Technological Impacts on Triaging Patients
Sorting of patients as a matter of clinical urgency defines medical triaging. Burgess, Kynoch, and Hines, 2019 describe triage as the procedure by which Emergency Departments (EDs) grade patient presentations for medical care. This ranking, however, takes place such that treatment is offered to the patients who need it most and have the highest likelihood of recovery. In so doing, hospitals ensure they are running their practices most cost-effectively while offering quality healthcare. Research links this practice to how medics handled injured soldiers during World War One. Due to the limitation of medical equipment and personnel in military environments, such soldiers got grouped into three groups. For optimum outcomes, the groupings included those who could survive without immediate medical care, those who would survive only with medical aid, and those who were likely to die even with healthcare.
The healthcare field has seen significant developments and improvements due to the ever-growing technological advancements. As a result, numerous changes are continually getting adapted by triage nurses. This paper aims at summarizing some of the impacts that technology has had on triaging of patients in EDs. For specification and relatability, we focus on common patient groups, including those dealing with heart failure and brain cancer. Also, the paper addresses other impacts that technology has caused in the general patient triage procedures.
Radio Frequency Identification
Radio Frequency Identification (RFID) is a handy tool in patient triaging. Thapa et al., 2017 engages an informative literary piece that documents some of the advantages pegged to the use of RFID. Overcrowding is a common challenge experienced by most EDs in the world. The integration of this piece of technology gets linked to significant de-crowding in several waiting rooms and emergency departments of several Australian hospitals. The incorporation of RFID systems in hospitals aids in remotely monitoring and measuring the length of stay and the frequency of which a patient visits the hospital. Such factors are useful in determining which patient is up next for consultation or may have an undetected, yet pressing medical issue, respectively. Similarly, the RHID technology is useful in the study of ambulance behavior and pick-up locations, including road accidents or fire accident sites. If nurses have prior knowledge of possibly being the recipient of an emergency ambulance, they can prepare and optimally triage the patients upon arrival.
Remote Dielectric Sensing
In his Journal of Cardiac Failure, Curran et al., 2018 advocate for increased incorporation of the Remote Dielectric Sensing (ReDS) technological systems for heart failure (HF) patients. For many HF patients and related hospitals, readmissions are a common occurrence. However, the use of the ReDS system in most EDs where triage decisions occur results in impeccable results. This FDA-approved device allows clinical officers to quickly and accurately measure lung fluid for HF patients. Levels of lung fluid are vital when triaging HF patients. Traditionally, this practice is a time-consuming and delicate process. As a result, only RNs and seasoned medical practitioners were capable of performing it. However, with technological improvements and, therefore, the introduction or ReDS, this operation is easier and cost-effective. Today, triage nurses can non-invasively perform this procedure and decide who among the HF patients at a given point in time requires immediate medical attention.
Dynamic Grouping and Prioritization algorithm
Most emergency departments in hospitals are overcrowded due to the increase in health issues, especially in industrialized states. Too many people at the EDs make it cumbersome to triage, and hence heightening the possibility of negative medical outcomes. This significant rise in the number of patients in hospitals causes a strain on common and traditional triage algorithms, such as the Emergency Severity Index (ESI). Ashour and Kremer (2016) suggest that the use of modernized triage algorithms allow for the rapid sorting and classification of patients according to the acuteness of their medical states. For instance, Group Technology (GT) has largely aided the development of the Dynamic Grouping and Prioritization (DGP) algorithm. The DGP can efficiently identify common case groups and grade them according to the system triage criterion. Various surveys show that in comparison to the ESI, the DGP outperforms in terms of shortening a patient’s time to bed (TTB) and length of stay (LOS). Technologically advanced triage algorithms remove the possibility of under or over triage, either of which has detrimental aftermaths.
Attenuated Total Reflection- Fourier transform Infrared
Butler et al., 2019 believe that non-symptomatic critical illnesses are some of the leading causes of mortality in hospitals. Triage nurses may, at times, dismiss critically ill individuals for not showing any related symptoms. According to Butler, non-specific symptoms and expensive triage procedures contribute to an increase in poor prognosis and time-to-diagnosis, especially in patients of brain cancer. The Attenuated Total Reflection (ATR)- Fourier Transform Infrared (FTIR) is a diagnosis spectrography for brain tumors. The development, testing, and use of this medical equipment get entirely owed to the great milestones in technological advancements relating to the medical field. The ATR-FTIR is a powerful diagnostic and triage tool that significantly reduces the time a potential brain cancer patient takes in the ED. This tool allows triage nurses to interrogate brain serum for top-notch diagnostics non-invasively. This system is capable of taking a comprehensive snapshot of the human brain and efficiently prioritize brain cancer patients in order of medical urgency.
Out Of House-Telephone Triage
Graversen et al., 2019 writes on the positive result of adaptation if telephone triage. In cases of minor healthcare needs, patients can remotely contact their healthcare providers through telephone services. Years of improvements and modifications of this system ensures its safety, reliability, and efficiency. Continued use of Out Of House (OOH) – Telephone Triage (TT) justify and defend its quality relating to healthcare. Through this system, triage nurses and personnel can determine whether or not an individual needs to check into a medical facility. The offering of such services remotely, or away from the hospital ensures a healthy regulation of operational costs and patient capacity, hence maximum outcomes. OOH-TT has largely aided in managing the ever-increasing workload for triage nurses. Also, several medical centers agree that this possibility of performing triage remotely prevents frequent hospital overcrowding, which is both a health hazard and a cause of nurse burnout.
Machine Learning
Machine learning (ML) is one of the most invaluable creations of technology in the world today. This skill produces brilliant results in any sector where it is applied. In medicine, machine learning is capable of predicting disease status from spectral data or information. Primarily, a computer program, software, or model is built and exposed to a known dataset then taught how to respond for varied results. This way, such models can detect illnesses and contribute to finding cures for diseases. According to Yan et al., 2019 manual triaging results in under or over triage due to unavoidable human errors. Human error is among the leading causes of adverse patient outcomes worldwide. The health sector, therefore, has incorporated machine learning in several medical procedures such as patient triaging. ML is useful in reducing physical triage workloads and assisting in clinical decision making relating to triaging. Through the use of ML, there is a notable improvement in the outcomes of patient triaging. According to Yan, the potential of machine learning could as well be the most significant breakthrough in procedures involving the triaging of patients.
Works cited
Ashour, Omar M., and Gül E. Okudan Kremer. “Dynamic patient grouping and prioritization: a new approach to emergency department flow improvement.” Health care management science 19.2 (2016): 192-205.
Burgess, Luke, Kathryn Kynoch, and Sonia Hines. “Implementing best practice in the emergency department triage process.” International journal of evidence-based healthcare 17.1 (2019): 27-35.
Butler, Holly J., et al. “Development of high-throughput ATR-FTIR technology for rapid triage of brain cancer.” Nature communications 10.1 (2019): 1-9.
Yan, Sam, et al. “Technology Road Mapping of Two Machine Learning Methods for Triaging Emergency Department Patients in Australia.” Proceedings of the 2019 International Conference on Pattern Recognition and Artificial Intelligence. 2019.
Curran, Lisa, et al. “Use of ReDS Technology to Triage Heart Failure Patients in the Emergency Department.” Journal of Cardiac Failure 24.8 (2018): S49.
Thapa, Rajip Raj, et al. “Use of Radio Frequency Identification Technology in Reducing Overcrowding at Hospital Emergency Departments.” (2017).
Quality of out-of-hours telephone triage by general practitioners and nurses: development and testing of the AQTT – an assessment tool was measuring communication, patient safety, and efficiency; Retrieved from https://www.tandfonline.com/doi/pdf/10.1080/02813432.2019.1568712 on 14/04/2020.