Medications can control pain, manage high blood pressure and cholesterol, and help treat serious diseases like cancer. However, when a medication is not administered correctly, it can jeopardize the health and safety of the patient. According to a study published in JAMIA, researchers from the Cincinnati Children’s Hospital Medical Center have developed a real-time, automated detection system that identifies medication administration errors (MAE). This new system has the potential to significantly reduce medication errors and the health risks associated with them.
Researchers analyzed 116 MAEs from 10,104 medication administrations from January to April 2017. They found that the automated system detected MAEs with a sensitivity of 85.3 percent, whereas current practices demonstrated a detection sensitivity of only 4.3 percent. The automated system also had a positive predictive value (PPV) of 78 percent and has the potential to decrease the length of time that a patient is exposed to harm from 256 minutes to 35 minutes.
A Solution to a Continuing Problem
Despite the use of more advanced technology like electronic health records and smart infusion pumps in healthcare settings, MAEs continue to occur. According to the researchers who developed the automated system, 72 percent of the 116 MAEs observed were clinical errors that would have a negative impact on patients. Significant overdoses or underdoses accounted for 13 percent of MAEs. The automated system detected nearly 87 percent of clinical errors that would impact patients and 100 percent of serious dosage errors.
The automated system may also help prevent alarm fatigue, which occurs when healthcare professionals experience a high volume of false alarms, causing them to become desensitized. This can lead to longer response times and legitimate alarms being missed. Current error detection practices are more likely to cause alarm fatigue because they are resource-intensive, or they have low PPVs.
Yizhao Ni, lead author of the study, said that by using real-time technology, the automated system can reduce harmful exposure to medication errors, particularly for long-time intravenous medications and infusions. Ni also pointed out that the automated system is better able to analyze the dose adjustments made during dynamic medication processes, when medication errors are more likely to be made.
Like any new technology, the automated system is not perfect. It made 45 errors when detecting MAEs, 29 percent of which occurred because the system relied on clinician-documented feeding rates, which were not always updated. Researchers plan to fix this by integrating real-time feeding information from the smart infusion pumps. Twenty-seven percent of the errors were due to the system’s Natural Language Processing (NLP) component, which did not identify the correct information when text messages contained similar medications. The system’s learner module would be able to remedy this problem, said Ni. Finally, to fully evaluate the system’s performance in a clinical practice, it will need to be integrated in the clinical workflow.
Baltimore Medical Malpractice Lawyers at LeViness, Tolzman & Hamilton Advocate for Victims of Medication Errors
If a medication error has caused you to become injured or seriously ill, contact the Baltimore medical malpractice lawyers at LeViness, Tolzman & Hamilton. We will fight to secure the maximum financial compensation you deserve and ensure that your legal rights are protected. To schedule a free consultation, call us today at 800-547-4LAW (4529) or contact us online.
Our offices are located in Baltimore, Columbia, Glen Burnie, and Towson, allowing us to represent medical malpractice victims in Maryland, including those in Anne Arundel County, Baltimore County, Carroll County, Harford County, Howard County, Montgomery County, Maryland’s Western Counties, Prince George’s County, Queen Anne’s County, Southern Maryland, and the Eastern Shore, as well as the communities of Catonsville, Essex, Halethorpe, Middle River, Rosedale, Gwynn Oak, Brooklandville, Dundalk, Pikesville, Nottingham, Windsor Mill, Lutherville, Timonium, Sparrows Point, Ridgewood, and Elkridge.