Clinical Decision Support System

CRITERIA: Integrating Computerized physician order entry as a CDSS

The paper should include 7 – 8 pages of content (excluding title page and reference list – abstract is not required) and address all of the following criteria.
Clinical decision support system (CDSS) Description (25 points):

Describe the problem (the difference between a perceived condition and a desired condition) the computerized CDSS is being considered or currently used to solve in the health care setting of your choice. Include background information and rationale as to why this CDSS was selected to solve the problem.
Explain the functional components and structures of the CDSS.
Include:

vendor name and location on the Web
systems architecture/configuration and how it works
Analyze market penetration/saturation and provide evidence with response. Assess whether the CDSS supports advanced nursing practice decision making by specifying the objectives and key decisions to be supported by the CDSS

Organization Utilization of CDSS (30 points):

Identify the health care setting in which the CDSS is being used as well as potential areas of expansion.
Describe the organizational stakeholders who will purchase, influence, or champion the product’s implementation and ongoing support. Discuss any problems encountered at the agency with regards to:

Positions held in the organization.
Scope of their authority to make decisions regarding the CDSS.
Role these people have in the identification of the problem.

Describe the organizational end user who will be impacted by the implementation of the product and how support for adoption will be garnered.
Predict how the CDSS will integrate into existing clinical workflow.

Include:

Risks
Benefits

Technical Implications of CDSS (25 points):

Identify the required and optional data and data sources used for the CDSS.
Describe the integration points of the software.
Appraise the deployment model and its risks and benefits.

Scholarly Writing & Evidence (10 points each):

The paper is limited to 7-8 pages (excluding the title page and references) and must reflect APA 7th edition standards for formatting (e.g., title page, 2-level headings, references, grammar, punctuation, mechanics, usage) and writing consistent with Standard American English. Be sure to include the requirements outlined in the scoring rubric.

*Scholarly articles integrated within the paper should come from the most current nursing or related literature (published no more than 7 years ago), but may be older if a seminal source or where there is a gap in the literature; at least one reference used within the paper should come from a discipline outside nursing. Minimum of 10 references required.

ANSWER

Clinical Decision support System

Describe the problem (the difference between a perceived condition and a desired condition) the computerized CDSS is being considered or currently used to solve in the health care setting of your choice. Include background information and rationale as to why this CDSS was selected to solve the problem.

Medical errors have been observed to be costly, both in terms of human life and money. Research has that medical errors are responsible for more life losses than breast cancer, HIV/AIDs, and road accidents combined (Kruk et al., 2018). Medical errors increase healthcare costs, threaten healthcare quality, and contribute to the crisis of medical malpractices. For instance, without the CDSS, most healthcare providers’ decisions are made during the times they interact with the patients on a personal level. The interaction is mostly during the ward rounds or at multidisciplinary meetings, meaning the professional’s medical decision will entirely depend on the short period of interaction. Eventually, the medical staff capitalizes on the observations presented by the professional in that short time. The medical professionals are considered to be knowledgeable and experienced; thus, their decisions are rarely disputed.

Further, it is observed that healthcare providers perceive a patient in the state they are currently and often overlook the changes within a normal range, like the patient’s condition before they got to the hospital. It is important to note that the initial error is a probable wrong diagnosis that invites an incorrect prescription. However, improper prescriptions can stand out as an independent medical error; even with the correct diagnosis, there is a possibility that a healthcare provider can give the wrong medication.

However, a computerized CDSS responsible for the diagnosis will not miss a detail. The medication-related DCSS considers all available data and can note all changes within a given limit for a specific patient. The system involves various interventions to improve clinical decision-making processes and ensure medical safety from all medical perspectives. It comes out as a necessary tool to achieve the benefits of electronic health records (EHRs) and physician order entries (CPOEs) to maximum levels. The medication-related CDSS makes it possible to notice the slightest alterations within the professional scope and any changes noticed on a given patient (Matos et al., 2020). It helps the physician to pick out the correct drug and provide it in the right dosage. However, having all patient data in the digital form does not necessarily translate to improved patient care. For starters, not all patients have their data in the EHRs. Also, it is possible that some healthcare providers are not capable of accessing the information in the EHR, or they are not up to date with current medical insights. The e-prescribing system benefits everybody associated with matters of patient care in a hospital. All the involved parties need to have an assurance that the e-prescribing system is reliable with its information.

The functional components and structures of the CDSS

According to Sutton et al. (2020), Kunhimangalam et al. created the medication-related diagnostic CDSS. It puts into use over 20 input fields, including diagnostic test outputs and symptoms. It is offered by the top-rated CDSS vendor called First Databank. First, Databank sends alerts to the current application, which serves as information to the physicians. The CDSS contains a highly skilled communications engine that is important to access desperate patient data. Disease management is facilitated by an optimized patient database where enough diagnostic information can be gathered from a modular knowledge base. Further, it contains a highly effective inference engine, which helps accelerate decision making. The CDSS provides a guideline for the physicians to follow, making it easier for them to make crucial decisions. The CDSS minimizes variations during the diagnostic process of a patient making the diagnostic process less complicated. 

Market penetration/saturation and provide evidence with a response. Assess whether the CDSS supports advanced nursing practice decision making by specifying the objectives and critical decisions to be supported by the CDSS

Implementing the clinical decision support system is receiving a lot of support from the government and initiatives. On the other hand, the growing rate of medical error incidences also contributes to the high growth of the market of the CDSS. Healthcare is on the verge of fully adopting cloud computing in healthcare due to rising prominence, big data access, and electronic health tools. It is estimated that the clinical decision support systems market is expected to grow by a whopping 12% by 2023 from the statistics carried out in 2018 (Karaca, Moonis, Zhang & Gezgez, 2019).

The diagnostic CDSS aims at improving patient outcomes and supporting nursing practices. It facilitates the conversion of patient data to information, which will help the nurse to try to better the patient’s condition. It is important to note that nurses who rely most on the CDSS are usually the less experienced ones. The professional nurses are observed to use the CDSS less often. However, in some situations, the nurse may ignore the recommendations suggested by the CDSS if they feel their judgment or the advice from their workmate is more appropriate for the current situation. Also, the alerts that keep coming to the systems sometimes come out as destruction to the nurses, discouraging interactions. As much as the CDSS offers support regarding decision-making, sometimes, the system has a few areas that need addressing to make the system complete.

Organization Utilization of CDSS 

Health care setting in which the CDSS is being used as well as potential areas of expansion.

Currently, diagnostic CDSS is being used in a hospital setting. It works for both in-patient and out-patient patients. The diagnostic CDSS is used to diagnose a patient’s condition and give a proper prescription for the patients. Depending on the symptoms displayed and the diagnosis given by the CDSS, the healthcare providers are in a better position to decide whether to admit the patient or treat them on an out-patient basis. The hospital and the healthcare providers get the jobs simplified by the diagnostic CDSS, and medical errors are minimized. On top of that, patients who visit the facility are beginning to trust the CDSS to handle the medical problems from diagnosis to prescription.

Another health care setting where the diagnostic CDSS is applicable is at the nursing home facilities. Nursing homes also require qualified nurses and nursing aides, making the diagnostic CDSS a necessity at most nursing homes. It is possible that the people being hosted in the nursing homes develop a complication (Zhang et al., 2016). It is essential in the nursing home as it can handle some of the difficulties, which are not complicated; otherwise, complex situations should be referred to a hospital. It is the job of the diagnostic CDSS to determine which cases need more attention and can be taken to more advanced facilities like hospitals. Issues that do not seem complicated can be given prescriptions with the help of the CDSS and be taken care of within the nursing home facility. Other healthcare settings where the CDSS can work are mental health facilities and dispensaries.

Organizational stakeholders who will purchase, influence, or champion the product’s implementation and ongoing support. Discuss any problems encountered at the agency with regards to:

The hospital setting’s primary stakeholders are physicians, patients, employers, pharmaceutical companies, insurance companies, and the government. These are the entities that would be positively affected by changes within the facility, for example implementing the diagnostic CDSS. The employers and physicians are responsible for ensuring their patients are receiving good healthcare without being exploited financially. The physicians are an intermediary of everything and often come out as the patients’ advocate (Ahluwalis et al., 2016). They have the upper hand at deciding if implementing the CDSS will benefit the facility and improve the quality of healthcare provision or not. The government will, in most cases, come in to give financial support. It leaves it up to the physicians to decide if it is essential because they are the professionals. Because the CDSS is considered cost-effective, implementation seems like an important step to take.

How the CDSS will integrate into existing clinical workflow.

Risks

CDSS is entirely dependent on computer literacy. Technical proficiency is essential in engaging the CDSS. The diagnostic CDSS comes out as problematic and depends a lot on the user skills. It becomes critical to evaluate the user’s technical competence before assigning them, or the facility should organize training sessions to ensure competence. The CDSS further requires maintenance. The systems, applications, and databases that power the CDSS demand constant technical maintenance (Baig et al., 2017). The continually changing clinical guidelines and nature of medical practices also require equally regular maintenance of the knowledge base and the rules that come with it.

Another risk involved in low-quality data and incorrect content. The EHRs, for example, depend highly on data from external and dynamic systems. For instance, the diagnostic CDSS may demand ordering supplies even when the hospital supplies are not enough. Problem lists and medication need to be continuously updated, and that information used appropriately. In cases of not designed systems, the users may develop workarounds that may compromise data like entering incorrect data. Quality of data is bound to impact the quality of decision support. The data becomes corrected when the data collection or process of inputting information is not up to standard.

Benefits

The CDSS is expected to reduce the risk of occurrence of medical errors. Determining the correct medication and prescribing the right doses is an essential part of health care provision. The CDSS ensures accurate medication information and calculators responsible for calculating amounts are accessible within the clinical workflow, thus minimize the risk of errors. On the same note, the degree of misdiagnosis in the hospitals is reduced by the CDSS because diagnosis is no longer made by the direct eye (Weant, Bailey & Baker, 2014). The common reasons for misdiagnosis include provider bias, cognitive errors, and diseases that are not common. When a diagnosis is not evident during a care crisis, healthcare professionals can employ diagnostic CDSS as a helper to identify the possible diagnosis.

Another benefit of this CDSS is that it improves the efficiency of the facility and patient throughput. The CDSS is responsible for ensuring the entire team is provided with reliable and consistent (Belard et al., 2017). Arming the healthcare providers with reliable resources ensures that the data used in clinical decision making can be counted on. The CDSS is further incorporated into the provider’s workflow, such that alert fatigue is minimized. All medical information required by healthcare providers can be accessed in one place. As a result, it reduces the need for having multiple logins and extra resources.

Technical Implications of CDSS

Identify the required and optional data and data sources used for the CDSS.

The most vital data source of the CDSS is HER. The CDSS capitalizes on the data stored in EHRs to determine the health history, for example. Apart from the medical history, the HER contains information on the treatment plans, vital signs of the patient, immunizations and immunization dates, radiology images, and test results, among other functionalities (Klein, 2019). These functionalities and data that the EHR encompasses are essential for the operations of the CDSS. For instance, giving out information about a patient’s history with medications and their allergies makes it easier for the CDSS to prescribe appropriate drugs. For example, the CDSS will ensure prescribing medications that the patient is not allergic to.

Apart from EHRs, the other optional data source for health information about a patient is claims data. Private and public medical insurers collect client’s data; these data consist of information like the demographics, insurance coverage, and copayments. It also contains the healthcare provider data and treatment details that show procedures and hospitalizations the patient has had. The insurance companies use these data for tracking health services, evaluating coverage, and managing payment. The CDSS can make use of information like these to carry on its operations smoothly. Other sources of data that the CDSS can capitalize on include the patient surveys, patient records, and the databases through which healthcare bills are met.

Describe the integration points of the software

The software’s integration points include the base. The bases are the rules that are organized into the system. It also included the algorithm that an organization uses to model the decisions and the available data. Secondly, the software has an inference engine. The engine helps by taking the programmed and organized rules and the data structures and applies them to the clinical data of the patient (Greens et al., 2018). After this, the information is applicable in the generation of the necessary action or output. The generated needed action is given to the physician. The third point of the software is its communication mechanism. Communication occurs through the website, HER fronted interface, or an application. The end-user, i.e., the physician, interacts with the system. For example, the physician receives the needed action via the communication mechanism.

 Appraise the deployment model and its risks and benefits

The deployment model is a pro forma model. A pro forma is a report containing a company’s earnings, and it excludes nonrecurring transactions (Christensen, Drake & Thornock, 2014). The model shows the expected results of the proposal’s trades. However, it emphasizes more on the cash flow, net revenues, and taxes. The approach uses both the declarative and formal techniques in modeling the procedural and logical features of tools availability and clinical decision-making. With the method, one may use argumentation logic, for example, reasons supporting and reasons against a particular decision instead of probability.

The principal risks of this model are that, in most cases, it uses nothing but a prediction. The disadvantage comes in because one may be off in one, if not all, the essential areas. Sometimes if one is out in just one place, the impacts on the company may be immense. Therefore, one should be careful when making their decisions with this model. The main advantage of this model is that it enables an organization to come up with a comparison between their historical data, and at the same time, create projections of their future performances.

References

Ahluwalia, S. C., Schreibeis-Baum, H., Prendergast, T. J., Reinke, L. F., & Lorenz, K. A. (2016). Nurses as intermediaries: how critical care nurses perceive their role in family meetings. American Journal of Critical Care, 25(1), 33-38.

Baig, M. M., GholamHosseini, H., Moqeem, A. A., Mirza, F., & Lindén, M. (2017). A systematic review of wearable patient monitoring systems–current challenges and opportunities for clinical adoption. Journal of medical systems, 41(7), 115.

Belard, A., Buchman, T., Forsberg, J., Potter, B. K., Dente, C. J., Kirk, A., & Elster, E. (2017). Precision diagnosis: a view of the clinical decision support systems (CDSS) landscape through the lens of critical

Christensen, T. E., Drake, M. S., & Thornock, J. R. (2014). Optimistic reporting and pessimistic investing: Do pro forma earnings disclosures attract short sellers?. Contemporary Accounting Research, 31(1), 67-102.

Greenes, R. A., Bates, D. W., Kawamoto, K., Middleton, B., Osheroff, J., & Shahar, Y. (2018). Clinical decision support models and frameworks: seeking to address research issues underlying implementation successes and failures. Journal of biomedical informatics, 78, 134-143. https://www.sciencedirect.com/science/article/pii/S1532046417302757

Karaca, Y., Moonis, M., Zhang, Y. D., & Gezgez, C. (2019). Mobile cloud computing based stroke healthcare system. International Journal of Information Management, 45, 250-261.

Klein Koerkamp, R. M. (2019). The road from analytical CDSS invention to implementation in healthcare (Master’s thesis, University of Twente).

Kruk, M. E., Gage, A. D., Joseph, N. T., Danaei, G., García-Saisó, S., & Salomon, J. A. (2018). Mortality due to low-quality health systems in the universal health coverage era: a systematic analysis of amenable deaths in 137 countries. The Lancet, 392(10160), 2203-2212.

Matos, A., Bankes, D. L., Bain, K. T., Ballinghoff, T., & Turgeon, J. (2020). Opioids, Polypharmacy, and Drug Interactions: A Technological Paradigm Shift Is Needed to Ameliorate the Ongoing Opioid Epidemic. Pharmacy, 8(3), 154.

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.

Weant, K. A., Bailey, A. M., & Baker, S. N. (2014). Strategies for reducing medication errors in the emergency department. Open access emergency medicine: OAEM, 6, 45. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4753984/

Zhang, N., Lu, S. F., Xu, B., Wu, B., Rodriguez-Monguio, R., & Gurwitz, J. (2016). Health information technologies: Which nursing homes adopted them?. Journal of the American Medical Directors Association, 17(5), 441-447. https://www.sciencedirect.com/science/article/abs/pii/S1525861016001286

To get your original copy of this completed paper, please Order Now