International Emergency Medicine Education Project
We promote emergency medicine and provide free, reusable education resources for medical students and educators
Hoffman JR, Wolfson AB, Todd K, Mower WR. Selective cervical spine radiography in blunt trauma: methodology of the National Emergency X-Radiography Utilization Study (NEXUS). Ann Emerg Med. 1998;32(4):461-469. doi:10.1016/s0196-0644(98)70176-3
Non-bagging approach:
Avoid the use of high-flow nasal oxygenation and mask CPAP or BiPAP due to a greater risk of aerosol generation.
NIPPV (Might be acceptable in a negative pressure room)
BVM with Viral Filter
Use video laryngoscopy rather than regular laryngoscope; to decrease exposure
Which of the following is the most appropriate next step in management for this patient‘s condition?
The patient in this scenario has decompensated into cardiac arrest from Ventricular Tachycardia (Vtach). The patient’s history of heart failure puts him at risk for cardiac arrhythmias. It is important to be suspicious of transient cardiac dysrhythmias for any patients who present to the Emergency Department with syncope and no prodromal symptoms. A lack of prodromal symptoms (i.e., diaphoresis, dizziness, nausea) prior to syncope should raise concern for a possible cardiac etiology of the syncope. Choice A (Synchronized Cardioversion) would be the correct management for patients with Vtach with a pulse or patients with tachyarrhythmias and hemodynamic instability (i.e., hypotension). Choice C (Transcutaneous Pacing) would be the correct management for patients with bradyarrhythmia and hemodynamic instability. If Transcutaneous Pacing is ineffective at increasing the heart rate, and the patient remains hemodynamically unstable, the next step would be Transvenous Pacing. But, our case is pulseless ventricular tachycardia, so there is no indication for transcutaneous pacing. Choice D (Intravenous adrenaline 1 mg) may be helpful in a patient with cardiac arrest with Pulseless Electrical Activity or Asystole, VTach, or VFib, but this is not the best initial action. The ACLS algorithm indicates that all patients with cardiac arrest due to Pulseless Ventricular Tachycardia or Ventricular Fibrillation should receive Asynchronized Cardioversion (Choice B). Asynchronized Cardioversion is also called defibrillation. CPR may be initiated prior to cardioversion if defibrillation pads are not attached to the patient.
Which of the following is the most appropriate next step in management for this patient‘s condition?
— iem-student (@iem_student) June 28, 2020
Long B, Koyfman A, Anantharaman V, Lim S, Ong MH, Kenneth T, Manning JE. “Chapter 24: Cardiac Resuscitation”. In: Tintinalli JE, Ma O, Yealy DM, Meckler GD, Stapczynski J, Cline DM, Thomas SH. eds. Tintinalli’s Emergency Medicine: A Comprehensive Study Guide, 9thed. McGraw-Hill.
The world is scared of COVID19. Brazilian health professionals too. But today I bring something else that has haunted Brazil for years. It’s dengue. Even with the COVID19 pandemic, the mosquito Aedes aegipty doesn’t give us a break.
Dengue is an arbovirus of the flavivirus genus, which is transmitted by the Aedes aegypti mosquito, and has 4 well-established serotypes: DENV-1, DENV-2, DENV-3, and DENV-4.
Dengue is an infectious viral disease which causes a feverish syndrome. Only in January, February and March, there are 94,149 probable cases of dengue in Brazil. In 2019, there were 1,527,119 cases. The intense summer, high temperatures, and rain helped with the proliferation of the vector last year. And, there was also a change in the serotype. Dengue has 4 circulating serotypes. Here in Brazil, the most common had been 1 and 4; however, the circulation of serotype 2 increased – linked to greater severity and hemorrhage. We cannot concentrate all efforts on COVID19 and forget about some diseases that continue to attack our population.
Deaths from dengue are preventable, except for fulminating cases. Many deaths from dengue are consequences of an error, it may be the delay in seeking health care, the lack of access to the network, and the difficulty in identifying the seriousness of the cases.
The fight to stop the transmission of dengue requires a collective effort because it is transmitted by insects, and that is where exactly the Aedes aegypti mosquito, the great star of dengue, comes into play. The Aedes aegypti mosquito thrives in standing water. The female is responsible for carrying the dengue virus. In addition to dengue, this mosquito can transmit urban yellow fever, Zika, and Chikungunya.
Then, a patient with a high fever, retro-orbital pain, myalgia, prostration, headache, and maculopapular rash arrives and a recent trip to tropical regions (like Brazil!) … think, it could be dengue!
“As per WHO guideline 2009, dengue patients can be further categorized on the severity basis that includes severe dengue patients, dengue patients with few warning signs, and dengue patients with no warning signs. Dengue hemorrhagic fever which is most severe out of these three categories mainly occurs in 5% of total dengue patients”.(2)
Although there is a test called NS1 (viral antigen research) widely used in Brazil for the diagnosis of dengue, with a sensitivity of 70% and specificity of 95%, it is not a good test to rule out the suspicion of Dengue even if it comes negative – and this pattern is repeated in all the other methods like Viral Antigen Research (NS1), Genetic Amplification Test (RRT-PCR) and Tissue immunohistochemistry. It must be done until the 3rd day; after that, its accuracy drops a lot. Moreover, if the patient has had dengue before, its diagnostic value drops. (4)
Regardless of this issue of time, some tests valid for patients are blood count (presence of atypical lymphocytes and thrombocytopenia) and those that demonstrate organ dysfunction, such as TGO and TGP, urea and creatinine) to monitor the severity of the case and guide your treatment. Hemoconcentration, evidenced by the progressive increase in hematocrit (Ht) is the main laboratory finding in the identification of capillary leakage so it can show the severity of the patient.
Do not freak out! If your patient has no alarm signs and no special conditions, treatment can be done on an outpatient basis, advising the patient on the warning signs and the importance of hydration. There is no specific antiviral treatment available in the market yet. Generally, treatment includes the mechanism of controlling fever and pain with paracetamol rather than aspirin (aspirin may promote bleeding), and increasing fluid intake ³. (Look for the specific protocol of your country for the treatment of dengue). And avoid using medications that affect the coagulation cascade, such as non-steroidal anti-inflammatory and acetylsalicylic acid.
Staging and start hydrating!
You may be asking yourself, why do some people develop dengue more seriously and others don’t?
Halstead’s theory states that the disease is becoming more and more severe as the patient becomes infected with different serotypes of the causative virus.
The idea is that in the first infection, the organism can defend itself by producing a series of antibodies that are specific to that invading serotype. But if reinfection with another type of virus occurs, these antibodies may even bind to the pathogen, but they are not effective in stopping them. And this connection also favors the entry of viruses into cells, which enhances their multiplication and, consequently, the patient’s clinical condition.
This is the most accepted theory. There are others, such as the theory of multicausality, which claims the severity of the disease is associated with the interaction between several factors, ranging from the pathogen’s virulence to environmental conditions and also from the disease itself and patient being infected (such as previous comorbidities, age, among others).
Here in Brazil, we have a popular saying “It’s just a bug!”. We use it as a joke when we go to the doctor and he tells us: “it’s just a viral disease, go home, get hydrated and rest!” Yes, dengue is a viral disease. But it deserves special attention, as it can turn into a serious organ dysfunction if not treated properly !!
Dear students,
We are pleased to open our fourth course for you; iEM/Lecturio – COVID-19 Clinal Readiness Course.
As we did in the EMCC course, we collaborated with Lecturio to provide you an excellent course to improve your knowledge in the clinical applications in COVID-19 cases.
The interactive course content is prepared by Lecturio’s expert educators Dr. Eisha Chopra, Dr. Julie Rice, Dr. Daniel Sweiden, Dr. Julianna Jung from John Hopkins University, Department of Emergency Medicine. Assessments of the course were prepared by Dr. Arif Alper Cevik from United Arab Emirates University, College of Medicine and Health Sciences.
One more time, we thank Lecturio for their amazing resources and support to our social responsibility initiative to help medical students in need during these challenging times.
As a part of our social responsibility initiative, iem-course.org will continue to provide free open online courses related to emergency medicine. We hope our courses help you to continue your education during these difficult times.
Please send us your feedback or requests about courses.
We are here to help you.
Best regards.
iEM Course is a social responsibility initiative of iEM Education Project
This course requires 2-4 hours of study time. The course content will be available for 7 days after the enrolment.
The candidates who successfully pass final summative assessment of the course will be provided course completion certificate.
Which of the following is the most appropriate next step in management for this patient‘s condition?
The patient in this scenario has an aortic dissection until proven otherwise. Administering anticoagulation (Choice A: Unfractionated Heparin Drip) would be the correct treatment for a pulmonary embolism. Although the patient has mild tachycardia and tachypnea on the exam, characteristics of the history and exam point closer to a diagnosis of aortic dissection. Features of the history that support a diagnosis of aortic dissection include pain described as “tearing”, “ripping”, or sharp pain radiating to the back. Other characteristics include unequal blood pressures in the extremities or neurological symptoms. Aortic dissections that migrate proximally may cause cardiac tamponade or a STEMI if they involve the coronary arteries. Choice C (Aspirin) would be the treatment for Acute Coronary Syndrome. Choice D (Call a Cardiology consultation) would not be appropriate for a patient with aortic dissection. A cardiothoracic surgical consultation would be appropriate in a patient with an aortic dissection involving the ascending aorta (Type A aortic dissection). Aortic dissections distal to the left subclavian artery that involve the descending aorta (Type B aortic dissection) are typically managed medically with blood pressure control. Choice B (IV Labetalol) is the correct answer as Aortic Dissections require aggressive blood pressure control with a goal of less than 120/80 mmHg. Beta-blockers, like Labetalol, are considered first-line therapy as they provide both alpha and beta-adrenergic receptor blockade. This allows the reduction of blood pressure without a reflex tachycardia response. Esmolol is an alternative therapy. Beta-blockers decrease vessel shearing forces that could worsen intimal vessel tearing. If beta-blockers alone cannot control blood pressure sufficiently, other medications can be included in the treatment regimen, like nicardipine, nitroglycerin, nitroprusside.
Which of the following is the most appropriate next step in management for this patient‘s condition?
— iem-student (@iem_student) June 21, 2020
Johnson GA, Prince LA. “Chapter 59: Aortic Dissection and Related Aortic Syndromes”. In: Tintinalli JE, Ma O, Yealy DM, Meckler GD, Stapczynski J, Cline DM, Thomas SH. eds. Tintinalli’s Emergency Medicine: A Comprehensive Study Guide, 9th ed. McGraw-Hill.
Welcome to the iEM Education Project Monthly Newsletter. We will share the achievements, information about top posts, chapters, activities and future plans of the project.
These countries viewed iEM content the most in May 2020.
How to read chest x-rays, by Ozlem Koksal
How to read pelvic x-rays, by Sara Nikolić and Gregor Prosen
How to Read C-Spine X-Ray, by Dejvid Ahmetović and Gregor Prosen
Overcrowding is a serious problem in healthcare systems all around the world. In particular, Emergency Departments, which, by definition, deal with acute and unscheduled patients, are more susceptible to overcrowding. Even the parts of the world with developed hospital systems suffer from ED overcrowding, the burden is heavier in the developing world. Emergency department crowding is a significant barrier that prevents patients from receiving adequate and timely care.
Researchers of this field and policymakers had recognized the importance of the problem for ages, but COVID-19 pandemic highlighted it once again. Asplin et al’s conceptual model, published in Annals of Emergency Medicine in August 2003, continues to be relevant today and helps all stakeholders of emergency care -researchers, policymakers and administrators alike- to come up with sounding solutions. According to this conceptual model (See figure below) causes of ED overcrowding is divided into 3 independent components, namely, input causes, throughput causes and output causes.
At different times, multiple components occur to some extent in all acute care centres. This conceptual model provides an overview of overcrowding causes so that administrators may review what’s failing and develop more efficient emergency department operations and policies. Subsequently, it will help to reduce ED crowding. Also, learning how ED, as a workplace, works on an organizational level has the potential to increase medical graduates’ interest in research and policymaking, thus, feedback on system design from diverse stakeholders.
Authors: Nardos Makkonen, MD and Amita Sudhir, MD
University of Virginia, USA
Life does not choose the logically best design to meet a new situation. It adapts what already exists...The result, unlike the clean straight lines of logic, is often irregular, messy.
In The Great Influenza, The story of the Deadliest Pandemic in History, the author John Barry states, “Life does not choose the logically best design to meet a new situation. It adapts what already exists…The result, unlike the clean straight lines of logic, is often irregular, messy.” This has never been more evident than now as the way we practice medicine changes fundamentally in the face of a new pandemic. While the news of a novel coronavirus spread, many in the scientific community found themselves struggling to find answers. In the wake of the pandemic, multiple studies were published aiming to identify risk factors, disease progression, and most importantly, therapeutic options.
As the number of positive cases grew exponentially, so did the urgency to find an effective therapy. Scientists and medical professionals were tasked with finding a swift solution. In addition to vaccine development, trials looking at the effectiveness of previously existing antiviral medications against SARS-CoV-2 were underway. A number of in-vitro models showed promising results – existing antiviral and antimalarial medications, including Hydroxychloroquine and Remdesivir, were noted to have cytotoxic properties against the novel coronavirus (1, 2). At first, it was difficult to tell how this could shape the management of affected patients. Then came a study that would change the global conversation on COVID therapies.
An article published on March 20th in the International Journal of Antimicrobial Agents looked at the effect of hydroxychloroquine and azithromycin on COVID positive patients. The study was an open-label, non-randomized clinical trial of thirty-six patients; twenty patients were treated with hydroxychloroquine, while sixteen were in the control group. The article looked at SARS–CoV-2 clearance from the nasopharynx after six days. Higher frequency of viral clearance was reported in the treatment group, hydroxychloroquine (plus azithromycin if deemed necessary) versus an untreated control group [14 out of 20 (70%) vs. 2 out of 16 (13%); P < 0.001]. The authors concluded that the addition of azithromycin to hydroxychloroquine was significantly more efficient for virus elimination (3). Multiple articles were published that questioned various aspects of the original article. Nonetheless, the original excitement surrounding the medication led to its widespread use for treatment of COVID positive patients in various hospitals across the world. However, in the ensuing months, multiple additional studies have been published that have informed our understanding of hydroxychloroquine as a treatment option for SARS–CoV-2, suggesting that it may not be the panacea that the initial study suggested it is.
One of the first randomized control trials on the topic was a multicenter, open-label, randomized control trial looking at 150 patients. Seventy-five patients were assigned to hydroxychloroquine plus standard of care, while the other 75 were assigned to standard of care alone. The primary endpoint of this study was looking at viral clearance by 28 days. The results suggested hydroxychloroquine was not associated with a significantly higher probability of negative conversion than the standard of care alone (4). In another retrospective cohort study of 1438 patients hospitalized in metropolitan New York, treatment with hydroxychloroquine, azithromycin, or both did not result in a significantly lower in-hospital mortality (5). A meta-analysis looked at eleven studies, including three randomized controlled trials and eight observational studies. Here, 2354 patients received hydroxychloroquine alone or in combination, while 1952 did not. The study found no significant difference in clinical progression, mortality, or viral clearance by RT-PCR among patients with COVID-19 infection who are treated with hydroxychloroquine compared with control groups (6). In addition, a significantly higher incidence of adverse events associated with hydroxychloroquine use across a number of studies was noted.
Adverse effects were also noted in a multinational registry analysis of the use of hydroxychloroquine or chloroquine with or without a macrolide for treatment of COVID-19. The registry comprised data from 671 hospitals in six continents. The findings show no confirmed benefit of hydroxychloroquine or chloroquine when used alone or with a macrolide on in-hospital outcomes for COVID-19. Notably, each of these drugs was found to be associated with decreased in-hospital survival and increased frequency of ventricular arrhythmias (7). Importantly, the Lancet has since released a letter of concern on 6/2/20 regarding its publication of this multinational registry analysis (8).
Beyond its potential therapeutic use for known COVID positive patients, hydroxychloroquine was touted as beneficial for prophylactic use. Prior to the publication of significant studies on the prophylactic efficacy of the medication, the Indian Council of Medical Research, under the Ministry of Health and Family Welfare, recommended chemoprophylaxis with hydroxychloroquine for asymptomatic health-care workers treating patients with suspected or confirmed COVID-19, and for asymptomatic household contacts of confirmed cases. The announcement led some in the scientific community to express concern, stating “the drug is untested, the benefits unknown, and the risks not negligible” (9). This concern was substantiated in subsequent studies. A recent randomized, double-blind, placebo-controlled trial analyzed the effect of hydroxychloroquine in postexposure prophylaxis. The study included 821 asymptomatic participants. 87.6% of the participants (719 of 821) had a high-risk exposure to a confirmed COVID contact. The primary outcome was symptomatic illness confirmed by a positive molecular assay or, if testing is not available, COVID-related symptoms. The results noted no significant difference in the primary outcome between participants receiving hydroxychloroquine (49 out of 414 [11.8%]) and those receiving placebo (58 out of 407 [14.3%]) (10). Additionally, side effects were noted to be more common with hydroxychloroquine than with placebo (40.1% vs. 16.8%).
On May 27th, Dr. Anthony Fauci, the director of National Institute of Allergy and Infectious Diseases, when asked about hydroxychloroquine, stated that “The scientific data is really quite evident now about the lack of efficacy.” As of now, the World Health Organization is planning on resuming Hydroxychloroquine clinical trials after previously halting studies due to safety concerns (11). One adage often repeated in medicine is that what we learn now may not apply in 10 years. In the age of COVID, what we learn now may not apply in the next few months or even weeks. Seeing images of ventilated patients, and at times dead bodies across hospital hallways have filled us all with a deep desire for a quick fix. As physicians, we are likely to grasp at any straws that might help us fight this disease; we have to be careful to look critically at the evidence. Hope springs for a cure with each new study, but we should apply the same rigorous scientific methodology to COVID that we have developed for other diseases. As we move towards alleviating the suffering of this pandemic, it is essential to avoid falling into pitfalls and causing more harm along the way.
One of the most convenient ways of learning and remembering the main components of disease and identifying a medical condition on an exam are Triads, and medical students/interns/residents swear by them.
Be it a question during rounds, a multiple-choice exam question to be solved, or even in medical practice, the famous triads help physicians recall important characteristics and clinical features of a disease or treatment in an instant.
Since exam season is here, this could serve as a rapid review to recall the most common medical conditions.
While there are a vast number of triads/pentads available online, I have listed the most important (high-yy) ones that every student would be asked about at least once in the duration of their course.
1) Lethal Triad also known as The Trauma Triad of Death
Hypothermia + Coagulopathy + Metabolic Acidosis
2) Beck’s Triad of Cardiac Tamponade
Muffled heart sounds + Distended neck veins + Hypotension
3) Virchow’s Triad – Venous Thrombosis
Hypercoagulability + stasis + endothelial damage
4) Charcot’s Triad – Ascending Cholangitis
Fever with rigors + Right upper quadrant pain + Jaundice
5) Cushing’s Triad – Raised Intracranial Pressure
Bradycardia + Irregular respiration + Hypertension
6) Triad of Ruptured Abdominal Aortic Aneurysm
Severe Abdominal/Back Pain + Hypotension + Pulsatile Abdominal mass
7) Reactive Arthritis
Can’t See (Conjunctivitis) + Can’t Pee (Urethritis) + Can’t Climb a Tree (Arthritis)
8) Triad of Opioid Overdose
Pinpoint pupils + Respiratory Depression + CNS Depression
9) Hakims Triad – Normal Pressure Hydrocephalus
Gait Disturbance + Dementia + Urinary Incontinence
10) Horner’s Syndrome Triad
Ptosis + Miosis + Anydrosis
11) Mackler’s Triad – Oesophageal Perforation (Boerhaave Syndrome)
Vomiting + Lower Thoracic Pain + Subcutaneous Emphysema
12) Pheochromocytoma
Palpitations + Headache + Perspiration (Diaphoresis)
13) Leriche Syndrome
Buttock claudication + Impotence + Symmetrical Atrophy of bilateral lower extremities
14) Rigler’s Triad – Gallstone ileus
Gallstones + Pneumobilia + Small bowel obstruction
15) Whipple’s Triad – Insulinoma
Hypoglycemic attack + Low glucose + Resolving of the attack on glucose administration
16) Meniere’s Disease
Tinnitus + Vertigo + Hearing loss
17) Wernicke’s Encephalopathy- Thiamine Deficiency
Confusion + Ophthalmoplegia + Ataxia
18) Unhappy Triad – Knee Injury
Injury to Anterior Cruciate Ligament + Medial collateral ligament + Medial or Lateral Meniscus
19) Henoch Schonlein Purpura
Purpura + Abdominal pain + Joint pain
20) Meigs Syndrome
Benign ovarian tumor + pleural effusion + ascites
21) Felty’s Syndrome
Rheumatoid Arthritis + Splenomegaly + Neutropenia
22) Cauda Equina Syndrome
Low back pain + Bowel/Bladder Dysfunction + Saddle Anesthesia
23) Meningitis
Fever + Headache + Neck Stiffness
24) Wolf Parkinson White Syndrome
Delta Waves + Short PR Interval + Wide QRS Complex
25) Neurogenic Shock
Bradycardia + Hypotension + Hypothermia
COVID-19 pandemic has caused drastic changes in personal and educational lives of medical students, who hold a unique position between being a student and a part of the health care workforce (1). The role of senior medical students who are on the brink of becoming licenced physicians, in particular, have been discussed thoroughly by experts from the perspective of safety, education and the need for skilled workforce. As the discussions continue, medical students got to stay home – as it should be, in my opinion – at least in most countries. Remote learning became the primary training modality all in a sudden.
Remote learning, even though the safest option, is not free of problems. Studying from home and continuing daily routine require a strong determination, especially when people have a lot on their minds. But most of all, clinical and procedural skills are hard, if not impossible, to translate into online learning. Medical students need alternative methods to physical practice of clinical and procedural skills, other than reading instructions and watching procedural videos. Mental practice may offer a solution for medical students who want to sharpen or at least retain procedural skills at home.
Mental practice refers to the introspective rehearsal or visualisation of psychomotor skills (2). It has been called many names including ‘‘imaginary practice,’’ ‘‘covert rehearsal,’’ ‘‘conceptualization,’’ or ‘‘mental imagery rehearsal’.’ It has been researched extensively in sports literature and is shown to provide both cognitive and motivational benefits (3). Can it do the same trick for medical training, though? At this point, being sceptical is perfectly normal. Let’s look into the literature.
Surprisingly, even as early as the 1900s, the scientists were discussing the effect of ideational elements in motor learning (4). In the 1930s, pioneer researchers had already experimented on rats that were deprived of kinesthetic impulses by sectioning of the cervical cord and discovered that even they could not run the maze as perfectly as normal rats in terms of motor skills, they still learned it (5, 6, 7). They asserted that kinesthetic impulses were neither sufficient nor necessary in learning of the motor skill. A few years later in 1940, researchers observed ideational clues helped human subjects to learn basic motor skills making fewer attempts, committing fewer errors, and spending less time (8). Subsequent studies tested mental practice against the physical in basketball free throws, dart games, and ring toss (9, 10). All reached the same conclusion: Mental practice was effective, even about as effective as physical practice in learning of motor skills.
Experiments on the use of mental practice in the area of medical training started a few decades later. One of the first studies examined the use of mental practice in the pelvic examination. The students who did 5-minute audio-guided mental practices before and after the physical practice on a model performed significantly better at skill examination (11). Research in this area has gained momentum recently. Mental practice was shown to facilitate medical students’ learning of suturing, venipuncture, cricothyroidotomy, and lumbar puncture (12-15). In some studies, it performed as effective as physical practice, and superior to studying text (12, 16).
The evidence shows that mental practice can be a strong and free learning tool. It can serve as a satisfactory substitute for physical practice in the days of the pandemic, which forces medical students to stay at home. But, let’s not get ahead of ourselves. Mental practice does not provide all of the answers. Remember the rats: They still needed motor practice to run perfectly and as fast as normal rats (7). In other words, you still need the train your muscles to operate smoothly what you have learned. Even after years of mental practice, one could never score a free throw if he or she is lacking the muscle strength to make the ball reach the basket. Admittedly, most medical procedures do not require large motor skills or much strength, but they still demand well-trained small muscles. However, until the world figures out how to put a medical student and a simulator together in the same room safely, the mental practice seems like a solid way of learning new procedures.
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.
