Running Head: CLINICAL DECISION SUPPORT SYSTEMS 1 Clinical Decision Support Systems Improving Patient Outcomes Stephanie Kessinger Army Baylor MHA HMIS 5317
CLINICAL DECISION SUPPORT SYSTEMS 2 Abstract Purpose: The purpose of this literature review is to determine the impact of clinical decision support systems (CDSS) on improving patient outcomes. Why: The goal of this study is to determine if clinical decision support systems are beneficial for hospital administrators to implement in healthcare organizations. Methods: The methods used for this literature review include articles from Google Scholar, CINAHL, Baylor Library, and US Army Stimson Library online databases. Key words searched include: decision support systems, healthcare, patient outcomes, and cost. Search criteria for articles included peer-reviewed, published from 2009 to present, English language, and research articles. Six original research articles and two systematic review articles are evaluated in this review. Findings: I concluded that measuring patient outcomes is rare, only one studied CDSS proved improved outcomes by reducing mortality rates. CDSS can improve documentation and adherence to protocol. Value: Overall, the value of incorporating CDSS into medical practice has more benefits than limitations. The greatest benefit to administrators is the cost savings indirectly associated with CDSS. Limitations include inconsistent quality, necessary maintenance, and hidden cost. Keywords: clinical decision support, compliance, improved patient outcomes, healthcare administration.
CLINICAL DECISION SUPPORT SYSTEMS 3 Clinical decision support systems improving patient outcomes The complex healthcare environment and advances with the electronic health record (EHR) has spawned the information technology industry to create clinical decision support systems (CDSS). Healthcare leaders implement CDSS to improve the clinical decision-making process, improve patient outcome, and decrease fiscal expenditure. These systems appear in a multitude of healthcare settings, such as pharmacies, laboratories, inpatient hospitals, and outpatient clinics. CDSS incorporates evidence-based medicine with simple reminders during medication ordering to complex recommendations on managing specialized patient populations (Rothman, Leonard, & Vigoda, 2012). The goal of this review of literature is to capture the benefits, implications, and limitations of the CDSS in practice. Healthcare administrators should be informed of CDSS ability to improve the healthcare organization. Rothman describes the two types of decision support systems in his article: active and passive decision support. Active DSS are automatic, to include prompts and alerts, such as with drug ordering incompatibility (Rothman, Leonard, & Vigoda, 2012). The other form is passive DSS; this requires the user to seek recommendations, by inputting data (Rothman, Leonard, & Vigoda, 2012). The passive CDSS are integrated in the electronic health record (EHR) or it can be stand-alone software that interoperates with the EHR. Methods This literature review evaluates six original research articles. Databases used to find these articles include Google Scholar, CINHAL, Army Stimson library, and Baylor University library online databases. Keywords searched include decision support systems, healthcare, cost, and patient outcomes. Search criteria narrowed by publication date, 2009 to present, English language, peer-reviewed journals, and research articles. CINHAL revealed 246 articles during
CLINICAL DECISION SUPPORT SYSTEMS 4 this search. I selected the research articles with original research and excluded articles pertaining to attitudes and qualitative results. Additional resources include systematic review articles. These review articles are utilized to gather baseline information and direct towards other research. These systematic review articles located via Google Scholar were selected due to the emphasis towards stakeholders and administrators. Two research articles were selected from the reference list of systematic review articles. Baylor University Library Online was used to locate articles mentioned in the review publications. Findings My review of the literature demonstrates that CDSS can improve the delivery of healthcare. It cannot prove that CDSS will have a direct impact on patient outcomes. These systems can vary from simple reminders during medication ordering to recommendations on managing specialized patient populations. This review of studies gives examples of the assortment of CDSS. Multiple forms of CDSS are present in the hospital setting. The active forms of decision support are automatically generated within the EHR are typically simple. It is a reminder or warning for the healthcare professional to complete a task. The first article demonstrated a simplistic form of CDSS (Lyerla, LeRouge, Cooke, Turpin, & Wilson, 2010). The system prompted the nurse to elevate the head-of-bed of ventilated patients. This simple system improved the compliance rate by 23% (Lyerla, LeRouge, Cooke, Turpin, & Wilson, 2010). Compliance of a recommended protocol can increase patient outcomes. Harrison and colleagues demonstrated an increase in documentation and adherence to protocol with implementation of a hypoglycemic electronic guideline (Harrison, Stalker, Henderson, & Lyerla, 2013). This electronic decision support system was more than a reminder
CLINICAL DECISION SUPPORT SYSTEMS 5 to complete a task. Based on input data, this CDSS recommended a specific action for the prevention and treatment of hypoglycemia among patients in a medical-surgical unit. The burn decision support system is the most complex system of all the systems reviewed for this paper. Their CDSS gave recommendation on hourly fluid rates during the first 48 hours of resuscitation based on input data. The result statistically demonstrates a decreased mortality rate, decreased ICU stay, and decreased ventilator day (Salinas, et al., 2011). These three studies conclude the inpatient CDSS; next is evaluation of the outpatient CDSS. Demand for primary and preventive care is expected to increase with implementation of the Affordable Care Act (ACA). CDSS are utilized in the outpatient setting to enhance the EHR. Schwarz and colleagues studied a CDSS to increase education among childbearing women when prescribed a medication harmful to a fetus (Schwarz, et al., 2012). The system would prompt the primary care provider to discuss contraception planning once ordering the harmful medication. Unfortunately, this addition to the decision support element was not significant, stated a need for refinement (Schwarz, et al., 2012). As the baby boomers age, the geriatric population continue to grow at a disproportionate rate. Litvin and colleagues completed a study on an embedded CDSS to increase geriatric education in an ambulatory setting. Overall, the study indicates the CDSS was useful to medical residents, but no statistical data was interpreted. The DSS was utilized more as a learning tool for providers to reinforce practice guidelines (Litvin, Davis, Moran, iverson, Zhao, & Zapka, 2012). The last article reviewed for this paper describes implementation of an asthma protocol decision support tool among emergency care providers. Kwok and colleagues created the asthma clinical assessment form as the guideline for the DSS. The findings increased documentation of
CLINICAL DECISION SUPPORT SYSTEMS 6 condition as well as a discharge plan (Kwok, Dinh, Dinh, & Chu, 2009). A discharge plan has been known to decrease future asthmatic events (Kwok, Dinh, Dinh, & Chu, 2009). Outpatient decision support systems are additional resources that can aid providers to streamline care. Downing and colleagues purposed the ability for decision support systems to integrate an individual s genome into the database to personalize medicine for treatment in care (Downing, Boyle, Brinner, & Osheroff, 2009). The development of such complexity will not only change the way medicine is practice, but also prevent unnecessary treatment that is incompatible with individual s genome. Contributions Clinical decision support systems provide multiple benefits. Administrators can gain perspective on CDSS with knowledge of the benefits and limitations. Contributions to practice include increased documentation, adherence to protocols, and improved patient outcomes. These benefits can greatly affect the cost savings of a healthcare organization. Each study increased provider documentation. Capturing the data, education, and patient problems will aid in many ways. Documentation can lead to a clear picture if the patient s condition for all healthcare providers to recognize. This increase in clarity will improve continuity of care among nurses and providers, leading to patient satisfaction and improved outcomes. Documentation can lead to timely billing and quicker reimbursements from thirdparty payers. CDSS has proven to improve adherence to clinical guidelines (Rothman, Leonard, & Vigoda, 2012). Established protocols, created with evidence-based medicine, it can lead to improved patient outcomes. Salinas et al. (2011) contributed the burn decision support system to decrease overall fluid requirements, therefore improving patient outcomes. This is the only
CLINICAL DECISION SUPPORT SYSTEMS 7 study that can statically indicate improved patient outcomes by comparing mortality rates (Salinas, et al., 2011). Improved medical practice can lead to improved outcomes and shorter length of stay. Administrators can modify DSS to recommend less invasive procedures to reduce medical overutilization, a growing problem among healthcare industries. The final contribution includes safety nets; it could reduce adverse drug reactions or allergies. Saving the industry costly iatrogenic conditions. CDSS are not without limitations. These limitations include alert fatigue, hidden cost and need for maintenance updates. Alert fatigue occurs when the provider becomes oblivious to the recommendations often due to time limitations (Downing, Boyle, Brinner, & Osheroff, 2009). Adherence to protocols can be accomplished through educational workshops, decreasing the need for simple CDSS (Rothman, Leonard, & Vigoda, 2012). The hidden cost of implementing a new CDSS can exceed the expectations. Administrators need awareness of heavy up-front cost, training cost, and annual maintenance cost prior to implementation Lastly, as medicine continues to advance, the decision support systems need to remain up-to-date. This is crucial for improved patient outcomes. Discussion and Conclusion Healthcare administrators have a myriad of choices with information technology within the medical arena. As electronic health records continue to evolve, more CDSS will emerge. The complexity of healthcare requires accurate, timely, and individualized clinical support systems to improve efficiency (Rothman, Leonard, & Vigoda, 2012). The most sophisticated EHR are embedding CDSS. The EHR transforms from a dumb record to a smart record with the
CLINICAL DECISION SUPPORT SYSTEMS 8 addition of decision support systems. It would behoove healthcare administrators to be knowledgeable on the opportunities and the limitations of decision support systems.
CLINICAL DECISION SUPPORT SYSTEMS 9 References Downing, G., Boyle, S., Brinner, K., & Osheroff, J. (2009). Information management to enable personalized medicine: stakeholder roles in building clinical decision support. Medical Informatics and Decision Making, 9 (44), 1-11. Harrison, R., Stalker, S., Henderson, R., & Lyerla, F. (2013). Use of a clinical decision support system to improve hypoglycemia management. MedSurg Nursing, 22 (4), 250-263. Kwok, R., Dinh, M., Dinh, D., & Chu, M. (2009). Improving adherence to asthma clinical guidelines and discharge documentation from emergency departments: implementation of a dynamic and integrated electronic decision support system. Emergency Medicine Australasia, 21, 31-37. Litvin, C., Davis, K., Moran, W., iverson, P., Zhao, Y., & Zapka, J. (2012). The use of clinical decision-support tools to facilitate geriatric education. Journal of the American Geriatrics Society, 60 (6), 1145-1149. Lyerla, F., LeRouge, C., Cooke, D., Turpin, D., & Wilson, L. (2010). A nursing clinical decision support system and potential predictors of head-of-bed position for patients receiving mechanical ventilation. American Journal of Critical Care, 19 (1), 39-47. Rothman, B., Leonard, J., & Vigoda, M. (2012). Future of electronic health records: implications for decision support. Mount Sinai School of Medicine, 79, 757-768. Salinas, J., Chung, K., Mann, E., Cancio, L., Kramer, G., Serio-Melvin, M., et al. (2011). Computerized decision support system improves fluid resuscitation following severe burns: an orginal study. Critcal Care Medicine, 39 (9), 2031-2038.
CLINICAL DECISION SUPPORT SYSTEMS 10 Schwarz, E., Parisi, S., Handler, S., Koren, G., Cohen, E., Shevchik, G., et al. (2012). Clinical decision support to promote safe prescribing to women of reproductive age: a clusterrandomized trial. Journal of General Internal Medicine, 27 (7), 831-838.
CLINICAL DECISION SUPPORT SYSTEMS 11 Improvements to rough draft Title Page Page 2 Page 3 Page 4 Page 5 Page 6 Page 7 Formatted the Running Header to Times New Roman, to include the page numbers Removed Running Head from header Corrected introduction title, removing capitalizations Corrected spelling error to decision Removed italics Removed anthropomorphism (throughout paper) Changed tone to active voice from passive voice (throughout paper) Restructured second to last sentence Added Keywords section Added double spaces between sentences (throughout paper) Added citations Did not add citation to last sentence, its my opinion, not pulled from any of the articles Corrected punctuation and abbreviations Bolded titles of sections Added more details to methods section Added citations Corrected article errors and punctuation errors Removed vague sentence Corrected grammar, spelling, and punctuation errors Added citation Abbreviation of et al. remained APA pg 175-177 Corrected grammar and article errors Removed italics