Introduction
When making a decision concerning one’s diagnosis and potential treatment, clinical professionals often address alternative opinions, including other clinicians and scholarly research. In order to facilitate the process of these decisions, clinical decision support (CDS) was created. CDS stands for “any system that assists health personnel in clinical decision making, using the individual characteristics of patients to generate specific assessments and recommendations that are presented to professionals for their consideration” (Martinez-Franco et al., 2018, p. 72). Hence, CDSs’ primary goal is to assist medical professionals in securing personalized treatment for a patient, patients’ diagnostics, and reminding a clinician to check up on patients.
Typology and Examples
Fundamentally, CDSs are divided into computerized and non-computerized, with the latter representing such tools as digital databases, guidelines, and support sources such as ClinicalKey (Kubben et al., 2019). Computerized CDSs, sometimes also known as clinical decision support systems (CDSSs), are divided into two groups: knowledge-based and non-knowledge based systems (Sutton et al., 2020). The former tend to operate based on the rules prescribed by specific sources such as scholarly evidence, practice, and patient data. Thus, once a certain situation is presented to CDSS, it presents a possible solution based on the data input in the system (Sutton et al., 2020). Non-knowledge based CDSSs, for their part, use artificial intelligence and machine learning in order to generate a response appropriate for the data input. Examples of CDSSs include laboratory or pharmacy information systems that provide clinicians with assistance on critical care and drug recommendation (Kubben et al., 2019). Modern health care is primarily focused on the implementation of CDSSs in the workplace, so it would be beneficial to discuss the systems’ benefits.
Benefits of CDSSs
It is reasonable to assume that the interaction with a computerized support system presents a series of advantages to clinical care. These advantages, according to Sutton et al. (2020), include patient safety and error reduction, better clinical management, cost containment due to error reduction and efficiency increase, diagnostics support, and the overall improvement of the workflow. Moreover, according to Segal et al. (2017), most benefits are associated with diagnostics, as such systems provide clinicians with a variety of perspectives on a diagnostic matter. Hence, it may be concluded that it is difficult to deny the positive aspects of implementing CDS in a workplace.
Risks of CDSSs
On the other hand, computerized assistance provides a variety of potential challenges for clinicians and patients. Thus, according to Sutton et al. (2020), the primary risks include alert fatigue, meaning the clinicians’ disregard for important alerts due to an exhaustive number of insignificant ones, high dependence on the support, and decrease in clinician’s competence and skills, and clinicians’ distrust. Moreover, when such a system is used outside the electronic health record (EHR) system, Martinez-Franco et al. (2018) claim the possible inapplicability of the support system in complex day-to-day care. For this reason, it becomes evident that the implementation of CDS is a beneficial tool when used as an assistant and not a primary decision-maker.
EHR Vendors
CDSSs may be used by clinicians in two primary ways: in isolation from EHS systems and within them. DXplain is an example of an independent system that helps clinicians make decisions based on the data presented to the system (Martinez-Franco et al., 2018). While it may be beneficial, there is a significant drawback of the absence of data synchronization. CDSSs within EHR systems, for their part, synchronize with the patient data and present relevant options and alerts. Examples of such EHR vendors include Epic and Cerner, as they have their own CDSSs embedded in the software. Hence, having discussed the typology and characteristics of CDSs, it may be concluded that the application of computerized CDSs, or CDSSs is of paramount importance for a clinical setting once the professionals are aware of the potential risks of such systems.
References
Kubben, P., Dumontier, M., & Dekker, A. (Eds.). (2019). Fundamentals of clinical and data science [E-book]. Springer. Web.
Martinez-Franco, A. I., Sanchez-Mendiola, M., Mazon-Ramirez, J. J., Hernandez-Torres, I., Rivero-Lopez, C., Spicer, T., & Martinez-Gonzalez, A. (2018). Diagnostic accuracy in Family Medicine residents using a clinical decision support system (DXplain): A randomized-controlled trial. Diagnosis, 5(2), 71-76. Web.
Segal, M. M., Rahm, A. K., Hulse, N. C., Wood, G., Williams, J. L., Feldman, L., Moore, G. J., Gehrum, D., Yefko, M., Mayernick, S., Gildersleeve, R., Sunderland, M. C., Bleyl, S. B., Haug, R., & Williams, M. S. (2017). Experience with integrating diagnostic decision support software with electronic health records: Benefits versus risks of information sharing. eGEMs, 5(1). Web.
Sutton, R. T., Pincock, D., Baumgart, D. C., Sadowski, D. C., Fedorak, R. N., & Kroeker, K. I. (2020). An overview of clinical decision support systems: Benefits, risks, and strategies for success. NPJ Digital Medicine, 3(1), 1-10. Web.