Student ultrasound education - current views and controversies.

As an extension of the clinical examination and as a diagnostic and problem-solving tool, ultrasound has become an established technique for clinicians. A prerequisite for high-quality clinical ultrasound practice is adequate student ultrasound training. In light of the considerable heterogeneity of ultrasound curricula in medical studies worldwide, this review presents basic principles of modern medical student ultrasound education and advocates for the establishment of an ultrasound core curriculum embedded both horizontally and vertically in medical studies.

Ultrasound during Advanced Life Support-Help or Harm?

Ultrasound is used in cardiopulmonary resuscitation (CPR) and advanced life support (ALS). However, there is divergence between the recommendations of many emergency and critical care societies who support its use and the recommendations of many international resuscitation organizations who either recommend against its use or recommend it only in limited circumstances. Ultrasound offers potential benefits of detecting reversable causes of cardiac arrest, allowing specific interventions. However, it also risks interfering with ALS protocols and increasing unhelpful interventions. As with many interventions in ALS, the evidence base for ultrasound use is weak, and well-designed randomized trials are needed. This paper reviews the current theory and evidence for harms and benefits.

Attitudes towards artificial intelligence in emergency medicine.

OBJECTIVE: To assess Australian and New Zealand emergency clinicians' attitudes towards the use of artificial intelligence (AI) in emergency medicine. METHODS: We undertook a qualitative interview-based study based on grounded theory. Participants were recruited through ED internal mailing lists, the Australasian College for Emergency Medicine Bulletin, and the research teams' personal networks. Interviews were transcribed, coded and themes presented. RESULTS: Twenty-five interviews were conducted between July 2021 and May 2022. Thematic saturation was achieved after 22 interviews. Most participants were from either Western Australia (52%) or Victoria (16%) and were consultants (96%). More participants reported feeling optimistic (10/25) than neutral (6/25), pessimistic (2/25) or mixed (7/25) towards the use of AI in the ED. A minority expressed scepticism regarding the feasibility or value of implementing AI into the ED. Multiple potential risks and ethical issues were discussed by participants including skill loss from overreliance on AI, algorithmic bias, patient privacy and concerns over liability. Participants also discussed perceived inadequacies in existing information technology systems. Participants felt that AI technologies would be used as decision support tools and not replace the roles of emergency clinicians. Participants were not concerned about the impact of AI on their job security. Most (17/25) participants thought that AI would impact emergency medicine within the next 10 years. CONCLUSIONS: Emergency clinicians interviewed were generally optimistic about the use of AI in emergency medicine, so long as it is used as a decision support tool and they maintain the ability to override its recommendations.

Applications of natural language processing at emergency department triage: A narrative review.

INTRODUCTION: Natural language processing (NLP) uses various computational methods to analyse and understand human language, and has been applied to data acquired at Emergency Department (ED) triage to predict various outcomes. The objective of this scoping review is to evaluate how NLP has been applied to data acquired at ED triage, assess if NLP based models outperform humans or current risk stratification techniques when predicting outcomes, and assess if incorporating free-text improve predictive performance of models when compared to predictive models that use only structured data. METHODS: All English language peer-reviewed research that applied an NLP technique to free-text obtained at ED triage was eligible for inclusion. We excluded studies focusing solely on disease surveillance, and studies that used information obtained after triage. We searched the electronic databases MEDLINE, Embase, Cochrane Database of Systematic Reviews, Web of Science, and Scopus for medical subject headings and text keywords related to NLP and triage. Databases were last searched on 01/01/2022. Risk of bias in studies was assessed using the Prediction model Risk of Bias Assessment Tool (PROBAST). Due to the high level of heterogeneity between studies and high risk of bias, a metanalysis was not conducted. Instead, a narrative synthesis is provided. RESULTS: In total, 3730 studies were screened, and 20 studies were included. The population size varied greatly between studies ranging from 1.8 million patients to 598 triage notes. The most common outcomes assessed were prediction of triage score, prediction of admission, and prediction of critical illness. NLP models achieved high accuracy in predicting need for admission, triage score, critical illness, and mapping free-text chief complaints to structured fields. Incorporating both structured data and free-text data improved results when compared to models that used only structured data. However, the majority of studies (80%) were assessed to have a high risk of bias, and only one study reported the deployment of an NLP model into clinical practice. CONCLUSION: Unstructured free-text triage notes have been used by NLP models to predict clinically relevant outcomes. However, the majority of studies have a high risk of bias, most research is retrospective, and there are few examples of implementation into clinical practice. Future work is needed to prospectively assess if applying NLP to data acquired at ED triage improves ED outcomes when compared to usual clinical practice.

Western Australian medical students' attitudes towards artificial intelligence in healthcare.

INTRODUCTION: Surveys conducted internationally have found widespread interest in artificial intelligence (AI) amongst medical students. No similar surveys have been conducted in Western Australia (WA) and it is not known how medical students in WA feel about the use of AI in healthcare or their understanding of AI. We aim to assess WA medical students' attitudes towards AI in general, AI in healthcare, and the inclusion of AI education in the medical curriculum. METHODS: A digital survey instrument was developed based on a review of available literature and consultation with subject matter experts. The survey was piloted with a group of medical students and refined based on their feedback. We then sent this anonymous digital survey to all medical students in WA (approximately 1539 students). Responses were open from the 7th of September 2021 to the 7th of November 2021. Students' categorical responses were qualitatively analysed, and free text comments from the survey were qualitatively analysed using open coding techniques. RESULTS: Overall, 134 students answered one or more questions (8.9% response rate). The majority of students (82.0%) were 20-29 years old, studying medicine as a postgraduate degree (77.6%), and had started clinical rotations (62.7%). Students were interested in AI (82.6%), self-reported having a basic understanding of AI (84.8%), but few agreed that they had an understanding of the basic computational principles of AI (33.3%) or the limitations of AI (46.2%). Most students (87.5%) had not received teaching in AI. The majority of students (58.6%) agreed that AI should be part of medical training and most (72.7%) wanted more teaching focusing on AI in medicine. Medical students appeared optimistic regarding the role of AI in medicine, with most (74.4%) agreeing with the statement that AI will improve medicine in general. The majority (56.6%) of medical students were not concerned about the impact of AI on their job security as a doctor. Students selected radiology (72.6%), pathology (58.2%), and medical administration (44.8%) as the specialties most likely to be impacted by AI, and psychiatry (61.2%), palliative care (48.5%), and obstetrics and gynaecology (41.0%) as the specialties least likely to be impacted by AI. Qualitative analysis of free text comments identified the use of AI as a tool, and that doctors will not be replaced as common themes. CONCLUSION: Medical students in WA appear to be interested in AI. However, they have not received education about AI and do not feel they understand its basic computational principles or limitations. AI appears to be a current deficit in the medical curriculum in WA, and most students surveyed were supportive of its introduction. These results are consistent with previous surveys conducted internationally.

Deep learning model to predict exercise stress test results: Optimizing the diagnostic test selection strategy and reduce wastage in suspected coronary artery disease patients.

BACKGROUND: Cardiac exercise stress testing (EST) offers a non-invasive way in the management of patients with suspected coronary artery disease (CAD). However, up to 30% EST results are either inconclusive or non-diagnostic, which results in significant resource wastage. Our aim was to build machine learning (ML) based models, using patients demographic (age, sex) and pre-test clinical information (reason for performing test, medications, blood pressure, heart rate, and resting electrocardiogram), capable of predicting EST results beforehand including those with inconclusive or non-diagnostic results. METHODS: A total of 30,710 patients (mean age 54.0 years, 69% male) were included in the study with 25% randomly sampled in the test set, and the remaining samples were split into a train and validation set with a ratio of 9:1. We constructed different ML models from pre-test variables and compared their discriminant power using the area under the receiver operating characteristic curve (AUC). RESULTS: A network of Oblivious Decision Trees provided the best discriminant power (AUC=0.83, sensitivity=69%, specificity=0.78%) for predicting inconclusive EST results. A total of 2010 inconclusive ESTs were correctly identified in the testing set. CONCLUSIONS: Our ML model, developed using demographic and pre-test clinical information, can accurately predict EST results and could be used to identify patients with inconclusive or non-diagnostic results beforehand. Our system could thus be used as a personalised decision support tool by clinicians for optimizing the diagnostic test selection strategy for CAD patients and to reduce healthcare expenditure by reducing nondiagnostic or inconclusive ESTs.

Right Iliac Fossa Pain other than Appendicitis: A Pictorial Review.

Right iliac fossa pain is a common presentation. Although appendicitis is the most common surgical emergency, many other pathologies can have similar presentations and should be considered. This review describes the findings and shows examples of conditions other than appendicitis that should be examined for in a patient who presents with right iliac fossa pain, particularly if the appendix is not seen or seen to be normal.

Applications of machine learning to undifferentiated chest pain in the emergency department: A systematic review.

BACKGROUND: Chest pain is amongst the most common reason for presentation to the emergency department (ED). There are many causes of chest pain, and it is important for the emergency physician to quickly and accurately diagnose life threatening causes such as acute myocardial infarction (AMI). Multiple clinical decision tools have been developed to assist clinicians in risk stratifying patients with chest. There is growing recognition that machine learning (ML) will have a significant impact on the practice of medicine in the near future and may assist with diagnosis and risk stratification. This systematic review aims to evaluate how ML has been applied to adults presenting to the ED with undifferentiated chest pain and assess if ML models show improved performance when compared to physicians or current risk stratification techniques. METHODS AND FINDINGS: We conducted a systematic review of journal articles that applied a ML technique to an adult patient presenting to an emergency department with undifferentiated chest pain. Multiple databases were searched from inception through to November 2020. In total, 3361 articles were screened, and 23 articles were included. We did not conduct a metanalysis due to a high level of heterogeneity between studies in both their methods, and reporting. The most common primary outcomes assessed were diagnosis of acute myocardial infarction (AMI) (12 studies), and prognosis of major adverse cardiovascular event (MACE) (6 studies). There were 14 retrospective studies and 5 prospective studies. Four studies reported the development of a machine learning model retrospectively then tested it prospectively. The most common machine learning methods used were artificial neural networks (14 studies), random forest (6 studies), support vector machine (5 studies), and gradient boosting (2 studies). Multiple studies achieved high accuracy in both the diagnosis of AMI in the ED setting, and in predicting mortality and composite outcomes over various timeframes. ML outperformed existing risk stratification scores in all cases, and physicians in three out of four cases. The majority of studies were single centre, retrospective, and without prospective or external validation. There were only 3 studies that were considered low risk of bias and had low applicability concerns. Two studies reported integrating the ML model into clinical practice. CONCLUSIONS: Research on applications of ML for undifferentiated chest pain in the ED has been ongoing for decades. ML has been reported to outperform emergency physicians and current risk stratification tools to diagnose AMI and predict MACE but has rarely been integrated into practice. Many studies assessing the use of ML in undifferentiated chest pain in the ED have a high risk of bias. It is important that future studies make use of recently developed standardised ML reporting guidelines, register their protocols, and share their datasets and code. Future work is required to assess the impact of ML model implementation on clinical decision making, patient orientated outcomes, and patient and physician acceptability. TRIAL REGISTRATION: International Prospective Register of Systematic Reviews registration number: CRD42020184977.

Artificial intelligence-enhanced echocardiography in the emergency department.

A focused cardiac ultrasound performed by an emergency physician is becoming part of the standard assessment of patients in a variety of clinical situations. The development of inexpensive, portable handheld devices promises to make point-of-care ultrasound even more accessible over the coming decades. Many of these handheld devices are beginning to integrate artificial intelligence (AI) for image analysis. The integration of AI into focused cardiac ultrasound will have a number of implications for emergency physicians. This perspective presents an overview of the current state of AI research in echocardiography relevant to the emergency physician, as well as the future possibilities, challenges and risks of this technology.

Credentialing of emergency medicine trainees in point-of-care ultrasound: An effective, efficient and enjoyable model.

OBJECTIVE: The Australasian College for Emergency Medicine Curriculum Framework contains numerous mentions of point-of-care ultrasound (PoCUS). However, obtaining formal PoCUS credentials is often problematic. The Fiona Stanley Hospital ED PoCUS training programme was devised to assist emergency medicine trainees to meet the credentialing requirements of the Australasian College for Emergency Medicine and the Australasian Society for Ultrasound in Medicine. METHODS: Six emergency medicine registrars are selected for each 6-month semester. Successful applicants nominate two modules of Australasian Society for Ultrasound in Medicine's Certificate in Clinician Performed Ultrasound and receive dedicated non-clinical time. For 3 h a week, an emergency physician holding formal PoCUS credentials supervises a pair of trainees while they perform scans on ED patients. During these sessions, trainee logbooks can be reviewed and assessments occur as required by the module. RESULTS: Over an 18-month period, 18 emergency registrars were involved, averaging eight 3-h sessions each. All selected the Extended Focused Abdominal Scan for Trauma module, 14 chose Abdominal Aortic Aneurysm and eight chose Basic Echo in Life Support. Overall, 30 (75%) of 40 modules were completed within the trainees' 6-month semester. Just under half of logged scans were obtained during the supervised sessions. Overall, the average number of scans performed exceeded each module's logbook requirements. Trainees perceived that involvement in the programme benefited their ability to manage patients. There was overwhelming support for the structure of the programme. CONCLUSIONS: The Fiona Stanley Hospital ED model is effective in assisting emergency medicine trainees to gain formal PoCUS credentials. As it requires relatively little organisation, time and staffing, it could be adopted in many EDs around Australia and New Zealand.

Ultrasound-guided femoral nerve blocks are not superior to ultrasound-guided fascia iliaca blocks for fractured neck of femur.

OBJECTIVE: To determine if an ultrasound-guided femoral nerve block (FNB) is superior to an ultrasound-guided fascia iliaca compartment block (FICB) in providing pain relief to patients with a neck of femur or proximal femoral fracture. METHODS: A double-blind randomised controlled trial was conducted. All participants received two blocks, one active and one placebo. An active FICB was administered to 52 participants and 48 participants received an active FNB. RESULTS: Analysis was completed on data collected from 100 participants. Most patients were elderly and the majority were female. Both FICB and FNB achieved clinically significant mean reductions in pain scores (2.62 for FICB and 2.3 for FNB). There was no significant difference in reduction in pain scores between the two cohorts, P = 0.408. CONCLUSIONS: Ultrasound-guided FNB is not superior to ultrasound-guided FICB, with both facilitating an equivalent analgesia effect in patients with a neck of femur or proximal femur fracture.

How to perform gastrointestinal ultrasound: Anatomy and normal findings.

Gastrointestinal ultrasound is a practical, safe, cheap and reproducible diagnostic tool in inflammatory bowel disease gaining global prominence amongst clinicians. Understanding the embryological processes of the intestinal tract assists in the interpretation of abnormal sonographic findings. In general terms, the examination principally comprises interrogation of the colon, mesentery and small intestine using both low-frequency and high-frequency probes. Interpretation of findings on GIUS includes assessment of bowel wall thickness, symmetry of this thickness, evidence of transmural changes, assessment of vascularity using Doppler imaging and assessment of other specific features including lymph nodes, mesentery and luminal motility. In addition to B-mode imaging, transperineal ultrasonography, elastography and contrast-enhanced ultrasonography are useful adjuncts. This supplement expands upon these features in more depth.

Point of Care Ultrasound: A WFUMB Position Paper.

Over the last decade, the use of portable ultrasound scanners has enhanced the concept of point of care ultrasound (PoC-US), namely, "ultrasound performed at the bedside and interpreted directly by the treating clinician." PoC-US is not a replacement for comprehensive ultrasound, but rather allows physicians immediate access to clinical imaging for rapid and direct solutions. PoC-US has already revolutionized everyday clinical practice, and it is believed that it will dramatically change how ultrasound is applied in daily practice. However, its use and teaching are different from continent to continent and from country to country. This World Federation for Ultrasound in Medicine and Biology position paper discusses the current status and future perspectives of PoC-US. Particular attention is given to the different uses of PoC-US and its clinical significance, including within emergency and critical care medicine, cardiology, anesthesiology, rheumatology, obstetrics, neonatology, gynecology, gastroenterology and many other applications. In the future, PoC-US will be more diverse than ever and be included in medical student training.

WFUMB Position Paper. Learning Gastrointestinal Ultrasound: Theory and Practice.

Gastrointestinal ultrasound (GIUS) is an ultrasound application that has been practiced for more than 30 years. Recently, GIUS has enjoyed a resurgence of interest, and there is now strong evidence of its utility and accuracy as a diagnostic tool for multiple indications. The method of learning GIUS is not standardised and may incorporate mentorship, didactic teaching and e-learning. Simulation, using either low- or high-fidelity models, can also play a key role in practicing and honing novice GIUS skills. A course for training as well as establishing and evaluating competency in GIUS is proposed in the manuscript, based on established learning theory practice. We describe the broad utility of GIUS in clinical medicine, including a review of the literature and existing meta-analyses. Further, the manuscript calls for agreement on international standards regarding education, training and indications.

Interrater agreement between expert and novice in measuring inferior vena cava diameter and collapsibility index.

BACKGROUND: In critical care medicine, US views of the inferior vena cava (IVC) and its change with respiration are used to estimate the intravascular volume status of unwell patients and, in particular, to answer the question: 'Is this patient likely to be fluid responsive?' Most commonly in the literature, the subxiphisternal (SX) window in the longitudinal plane is utilised. To date, no study has specifically assessed interrater agreement in estimating IVC diameter between emergency medicine specialists (experts) and trainees (learners). OBJECTIVES: To determine the interrater agreement between an expert (senior emergency specialist with US qualifications) and learner (emergency medicine trainee) when measuring IVC diameter (IVCD) and IVC collapsibility index (IVCCI) in the SX longitudinal US window in healthy volunteers. METHODS: Healthy volunteers (ED staff) were scanned in the supine position using a sector (cardiac) probe of a portable US machine, in the SX longitudinal position. The maximum and minimum diameters of the IVC were measured in each of these positions and the IVCCI calculated. Results were analysed using Bland-Altman plots. RESULTS: In the longitudinal SX window, the operators' measurements of maximum IVCD differed by an average of 1.9 mm (95% limits of agreement -9.4 mm to +5.5 mm) and their measurement of IVCCI differed by an average of 4% (95% limits of agreement -30% to 38%). CONCLUSIONS: The wide 95% limits of agreement demonstrate a poor interrater agreement between the IVC US measurements obtained by expert and learner users in the assessment of fluid status. These ranges are greater than clinically acceptable.

International evidence-based recommendations for focused cardiac ultrasound.

BACKGROUND: Focused cardiac ultrasound (FoCUS) is a simplified, clinician-performed application of echocardiography that is rapidly expanding in use, especially in emergency and critical care medicine. Performed by appropriately trained clinicians, typically not cardiologists, FoCUS ascertains the essential information needed in critical scenarios for time-sensitive clinical decision making. A need exists for quality evidence-based review and clinical recommendations on its use. METHODS: The World Interactive Network Focused on Critical UltraSound conducted an international, multispecialty, evidence-based, methodologically rigorous consensus process on FoCUS. Thirty-three experts from 16 countries were involved. A systematic multiple-database, double-track literature search (January 1980 to September 2013) was performed. The Grading of Recommendation, Assessment, Development and Evaluation method was used to determine the quality of available evidence and subsequent development of the recommendations. Evidence-based panel judgment and consensus was collected and analyzed by means of the RAND appropriateness method. RESULTS: During four conferences (in New Delhi, Milan, Boston, and Barcelona), 108 statements were elaborated and discussed. Face-to-face debates were held in two rounds using the modified Delphi technique. Disagreement occurred for 10 statements. Weak or conditional recommendations were made for two statements and strong or very strong recommendations for 96. These recommendations delineate the nature, applications, technique, potential benefits, clinical integration, education, and certification principles for FoCUS, both for adults and pediatric patients. CONCLUSIONS: This document presents the results of the first International Conference on FoCUS. For the first time, evidence-based clinical recommendations comprehensively address this branch of point-of-care ultrasound, providing a framework for FoCUS to standardize its application in different clinical settings around the world.

Detection of intraperitoneal free gas by ultrasound.

Introduction: Patients with acute abdominal pain may have unsuspected pneumoperitoneum, and be investigated with ultrasound. Although not the primary imaging modality for this condition, ultrasound will usually demonstrate signs of free intraperitoneal or extra-luminal gas. Methods: Sonographic signs of pneumoperitoneum are described, along with the limitations and pitfalls of the technique. The reported accuracy of these signs is described. Conclusion: The different signs that may be seen are described, and it is suggested that all who ultrasound patients for abdominal pain should be aware of these.