How artificial intelligence could transform emergency care.

Artificial intelligence (AI) in healthcare is the ability of a computer to perform tasks typically associated with clinical care (e.g. medical decision-making and documentation). AI will soon be integrated into an increasing number of healthcare applications, including elements of emergency department (ED) care. Here, we describe the basics of AI, various categories of its functions (including machine learning and natural language processing) and review emerging and potential future use-cases for emergency care. For example, AI-assisted symptom checkers could help direct patients to the appropriate setting, models could assist in assigning triage levels, and ambient AI systems could document clinical encounters. AI could also help provide focused summaries of charts, summarize encounters for hand-offs, and create discharge instructions with an appropriate language and reading level. Additional use cases include medical decision making for decision rules, real-time models that predict clinical deterioration or sepsis, and efficient extraction of unstructured data for coding, billing, research, and quality initiatives. We discuss the potential transformative benefits of AI, as well as the concerns regarding its use (e.g. privacy, data accuracy, and the potential for changing the doctor-patient relationship).

Acute patients discharged without an established diagnosis: risk of mortality and readmission of nonspecific diagnoses compared to disease-specific diagnoses.

BACKGROUND: Nonspecific discharge diagnoses after acute hospital courses represent patients discharged without an established cause of their complaints. These patients should have a low risk of adverse outcomes as serious conditions should have been ruled out. We aimed to investigate the mortality and readmissions following nonspecific discharge diagnoses compared to disease-specific diagnoses and assessed different nonspecific subgroups. METHODS: Register-based cohort study including hospital courses beginning in emergency departments across 3 regions of Denmark during March 2019-February 2020. We identified nonspecific diagnoses from the R- and Z03-chapter in the ICD-10 classification and excluded injuries, among others-remaining diagnoses were considered disease-specific. Outcomes were 30-day mortality and readmission, the groups were compared by Cox regression hazard ratios (HR), unadjusted and adjusted for socioeconomics, comorbidity, administrative information and laboratory results. We stratified into short (3-<12 h) or lengthier (12-168 h) hospital courses. RESULTS: We included 192,185 hospital courses where nonspecific discharge diagnoses accounted for 50.7% of short and 25.9% of lengthier discharges. The cumulative risk of mortality for nonspecific vs. disease-specific discharge diagnoses was 0.6% (0.6-0.7%) vs. 0.8% (0.7-0.9%) after short and 1.6% (1.5-1.7%) vs. 2.6% (2.5-2.7%) after lengthier courses with adjusted HRs of 0.97 (0.83-1.13) and 0.94 (0.85-1.05), respectively. The cumulative risk of readmission for nonspecific vs. disease-specific discharge diagnoses was 7.3% (7.1-7.5%) vs. 8.4% (8.2-8.6%) after short and 11.1% (10.8-11.5%) vs. 13.7% (13.4-13.9%) after lengthier courses with adjusted HRs of 0.94 (0.90-0.98) and 0.95 (0.91-0.99), respectively. We identified 50 clinical subgroups of nonspecific diagnoses, of which Abdominal pain (n = 12,462; 17.1%) and Chest pain (n = 9,599; 13.1%) were the most frequent. The subgroups described differences in characteristics with mean age 41.9 to 80.8 years and mean length of stay 7.1 to 59.5 h, and outcomes with < 0.2-8.1% risk of 30-day mortality and 3.5-22.6% risk of 30-day readmission. CONCLUSIONS: In unadjusted analyses, nonspecific diagnoses had a lower risk of mortality and readmission than disease-specific diagnoses but had a similar risk after adjustments. We identified 509 clinical subgroups of nonspecific diagnoses with vastly different characteristics and prognosis.

Collaborative virtual reality environment in disaster medicine: moving from single player to multiple learners.

BACKGROUND: The use of virtual reality (VR) in healthcare education is on the increase. In disaster medicine, it could be a solution to the cost and logistic constraints for a "full-scale" scenarios. However, VR is mainly designed for single players, which is not appropriate for the objectives pursued in disaster medicine. We decided to evaluate the educational value of using individual VR simulation in disaster medicine on a group of learners. METHODS: The VR scenario used was a reproduction of a major train crash, with 21 victims and whose objectives were START triage and first aid techniques. The sessions were carried out in multi-participant groups with different roles (active and immersed with headset, paper triage without headset, and active for communications not immersed in the headset). Their perceived self-efficacy was assessed before (T0), after (T1) and 2 months (T2) after the training. Satisfaction and confidence in learning were also measured. RESULTS: The median levels of satisfaction and confidence in learning were of 21/25 and 32/40 respectively. Their perceived self-efficacy increased significantly between T0 and T1 (p < 0.001), and remained stable until T2. The different roles of participant showed no difference in terms of satisfaction, confidence in learning or changes in perceived self-efficacy. One third of the participants agreed that the number of participants had interfered with their learning. A significant negative correlation (rS = -0.51, p = 0.002) was found between satisfaction and the fact of having been hindered by the number of participants. Around 90% of participants found the activity entertaining and found the new technologies appropriate for learning technical skills. CONCLUSIONS: This first experience of VR in a group setting is satisfactory and shows its positive effects. The limitations highlighted here will enable areas of improvement to be identified for the use of VR in disaster medicine, pending the development of multi-player tools. It would now be appropriate to analyse the impact of this type of simulation on learning and its retention over time.

Prehospital identification of intracerebral haemorrhage: a scoping review of early clinical features and portable devices.

INTRODUCTION: Prehospital identification of intracerebral haemorrhage (ICH) in suspected stroke cases may enable the initiation of appropriate treatments and facilitate better-informed transport decisions. This scoping review aims to examine the literature to identify early clinical features and portable devices for the detection of ICH in the prehospital setting. METHODS: Three databases were searched via Ovid (MEDLINE, EMBASE and CENTRAL) from inception to August 2022 using prespecified search strategies. One reviewer screened all titles, abstracts and full-text articles for eligibility, while a second reviewer independently screened 20% of the literature during each screening stage. Data extracted were tabulated to summarise the key findings. RESULTS: A total of 6803 articles were screened for eligibility, of which 22 studies were included for analysis. Among them, 15 studies reported on early clinical features, while 7 considered portable devices. Associations between age, sex and comorbidities with the presence of ICH varied across studies. However, most studies reported that patients with ICH exhibited more severe neurological deficits (n=6) and higher blood pressure levels (n=11) at onset compared with other stroke and non-stroke diagnoses. Four technologies were identified for ICH detection: microwave imaging technology, volumetric impedance phase shift spectroscopy, transcranial ultrasound and electroencephalography. Microwave and ultrasound imaging techniques showed promise in distinguishing ICH from other diagnoses. CONCLUSION: This scoping review has identified potential clinical features for the identification of ICH in suspected stroke patients. However, the considerable heterogeneity among the included studies precludes meta-analysis of available data. Moreover, we have explored portable devices to enhance ICH identification. While these devices have shown promise in detecting ICH, further technological development is required to distinguish between stroke subtypes (ICH vs ischaemic stroke) and non-stroke diagnoses.

Wasp sting-induced bilateral thalamic and midbrain infarction.

A male patient in his early 40s presented to the emergency department with an acute onset of respiratory distress and facial oedema, indicative of anaphylaxis. These symptoms emerged 2 hours subsequent to a wasp sting on the left side of his face. Despite initial stabilisation, the patient's state deteriorated into somnolence and disorientation. Notably, he denied any history of seizures, sensory or motor deficits, or bowel/bladder complications. Physical examination unveiled no focal neurological deficits. Routine laboratory tests and drug screening yielded no significant findings. Subsequent brain MRI with angiography exposed bilateral thalami diffusion restriction, strongly implying an acute infarction within the artery of Percheron territory, an atypical vascular variant. The sequence of events, alongside the absence of other conclusive aetiologies, indicated a wasp sting-induced thalamic infarction driven by vasogenic and thrombogenic effects of inflammatory substances.

Prevalence of work-related musculoskeletal disorders and associated factors affecting emergency medical services professionals in Jordan: a cross-sectional study.

OBJECTIVES: Emergency medical services (EMSs) personnel are at high risk for developing work-related musculoskeletal disorders (WMSDs). However, no studies have yet investigated the prevalence and effect of these disorders on the Jordanian EMS personnel. Therefore, this study aimed to determine the prevalence of WMSDs among Jordanian EMS personnel and its associated factors. DESIGN: This study used a cross-sectional design. Participants were asked to complete a self-administrated and validated questionnaire to measure the WMSDs, including a demographic survey and the Nordic Musculoskeletal Questionnaire. Descriptive and multivariable regression analyses were used. SETTING: The Jordanian Civil Defence stations in the main cities of Jordan. PARTICIPANTS: The sample consisted of 435 EMS workers which were obtained across the country of Jordan. A total of 79.0% of the participants were male, with a mean age of 27.9 (±4.3 SD) years. RESULTS: The pain in the lower back (308, 70.8%) and neck (252, 57.9%) were the most reported in the last 12 months. Furthermore, about half of the participants reported having pain in their upper back (234, 53.8%), knee (227, 52.2%) and shoulder (226, 52.0%) pain in the last 12 months. Overall, WMSDs in at least one body part were significantly associated with age, experience, being a male, increased body mass index and lower educational level. CONCLUSIONS: There is a high prevalence of musculoskeletal complaints among EMS personnel. Multiple variables may be incorporated into a national prevention campaign and professional development programme to educate EMS personnel on avoiding WMSDs.

Association between school learning models and psychological and social health visits to the emergency room.

Objectives: We aimed to assess the impact of in-person and distance school learning models on children's visits to the emergency department (ED) for psychological or social ("psychosocial") complaints. Methods: We analyzed presentations to one emergency department in a mid-sized Midwestern city. We used the public school system schedule to determine in-person and distance learning periods by the grade level. We calculated the incidence of visits to the emergency department during academic years 2018-2019, 2019-2020, and 2020-2021, with particular attention to the time after March 13, 2020, which was the pandemic period. We compared the incidence of visits during in-person versus distance learning school models. Results: A total of 7181 visits occurred during the academic years studied, 17.1% due to psychosocial complaints. The incidence of psychosocial visits to the ED was lower during distance learning than during the pandemic in-person learning period (given per 1000 student years: 20.5 vs. 24.1, p = 0.14). This difference was statistically significant among middle schoolers (23.3 vs. 46.6, p < 0.001). While not statistically significant, the difference among high schoolers was pragmatically relevant (38.2 vs. 49.3, p = 0.086). Conclusions: Distance learning was associated with a decrease in the incidence of psychosocial visits to the emergency department relative to in-person learning. Future investigation is required to verify results and better understand any causative relationships.

Integrating Pre-test Probability and Point-of-Care Ultrasound (POCUS) in the Emergency Department (ED) Diagnosis of Small Bowel Obstruction (SBO).

Introduction A computed tomography (CT) scan and point-of-care ultrasound (POCUS) are commonly employed for diagnosing small bowel obstructions (SBOs). Prior studies demonstrated that POCUS has 90-95% sensitivity and specificity compared with CT scanning, which is the gold standard. Unlike other imaging modalities (in which the ordering and performing clinician are not the same), POCUS-performing/interpreting sonologists must recognize the risk of confirmation bias in the POCUS application. Per Bayesian analysis, the likelihood of a diagnosis being true following a diagnostic test is based on the ordering clinician's pre-test probability and the test characteristics (sensitivity and specificity, from which positive and negative likelihood ratios can be calculated). Consequently, establishing pre-test probability is important in informing downstream diagnostic or therapeutic interventions, as pre-test probability influences post-test odds. Little research has been done on the role of POCUS sonologist's pre-test probability and actual POCUS results regarding SBO. This study assessed the role of POCUS, integrating pre-test probability and POCUS results to determine post-test odds. Methods One hundred six patients were recruited on a convenience basis and underwent POCUS and CT between April 2017 and December 2022. All sonographers were credentialed in POCUS. POCUS sonologists' pre-test probabilities and POCUS and CT results were captured, which were compared. Sensitivity, specificity, LR+, and LR- were calculated, and correlations were made between pre-test probability and POCUS and CT results.  Results POCUS exhibited a sensitivity of 92% and specificity of 90%, with a corresponding positive likelihood ratio (LR+) of 9.3 and a negative likelihood ratio (LR-) of 0.09 for diagnosing SBO. Among patients with a high pre-test probability of SBO, a negative ultrasound yielded post-test odds of 0.4%, whereas a positive POCUS yielded post-test odds of 39.6%. Among patients with a low pre-test probability, a negative POCUS resulted in post-test odds of 0%, while a positive POCUS led to post-test odds of 2.1%, yielding a number needed to scan (NNS) of ~50 to identify a patient with an SBO on CT. Conclusion This study confirmed POCUS's sensitivity and specificity of ~90-95% and a corresponding LR+ of 9.2 and LR- of 0.9. Pre-test probability substantially affected post-test odds. Patients with a high pre-test probability and a positive POCUS had post-test odds of 39.6 and should have a confirmatory CT, while those with a negative POCUS have very low post-test odds and very likely will not benefit from CT. Patients with low pre-test probability and a positive POCUS have post-test odds of 2.1%, similar to the Wells Score and HEART score; such patients may not benefit from a CT, though clinicians should use their judgment/discretion. Patients with a low pre-test probability and a negative POCUS have post-test odds of 0% and should not have a CT. Among low pre-test probability patients, the NNS was ~50 to identify patients with an SBO on CT.

The Impact of Faculty Gender on Resident Evaluations of Faculty Performance in Emergency Medicine.

INTRODUCTION: Gender bias impacts the promotion and tenure of female emergency medicine (EM) physicians and limits their ability to advance in academic rank. Many factors influence the promotion and tenure process including research, evaluations, opportunities for leadership, sponsorship, and mentorship. The goal of this study is to determine if resident evaluations of EM faculty differ by faculty gender. METHODS: A quantitative analysis was used to examine 14,613 teaching evaluations of faculty by residents at a single academic center (The Ohio State University Wexner Medical Center, Columbus) in the years 2017-2019. Anonymized ratings of male and female faculty on a five-point Likert scale were compared using Fischer's exact test and adjusting for multiple comparisons. RESULTS: Male faculty were more likely to hold the rank of Associate Professor or Professor. When taking both faculty gender and rank into account, male Clinical Instructors and Assistant Professors had significantly higher evaluation scores by residents in the domain of resident autonomy than their female counterparts. Regardless of gender or faculty rank, the majority of faculty received scores greater than four. CONCLUSION: A significant gender difference was found in resident evaluation scores of faculty in the domain of resident autonomy at the level of Clinical Instructor and Assistant Professor. Resident autonomy refers to the degree of supervision by faculty which evolves over time and is primarily based on level of training. This is important as it demonstrates a gender difference in scores that could be used to determine faculty compensation and promotion. Evaluation tools used for promotion and tenure of academic faculty should be evaluated for implicit bias and appropriate statistical analysis.

Stroke in a Patient With Antiphospholipid Syndrome.

Antiphospholipid syndrome (APS) is characterized by the occurrence of thrombotic events and/or obstetric complications in the presence of antiphospholipid antibodies. It is considered one of the most common acquired thrombophilias. The presentation of stroke in patients with APS has been described in some studies; however, it is not frequent enough and there is not much information available regarding the indications for pharmacological thrombolysis and the safety of thrombolytic treatment. Likewise, current evidence does not describe contraindications to thrombolytic therapy in cases of this diagnosis, which makes management with fibrinolysis safe in these cases. A clinical case of stroke is presented in which pharmacological thrombolysis is performed with a successful outcome, without complications of angioedema or bleeding. Likewise, concerning the case, the main neurological manifestations associated with APS, especially in its association with stroke, are described.

Defining Incidental Versus Non-incidental COVID-19 Hospitalizations.

Background Rates of COVID-19 hospitalization are an important measure of the health system burden of severe COVID-19 disease and have been closely followed throughout the pandemic. The highly transmittable, but often less severe, Omicron COVID-19 variant has led to an increase in hospitalizations with incidental COVID-19 diagnoses where COVID-19 is not the primary reason for admission. There is a strong public health need for a measure that is implementable at low cost with standard electronic health record (EHR) datasets that can separate these incidental hospitalizations from non-incidental hospitalizations where COVID-19 is the primary cause or an important contributor. Two crude metrics are in common use. The first uses in-hospital administration of dexamethasone as a marker of non-incidental COVID-19 hospitalizations. The second, used by the United States (US) CDC, relies on a limited set of COVID-19-related diagnoses (i.e., respiratory failure, pneumonia). Both measures likely undercount non-incidental COVID-19 hospitalizations. We therefore developed an improved EHR-based measure that is better able to capture the full range of COVID-19 hospitalizations. Methods We conducted a retrospective study of ED visit data from a national emergency medicine group from April 2020 to August 2023. We assessed the CDC approach, the dexamethasone-based measure, and alternative approaches that rely on co-diagnoses likely to be related to COVID-19, to determine the proportion of non-incidental COVID-19 hospitalizations. Results Of the 153,325 patients diagnosed with COVID-19 at 112 general EDs in 17 US states, and admitted or transferred, our preferred measure classified 108,243 (70.6%) as non-incidental, compared to 71,066 (46.3%) using the dexamethasone measure and 77,399 (50.5%) using the CDC measure. Conclusions Identifying non-incidental COVID-19 hospitalizations using ED administration of dexamethasone or the CDC measure provides substantially lower estimates than our preferred measure.

Regional Inequality and Associated Factors of Emergency Medicine Beds Distribution in China.

Objective: The regional inequality of emergency medicine beds distribution has a great impact on population health as well as the accessibility of emergency services. This study aimed to explore the regional inequality of emergency medicine bed distribution and its influencing factors. Methods: The Gini coefficient and health resource agglomeration were used to analyze the regional inequality of emergency medicine beds distribution by area from 2012 to 2021 in China. Grey correlation models were used to explore the factors influencing the regional inequality of emergency medicine beds distribution. Results: From 2012 to 2021, Gini coefficients of emergency medicine beds distribution by geographic in China showed a worsening trend, rising from 0.6229 to 0.6636. The average HRAD index was 3.43 in the east and 0.44 in the west. Population structure factors have the greatest influence on the regional inequality of emergency medicine beds distribution. Conclusion: Health resources allocation strategy only according to population size should be changed. In formulating policies for emergency medicine beds allocation should take into account population structure, financial structure of expenditure, the inequality of geographical distribution and so on.

Acute Muscle Rigidity Secondary to Tetanus: A Toxicology Simulation Case for Fourth-Year Medical Students.

Introduction: Tetanus is uncommon in the United States secondary to vaccination. However, vaccination hesitancy is increasing. This case challenges medical students to consider tetanus in the differential and understand its complications. Methods: Fourth-year medical students took a pretest on the neurotransmitter glycine and associated disease states. They received two 10-minute lectures on glycine and acid-base abnormalities. Students then participated in a simulation featuring a 27-year-old man bitten by a dog, resulting in tetanus. Required equipment included a mannequin with monitor, a defibrillator, and personal protective equipment. Critical actions consisted of learners dividing up roles amongst each other, using closed-loop communication, placing the patient on a cardiac monitor, choosing to establish IV access and intubate the patient, starting IV fluids, and administering tetanus immunoglobulin. The case ended after 20 minutes. Outcome measurements encompassed performance on a posttest and critical actions. Results: Twenty students participated. Mean pretest and posttest scores were 69.5 and 92.5, respectively (p < .001). All groups completed the items on the critical actions checklist within a 20-minute time frame. Discussion: Rising vaccine hesitancy may increase the likelihood of physicians encountering new cases of tetanus and require them to perform lifesaving management of a patient presenting with muscle rigidity. This simulation provides learners with hands-on experience caring for a patient with tetanus and muscle rigidity. It can improve their knowledge of recognition, assessment, and decision-making toward lifesaving management of tetanus by allowing them to practice their skills in a safe environment.

Academic Detailing as a Health Information Technology Implementation Method: Supporting the Design and Implementation of an Emergency Department-Based Clinical Decision Support Tool to Prevent Future Falls.

BACKGROUND: Clinical decision support (CDS) tools that incorporate machine learning-derived content have the potential to transform clinical care by augmenting clinicians' expertise. To realize this potential, such tools must be designed to fit the dynamic work systems of the clinicians who use them. We propose the use of academic detailing-personal visits to clinicians by an expert in a specific health IT tool-as a method for both ensuring the correct understanding of that tool and its evidence base and identifying factors influencing the tool's implementation. OBJECTIVE: This study aimed to assess academic detailing as a method for simultaneously ensuring the correct understanding of an emergency department-based CDS tool to prevent future falls and identifying factors impacting clinicians' use of the tool through an analysis of the resultant qualitative data. METHODS: Previously, our team designed a CDS tool to identify patients aged 65 years and older who are at the highest risk of future falls and prompt an interruptive alert to clinicians, suggesting the patient be referred to a mobility and falls clinic for an evidence-based preventative intervention. We conducted 10-minute academic detailing interviews (n=16) with resident emergency medicine physicians and advanced practice providers who had encountered our CDS tool in practice. We conducted an inductive, team-based content analysis to identify factors that influenced clinicians' use of the CDS tool. RESULTS: The following categories of factors that impacted clinicians' use of the CDS were identified: (1) aspects of the CDS tool's design (2) clinicians' understanding (or misunderstanding) of the CDS or referral process, (3) the busy nature of the emergency department environment, (4) clinicians' perceptions of the patient and their associated fall risk, and (5) the opacity of the referral process. Additionally, clinician education was done to address any misconceptions about the CDS tool or referral process, for example, demonstrating how simple it is to place a referral via the CDS and clarifying which clinic the referral goes to. CONCLUSIONS: Our study demonstrates the use of academic detailing for supporting the implementation of health information technologies, allowing us to identify factors that impacted clinicians' use of the CDS while concurrently educating clinicians to ensure the correct understanding of the CDS tool and intervention. Thus, academic detailing can inform both real-time adjustments of a tool's implementation, for example, refinement of the language used to introduce the tool, and larger scale redesign of the CDS tool to better fit the dynamic work environment of clinicians.

Discussion paper: implications for the further development of the successfully in emergency medicine implemented AUD2IT-algorithm.

The AUD2IT-algorithm is a tool to structure the data, which is collected during an emergency treatment. The goal is on the one hand to structure the documentation of the data and on the other hand to give a standardised data structure for the report during handover of an emergency patient. AUD2IT-algorithm was developed to provide residents a documentation aid, which helps to structure the medical reports without getting lost in unimportant details or forgetting important information. The sequence of anamnesis, clinical examination, considering a differential diagnosis, technical diagnostics, interpretation and therapy is rather an academic classification than a description of the real workflow. In a real setting, most of these steps take place simultaneously. Therefore, the application of the AUD2IT-algorithm should also be carried out according to the real processes. A big advantage of the AUD2IT-algorithm is that it can be used as a structure for the entire treatment process and also is entirely usable as a handover protocol within this process to make sure, that the existing state of knowledge is ensured at each point of a team-timeout. PR-E-(AUD2IT)-algorithm makes it possible to document a treatment process that, in principle, does not have to be limited to the field of emergency medicine. Also, in the outpatient treatment the PR-E-(AUD2IT)-algorithm could be used and further developed. One example could be the preparation and allocation of needed resources at the general practitioner. The algorithm is a standardised tool that can be used by healthcare professionals of any level of training. It gives the user a sense of security in their daily work.

Emergency department discharge practices for children with acute wheeze and asthma: a survey of discharge practice and review of safety netting instructions in the UK and Ireland.

OBJECTIVE: Recovery from acute wheeze and asthma attacks should be supported with safety netting, including treatment advice. We evaluated emergency department (ED) discharge practices for acute childhood wheeze/asthma attacks to describe variation in safety netting and recovery bronchodilator dosing. DESIGN: Two-phase study between June 2020 and September 2021, comprising (1) Departmental discharge practice survey, and (2) Analysis of written discharge instructions for caregivers. SETTING: Secondary and tertiary EDs in rural and urban settings, from Paediatric Emergency Research in the UK and Ireland (PERUKI). MAIN OUTCOME MEASURES: Describe practice and variation in discharge advice, treatment recommendations and safety netting provision. RESULTS: Of 66/71 (93%) participating sites, 62/66 (93.9%) reported providing written safety netting information. 52/66 (78.8%) 'nearly always' assessed inhaler/spacer technique; routine medication review (21/66; 31.8%) and adherence (16/66; 21.4%) were less frequent. In phase II, 61/66 (92.4%) submitted their discharge documents; 50/66 (81.9%) included bronchodilator plans. 11/66 (18.0%) provided Personalised Asthma Action Plans as sole discharge information. 45/50 (90%) provided 'fixed' bronchodilator dosing regimes; dose tapering was common (38/50; 76.0%). Median starting dose was 10 puffs 4 hourly (27/50, 54.0%); median duration was 4 days (29/50, 58.0%). 13/61 (21.3%) did not provide bronchodilator advice for acute deterioration; where provided, 42/48 (87.5%) recommended 10 puffs immediately. Subsequent dosages varied considerably. Common red flags included inability to speak (52/61, 85.2%), inhalers not lasting 4 hours (51/61, 83.6%) and respiratory distress (49/61, 80.3%). CONCLUSIONS: There is variation in bronchodilator dosing and safety netting content for recovery following acute wheeze and asthma attacks. This reflects a lack of evidence, affirming need for further multicentre studies regarding bronchodilator recovery strategies and optimal safety netting advice.

Do Suicide Attempters Have a Right Not to Be Stabilized in an Emergency?

The standard of care in the United States favors stabilizing any adult who arrives in an emergency department after a failed suicide attempt, even if he appears decisionally capacitated and refuses life-sustaining treatment. I challenge this ubiquitous practice. Emergency clinicians generally have a moral obligation to err on the side of stabilizing even suicide attempters who refuse such interventions. This obligation reflects the fact that it is typically infeasible to determine these patients' level of decisional capacitation-among other relevant information-in this unique setting. Nevertheless, I argue, stabilizing suicide attempters over their objection sometimes violates a basic yet insufficiently appreciated right of theirs-the right against bodily invasion. In such cases, it is at least prima facie wrong to stabilize a patient who wants to die even if they lack a contrary advance directive or medical order and suffer from no terminal physical illness.

Intussusception as a Presentation of Anisakis Infestation in the Global Era of Raw Fish Consumption: A Case Report and Literature Review.

Anisakiosis, also known as Anisakis larvae infestation, is an increasing parasitic infestation due to the worldwide spread of raw fish and shellfish consumption habits. We present a rare presentation of intestinal intussusception as a preoperative diagnosis and noticed it postoperatively due to Anisakis larvae. A 43-year-old man presented to the emergency department with abdominal pain around the umbilicus and vomiting for several hours. On physical examination at presentation, he had tenderness in the lower abdomen. His radiological studies showed a right-sided pseudo-kidney sign and ileo-colonic intussusception on ultrasound echography. His computed tomography images added findings of submucosal edema and wall thickening in the terminal ileum, swollen regional lymph nodes, and ascites. An urgent laparotomy was performed for ileo-colonic intussusception of an unknown cause. During the laparotomy, the ileocecal intussusception was manually reduced after dissecting the adhesion due to the previous appendectomy, and a partial ileotomy was undertaken using the Endo-GIA automatic anastomosis device. At the resected ileal wall surface, the presence of Anisakis larvae was noticed, and anisakidosis was diagnosed. The dietary history taken post-operatively revealed that he had eaten salmon, bonito, and squid sashimi four days prior to his emergency department visit. His postoperative course was uneventful, and he was discharged from the hospital on the fifth day postoperatively. Anisakiosis must be in the differential diagnosis of intussusception, and eating history seems like a cue to diagnose, and it might be meaningful to clinicians.

Severe Sinus Dysfunction in the Context of Chronic Lithium Intoxication and Poorly Controlled Hypothyroidism.

Cardiotoxicity associated with lithium is not a common event; however, it is potentially life-threatening, manifesting electrocardiographically with sinoatrial blocks, high-degree atrioventricular blocks, QT prolongation, and ventricular tachyarrhythmias. This case report presents a patient with severe sinus dysfunction in a clinically severe presentation secondary to cardiogenic shock. The patient sought medical attention for a one-week history of non-anginal chest pain, dizziness without syncope, generalized weakness, and somnolence progressing to bedridden status in the days preceding hospital admission. Laboratory findings revealed elevated blood levels of lithium and thyroid-stimulating hormone (TSH), along with concomitant Acute Kidney Injury Network (AKIN) II acute kidney injury. Subsequently, the patient was admitted to the intensive care unit, where persistent extreme sinus bradycardia of 30 bpm (beats per minute) with sinus pauses without ischemic changes was observed. The patient received supportive treatment, including renal replacement therapy, resulting in complete recovery of hemodynamic status without the need for long-term cardiac conduction devices.

Identifying signs and symptoms of urinary tract infection from emergency department clinical notes using large language models.

BACKGROUND: Natural language processing (NLP) tools including recently developed large language models (LLMs) have myriad potential applications in medical care and research, including the efficient labeling and classification of unstructured text such as electronic health record (EHR) notes. This opens the door to large-scale projects that rely on variables that are not typically recorded in a structured form, such as patient signs and symptoms. OBJECTIVES: This study is designed to acquaint the emergency medicine research community with the foundational elements of NLP, highlighting essential terminology, annotation methodologies, and the intricacies involved in training and evaluating NLP models. Symptom characterization is critical to urinary tract infection (UTI) diagnosis, but identification of symptoms from the EHR has historically been challenging, limiting large-scale research, public health surveillance, and EHR-based clinical decision support. We therefore developed and compared two NLP models to identify UTI symptoms from unstructured emergency department (ED) notes. METHODS: The study population consisted of patients aged ≥ 18 who presented to an ED in a northeastern U.S. health system between June 2013 and August 2021 and had a urinalysis performed. We annotated a random subset of 1250 ED clinician notes from these visits for a list of 17 UTI symptoms. We then developed two task-specific LLMs to perform the task of named entity recognition: a convolutional neural network-based model (SpaCy) and a transformer-based model designed to process longer documents (Clinical Longformer). Models were trained on 1000 notes and tested on a holdout set of 250 notes. We compared model performance (precision, recall, F1 measure) at identifying the presence or absence of UTI symptoms at the note level. RESULTS: A total of 8135 entities were identified in 1250 notes; 83.6% of notes included at least one entity. Overall F1 measure for note-level symptom identification weighted by entity frequency was 0.84 for the SpaCy model and 0.88 for the Longformer model. F1 measure for identifying presence or absence of any UTI symptom in a clinical note was 0.96 (232/250 correctly classified) for the SpaCy model and 0.98 (240/250 correctly classified) for the Longformer model. CONCLUSIONS: The study demonstrated the utility of LLMs and transformer-based models in particular for extracting UTI symptoms from unstructured ED clinical notes; models were highly accurate for detecting the presence or absence of any UTI symptom on the note level, with variable performance for individual symptoms.