Using Clinical Decision Support Tools to Improve Patient Care

March 21, 2018


By Erin Sherer, PA-C, RD

It is 2018 and, as you might have imagined, technology and medicine are integrated in ways unimaginable even a decade ago.  Of course, using technology is a regular part of most our personal lives, so it should be no surprise that it now plays such a prominent role in improving patient care.  However, with so much data (and so many data delivery options) available to clinicians, how can a practitioner confirm what is relevant and what is not? New journal articles come out daily, making it impossible to keep up with all of the recommendations and guidelines for disease management.  While it is important to stay abreast of current topics, keeping up with the changing severity indices (as well as all of the different equations and scores that can help guide patient care) takes time that working clinicians just do not have. That is where clinical decision support tools and medical calculators can be useful alternatives for first-person reading and review.  These tools can help reduce the variability in clinical care by providing clinicians with the most up-to-date medical evidence available, and provide the most efficient way to use precious "free" time.

For example, if a patient presents in the emergency room with chest pain, instead of combining all of the latest available research on my own, I can opt to calculate their "HEART Score" in addition to my normal practice (Backus, 2008).  The HEART Score helps predict a patient's 6-week risk for a major cardiac event. By using this tool, I can determine the patient's risk stratification which can guide their treatment. The HEART Score was originally developed by Six, Backus and Kelder et al (2008) and was tested in an emergency department setting in a cohort of 122 patients who presented with chest pain.  Since then, it has been validated several times and continues to outperform other clinical decision rules with regards to their ability to safely identify low risk patients with chest pain (Poldervaart et al, 2017).

Prior to booking a patient for surgery, I might augment my care regime by using the "POSSUM Score" to estimate operative morbidity and mortality risk.  POSSUM is an acronym for Physiological and Operative Severity Score for the enUmeration of Mortality and morbidity (Copeland, 1991). By using this tool, I can calculate a risk score to determine whether or not the patient would actually benefit from having surgery or not.  This tool was developed by Copeland and colleagues in a large study involving 1,372 patients who underwent elective or emergency surgery in the United Kingdom (Copeland, Jones, Walters, 1991). The tool has been validated in many studies since then (Sharrock, McLachlan, Chambers, Bailey, and Kirkby-Bott, 2017).

The care I provide can be broadened by utilizing the "APACHE II Score," which may be useful when evaluating patients in the intensive care unit (ICU).  That tool provides and estimate of ICU mortality and may be particularly helpful with discussing prognosis and care plans with family members (Knaus, 1985).  This tool was validated in a large prospective study involving 5,815 patients from 13 different hospitals (Knaus, Draper, Wagner, and Zimmerman,1985).

Additionally, many hospital systems and clinics have incorporated their own tools to improve patient care.  For example, many electronic medical record systems have features that can help improve patient care, such as: notifications for allergy alerts; medication interactions; hard-stops preventing clinician's from ordering antibiotics prior to ordering cultures; and hard-stops preventing clinician's from discharging patients prior to reviewing all test results.  It is likely that some of the clinicians in your practice or hospital system have also developed clinical pathways that can help provide guidance when you are unsure how to manage a patient with a condition.

It is important to note that not all clinical decision support tools are created equally, and some may not be useful for certain circumstances.  A study published in 2016 conducted by Bahm, Freedman, Guan and Guttman indicated that clinical decision tools used for diagnosing and treating acute gastroenteritis in pediatric emergency visits did not have an impact on admission or ED visits.  The large study involved 57,921 patients, which included 2,401 admitted patients and 55,520 discharged patients and took place over 3 years. The authors concluded that the presence of "ED clinical decision tools to promote guideline adherence does not seem to lower hospital admission rates for acute gastroenteritis" (p. 608). Additionally, they found that "encouraging the use of oral rehydration therapy at triage was associated with lower return visit rates but the availability of printed discharge instructions may encourage return visits" (p. 608).  This is important because despite our desire to stratify risk, we must remember that each patient is individual and our care must take that into consideration.

Additionally, there are limitations to using these technologies and advances.  There is a great deal of "provider mistrust" and "resistance coupled with the absence of clear guidance from regulatory bodies" which can further limit the use and potential of clinical decision support tools (Belard, et al, 2017, p. 261).  However; despite these challenges it is important to continue to develop tools that can improve patient care especially in areas of medicine and surgery that require complex and individualized decision-making.

Using clinical decision support tools in our medical and surgical practices can further encourage us to provide evidence-based care and to stay up-to-date on the latest advances even if we do not have the requisite time to peruse journals and read every case study.  This technology can also help us recognize when tests may be unnecessary and when patients may be able to avoid an unnecessary hospitalization. Clinical decision support tools can also help us personalize medicine by allowing us to assess an individual's risk for a particular procedure instead of just using population-based information to stratify risks. It will be especially important for PAs (and all clinicians) to become familiar with the most common calculators and apps available in order to enhance patient care.


Below is a list of useful medical calculators:

MDCalc: https://www.mdcalc.com/

DynaMed: http://www.dynamed.com/home/

UpToDate: https://www.uptodate.com/home/medical-calculators

Calculate by QxMD:  https://qxmd.com/calculate-by-qxmd



References:
Bahm, A., Freedman, S. B., Guan, J., & Guttmann, A. (2016). Evaluating the Impact of Clinical Decision Tools in Pediatric Acute Gastroenteritis: A Populationā€based Cohort Study. Academic Emergency Medicine, 23(5), 599-609.

Backus, B. (2008).  HEART Score, MDCalc. Retrieved from https://www.mdcalc.com/heart-score-major-cardiac-events

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 care. Journal of Clinical Monitoring and Computing, 31(2), 261-271.

Bookman K et al. Embedded Clinical Decision Support in Electronic Health Record Decreases Use of High-cost Imaging in the Emergency Department: EmbED study. AEM July 2017.

Copeland, G. P., Jones, D., & Walters, M. P. O. S. S. U. M. (1991). POSSUM: a scoring system for surgical audit. British Journal of Surgery, 78(3), 355-360.

Copeland, G. (1991).  POSSUM Score, MDCalc. Retrieved from  https://www.mdcalc.com/possum-operative-morbidity-mortality-risk

Knaus, W. A., Draper, E. A., Wagner, D. P., & Zimmerman, J. E. (1985). APACHE II: a severity of disease classification system. Critical Care Medicine, 13(10), 818-829.

Knaus, W. (1985).  APACHE II Score, MD Calc.  Retrieved from https://www.mdcalc.com/apache-ii-score

Poldervaart, J. M., Reitsma, J. B., Backus, B. E., Koffijberg, H., Veldkamp, R. F., Monique, E., ... & el Farissi, M. (2017). Effect of Using the HEART Score in Patients With Chest Pain in the Emergency DepartmentA Stepped-Wedge, Cluster Randomized TrialHEART Score in Patients With Chest Pain in the Emergency Department. Annals of Internal Medicine, 166(10), 689-697.

Sharrock, A. E., McLachlan, J., Chambers, R., Bailey, I. S., & Kirkby-Bott, J. (2017). Emergency Abdominal Surgery in the Elderly: Can We Predict Mortality? World Journal of Surgery, 41(2), 402-409.

Siedler, M. R., Allen, J. I., Falck-Ytter, Y. T., & Weinberg, D. S. (2015). AGA Clinical Practice Guidelines: Robust, Evidence-Based Tools for Guiding Clinical Care Decisions. Gastroenterology, 149(2), 493-495.

Six, A. J., Backus, B. E., & Kelder, J. C. (2008). Chest pain in the emergency room: value of the HEART score. Netherlands Heart Journal, 16(6), 191-196.