Decision Making Support Tools

Decision Making Support Tools

Clinical decision-making is a continuous, contextual and evolving process that entails making up one’s mind to facilitate the care that is being provided to the patients. The nurse collects data during the assessment to the patient, interprets the data and evaluates it to come up with an evidenced-based option, which turns to be the best choice of action (Musen, Middleton, & Greenes, 2014). In the process, a continuous framework that is used for the clinical decision making that is specific for the nurses is then developed to guide nursing practice. In the long haul, the quality and safety of care provided by the nurses are raised.

Clinical decision support tool is an application that allows analysis of clinical data to provide the healthcare team with easy avenues of making clinical decisions. This tool is an adaptation of the decision support system that is usually used to support various businesses (Berner, & La Lande, 2016). Various clinical decision support tools with some being simple, and others advanced have been integrated into the electronic health record systems.

Nurses use the clinical decision support tool to prepare the nursing diagnoses and to evaluate and review the outcome with the intention of improving the outcome in the condition at hand. They do this by carrying out data mining where they examine the patients’ history and records and compare it with various clinical researches to determine the prognosis of patients’ condition (Musen, Middleton, & Greenes, 2014). The analysis assists in predicting potential occurrences, which can entail drug interaction or disease symptoms. For instance after getting a history of swellings and hypothermia from a patient following a bee sting, a nurse can be cautious in administering penicillin while treating a bacterial infection to such a patient. This is so because the occurrence of hypersensitivity reaction happens when one is re-exposed to an antigen, which is familiar to the body. In this case, the patient had a bee sting, and the body formed specific antigens against IgE hence the exposure to such antigens such as penicillin has a high probability of developing antibodies, which will lead to the production of biological products leading to an allergic reaction.

In the above case, the nurse uses history to guide his or her practice while at the same time refers to research to get the information on what to expect while caring for the patient. In the end, the nurse gets ready to manage the condition since he expects the unusual occurrences of the allergic reaction. Besides, he will be able to observant in determining the symptoms that may occur after the penicillin administration hence safety to the patient being treated. Some nurses prefer to avoid the use or over-relying of the clinical decision support tool and instead base their care provision on the professional experience that they have gathered. This still falls under the informal clinical decision-making tool through its use is limited as one can only apply it in areas he or she has experience. The electronic system provides an opportunity for even the new practitioners hence reliable across the entire healthcare team.

There exist two main types of the clinical decision support tools.  One of the systems uses a knowledge base, which applies certain rule the data of the patient entered via the use of an inference engine and displays the outcome to the end user. The other type is one without a knowledge base, which relies on the machine learning to do the analysis of the clinical data.

The clinical decision support tool serves essential functions in providing care to the patients. With efficient use, the tool has increased the quality of care to patients, enhanced the health outcomes of the patients, have also assisted in reducing the medical errors as well as preventing the adverse drug reaction, lowering the cost of providing care as well as improvement of the provider and patient satisfaction with the services provided.

The nursing care has even been enhanced markedly since the tool provides alerts, notifications and credible care suggestions that when applied, the health outcome improves. The toll entails computerized alerts and reminders to both the patient and the healthcare providers. It also contains clinical guidelines for various nursing procedures as well as condition-specific order sets. Moreover, the clinical decision system tool contains focused patient data reports as well as summaries, diagnostic support for various conditions as well as contextual relevant reference information (Estrom et al., 2015). All these make the nurse to be equipped with all that may be needed to make a decision as well as carrying the processed aimed at improving the care of the patient.

An example of the application of this tool was during my working time in the burns unit and encountered an extensive burn. The tool guided me in the priority care that the patient was to receive such as the maintenance of fluid balance as well as keeping the environment warm for the patient. The tool also provided the guideline for the care of the burnt regions regarding the preferred fluid—normal saline to use in cleaning as well as the cream—silver sulphadiazine to apply to the sites. I was also able to get alerts on the derailed vital signs since the impaired skin integrity tampers with the hemodynamic balance of patients. I was also capable of determining the nursing diagnoses of the patient ranging from the risk of electrolyte balance, the risk of infection, the risk for hypothermia as well as pain and give direction on the interventions that I undertook to manage the situation. At the same time, the tool also guided the entire healthcare team in the medical management of patients and in the consideration of other interventions such as surgical management.

In the above example the tool, assisted me in guiding my care provision, diagnosing the nursing needs of the patient as well as giving me notifications on the derailment of the patient’s vital signs. All this led to a successful management of about 37 percent burn, which healed with no contracture or any other complication.

The healthcare providers using the electronic health records as well as applying the clinical decision support tool can enhance the patient care, get access to the patients chart remotely as well as alerting the nurse on the medical error or any derailment in the patients’ parameters essential laboratory values(Estrom et al., 2015). The system allows for better clinical benefits that originate from the provision of the recommended patient care, ordering of the appropriate tests and drugs as well as facilitating patient communication. The experience in using the system is also significant in caring for various patients presenting with various clinical conditions.

The clinical decision support tool enables the nurses to be guided in all they do in an ideal manner with instances of dilemma prevented. The tool serves to make care provision universal in the manner of provision as well as maintaining high-quality care. With this in mind, I will be able to incorporate the use of the system in guiding my practice to ensure the ideal procedures are maintained together with providing quality care that is safe to all the patients that I will be serving.




Algaze, C. A., Wood, M., Pageler, N. M., Sharek, P. J., Longhurst, C. A., & Shin, A. Y. (2015).

Use of a checklist and clinical decision support tool reduces laboratory use and improves

cost. Pediatrics, peds-2014.

Berner, E. S., & La Lande, T. J. (2016). Overview of clinical decision support systems. In

Clinical decision support systems(pp. 1-17). Springer International Publishing.

Ekstrom, H. L., O’Connor, P. J., Margolis, K. L., Rush, W. A., Amundson, G. H., Appana, D.,&

Sperl-Hillen, J. M. (2015). Evaluation of Provider Experience With an Electronic Health

Record-Based Clinical Decision Support Tool. Journal of Patient-Centered Research and

Reviews, 2(2), 118.

Musen, M. A., Middleton, B., & Greenes, R. A. (2014). Clinical decision-support systems. In

Biomedical informatics (pp. 643-674). Springer London.