Introduction
Electronic health records (EHRs) are becoming more popular in medical institutions due to their ability to make information more accessible across different departments and facilities. They standardize data such as medication orders, reducing confusion and allowing for transparency in treatments. Computerized provider order entry (CPOE) systems are employed for drug requisitions, but they show some drawbacks. Clinical decision support systems (CDSSs) are designed to help resolve some of the concerns by offering medical workers assistance during medication and dosage selection based on the patient’s data. This paper proposes the implementation of a CDSS to supplement a CPOE system for propofol at a practice site.
Propofol and Its Issues
Propofol is an essential anesthetic drug that has been discovered relatively recently but sees widespread use, particularly in surgery and intensive care. Fan et al. (2015) discuss the variety of beneficial traits of the medication that makes it a popular choice, particularly its applications for neurosurgery. Research into the effects of propofol is still ongoing, and its full consequences remain unknown for the present. Overall, the drug is generally believed to be safe for use and is, therefore, employed by many specialists. However, recent incidents suggest that it may exhibit dangerous characteristics when applied to specific populations, such as children.
Infants, particularly critically ill ones, are a vulnerable group that can be affected by a variety of complications. Shimizu et al. (2019) discuss the propofol infusion syndrome, a condition with a high mortality rate that rarely occurs in patients, both young and adult, after a propofol sedation. Their study does not identify the cause, but it suggests a maximum dosage that may be considered safe. Nevertheless, Shimizu et al. (2019) note that the use of propofol is discouraged in Japan as a result of a recent propofol infusion syndrome incident. Medical institutions across the world should take note of the condition and try to assign dosages with a high degree of caution, especially for children.
Design Development Rationale
The facility discussed in this paper employs propofol for anesthetic purposes, and its patient range includes children. A CPOE system is in place for drug requests, but according to Haddad et al. (2015), it is insufficient for improvement without protocols that consider patient factors, which may be described as a CDSS. There have not been any recent incidents that involved propofol, but an additional safeguard is a desirable addition. Whitehead et al. (2019) note that a test-based CDSS can improve the accuracy of prescriptions and treatments for drugs. As such, the facility should develop a supplement for its CPOE that recommends proper uses for propofol and, possibly, other medications.
Implementation and Adoption
The data on the causes of the propofol infusion syndrome is currently not detailed or verified with sufficient evidence to support the use of specific guidelines. However, propofol is a well-researched drug, and its general applicability conditions are known. Vaghela, Bhatt, and Mistry (2015) discuss various CDSS designs, and the neural network approach appears to be the most suitable. The ability to organically adapt to new data, such as incidents or further research, is a distinguishing trait of the design. As such, the system could be modified in the future without significant difficulty compared to other methods.
The medical workers at the facility in question already use a CPOE system, and the CDSS should be integrated into the framework. As described by Whitehead (2019), the application will review the prescription orders by a clinician and compare it against the patient’s data to identify missing tests and inappropriate medications or dosages. The adoption should not be accompanied with significant difficulty, as appropriate medication requests should occur mostly without outward change. Other institutions in the future may adopt the CDSS, allowing it to learn from higher numbers of cases. As a result, its accuracy can improve, and the system may gain value for researchers.
Potential Issues and Solutions
A neural network design may present challenges, as its decisions may not match those of qualified professionals due to considerations that may be difficult to identify. Medical workers would then be disinclined to use its judgments, considering them potentially incorrect or harmful. The issue can be partially resolved with adjustments to the system’s training that would make traditional approaches more likely to be used. However, the discrepancy may also present an interest to researchers, who can collaborate with information technology professionals to study the reasoning behind the machine’s decisions and test their efficiency in a controlled environment. Thus, the system can be used as a source of innovation and improvement.
Conclusion
Propofol is a well-known and popular drug that is used for anesthesia in surgery and intensive care worldwide. However, it may have potentially fatal side effects, especially when applied to critically ill children. Therefore, a dosage and selection control safeguard would be beneficial to medical institutions that use propofol. This paper proposes the implementation of a neural network-based clinical decision support system to supplement its computerized provider order entry framework. The adoption of the change should not be challenging to most personnel, and it may be expanded to other institutions. There may be concerns over the accuracy of the system, but it should be possible to resolve them and potentially learn from unusual decisions.
References
Fan, W., Zhu, X., Wu, L., Wu, Z., Li, D., Huang, F., & He, H. (2015). Propofol: An anesthetic possessing neuroprotective effects. European Review of Medical and Pharmacological Sciences, 19(8), 1520-1529.
Haddad, S. H., Gonzales, C. B., Deeb, A. M., Tamim, H. M., Al Dawood, A. S., Al Babtain, I.,… & Arabi, Y. M. (2015). Computerized physician order entry of a sedation protocol is not associated with improved sedation practice or outcomes in critically ill patients. BMC Anesthesiology, 15. Web.
Shimizu, N., Akiyama, L., Imai, K., Miyashita, N., Mizushiro, N., Ikeyama, T.,… & Watanabe, I. (2019). Pediatric metabolism after propofol infusion in a pediatric intensive care unit. Chiba Medical Journal, 95, 1-5.
Vaghela, C., Bhatt, N., & Mistry, D. (2015). A survey on various classification techniques for clinical decision support system. International Journal of Computer Applications, 116(23), 14-17.
Whitehead, N. S., Williams, L., Meleth, S., Kennedy, S., Ubaka-Blackmoore, N., Kanter, M.,… & Nichols, J. (2019). The effect of laboratory test–based clinical decision support tools on medication errors and adverse drug events: A laboratory medicine best practices systematic review. The Journal of Applied Laboratory Medicine. Web.