Artificial Intelligence in Emergency Medicine

Artificial Intelligence in Emergency Medicine

Progressing through my medical training, I have witnessed the progression of paper-based medical records, all the way to different forms of electronic medical records, let alone intelligence infused medical records. It is safe to say that health informatics has evaded the way we practice medicine in all its disciplines and all across health care systems.

Artificial intelligence (AI) describes the capability of a machine to learn human cognitive functions and learning. AI applications in healthcare have brought in a paradigm shift powered by data mapping, data aggregation, analytics, and algorithmic techniques that can simulate our decision making as clinicians.

Furthermore, it can predict and suggest clinical pathways, data-based prognosis, and outcomes. AI has already been incorporated in major disciplines such as genetics, diagnostic imaging, neurology, and cancer. Yet, its path into emergency medicine (EM) is still paving its way for vast integration.

EM is a unique field of medicine, as its rich with varying paces of practice, the criticality of conditions, acuity of diagnostic decisions, and a highly stressful environment. It puts their providers consistently on a stretched active clinical decision making and interventions. Hence it is worth to foresee how AI can help enhance and complement the emergency department (ED) functions and add significant benefits to the EM physician’s daily tasks.

One of the main applications of AI is triage. Efficient triage can significantly enhance patients flow, lengths of stay, resource allocations, and risk stratifications. A study published by the American College of Emergency Physicians evaluated electronic triage (E-Triage) systems based on machine learning as opposed to the Emergency Severity Index (ESI). They found out that E-Triage can more accurately classify ESI level 3 patients and highlight opportunities to use predictive analytics to support triage and decision making. (1) A lot more studies established the use of different forms of electronic triage algorithms in improving patient distribution by clinical outcomes, and improved acuity predictions.

Another application of AI was significantly noted in diagnostic imaging departments. Offering remote clinics with restricted resources access to tools for reading imaging needed for active clinical interventions. Feeding into these AI systems is a wealth of comparative studies to predict and describe abnormal studies, and enhance its predictions. Let alone how efficient it would be in a fast-paced ED, getting approximate quick predictions that can be overseen by supervising radiologists.

Additionally, AI has been used in monitoring patient’s vitals, and predicting deteriorating clinical course, requiring early resource utilization and critical decision making in a timely manner. One significant example where AI and machine learning is heavily invested in is Sepsis, and mortality prediction scores, aiding at early detection, guiding clinical course and interventions by using simple data trajectories and analysis.

Another utilization of AI in an ED setting is predictions of Acute Coronary Syndromes, predicting the urgent need for revascularization from reading 12 Lead electrocardiographs (ECGs). A Study done in Keio University Hospital developed an AI model enabled to detect patients requiring urgent revascularization within 48 hours from only 12 leads electrocardiogram. (2) This significantly helps fast pace a lot of the grey cases we see and monitor in our ED’s, especially if validated with risk stratification scores we are already utilizing.

It is worth saying that there are still some barriers to the vast adoption of AI integration to EDs as it’s still a new evolving technology, with restrictive access, ethical discussions, safety, and needed regulations.

I personally have always had a utopian vision of how far health informatics can take our clinical practice, specifically EM. Injecting machine learning and AI into healthcare curates the perfect system that could decrease lengths of stay, intelligently and safely triage our patients, predict clinical course, suggest evidence-based treatment pathways, reduce medication errors and improve clinical outcomes. A more utopian version of my vision is how such a system can help remote and restricted regions requiring extensive resources to aid the reach of its care to underserved populations. It goes without saying that most of these do exist in one way or another, some are still being enhanced, and some are under the works for the next stage. We would foresee its progress nonetheless and slow infusion into our daily practice.

References and Further Reading

  1. Levin S, Toerper M, Hamrock E, et al. Machine-Learning-Based Electronic Triage More Accurately Differentiates Patients With Respect to Clinical Outcomes Compared With the Emergency Severity Index. Ann Emerg Med. 2018;71(5):565‐574.e2. doi:10.1016/j.annemergmed.2017.08.005
  2. Goto S, Kimura M, Katsumata Y, et al. Artificial intelligence to predict needs for urgent revascularization from 12-leads electrocardiography in emergency patients. PLoS One. 2019;14(1):e0210103. Published 2019 Jan 9. doi:10.1371/journal.pone.0210103
  3. McParland, Aidan. (2019). Applications of artificial intelligence in emergency medicine. University of Toronto medical journal. 96.
  4. Liu, Janny & Chen, Yongchun & Lan, Li & Lin, Boli & Chen, Weijian & Wang, Meihao & Li, Rui & Zhao, Bing & Hu, Zilong & Duan, Yuxia. (2018). Prediction of rupture risk in anterior communicating artery aneurysms with a feed-forward artificial neural network. European Radiology. 28. 10.1007/s00330-017-5300-3.
  5. Berlyand, Yosef & Raja, Ali & Dorner, Stephen & Prabhakar, Anand & Sonis, Jonathan & Gottumukkala, Ravi & Succi, Marc & Yun, Brian. (2018). How artificial intelligence could transform emergency department operations. The American Journal of Emergency Medicine. 36. 10.1016/j.ajem.2018.01.017.
  6. LIU, N., ZHANG, Z., WAH HO, A., HOCK ONG, M.. Artificial intelligence in emergency medicine. Journal of Emergency and Critical Care Medicine, North America, 2, oct. 2018. Available at: <;. Date accessed: 22 May. 2020.
  7. Stewart J, Sprivulis P, Dwivedi G. Artificial intelligence and machine learning in emergency medicine. Emerg Med Australas. 2018;30(6):870‐874. doi:10.1111/1742-6723.13145
  8. Lee S, Mohr NM, Street WN, Nadkarni P. Machine Learning in Relation to Emergency Medicine Clinical and Operational Scenarios: An Overview. West J Emerg Med. 2019;20(2):219‐227. doi:10.5811/westjem.2019.1.41244
Cite this article as: Shaza Karrar, UAE, "Artificial Intelligence in Emergency Medicine," in International Emergency Medicine Education Project, June 5, 2020,, date accessed: September 27, 2023

3D Video Laryngoscopes

Laryngoscopy can be described as endoscopy of the larynx, which used to facilitate tracheal intubation during general anesthesia or cardiopulmonary resuscitation. For decades, direct laryngoscopy has been the standard technique for tracheal intubation. But today, there are two main types of laryngoscopy: direct and indirect. Indirect laryngoscopy means the provider visualizes the patient’s vocal cords without having a direct line of sight. Indirect Laryngoscopy includes video laryngoscopes, fiberoptic bronchoscopes, and optically-enhanced laryngoscopes. Video laryngoscopy introduced in recent years and it aims to overcome the limitations of direct laryngoscopy by using a camera attached to the laryngoscope. While it has clear advantages over direct laryngoscopy, video laryngoscopy still has a high cost of investment. It remains a rare commodity for Emergency Medicine clinics, especially in resource-limited settings.

While the COVID-19 pandemic was affecting the world, the people who were under the most significant risk were healthcare workers. We know that the risk of transmission of the disease is quite high, especially when performing high-risk medical procedures such as endotracheal intubation. It is a known fact that personal protective equipment such as masks or face shields are very important in protection. But it is even more important to stay physically away from the patient whenever possible. When intubating a patient, video laryngoscopy has a clear advantage in terms of eliminating the need to approach the patient’s head and trying to have a direct line of sight.

Video laryngoscopy devices are expensive. But, if you think about the essential components of it, you can easily realize that it doesn’t have to be this way. You need a blade, a camera system, a display, and a way to attach the blade and the camera system. While laryngoscopy blades are essential for Emergency clinics anyway, I can safely assume every Emergency clinic has them. A camera system and a display are also both fairly cheap and easy to obtain for most of the places on earth. Find those three and voila! You have a cheap video laryngoscope (In this post, I will not elaborate on the technique of combining a normal blade with a video camera).

For those who want to go to the next level, there are some ways of making your very own prettier video laryngoscopy devices. You just need a 3D printer, but luckily it is possible to find 3D printers in many cities these days.

So here we go.


The pandemic paved the way for innovation in many ways. Numerous doctors from all over the world rolled up their sleeves to develop new medical devices. Yasemin Özdamar, an Emergency Medicine specialist from Turkey, designed 3D-printable video laryngoscope blades named “Umay” (possibly an allusion to Orkhon inscriptions) in pediatric and adult forms based on normal laryngoscope blades.

The printing files of these blades can be downloaded for free in formats suitable for printing with PLA material, which is frequently used in 3D printers, and PA12, which is preferred for more professional printing. You can download the files here: Pediatric – Adult.


AirAngel is a not-for-profit tutorial center dedicated to making video laryngoscopes accessible in under-resourced nations. You can purchase the blade or video laryngoscopy devices from their website with a fairly low price of US$100-180. You can also get the file of the blade for free and 3D print it yourself. Its design is really similar to a D blade. You can head to AirAngel’s website and grab the printing file now.

Here is an example tutorial for AirAngel:

In our tests (in Turkey), the cost of printing one blade approximately 50 Turkish Liras (roughly equal to US$7 with today’s exchange rates). We also bought a “Borescope USB Camera” with a camera head outer diameter of 5.5mm from our local internet store for approximately US$13 (A similar product from Amazon). So, the cost was US$20 in total, which is cheaper than AirAngel’s offer, and a lot cheaper than a conventional video laryngoscope. We have attached the camera to the blade using special parts on them and connected the camera to a phone. And under a minute, a video laryngoscope was born.

Please note: The intended purpose of these designs is to be used as a training tool. They do not replace any medical-grade video laryngoscope systems. They are not in any way approved medical device designs, nor have they been reviewed by the FDA or any other organization. Be aware that many plastics vary in strength, heat resistance, and chemical resistance. The strength and durability of the blade will vary depending on what you print it with. Harmful and life-threatening complications may occur if pieces break in the airway.

Cite this article as: Ibrahim Sarbay, Turkey, "3D Video Laryngoscopes," in International Emergency Medicine Education Project, May 4, 2020,, date accessed: September 27, 2023

5 Ways Technology Drives Medicine to New Horizons

5 ways technology drives medicine

Recently, I published a Turkish article about my predictions on how emergency medicine will be in 2040 in the well-known Turkish FOAMed blog In this article, we had the opportunity to brainstorm through a futuristic story about a typical Emergency Department in 2040. We have also conducted an online survey to collect the future projections of more than 40 scientists working on medicine, genetics and engineering fields; and included these predictions in the said article.

As this article was praised, I want to write about 5 ways technology will change Emergency Medicine in the coming years.

Let’s start.

Virtual Reality


Virtual reality is an immersive, three-dimensional, computer-generated environment. While it may seem like technology for gaming and entertainment, it is exceptionally suitable to be used in medicine. One of the most prominent applications of it is in teaching Anatomy, allowing manipulations and dissections on the human body, more precisely than classical cadaveric dissections. Any medical student can access these materials from anywhere in the world. It is also cost-effective and requires less expertise, making it a dream come true for medical faculties(1). Surgical teams started to use 3D printing to build amazingly lifelike reproductions of real patients, and VR will only make it easier and better.

Artificial Intelligence

artificial intelligence

Artificial Intelligence (AI) is a popular term these days. It means “a system’s ability to correctly interpret external data, to learn from such data, and to use those learnings to achieve specific goals and tasks through flexible adaptation.”(2) Scientists all over the world are working determinedly to gain maximum benefit from this technology. AI outperforms a conventional algorithm for emergency department electrocardiogram interpretation. Apparently, it can even diagnose heart arrhythmias with cardiologist-level accuracy. An AI-enabled ECG can detect if a patient has atrial fibrillation even if the patient has a normal sinus rhythm during the test(3). Can we determine the ejection fraction using ECG? For sure. Is it possible to determine age and gender? Of course. If you are tired about ECG, let’s try another one: Can atrial fibrillation be detected just by looking at a patient’s face? Well it turns out deep-learning and a smartphone camera are all you need to do so. AI is capable of surpassing human experts in breast cancer prediction, and it can read X-Rays better than humans. It can diagnose pneumonia better than radiologists. An Israeli company announced that its algorithms were successful in helping to detect the presence of coronary artery disease. Another initiative, Sonde Health Inc., develops a voice-based technology platform for monitoring and diagnosing mental and physical medical conditions. AI will also help to solve doctor shortages: According to MIT Technology Review, Chinese doctors and tech companies are developing tools to automate routine medical tasks and alleviate China’s doctor shortage.

And these are just the baby steps of AI!

Health Wearables

health wearables

When we say «Health wearables,» the first thing that comes into mind might be a smartwatch capable of health features, but it covers an area much broader than that (Can we count pocket-sized ultrasound devices as Health Wearables? Probably.) A tech company Kymira works on a heart monitoring t-shirt that uses a single-lead ECG and movement reducing hardware to offer an accurate reading of heart rate during exercise. Just like Apple WatchAliveCor’s Kardia measures ECGs and can detect atrial fibrillation with high sensitivity. With the slogan of «Personal ECG for the whole family», Wiwe can detect arrhythmias, help making risk assessment for stroke and sudden cardiac arrest, and also determine blood oxygen levels. The Clinicloud, the EKO Core, the eKuore Pro measure heart and lung sounds as digital stethoscopes. Omron Blood Pressure Smartwatch and the MOCAcare pocket sensor, can monitor blood pressure.

Traditionally EEGs are tests that require hospital settings, but a new device lets you record EEGs in your home. With a noninvasive neural interface that sits on the back of the head, it is possible to control compatible software. Do you want to send a text message with a thought? Say no more!

Great new apps and devices let visually impaired people engage with their environments in ways that were a dream once.

3D Printers

The 3D printing process builds a three-dimensional object from a computer-aided design model. Due to the increasing technological developments, there have been significant improvements in the field of 3D printing in recent years. For example, US-based CELLINK develops bioprinters and bioprinting materials for providing models to enable 3D cell culture, personalized medicine, and enhanced therapeutics. United Therapeutics, managed to bioprint lung tissues. Scientists from Spain have presented a prototype for a 3D bioprinter that can make functional human skin. 3D printed orthopedic casts became an alternative to conventional casting to treating bone fractures.

CRISPR and genomics


CRISPR is the abbreviation of «clustered regularly interspaced short palindromic repeats,» and it is a family of DNA sequences found within the genomes of prokaryotic organisms. Since the description of it in 1987 by Yoshizumi Ishino and his colleagues’, CRISPR have attracted researchers’ attention due to its great potential. By the end of 2014 more than 1000 research papers had been published that mentioned CRISPR (4). CRISPR associated nucleases have shown to be useful as a tool for molecular testing. Scientists used CRISPR to successfully delete one of the defective genes responsible for hypertrophic cardiomyopathy in human embryos. In 2017, a team of Chinese researchers successfully increased resistance to HIV in mice by replicating a mutation. Researchers managed to treat mice infected with antibiotic-resistant infections using CRISPR-engineered bacteriophages. CRISPR may help grow new and healthier food. It also helps fighting with the disease in Ways we couldn’t even imagine in the past: By targeting female reproduction in the malaria mosquito vector Anopheles gambiae, scientists try to eradicate malaria.


We still have a long way to go. It is not difficult to predict that some of the «magnificent» innovations promoted today will turn up to be phony. Although technology advances; problems such as anti-vaccination, global warming, poverty will open up new fronts. Still, the future will absolutely bring great potentials. We are eagerly looking forward to see.

References and Further Reading

  1. Al-Jibury O. Use of Virtual Reality in Medical Education – Reality or Deception? Med Case Rep. 2017, 3:1. doi: 10.21767/2471-8041.1000039
  2. Kaplan, Andreas; Haenlein, Michael (1 January 2019). “Siri, Siri, in my hand: Who’s the fairest in the land? On the interpretations, illustrations, and implications of artificial intelligence”. Business Horizons. 62 (1): 15–25. doi:10.1016/j.bushor.2018.08.004
  3. Attia ZI, Noseworthy PA, Lopez-Jiminez F, et al. An Artificial Intelligence-Enabled ECG Algorithm for the Identification of Patients With Atrial Fibrillation During Sinus Rhythm: A Retrospective Analysis of Outcome Prediction. Lancet 2019;394:861-867.
  4. Doudna JA, Charpentier E. Genome editing. The new frontier of genome engineering with CRISPR-Cas9. Science 2014. 346 (6213): 1258096. doi:10.1126/science.1258096
Cite this article as: Ibrahim Sarbay, Turkey, "5 Ways Technology Drives Medicine to New Horizons," in International Emergency Medicine Education Project, January 24, 2020,, date accessed: September 27, 2023

Point-of-Care Resources in the ED

Point-of-Care Resources in the ED

In the era of Free Open-Access Medical education, there are countless invaluable resources available for medical learners. Over the years, they have been designed and optimized for more portable use, with the possibility of serving as on-the-go resources for trainees. Having just completed my third year of medical school – and also, my first year of clerkship – I have discovered several point-of-care tools that have proven to be immensely useful in the emergency department (ED). 

Not only have they been wonderful for obtaining quick information and have helped guide my history-taking, physical examinations, differential diagnoses and management, but they have also helped me learn through repetition using the same sources of information.

The majority of these are available both online and as mobile applications, so they are very accessible in the ED setting when you have multiple patients on the go with a variety of concerns.​

Below are a few that I have found particularly helpful this past year. As always, these resources are designed purely as clinical aids and are not meant to replace clinical judgment.

For accessibility purposes, I have only included free resources; however, some do offer additional features that are available for purchase. I have no affiliation with any of these and am commenting solely on the basic features that are available.


by Sentral Clinical Research Services, LLC
Download: Google Play l Apple

QuickEM features a list of common adult and pediatric complaints, ranging from syncope to hematuria. For each presentation, it lists considerations for histories, physicals, differentials, investigations, treatments and disposition. There is also a tool which facilitates the calculation of various useful parameters, such as QTc and Well’s score for DVT and PE. One unique component of this application is that it provides clinical pearls at the end of each topic and allows you to make personalized notes for each presentation, which you can refer back to. Additionally, a list of references is provided for further review. Overall, QuickEM breaks down a broad range of presentations into essential components, and has served as a very useful and quick EM-specific resource.


by MD Aware, LLC
Download: Google Play l Apple

MDCalc can be used online or through a mobile application. It has a long list of formulae which can be sorted by specialty (unsurprisingly, there are quite a few for EM!). One really great feature is the “favorites” section, which allows you to add specific formulae to your folder for easier reference. Once you’ve done the calculation, there is also a section that addresses subsequent investigation and management steps, as well as an evidence section that highlights the associated studies behind the formula. Overall, not only has it helped me easily calculate parameters, but it has also expanded my knowledge base by addressing the reasoning behind commonly-used clinical measures.


by LineageMedical Inc.
Download: Google Play l Apple

Orthobullets has been a staple resource throughout my Orthopedic Surgery block and then during my EM rotations for musculoskeletal-related presentations. It includes an extensive list of topics and outlines relevant anatomy, pathology, differential diagnosis, investigations and management, while also highlighting specific surgical techniques. Moreover, it includes a question bank, sample cases and educational videos, all of which are excellent for general MSK review. It can be downloaded onto your phone for easier, on-the-go use, but it does require you to register for an account (free) if you would like to access the additional features (cases, question bank, videos, etc.).


by National Health Care Provide Solutions, LLC
Download: Google Play l Apple

I started using this mobile application as a quick review before going into the simulation lab during my EM rotations. It provides easy access to numerous ACLS, BLS and PALS algorithms that can be viewed as images or approached using an interactive step-by-step feature. There are also some embedded instructional videos to consolidate all of the content. Not only does this application allow you to flip through various algorithms fairly effortlessly, but it also lets you test your knowledge and identify areas for further review through multiple-choice questionnaires.

By no means is this an exhaustive list – there are so many wonderful resources out there that I have not mentioned and that I have yet to discover! These are just several that I have regularly used and that have come up repeatedly through discussion with my colleagues. What are some point-of-care resources that have been invaluable to your education and have been helpful throughout your rotations? We would love to hear about them!

Cite this article as: Nada Radulovic, Canada, "Point-of-Care Resources in the ED," in International Emergency Medicine Education Project, June 5, 2019,, date accessed: September 27, 2023