- A new algorithm improves ADR detection through incorporating nurse observations and lab research data into EHR technology.
A recent study funded by the Korean Health Technology R&D Project, Ministry of Health and Welfare, and the Ministry of Food and Drug Safety found two new algorithms integrated in EHR technology can improve adverse drug reaction (ADRs) detection in patients and avoid negative health outcomes.
The two new algorithms, MetaLAB and MetaNurse, were designed by Korean researchers to replace CLEAR, the former algorithm intended for ADR detection using EHR technology.
Additional benefits of MetaLAB that were not possible through CLEAR include a meta-analysis technique normalized annually and improved patient-sampling and comparison-group creation. MetaNurse is designed to quantify symptoms only detected through bedside nurse observations which cannot be noted or determined in a lab.
Through integrating MetaLAB and MetaNurse algorithms into EHR technology, researchers have observed increased rates of accurate ADR detection in comparison to ADR detection possible through CLEAR.
Algorithms designed to detect ADRs through lab tests and raw data alone are not sufficient in surveying all symptoms.
Instead, the report states, “The present study demonstrates the symbiosis of laboratory test results and nursing statements for ADR signal detection in terms of their system organ class coverage and performance profiles.”
Combining physically detectable symptoms gained through nurse observation with lab test results optimizes ADR detection.
Because of the capabilities offered through EHR technology, it is possible to advance the functionalities presently available and widen the breadth of what EHRs are able to quantify.
Prescription, laboratory, and clinical information existing on EHR systems could potentially prove instrumental in launching a variety of studies regarding the surveillance of pharmaceutical drugs and technologies and their impact on patients. Thus far, monitoring ADR signals from lab results regarding certain medications has driven EHR-based pharmacovigilant studies. However, this approach has only been successful in evaluating a small faction of all drugs and ADRs. The new MetaLAB and MetaNurse algorithms seek to fill in the gaps previous algorithms have missed by combining insights gained from lab results and clinician narratives regarding observable symptoms into EHR technology.
Nurses reportedly play a much more vital role in discovering and reporting ADRs than both doctors and pharmacists. Therefore, their reports are imperative to ADR detection and have been prioritized as necessary to integrate into EHR technology to make EHR-based pharmacovigilance more useful.
The new algorithms were not only more effective in ADR detection, but more efficient in standardizing biomedical vocabularies to streamline EHR searches for users. Users can more easily search and compare clinical symptoms, signs, procedures, treatments, and test results indicative of adverse drug reactions. Easing the searching process for clinicians is quickens diagnosis and ultimately improves quality of care.
Observing the improved performance of these new algorithms in comparison to past means of detecting ADRs revealed a significant number of ADR signals that had previously flown completely under the radar under previous systems.
These updated algorithms show EHR technology holds potential to improve patient care more and more as the technology itself is updated, amended, and integrated with advanced algorithms.
Utilizing EHRs to improve patient care by providing a more comprehensive, timely, and accurate picture of a patient’s medical history and current symptoms is one of the primary prerogatives of the health industry moving forward. Improving EHR technology through algorithms designed to streamline the aggregation of useful, relevant data is another step toward optimizing existing technology to promote coordinated care.