Background: Medical history contributes approximately 80% to a diagnosis, although physical examinations and laboratory investigations increase a physician's confidence in the medical diagnosis. The concept of artificial intelligence (AI) was first proposed more than 70 years ago. Recently, its role in various fields of medicine has grown remarkably. However, no studies have evaluated the importance of patient history in AI-assisted medical diagnosis.
Objective: This study explored the contribution of patient history to AI-assisted medical diagnoses and assessed the accuracy of ChatGPT in reaching a clinical diagnosis based on the medical history provided.
Methods: Using clinical vignettes of 30 cases identified in The BMJ, we evaluated the accuracy of diagnoses generated by ChatGPT. We compared the diagnoses made by ChatGPT based solely on medical history with the correct diagnoses. We also compared the diagnoses made by ChatGPT after incorporating additional physical examination findings and laboratory data alongside history with the correct diagnoses.
Results: ChatGPT accurately diagnosed 76.6% (23/30) of the cases with only the medical history, consistent with previous research targeting physicians. We also found that this rate was 93.3% (28/30) when additional information was included.
Conclusions: Although adding additional information improves diagnostic accuracy, patient history remains a significant factor in AI-assisted medical diagnosis. Thus, when using AI in medical diagnosis, it is crucial to include pertinent and correct patient histories for an accurate diagnosis. Our findings emphasize the continued significance of patient history in clinical diagnoses in this age and highlight the need for its integration into AI-assisted medical diagnosis systems.
Background: Substance use and overdose deaths make up a substantial portion of injury-related deaths in the United States, with the state of Ohio leading the nation in rates of diagnosed substance use disorder (SUD). Ohio's growing epidemic has indicated a need to improve SUD care in a primary care setting through the engagement of multidisciplinary providers and the use of a comprehensive approach to care.
Objective: The purpose of this study was to assess the ability of the Weitzman Extension for Community Healthcare Outcomes (ECHO): Comprehensive Substance Use Disorder Care program to both address and meet 7 series learning objectives and address substances by analyzing (1) the frequency of exposure to the learning objective topics and substance types during case discussions and (2) participants' change in knowledge, self-efficacy, attitudes, and skills related to the treatment of SUDs pre- to postseries. The 7 series learning objective themes included harm reduction, team-based care, behavioral techniques, medication-assisted treatment, trauma-informed care, co-occurring conditions, and social determinants of health.
Methods: We used a mixed methods approach using a conceptual content analysis based on series learning objectives and substances and a 2-tailed paired-samples t test of participants' self-reported learner outcomes. The content analysis gauged the frequency and dose of learning objective themes and illicit and nonillicit substances mentioned in participant case presentations and discussions, and the paired-samples t test compared participants' knowledge, self-efficacy, attitudes, and skills associated with learning objectives and medication management of substances from pre- to postseries.
Results: The results of the content analysis indicated that 3 learning objective themes-team-based care, harm reduction, and social determinants of health-resulted in the highest frequencies and dose, appearing in 100% (n=22) of case presentations and discussions. Alcohol had the highest frequency and dose among the illicit and nonillicit substances, appearing in 81% (n=18) of case presentations and discussions. The results of the paired-samples t test indicated statistically significant increases in knowledge domain statements related to polysubstance use (P=.02), understanding the approach other disciplines use in SUD care (P=.02), and medication management strategies for nicotine (P=.03) and opioid use disorder (P=.003). Statistically significant increases were observed for 2 self-efficacy domain statements regarding medication management for nicotine (P=.002) and alcohol use disorder (P=.02). Further, 1 statistically significant increase in the skill domain was observed regarding using the stages of change theory in interventions (P=.03).
Conclusions: These findings indicate that the ECHO program's content aligned with its stated l
Background: Digital competence is listed as one of the key competences for lifelong learning and is increasing in importance not only in private life but also in professional life. There is consensus within the health care sector that digital competence (or digital literacy) is needed in various professional fields. However, it is still unclear what exactly the digital competence of health professionals should include and how it can be measured.
Objective: This scoping review aims to provide an overview of the common definitions of digital literacy in scientific literature in the field of health care and the existing measurement instruments.
Methods: Peer-reviewed scientific papers from the last 10 years (2013-2023) in English or German that deal with the digital competence of health care workers in both outpatient and inpatient care were included. The databases ScienceDirect, Scopus, PubMed, EBSCOhost, MEDLINE, OpenAIRE, ERIC, OAIster, Cochrane Library, CAMbase, APA PsycNet, and Psyndex were searched for literature. The review follows the JBI methodology for scoping reviews, and the description of the results is based on the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) checklist.
Results: The initial search identified 1682 papers, of which 46 (2.73%) were included in the synthesis. The review results show that there is a strong focus on technical skills and knowledge with regard to both the definitions of digital competence and the measurement tools. A wide range of competences were identified within the analyzed works and integrated into a validated competence model in the areas of technical, methodological, social, and personal competences. The measurement instruments mainly used self-assessment of skills and knowledge as an indicator of competence and differed greatly in their statistical quality.
Conclusions: The identified multitude of subcompetences illustrates the complexity of digital competence in health care, and existing measuring instruments are not yet able to reflect this complexity.
Background: Artificial intelligence models can learn from medical literature and clinical cases and generate answers that rival human experts. However, challenges remain in the analysis of complex data containing images and diagrams.
Objective: This study aims to assess the answering capabilities and accuracy of ChatGPT-4 Vision (GPT-4V) for a set of 100 questions, including image-based questions, from the 2023 otolaryngology board certification examination.
Methods: Answers to 100 questions from the 2023 otolaryngology board certification examination, including image-based questions, were generated using GPT-4V. The accuracy rate was evaluated using different prompts, and the presence of images, clinical area of the questions, and variations in the answer content were examined.
Results: The accuracy rate for text-only input was, on average, 24.7% but improved to 47.3% with the addition of English translation and prompts (P<.001). The average nonresponse rate for text-only input was 46.3%; this decreased to 2.7% with the addition of English translation and prompts (P<.001). The accuracy rate was lower for image-based questions than for text-only questions across all types of input, with a relatively high nonresponse rate. General questions and questions from the fields of head and neck allergies and nasal allergies had relatively high accuracy rates, which increased with the addition of translation and prompts. In terms of content, questions related to anatomy had the highest accuracy rate. For all content types, the addition of translation and prompts increased the accuracy rate. As for the performance based on image-based questions, the average of correct answer rate with text-only input was 30.4%, and that with text-plus-image input was 41.3% (P=.02).
Conclusions: Examination of artificial intelligence's answering capabilities for the otolaryngology board certification examination improves our understanding of its potential and limitations in this field. Although the improvement was noted with the addition of translation and prompts, the accuracy rate for image-based questions was lower than that for text-based questions, suggesting room for improvement in GPT-4V at this stage. Furthermore, text-plus-image input answers a higher rate in image-based questions. Our findings imply the usefulness and potential of GPT-4V in medicine; however, future consideration of safe use methods is needed.
Background: The COVID-19 pandemic has highlighted the growing relevance of telehealth in health care. Assessing health care and nursing students' telehealth competencies is crucial for its successful integration into education and practice.
Objective: We aimed to assess students' perceived telehealth knowledge, skills, attitudes, and experiences. In addition, we aimed to examine students' preferences for telehealth content and teaching methods within their curricula.
Methods: We conducted a cross-sectional web-based study in May 2022. A project-specific questionnaire, developed and refined through iterative feedback and face-validity testing, addressed topics such as demographics, personal perceptions, and professional experience with telehealth and solicited input on potential telehealth course content. Statistical analyses were conducted on surveys with at least a 50% completion rate, including descriptive statistics of categorical variables, graphical representation of results, and Kruskal Wallis tests for central tendencies in subgroup analyses.
Results: A total of 261 students from 7 bachelor's and 4 master's health care and nursing programs participated in the study. Most students expressed interest in telehealth (180/261, 69% very or rather interested) and recognized its importance in their education (215/261, 82.4% very or rather important). However, most participants reported limited knowledge of telehealth applications concerning their profession (only 7/261, 2.7% stated profound knowledge) and limited active telehealth experience with various telehealth applications (between 18/261, 6.9% and 63/261, 24.1%). Statistically significant differences were found between study programs regarding telehealth interest (P=.005), knowledge (P<.001), perceived importance in education (P<.001), and perceived relevance after the pandemic (P=.004). Practical training with devices, software, and apps and telehealth case examples with various patient groups were perceived as most important for integration in future curricula. Most students preferred both interdisciplinary and program-specific courses.
Conclusions: This study emphasizes the need to integrate telehealth into health care education curricula, as students state positive telehealth attitudes but seem to be not adequately prepared for its implementation. To optimally prepare future health professionals for the increasing role of telehealth in practice, the results of this study can be considered when designing telehealth curricula.
Background: Previous research applying large language models (LLMs) to medicine was focused on text-based information. Recently, multimodal variants of LLMs acquired the capability of recognizing images.
Objective: We aim to evaluate the image recognition capability of generative pretrained transformer (GPT)-4V, a recent multimodal LLM developed by OpenAI, in the medical field by testing how visual information affects its performance to answer questions in the 117th Japanese National Medical Licensing Examination.
Methods: We focused on 108 questions that had 1 or more images as part of a question and presented GPT-4V with the same questions under two conditions: (1) with both the question text and associated images and (2) with the question text only. We then compared the difference in accuracy between the 2 conditions using the exact McNemar test.
Results: Among the 108 questions with images, GPT-4V's accuracy was 68% (73/108) when presented with images and 72% (78/108) when presented without images (P=.36). For the 2 question categories, clinical and general, the accuracies with and those without images were 71% (70/98) versus 78% (76/98; P=.21) and 30% (3/10) versus 20% (2/10; P≥.99), respectively.
Conclusions: The additional information from the images did not significantly improve the performance of GPT-4V in the Japanese National Medical Licensing Examination.
Background: Access to reliable and accurate digital health web-based resources is crucial. However, the lack of dedicated search engines for non-English languages, such as French, is a significant obstacle in this field. Thus, we developed and implemented a multilingual, multiterminology semantic search engine called Catalog and Index of Digital Health Teaching Resources (CIDHR). CIDHR is freely accessible to everyone, with a focus on French-speaking resources. CIDHR has been initiated to provide validated, high-quality content tailored to the specific needs of each user profile, be it students or professionals.
Objective: This study's primary aim in developing and implementing the CIDHR is to improve knowledge sharing and spreading in digital health and health informatics and expand the health-related educational community, primarily French speaking but also in other languages. We intend to support the continuous development of initial (ie, bachelor level), advanced (ie, master and doctoral levels), and continuing training (ie, professionals and postgraduate levels) in digital health for health and social work fields. The main objective is to describe the development and implementation of CIDHR. The hypothesis guiding this research is that controlled vocabularies dedicated to medical informatics and digital health, such as the Medical Informatics Multilingual Ontology (MIMO) and the concepts structuring the French National Referential on Digital Health (FNRDH), to index digital health teaching and learning resources, are effectively increasing the availability and accessibility of these resources to medical students and other health care professionals.
Methods: First, resource identification is processed by medical librarians from websites and scientific sources preselected and validated by domain experts and surveyed every week. Then, based on MIMO and FNRDH, the educational resources are indexed for each related knowledge domain. The same resources are also tagged with relevant academic and professional experience levels. Afterward, the indexed resources are shared with the digital health teaching and learning community. The last step consists of assessing CIDHR by obtaining informal feedback from users.
Results: Resource identification and evaluation processes were executed by a dedicated team of medical librarians, aiming to collect and curate an extensive collection of digital health teaching and learning resources. The resources that successfully passed the evaluation process were promptly included in CIDHR. These resources were diligently indexed (with MIMO and FNRDH) and tagged for the study field and degree level. By October 2023, a total of 371 indexed resources were available on a dedicated portal.
Conclusions: CIDHR is a multilingual digital health education semantic search engine and platform that aims to increase the acce