Emergency room visits in the United States total approximately 130 million yearly.¹ This, combined with the fact that there are approximately 40 emergency department (ED) visits per 100 people in the US and 70% of these patients spend over 2 hours in the ED,¹ makes efficient triaging essential. Patient triage is used especially in emergency medicine to organize patients by injury and/or illness severity and to instruct providers on who to treat first.² Triage is done in both pre-hospital settings by emergency medical services (EMS) providers and in-hospital settings by nurses and physicians, and digital innovations are emerging  as a crucial part of this patient care. Typically, triage involves face to face interactions between patient and provider, including taking vitals, asking questions about the injury, and relaying information to other medical personnel.³ However, digital health interventions such as artificial intelligence, machine learning technologies, wearable devices and tele-triage, are emerging to alleviate heavy patient traffic in emergency situations.

Artificial intelligence (AI), and in particular machine learning (ML), have already been used throughout patient care in the medical field, prominently in the analysis of medical imaging and clinical decision support.⁴ Throughout the pandemic, however, AI has been increasingly developed and researched for multiple additional medical applications, including patient triage.^4-9 Specifically, AI and ML systems use data to predict critical care needs and the chances of hospital admission along with other important outcomes, such as mortality.^5,6 AI and ML could also be used in emergency settings to determine or predict specific outcomes or diagnoses. For example, some researchers are aiming to develop ML interfaces that can identify sepsis and cardiac arrest with more accuracy than current, more traditional methods.^8,9 These studies, though preliminary, assert that systems using AI and ML can identify these specific diagnoses more accurately than traditional methods, which could lead to early identification of high-risk outcomes in the emergency department.^8,9 Artificial intelligence and machine learning programs are emerging innovations that can be applied to aid in triage in the emergency department, with researching showing strong signs of efficacy, accuracy, and adaptability.⁵

Wearable technology (e.g.,  FitBit, Apple Watch, Amazon Halo) is a very popular digital health option among general US consumers, and the ability to interface directly with physicians and nurses through wearables is already being developed.¹⁰ Patient triage through wearables is a relatively new innovation, and since monitoring a patient's vital signs should ideally be continuous in emergency care settings, these devices are exciting options. One Australian study’s wearables accurately detected respiratory and cardiovascular events in patients, suggesting a promising future for “hands-free monitoring devices” to help triage in emergency care settings.¹¹ In addition to hospital applications, wearable technology can also be used by EMS providers before patients get to the hospital. For example, researchers in Indonesia found efficacy in a low-cost device that works in conjunction with a mobile device to aid first responders to triage in mass casualty incidents by showing them continuous basic vitals (e.g., heart rate, oxygenation level, and respiratory rate).¹² Wearable monitors to aid in triage are being studied around the world, and are inexpensive options to aid healthcare providers in both pre-hospital and hospital settings.

A final route for digital health innovations to assist in patient triage is through telehealth, which has increased dramatically since the outbreak of COVID-19 and has improved equitable access to healthcare.^13,14,15 Specifically, one CDC study on health centers disclosed that roughly one-third of visits to health centers between June and November of 2020 occurred via telehealth.¹³ Telehealth became a common practice for primary care providers, but the need for modified patient-care practices went beyond annual visits and prompted emergency departments to explore various virtual health solutions.¹⁴ One of these solutions was tele-triage, where ED providers virtually performed their screening while the patient was isolated in another location.¹⁴ This solution, although mostly a temporary fix brought on by the unique nature of the pandemic, may be adapted further to be used in situations where isolation is necessary, such as treating other infectious diseases or awaiting laboratory results. Additionally, a British study performed by the National Health Service found that video-triage was safe, effective, and had higher patient and clinician satisfaction than the traditional tele-triage option typically used by ambulance emergency responses, suggesting potential  EMS implementations as well.¹⁵ Although telehealth may come with technical problems, these innovations are effective and with further research could be easily implemented into triage systems in emergency rooms across the country and world.¹⁵

Over the past decade, tremendous research and innovation on digital health technologies and interventions has been done. While digital assistance on patient triage is novel and has been explored mainly outside the US, promising preliminary results suggest that AI, ML, wearables, and tele-triage are good options for reducing hospital wait times, speeding up accurate diagnoses, and prioritizing injuries in a variety of healthcare settings. Assisting providers with triage, which is a stressful and time-consuming part of their job, is paramount to improving patient care in the emergency department. Further studies of triage systems are sure to come and this is an exciting application of digital technologies to assist providers and patients alike. 

References

1. Cairns C., Kang K., Santo L. (2018). National Hospital Ambulatory Medical Care Survey: 2018 emergency department summary tables. National Center for Health Statistics. https://www.cdc.gov/nchs/data/nhamcs/ web_tables/2018_ed_web_tables-508.pdf.
2. Yancey, C. C., & O'Rourke, M. C. (2021). Emergency department triage. In StatPearls [Internet]. StatPearls Publishing.
3. Understanding the triage process in our emergency department. (2019, April 25). UPMC Western Maryland. https://www.wmhs.com/understanding-the-triage-process-in-ER
4. Artificial Intelligence in Medicine | IBM. (n.d.). Retrieved August 15, 2022, from https://www.ibm.com/topics/artificial-intelligence-medicine. 
5. Liu, Q., Yang, L., & Peng, Q. (2022). Artificial intelligence technology-based medical information processing and emergency first aid nursing management. Computational and Mathematical Methods in Medicine, 2022, 1–9. https://doi.org/10.1155/2022/8677118 
6. Sánchez-Salmerón, R., Gómez-Urquiza, J. L., Albendín-García, L., Correa-Rodríguez, M., Martos-Cabrera, M. B., Velando-Soriano, A., & Suleiman-Martos, N. (2022). Machine learning methods applied to triage in emergency services: A systematic review. International Emergency Nursing, 60, 101109. https://doi.org/10.1016/j.ienj.2021.101109 
7. Salman, O. H., Taha, Z., Alsabah, M. Q., Hussein, Y. S., Mohammed, A. S., & Aal-Nouman, M. (2021). A review on utilizing machine learning technology in the fields of electronic emergency triage and patient priority systems in telemedicine: Coherent taxonomy, motivations, open research challenges and recommendations for intelligent future work. Computer Methods and Programs in Biomedicine, 209, 106357. https://doi.org/10.1016/j.cmpb.2021.106357
8. Lin, P.-C., Chen, K.-T., Chen, H.-C., Islam, Md. M., & Lin, M.-C. (2021). Machine learning model to identify sepsis patients in the emergency department: Algorithm development and validation. Journal of Personalized Medicine, 11(11), 1055. https://doi.org/10.3390/jpm11111055
9. Tsai, C. L., Lu, T. C., Fang, C. C., Wang, C. H., Lin, J. Y., Chen, W. J., & Huang, C. H. (2022). Development and Validation of a Novel Triage Tool for Predicting Cardiac Arrest in the Emergency Department. The western journal of emergency medicine, 23(2), 258–267. https://doi.org/10.5811/westjem.2021.8.53063
10. Krummel, T. M. (2019). The rise of wearable technology in health care. JAMA Network Open, 2(2), e187672. https://doi.org/10.1001/jamanetworkopen.2018.7672
11. Polley, C., Jayarathna, T., Gunawardana, U., Naik, G., Hamilton, T., Andreozzi, E., Bifulco, P., Esposito, D., Centracchio, J., & Gargiulo, G. (2021). Wearable bluetooth triage healthcare monitoring system. Sensors, 21(22), 7586. https://doi.org/10.3390/s21227586
12. Niswar, M., Wijaya, A. S., Ridwan, M., Adnan, Ilham, A. A., Sadjad, R. S., & Vogel, A. (2015). The design of wearable medical device for triaging disaster casualties in developing countries. 2015 Fifth International Conference on Digital Information Processing and Communications (ICDIPC), 207–212. https://doi.org/10.1109/ICDIPC.2015.7323030
13. Demeke, H. B. (2021). Trends in use of telehealth among health centers during the covid-19 pandemic—United states, june 26–november 6, 2020. MMWR. Morbidity and Mortality Weekly Report, 70. https://doi.org/10.15585/mmwr.mm7007a3
14. Uscher-Pines, L., Sousa, J., Mehrotra, A., Schwamm, L. H., & Zachrison, K. S. (2021). Rising to the challenges of the pandemic: Telehealth innovations in U.S. emergency departments. Journal of the American Medical Informatics Association, 28(9), 1910–1918. https://doi.org/10.1093/jamia/ocab092 
15. Bell, F., Pilbery, R., Connell, R., Fletcher, D., Leatherland, T., Cottrell, L., & Webster, P. (2021). The acceptability and safety of video triage for ambulance service patients and clinicians during the COVID-19 pandemic. British Paramedic Journal, 6(2), 49–58. https://doi.org/10.29045/14784726.2021.9.6.2.49