Complex Clinical Tasks Research Articles

Evaluating the Performance of ChatGPT in the Prescribing Safety Assessment: Implications for Artificial Intelligence-Assisted Prescribing.

Objective With the rapid advancement of artificial intelligence (AI) technologies, models likeChat Generative Pre-Trained Transformer (ChatGPT) are increasingly being evaluated for their potential applications in healthcare. The Prescribing Safety Assessment (PSA) is a standardised test for junior physicians in the UK to evaluate prescribing competence. This study aims to assess ChatGPT's ability to pass the PSA and its performance across different exam sections. Methodology ChatGPT (version GPT-4) was tested on four official PSA practice papers, each containing 30 questions, in three independent trials per paper, with answers evaluated using official PSA mark schemes. Performance was measured by calculating overall percentage scores and comparing them to the pass marks provided for each practice paper. Subsection performance was also analysed to identify strengths and weaknesses. Results ChatGPT achieved mean scores of 257/300 (85.67%), 236/300 (78.67%), 199/300 (66.33%), and 233/300 (77.67%) across the four papers, consistently surpassing the pass marks where available. ChatGPT performed well in sections requiring factual recall, such as "Adverse Drug Reactions", scoring 63/72 (87.50%), and "Communicating Information", scoring 63/72 (88.89%). However, it struggled in "Data Interpretation", scoring 32/72 (44.44%), showing variability across trials and indicating limitations in handling more complex clinical reasoning tasks. Conclusion While ChatGPT demonstrated strong potential in passing the PSA and excelling in sections requiring factual knowledge, its limitations in data interpretation highlight the current gaps in AI's ability to fully replicate human clinical judgement. ChatGPT shows promise in supporting safe prescribing, particularly in areas prone to human error, such as drug interactions and communicating correct information. However, due to its variability in more complex reasoning tasks, ChatGPT is not yet ready to replace human prescribers and should instead serve as a supplemental tool in clinical practice.

Revealing the hidden vulnerabilities of psychiatrists: Insights from the Romanian health system. A sociological and empirical study

It is well known that the medical and sociological literature abounds in materials that present a whole series of categories of patients as being part of vulnerable population categories. Medical professionals, and doctors, in particular, are seen as parts of the therapeutic relationship holding power, also leading to an image of a 'privileged' social group. Although this idea is a predominant one within classical sociological theories, but also within the traditional image of the doctor, if we look in a certain context, such as the functional one of the Romanian health system, we can reveal another social image of today's psychiatrist. The present work wants to outline such a picture, starting from theoretical landmarks of medical sociology and observing a whole series of social realities identified through empirical research based on ethnographic evidence, but also on analyses of publicly available secondary data. The conceptualization of the vulnerability of psychiatrists will be highlighted within the complex interactions within the health system, which is in a problematic relationship with the entire social system. Finally, we want to undertake exploratory research on the specific vulnerabilities of psychiatrists (some vulnerabilities characterizing the entire professional body of doctors): complex clinical tasks, limited collaboration with other categories of doctors, limitation of resources specific to the profession (paraclinical and laboratory examinations), rigid control, extensive and overlapping of different control bodies, geographical isolation from other medical institutions and the emotional impact in the face of patients' suffering. The vulnerability of doctors overlaps, but also inverts, that of patients, accentuating a whole series of already existing problems. Defining the group of psychiatrists as a vulnerable social group generates the need to identify answers for a problem that we consider fundamental: difficulties arising in the complex of mental health care can lead to a real social problem.

BI-RADS Category Assignments by GPT-3.5, GPT-4, and Google Bard: A Multilanguage Study.

Background The performance of publicly available large language models (LLMs) remains unclear for complex clinical tasks. Purpose To evaluate the agreement between human readers and LLMs for Breast Imaging Reporting and Data System (BI-RADS) categories assigned based on breast imaging reports written in three languages and to assess the impact of discordant category assignments on clinical management. Materials and Methods This retrospective study included reports for women who underwent MRI, mammography, and/or US for breast cancer screening or diagnostic purposes at three referral centers. Reports with findings categorized as BI-RADS 1-5 and written in Italian, English, or Dutch were collected between January 2000 and October 2023. Board-certified breast radiologists and the LLMs GPT-3.5 and GPT-4 (OpenAI) and Bard, now called Gemini (Google), assigned BI-RADS categories using only the findings described by the original radiologists. Agreement between human readers and LLMs for BI-RADS categories was assessed using the Gwet agreement coefficient (AC1 value). Frequencies were calculated for changes in BI-RADS category assignments that would affect clinical management (ie, BI-RADS 0 vs BI-RADS 1 or 2 vs BI-RADS 3 vs BI-RADS 4 or 5) and compared using the McNemar test. Results Across 2400 reports, agreement between the original and reviewing radiologists was almost perfect (AC1 = 0.91), while agreement between the original radiologists and GPT-4, GPT-3.5, and Bard was moderate (AC1 = 0.52, 0.48, and 0.42, respectively). Across human readers and LLMs, differences were observed in the frequency of BI-RADS category upgrades or downgrades that would result in changed clinical management (118 of 2400 [4.9%] for human readers, 611 of 2400 [25.5%] for Bard, 573 of 2400 [23.9%] for GPT-3.5, and 435 of 2400 [18.1%] for GPT-4; P < .001) and that would negatively impact clinical management (37 of 2400 [1.5%] for human readers, 435 of 2400 [18.1%] for Bard, 344 of 2400 [14.3%] for GPT-3.5, and 255 of 2400 [10.6%] for GPT-4; P < .001). Conclusion LLMs achieved moderate agreement with human reader-assigned BI-RADS categories across reports written in three languages but also yielded a high percentage of discordant BI-RADS categories that would negatively impact clinical management. © RSNA, 2024 Supplemental material is available for this article.

Clinical Decision Support Requirements for Ventricular Tachycardia Diagnosis Within the Frameworks of Knowledge and Practice: Survey Study.

Ventricular tachycardia (VT) diagnosis is challenging due to the similarity between VT and some forms of supraventricular tachycardia, complexity of clinical manifestations, heterogeneity of underlying diseases, and potential for life-threatening hemodynamic instability. Clinical decision support systems (CDSSs) have emerged as promising tools to augment the diagnostic capabilities of cardiologists. However, a requirements analysis is acknowledged to be vital for the success of a CDSS, especially for complex clinical tasks such as VT diagnosis. The aims of this study were to analyze the requirements for a VT diagnosis CDSS within the frameworks of knowledge and practice and to determine the clinical decision support (CDS) needs. Our multidisciplinary team first conducted semistructured interviews with seven cardiologists related to the clinical challenges of VT and expected decision support. A questionnaire was designed by the multidisciplinary team based on the results of interviews. The questionnaire was divided into four sections: demographic information, knowledge assessment, practice assessment, and CDS needs. The practice section consisted of two simulated cases for a total score of 10 marks. Online questionnaires were disseminated to registered cardiologists across China from December 2022 to February 2023. The scores for the practice section were summarized as continuous variables, using the mean, median, and range. The knowledge and CDS needs sections were assessed using a 4-point Likert scale without a neutral option. Kruskal-Wallis tests were performed to investigate the relationship between scores and practice years or specialty. Of the 687 cardiologists who completed the questionnaire, 567 responses were eligible for further analysis. The results of the knowledge assessment showed that 383 cardiologists (68%) lacked knowledge in diagnostic evaluation. The overall average score of the practice assessment was 6.11 (SD 0.55); the etiological diagnosis section had the highest overall scores (mean 6.74, SD 1.75), whereas the diagnostic evaluation section had the lowest scores (mean 5.78, SD 1.19). A majority of cardiologists (344/567, 60.7%) reported the need for a CDSS. There was a significant difference in practice competency scores between general cardiologists and arrhythmia specialists (P=.02). There was a notable deficiency in the knowledge and practice of VT among Chinese cardiologists. Specific knowledge and practice support requirements were identified, which provide a foundation for further development and optimization of a CDSS. Moreover, it is important to consider clinicians' specialization levels and years of practice for effective and personalized support.

Riding to the Rescue: A Comprehensive Review of Health and Safety Measures in Ambulance Cars

Paramedics are registered health professionals in numerous countries. Whilst ambulance services must prioritize their patients, they also require personnel to be healthy to perform at their utmost to provide optimal patient care. Ambulance transport is associated with predictable and likely preventable occupant hazards. Ambulance services provide care 24 hours a day, 7 days a week, and shift work is known to be a risk factor for poor health. Working unsociable hours has detrimental consequences on the health and well-being of healthcare workers and can ultimately result in compromised patient care. Ambulance service utilization rates are high, with paramedics working in unpredictable environments, and undertaking complex clinical and manual handling tasks whilst caring for critically unwell patients; thus, there are several reasons postulated for poor health in this professional group. These include injuries, serious infections, high rates of musculoskeletal diseases, stress, and mental health problems. This review article aims to identify the occupational risks in an ambulance service, assess their impact on the health of employees, and explore control measures that can be implemented to reduce the risks and improve the safety of healthcare workers and patients.

Use of fine-needle puncture under endosonographic control in the diagnosis of left atrium sarcoma – case report

Background. Over the past 30 years, with the development of endoscopic technologies and the advent endoscopic ultrasound-guided fine-needle aspiration (EuS-FnA) it has become possible to diagnose with preliminary verification of cardiac tumors, which in turn is an undoubted advantage in detecting cardiac pathology. A rare clinical case is presented: the detection of a tumor of the left atrium using high-tech endoscopic techniques, in particular a EuS-FnA. when studying the surgical material using immunohistochemistry and FISH hybridization, the final diagnosis sounded like intimal sarcoma. Diagnosis of intimal sarcoma is a complex clinical task, and difficulties in making a diagnosis delay the duration of treatment. Our experience demonstrates the modern role of endoscopy as a minimally invasive method of diagnosing intracardiac tumors.

Leveraging ChatGPT in the Pediatric Neurology Clinic: Practical Considerations for Use to Improve Efficiency and Outcomes

BackgroundArtificial intelligence (AI) is progressively influencing healthcare sectors, including pediatric neurology. This paper aims to investigate the potential and limitations of using ChatGPT, a large language model (LLM) developed by OpenAI, in an outpatient pediatric neurology clinic. The analysis focuses on the tool's capabilities in enhancing clinical efficiency, productivity, and patient education. MethodThis is an opinion-based exploration supplemented with practical examples. We assessed ChatGPT's utility in administrative and educational tasks such as drafting medical necessity letters and creating patient educational materials. ResultsChatGPT showed efficacy in streamlining administrative work, particularly in drafting administrative letters and formulating personalized patient education materials. However, the model has limitations in performing higher-order tasks like formulating nuanced differential diagnoses. Additionally, ethical and legal concerns, including data privacy and the potential dissemination of misinformation, warrant cautious implementation. ConclusionsThe integration of AI tools like ChatGPT in pediatric neurology clinics has demonstrated promising results in boosting efficiency and patient education, despite present limitations and ethical concerns. As technology advances, we anticipate future applications may extend to more complex clinical tasks like precise differential diagnoses and treatment strategy guidance. Careful, patient-centered implementation is essential for leveraging the potential benefits of AI in pediatric neurology effectively.

АВТОМАТИЗИРОВАННАЯ СИСТЕМА ИЗВЛЕЧЕНИЯ КЛИНИЧЕСКИ РЕЛЕВАНТНЫХ ТЕРМИНОВ UMLS ИЗ ТЕКСТОВ АНГЛОЯЗЫЧНЫХ СТАТЕЙ НА ПРИМЕРЕ АКСИАЛЬНОГО СПОНДИЛОАРТРИТА

Significance. Early detection of axial spondyloarthritis (axSpA) is a complex clinical task. Quality improvement of axSpA diagnostics in primary care settings is possible with the help of decision-making information systems based on the ontological approach application. The key stage of the decision-making system development consists of the elaboration of a set of clinical terms. This set should fully describe clinical area or sub-area under study. One of the essential requirements is compliance of the clinical terms used with the existing clinical nomenclatures. Currently, the largest set of clinical terms is the Unified Medical Language System (UMLS) metathesaurus. The majority of UMLS terms is presented in English only. The development of tools for the analysis of unstructured texts and recognition of clinically relevant UMLS entities make it possible to elaborate a set of terms describing axSpA diagnostic aspects. This will also help to compile a list of UMLS terminology nomenclatures for their priority adaptation and expert translation into Russian. The purpose of this study is to develop an automated system for recognizing clinically relevant UMLS terms in texts of the English-language articles. Material and methods. The research material has included English terms (11.2 million) aggregated from 76 nome6nclatures of the current UMLS (2022AB) version. In addition, the study has used texts of PubMed clinical abstracts in English. Queries to the UMLS graph model, semantic algorithms for unstructured texts and machine-learning methods have been applied for data collection and analysis. Results. The study has elaborated a set of high-accuracy regular expressions (F1-score=98%) for metadata elimination from the text corpus. Then the authors have identified patterns for searching clinically relevant terms in the aggregated set of UMLS concepts. Using a logistic regression algorithm, the authors have trained a binary classification model. Input data for the created classificatory are information about an UMLS term. Output data are a label indicating the presence or absence of clinical relevance. Conclusion. The binary classification model has been validated individually and double-tested on different data samples. Values of the accuracy, sensitivity and specificity of metrics equal to 91%, 90% and 91%, respectively, for the validation sample (a number of axSpA terms). In addition, this model has been tested on the sets of terms aggregated for any two diseases. Values of the accuracy metric equal to 91% and 90%, respectively. With the help of the developed machine-learning model, the study has estimated that UMLS contains 1.5 million unique terms applicable to describing a clinical picture. In addition, lists of priority UMLS data sources and thematic groups have been compiled. These clinically relevant UMLS terms should be adapted and translated into Russian as soon as possible.

A Systematic Review of Artificial Intelligence and Machine Learning Applications to Inflammatory Bowel Disease, with Practical Guidelines for Interpretation.

BackgroundInflammatory bowel disease (IBD) is a gastrointestinal chronic disease with an unpredictable disease course. Computational methods such as machine learning (ML) have the potential to stratify IBD patients for the provision of individualized care. The use of ML methods for IBD was surveyed, with an additional focus on how the field has changed over time.MethodsOn May 6, 2021, a systematic review was conducted through a search of MEDLINE and Embase databases, with the search structure (“machine learning” OR “artificial intelligence”) AND (“Crohn* Disease” OR “Ulcerative Colitis” OR “Inflammatory Bowel Disease”). Exclusion criteria included studies not written in English, no human patient data, publication before 2001, studies that were not peer reviewed, nonautoimmune disease comorbidity research, and record types that were not primary research.ResultsSeventy-eight (of 409) records met the inclusion criteria. Random forest methods were most prevalent, and there was an increase in neural networks, mainly applied to imaging data sets. The main applications of ML to clinical tasks were diagnosis (18 of 78), disease course (22 of 78), and disease severity (16 of 78). The median sample size was 263. Clinical and microbiome-related data sets were most popular. Five percent of studies used an external data set after training and testing for additional model validation.DiscussionAvailability of longitudinal and deep phenotyping data could lead to better modeling. Machine learning pipelines that consider imbalanced data and that feature selection only on training data will generate more generalizable models. Machine learning models are increasingly being applied to more complex clinical tasks for specific phenotypes, indicating progress towards personalized medicine for IBD.

Renal Function Protection as an Important Component of a Comprehensive Approach to the Management of Patients with Atrial Fibrillation

The increase in the life expectancy of the population is accompanied by an increase in the prevalence of diseases for which old and senile age are risk factors. Atrial fibrillation (AF) and chronic kidney disease (CKD) are two diseases that can coexist in a patient. The risk of ac thromboembolic and hemorrhagic events in this case increases due to the mutual aggravating influence of these diseases. In addition, these patients have a high incidence of coronary events, and cardiovascular complications are the main cause of death in patients with AF and CKD. Consequently, such patients require an integrated approach to treatment, and their management is a complex clinical task. The direct oral anticoagulant rivaroxaban has been most studied in a population of comorbid AF and CKD patients and has proven a high efficacy and safety profile in these patients in randomized controlled trials. In addition, rivaroxaban has shown a significant reduction in the risk of myocardial infarction in various patients, as well as the possibility of preserving renal function to a greater extent compared with warfarin therapy, and a possible positive effect on reducing the risk of cognitive impairment. A single dosing regimen can improve adherence to treatment, which is one of the key conditions for achieving the above effects. Thus, these factors make it possible to achieve comprehensive protection of comorbid patients with AF and CKD.

Deep-Precognitive Diagnosis: Preventing Future Pandemics by Novel Disease Detection With Biologically-Inspired Conv-Fuzzy Network.

Deep learning-based Computer-Aided Diagnosis has gained immense attention in recent years due to its capability to enhance diagnostic performance and elucidate complex clinical tasks. However, conventional supervised deep learning models are incapable of recognizing novel diseases that do not exist in the training dataset. Automated early-stage detection of novel infectious diseases can be vital in controlling their rapid spread. Moreover, the development of a conventional CAD model is only possible after disease outbreaks and datasets become available for training (viz. COVID-19 outbreak). Since novel diseases are unknown and cannot be included in training data, it is challenging to recognize them through existing supervised deep learning models. Even after data becomes available, recognizing new classes with conventional models requires a complete extensive re-training. The present study is the first to report this problem and propose a novel solution to it. In this study, we propose a new class of CAD models, i.e., Deep-Precognitive Diagnosis, wherein artificial agents are enabled to identify unknown diseases that have the potential to cause a pandemic in the future. A de novo biologically-inspired Conv-Fuzzy network is developed. Experimental results show that the model trained to classify Chest X-Ray (CXR) scans into normal and bacterial pneumonia detected a novel disease during testing, unseen by it in the training sample and confirmed to be COVID-19 later. The model is also tested on SARS-CoV-1 and MERS-CoV samples as unseen diseases and achieved state-of-the-art accuracy. The proposed model eliminates the need for model re-training by creating a new class in real-time for the detected novel disease, thus classifying it on all subsequent occurrences. Second, the model addresses the challenge of limited labeled data availability, which renders most supervised learning techniques ineffective and establishes that modified fuzzy classifiers can achieve high accuracy on image classification tasks.

Development of paradigms for the diagnosis of "covert cognition" and cognitive motor dissociation in patients with chronic disorders of consciousness

The detection of signs of consciousness in patients with chronic disorders of consciousness is a complex clinical task. In recent decades, instrumental methods have been used to improve the accuracy of diagnostics. The phenomenon of covert cognition and cognitive motor dissociation have been demonstrated in a small proportion of patients in studies using instrumental methods in combination with different paradigms. This article describes the main features of the diagnostic paradigms used for such purposes. Currently, the development of its own complex of paradigms is held at the Research Center of Neurology collaboratively with group of neuropsychologists from Lomonosov Moscow State University. The general characteristics of this complex of paradigms are indicated. The practical significance of detecting the phenomenon of covert cognition and cognitive motor dissociation in patients with chronic disorders of consciousness is discussed.

Cephalalgia against the background of systemic mastocytosis: a clinical case

The article presents a clinical case of comorbid pathology – development of migraine against the background of systemic mastocytosis. The classification and clinical manifestations of systemic mastocytosis, a rare blood disease, are given. This clinical case illustrates an example of excessive mast cell degranulation (with the release of proinflammatory and vasodilating agents as a result of mast cell pathology). In this regard, in addition to the pathogen-specific therapy for systemic mastocytosis (including prevention of mast cell degranulation), it seems important to describe the effectiveness and the possibility of prescribing preventive and emergency therapy for migraine against the background of the underlying hematological disease – systemic mastocytosis. Treatment of cephalalgia in patients with mastocytosis is a complex clinical task, in the solution of which it is necessary to take into account serious limitations in prescription of acetylsalicylic acid and other non-steroidal anti-inflammatory drugs.

Clinical features of all-ceramic restorations in the oral cavity

BACKGROUND: Porcelain veneers make up the particular section of prosthetic dentistry. Veneers are necessary for frontal teeth restorations.&#x0D; AIM: To study the principles of dental preparation and the features of the formation of a natural anatomical contour on all-ceramic restorations.&#x0D; MATERIAL AND METHODS: To achieve a high-quality result of prosthetics with all-ceramic fixed prostheses, it is necessary to take into account many important aesthetic criteria: the shape of the tooth, the inclination of the axes of the teeth, the interdental space and the level of interdental contacts, the gum biotype, its color, the position of the gingival margin, the zenith of the gingival contour; tooth color (shades); the level of the cutting edge of the incisors; the relief of the teeth surface; the smile line and the position of the lower lip.&#x0D; To determine the color-optical characteristics of future prostheses, it is convenient to use the Vitapan 3-D Master Shade Guide color scale.&#x0D; For the manufacture of facings, it is necessary to take into account that the preparation is carried out within the enamel layer, the facings are made only for vital teeth, as clinically possible, while preserving the natural boundaries of the tooth.&#x0D; Prosthetics with ceramic prostheses is not recommended for dental dystopia (lingual, palatal position); significant loss of hard tooth tissues, their increased erasability, incomplete orthopedic treatment, deep bite, parafunctions of the masticatory muscles. Before manufacturing the facings, it is necessary to perform an X-ray examination of the teeth to be restored; assess the state of oral hygiene, determine the color of the future structure, replace all failed fillings, assess the condition of the interdental gap and the contact point.&#x0D; RESULTS: It is necessary to preserve the vestibular relief of the tooth surface, the uniformity of the lining, Contact with the surface (cutting edge) of the antagonist tooth should not be placed on the surface or on the border of the lining, but only on the tooth tissues.&#x0D; The advantage should be given to dissection by partial or complete palatal (lingual) overlap. The facings are fixed with the help of light polymerization composite materials, removing the excess with polishing boron.&#x0D; CONCLUSION: If there are significant risks and the patient refuses orthodontic treatment, the creation of contact points on veneers is a complex clinical task. In addition, with the destruction of the crown part of more than 1/3, the use of veneers is risky due to the increase in the layer of ceramic cladding, there is a possibility of chipping of the lining and the risk of manifestation of pulpitis after preparation. Under such conditions, it is desirable to carry out depulpation of teeth, restoration with zirconium stump pin tabs and prosthetics with zirconium crowns with ceramic lining.

ИСПОЛЬЗОВАНИЕ ВИДЕОКОНФЕРЕНЦ СВЯЗИ ДИСТАНЦИОННОЙ ПЛАТФОРМЫ ZOOM ДЛЯ ПРЕПОДАВАНИЯ АНАТОМИИ СТУДЕНТАМ-МЕДИКАМ НА ПРАКТИЧЕСКИХ ЗАНЯТИЯХ

Distance learning of students has become one of the main methods of obtaining knowledge for the period of forced isolation due to the worsened epidemiological situation. The discipline of human anatomy is fundamental and requires not only a digital approach to independently solve tasks, but also the direct use of the ZOOM conference portal for conducting practical classes with students. The purpose of this study is to evaluate the effectiveness of teaching students using the zoom remote platform. In the course of research on the results of the course of teaching practical classes in the discipline of human anatomy, students were surveyed and tested to assess their academic performance and ease of use of this remote digital portal application. As a result, the use of videoconferencing facilitates the acquisition of knowledge by students, improves their academic performance. More than 90% of students consider it necessary to conduct a daily lesson in the video format. 3% of students consider this format time-consuming and inconvenient, but 95% of students believe that it is through videoconferencing that there is a direct connection with the teacher, during which it is possible to analyze complex clinical tasks. Thus, by sharing our experience and showing the advantages of using this video format conference platform in practical classes on anatomy to improve the quality of distance learning.

Nursing and precision predictive analytics monitoring in the acute and intensive care setting: An emerging role for responding to COVID-19 and beyond.

As the global response to COVID-19 continues, nurses will be tasked with appropriately triaging patients, responding to events of clinical deterioration, and developing family-centered plans of care within a healthcare system exceeding capacity. Predictive analytics monitoring, an artificial intelligence (AI)-based tool that translates streaming clinical data into a real-time visual estimation of patient risks, allows for evolving acuity assessments and detection of clinical deterioration while the patient is in pre-symptomatic states. While nurses are on the frontline for the COVID-19 pandemic, the use of AI-based predictive analytics monitoring may help cognitively complex clinical decision-making tasks and pave a pathway for early detection of patients at risk for decompensation. We must develop strategies and techniques to study the impact of AI-based technologies on patient care outcomes and the clinical workflow. This paper outlines key concepts for the intersection of nursing and precision predictive analytics monitoring.

It is not just about equipment and beds: Critical care nursing meeting the challenge of the second COVID-19 wave in Italy.

It is not just about equipment and beds: Critical care nursing meeting the challenge of the second COVID-19 wave in Italy.

Computer‐aided diagnosis in the era of deep learning

Computer-aided diagnosis (CAD) has been a major field of research for the past few decades. CAD uses machine learning methods to analyze imaging and/or nonimaging patient data and makes assessment of the patient's condition, which can then be used to assist clinicians in their decision-making process. The recent success of the deep learning technology in machine learning spurs new research and development efforts to improve CAD performance and to develop CAD for many other complex clinical tasks. In this paper, we discuss the potential and challenges in developing CAD tools using deep learning technology or artificial intelligence (AI) in general, the pitfalls and lessons learned from CAD in screening mammography and considerations needed for future implementation of CAD or AI in clinical use. It is hoped that the past experiences and the deep learning technology will lead to successful advancement and lasting growth in this new era of CAD, thereby enabling CAD to deliver intelligent aids to improve health care.

Prognostication in post-stroke aphasia: How do speech pathologists formulate and deliver information about recovery?

Prognostication is a complex clinical task that involves forming a prediction about recovery and communicating prognostic information to patients and families. In aphasia, recovery is difficult to predict and evidence-based guidance on prognosis delivery is lacking. Questions about aphasia prognosis commonly arise, but it is unknown how speech pathologists formulate and deliver information about expected recovery. An understanding of current practice in prognostication is needed to develop evidence-based guidelines for this process, and is necessary in order to ensure successful future implementation of recommended practice regarding prognosis delivery. To identify the factors speech pathologists consider important when responding to questions about aphasia prognosis; to examine how they respond in different scenarios; and to evaluate their current attitudes towards aphasia prognostication. A total of 54 speech pathologists participated in an online survey featuring hypothetical aphasia prognosis delivery scenarios, short-response questions and ratings. Open responses were analysed thematically. Multiple-choice responses were analysed using descriptive statistics and non-parametric tests. Speech pathologists regarded factors relating to the nature and severity of post-stroke deficits, an individual's level of motivation and the availability of social support as most important for forming an aphasia prognosis. When delivering prognostic information, considerations of the recipient's emotional well-being, hope and expectations, and comprehension of information were regarded as most important. Speech pathologists' prognosis responses varied in content and manner of communication. The content of the responses included predictions of recovery and information about various attributes and activities contributing to recovery. Prognostic information was most frequently communicated through qualitative probability expressions, general statements and uncertainty-based expressions. A need for more professional support in aphasia prognostication was indicated. There is variation in the way speech pathologists respond to questions about aphasia prognosis, and it is unknown how these conversations affect people with aphasia and their significant others. Further research to understand speech pathologists' clinical reasoning and professional support needs, and the perspectives of people living with aphasia, may help to develop an evidence-based approach to prognostication in aphasia. What this paper adds What is already known on this subject Questions about aphasia prognosis are difficult to answer. Current methods for predicting aphasia recovery are yet to demonstrate the reliability and individual specificity required for clinical application. At present, there is no evidence-based guidance or support for prognosis delivery in aphasia. What this study adds to existing knowledge There is variation in the way speech pathologists predict aphasia recovery, the prognostic information they deliver and the manner in which they communicate prognoses. Current approaches to aphasia prognostication are reliant on experience and professional judgement, and speech pathologists desire more support for undertaking this task. What are the potential or actual clinical implications of this work? Speech pathologists lack a consistent approach to aphasia prognostication and desire more support in this task. The present findings offer insight into clinician attitudes and practice, and provide a direction for future research to establish best-practice guidelines for this complex and demanding area of aphasia management.

Turning Objective Structured Clinical Examinations into Reality.

Objective structured clinical examinations assess learners "showing how" to perform complex clinical tasks. Devised as summative evaluations, these examinations with immediate feedback are useful formative evaluations to improve learner performance. This review describes how objective structured clinical examinations have been used in rheumatology education. Steps for creating an objective structured clinical examination are discussed. Validity and reproducibility are important considerations, especially for high-stakes summative objective structured clinical examinations. Consideration of the potential benefits in clinical education and their hazards are reviewed. When well-designed, formative objective structured clinical examinations have high educational value for learners and medical educators.