Dear Editor:
The emergency medical dispatcher (EMD) serves as a crucial link between individuals in need of emergency medical assistance and the emergency medical services (EMS) resource delivery system. Through their expertise and training, EMDs are able to accurately assess emergency situations, provide appropriate guidance over the phone, and dispatch the necessary EMS personnel to the scene. With adequate training, program management, supervision, and medical guidance, the EMD can accurately assess the caller's needs, choose an appropriate response approach, furnish relevant information to responders, and offer suitable assistance and guidance to patients through the caller. By diligently adhering to a written and medically approved EMD protocol, informed decisions regarding EMS responses can be made in a reliable, replicable, and fair manner (1, 2).
Artificial intelligence (AI) is the concept of a computer program that utilizes existing information to make decisions and enhances its performance based on accumulated experience. Machine learning (ML), a crucial aspect of AI, focuses on developing systems that learn from past data to create models for classification, clustering, or regression. ML algorithms excel at recognizing patterns in intricate datasets, making them valuable for interpreting outcomes and generating personalized clinical judgments (3). In recent years, advancements in AI have made a significant impact on various industries, and EMS is no exception. AI has the potential to revolutionize the way emergency medical dispatching is conducted, improving response times, accuracy, and ultimately, patient outcomes (4, 5).
AI has the potential to revolutionize how emergency calls are managed and responded to, ultimately improving the quality and efficiency of emergency medical care. Traditionally, EMS dispatching has relied on human operators to receive emergency calls, assess the situation, and dispatch appropriate resources. However, this process can be time-consuming and prone to human error, especially during high-pressure situations like out-of-hospital cardiac arrest when quick decisions are crucial (5). AI-driven dispatching systems, equipped with natural language processing and machine learning capabilities, can analyze and prioritize incoming emergency calls based on the severity and urgency of the situation. These systems can identify key information, such as location, symptoms, and available resources, and provide real-time recommendations for dispatching appropriate medical teams or resources (6). By leveraging AI, emergency call centers can optimize resource allocation, leading to faster response times and improved patient outcomes. AI algorithms can analyze historical data and ongoing trends to predict demand patterns, enabling better deployment of EMS units and reducing response time variability. Additionally, AI can assist in identifying potential cardiac events, strokes, or other medical emergencies by analyzing voice patterns or vital signs shared during emergency calls, facilitating early intervention and potentially saving lives (7, 8). ML system is able to recognize a higher proportion of out-of-hospital cardiac arrest (OHCA) cases within the first minute compared to human dispatchers. ML system has the potential to be a useful tool in emergency calls (9).
It is important to emphasize that while AI can improve emergency dispatching, it should always complement, not replace, the human element. Trained professionals will continue to play a critical role in decision-making and providing empathetic support during emergencies. AI should be seen as a powerful tool to enhance their capabilities rather than a substitute for their expertise. As AI continues to advance, it is crucial for emergency medical services and policymakers to embrace these technologies responsibly. Safeguards must be in place to ensure data privacy, transparency, and ongoing monitoring of AI systems to mitigate biases and ensure equitable emergency response (5, 6).
1. Conclusion:
The integration of AI in EMS dispatching has the potential to revolutionize emergency care by optimizing resource allocation, reducing response times, and ultimately saving lives. It is imperative that we invest in research, implementation, and ongoing evaluation to maximize the benefits of AI while upholding ethical guidelines and maintaining the human touch in emergency medical services.
2. Declarations:
2.1. Acknowledgment
None.
2.2. Author contribution
PE and KJ: Conception and design of the work.
PE: Drafting the work and revising it critically for important intellectual content and translation.
PE and KJ: Read and approved the final version and accountable for all aspects of the work.
2.3. Conflict of interest
The authors declare that they have no conflict of interest.
2.4. Funding and supports
This research received no specific grant from any funding agencies in the public, commercial, or non-profit sectors
25. Using artificial intelligence chatbots
Not used in this article.
References
- 1.Crabb DB, Elmelige YO, Gibson ZC, Ralston DC, Harrell C, Cohen SA, et al. Unrecognized cardiac arrests: A one-year review of audio from emergency medical dispatch calls. Am J Emerg Med. 2022;54:127–30. doi: 10.1016/j.ajem.2022.01.068. [DOI] [PubMed] [Google Scholar]
- 2.Dong X, Ding F, Zhou S, Ma J, Li N, Maimaitiming M, et al. Optimizing an emergency medical dispatch system to improve prehospital diagnosis and treatment of acute coronary syndrome: Nationwide retrospective study in China. J Med Internet Res. 2022;24(11):e36929. doi: 10.2196/36929. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 3.Ledziński Ł, Grześk G. Artificial Intelligence Technologies in Cardiology. J Cardiovasc Dev Dis. 2023;10:5. doi: 10.3390/jcdd10050202. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 4.Bajwa J, Munir U, Nori A, Williams B. Artificial intelligence in healthcare: transforming the practice of medicine. Future Health J. 2021;8(2):e188–e94. doi: 10.7861/fhj.2021-0095. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 5.Scholz ML, Collatz-Christensen H, Blomberg SNF, Boebel S, Verhoeven J, Krafft T. Artificial intelligence in Emergency Medical Services dispatching: assessing the potential impact of an automatic speech recognition software on stroke detection taking the Capital Region of Denmark as case in point. Scand J Trauma Resusc Emerg Med. 2022;30(1):36. doi: 10.1186/s13049-022-01020-6. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 6.Chenais G, Lagarde E, Gil-Jardiné C. Artificial Intelligence in Emergency Medicine: Viewpoint of Current Applications and Foreseeable Opportunities and Challenges. J Med Internet Res. 2023;25:e40031. doi: 10.2196/40031. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 7.Bohr A, Memarzadeh K. The rise of artificial intelligence in healthcare applications. Artificial Intelligence in healthcare: Elsevier. 2020:25–60. [Google Scholar]
- 8.Chang I, Lee SC, Do Shin S, Song KJ, Ro YS, Park JH, et al. Effects of dispatcher-assisted bystander cardiopulmonary resuscitation on neurological recovery in paediatric patients with out-of-hospital cardiac arrest based on the pre-hospital emergency medical service response time interval. Resuscitation. 2018;130:49–56. doi: 10.1016/j.resuscitation.2018.06.029. [DOI] [PubMed] [Google Scholar]
- 9.Byrsell F, Claesson A, Ringh M, Svensson L, Jonsson M, Nordberg P, et al. Machine learning can support dispatchers to better and faster recognize out-of-hospital cardiac arrest during emergency calls: a retrospective study. Resuscitation. 2021;162:218–26. doi: 10.1016/j.resuscitation.2021.02.041. [DOI] [PubMed] [Google Scholar]