kulikowski & Weiss, 1982).
The early CDSS were developed in the 1970s, derived from expert systems where developers tried to emulate machines to think like expert clinicians when treating patients (Stowa et al., 2006). From these early studies, there was growing recognition that they could assist clinicians with routine tasks by providing various functionalities (Callen, Johanna, Westbrook, & Braithwaite, 2006; Georgiou, Lam, & Westbrook, 2008) that would assist clinicians with accurate diagnosis and minimize human error (Kawamoto, Houlihan, Balas, & Lobach, 2005).
However, the adoption of CDSS to their full capacity has not been as substantial as expected. There are barriers to their implementation (Aarts & Koppel, 2009) and challenges to accessing and linking the myriad of information that exists in silos. These challenges remain to be resolved (Sittig et al., 2008).
The potential to improve health via CDSS has been shown to be positive, and work is being done in the domains of geriatrics (Vairaktarakis et al., 2015), in pediatrics, education, laboratories, radiology and health administration.
This chapter covers the development and application of CDSS and discusses functionalities, limitations and challenges with the adoption of new technology. The chapter provides guidelines for better uptake of CDSS and provides a critique of various problems with, and reactions to, their application.