Comparison of the Performance of GPT-3.5 and GPT-4 With That of Medical Students on the Written German Medical Licensing Examination: Observational Study.

BACKGROUND: The potential of artificial intelligence (AI)-based large language models, such as ChatGPT, has gained significant attention in the medical field. This enthusiasm is driven not only by recent breakthroughs and improved accessibility, but also by the prospect of democratizing medical knowledge and promoting equitable health care. However, the performance of ChatGPT is substantially influenced by the input language, and given the growing public trust in this AI tool compared to that in traditional sources of information, investigating its medical accuracy across different languages is of particular importance. OBJECTIVE: This study aimed to compare the performance of GPT-3.5 and GPT-4 with that of medical students on the written German medical licensing examination. METHODS: To assess GPT-3.5's and GPT-4's medical proficiency, we used 937 original multiple-choice questions from 3 written German medical licensing examinations in October 2021, April 2022, and October 2022. RESULTS: GPT-4 achieved an average score of 85% and ranked in the 92.8th, 99.5th, and 92.6th percentiles among medical students who took the same examinations in October 2021, April 2022, and October 2022, respectively. This represents a substantial improvement of 27% compared to GPT-3.5, which only passed 1 out of the 3 examinations. While GPT-3.5 performed well in psychiatry questions, GPT-4 exhibited strengths in internal medicine and surgery but showed weakness in academic research. CONCLUSIONS: The study results highlight ChatGPT's remarkable improvement from moderate (GPT-3.5) to high competency (GPT-4) in answering medical licensing examination questions in German. While GPT-4's predecessor (GPT-3.5) was imprecise and inconsistent, it demonstrates considerable potential to improve medical education and patient care, provided that medically trained users critically evaluate its results. As the replacement of search engines by AI tools seems possible in the future, further studies with nonprofessional questions are needed to assess the safety and accuracy of ChatGPT for the general population.

Assessing ChatGPT's ability to pass the FRCS orthopaedic part A exam: A critical analysis.

AI technology has made significant advancements in recent years, with the notable development of ChatGPT in November 2022. Users have observed evidence of deductive reasoning, logical thinking, and coherent thought in ChatGPT's responses. This study aimed to determine if ChatGPT has the capability to pass the Orthopaedic Fellow of the Royal College of Surgeons (FRCS Orth) Part A exam. METHODS: To assess ChatGPT4's ability to pass the Orthopaedic FRCS Orth Part A exam, a study was conducted using 240 mock FRCS Orth Part A questions. The study evaluated the accuracy of ChatGPT's answers and the response time for each question. Descriptive statistics were employed to analyse the chatbot's performance. RESULTS: The evaluation revealed that ChatGPT4 achieved an overall score of 67.5% on Part A of the exam. However, ChatGPT4 did not meet the overall pass mark required for the FRCS Orth Part A exam. CONCLUSION: This study demonstrates that ChatGPT was unable to pass the FRCS Orthopaedic examination. Several factors contributed to this outcome, including the lack of critical or high-order thinking abilities, limited clinical expertise, and the inability to meet the rigorous requirements of the exam.

Do medical students with a disability experience adverse educational outcomes on UK medical courses?

BACKGROUND: International data demonstrate that medical students with disabilities experience differential awarding. One cross-sectional study finds lower graduation rates and scores in written exams, with no impact on clinical exams. Disabled students graduated with lower decile scores. This quantitative, retrospective, longitudinal study explored the impact of disability on exam performance, course performance and course discontinuation. METHOD: Anonymised data were obtained for 1743 students on a UK graduate medical programme from 2011 to present. Statistical tests, including t-tests and one-way ANOVA were conducted for main effects of demographic variables on exam results and categorical outcomes. Regression models established the effects of variables and sub-categories of variables on results and categorical outcomes. RESULTS: Significant main effects of disability on exam scores were identified, as well as failure probability. Regressions showed significant differences in outcomes between different types of disability, with mental health conditions predicting course discontinuation. A significant amplifying effect was found for BAME students with disability. CONCLUSION: Disability had a significant negative impact on all course outcomes, illustrating inequity in medical training and an area of focus for curriculum development. Intersectional data identified a key disadvantaged subgroup of medical students.

Pain intensity and functional limitation are not related with medical image findings in patients with shoulder pain / A intensidade da dor e a limitação funcional não estão relacionadas com os achados em imagens de pacientes com dor no ombro

BACKGROUND AND OBJECTIVES: Shoulder pain limits patients' ability to perform daily life activities, as well as to carry out professional activities. This study aimed at evaluating the relationship between pain intensity, incapacity and medical image findings of patients with shoulder pain. METHODS: This was an observational analytical study with 54 patients with possible shoulder injury. Participants have answered an incapacity questionnaire, a pain intensity scale and then were submitted to image exams. Incapacity, pain intensity and image diagnosis were correlated, in addition to comparing pain intensity and level of incapacity among participants with and without medical image abnormalities. RESULTS: Mean pain intensity was 7.4±2.52. There has been a high degree of incapacity (mean of 57.2%). Image findings have shown abnormalities in 59.3% of reports. There has been no correlation between image findings and pain intensity, as well as there has also been no correlation between image findings and incapacity. There has been high correlation between pain intensity and incapacity (Rho=0.67; p<0.001). Pain intensity and incapacity were not different between participants with and without some type of abnormality at image exams. CONCLUSION: Patients with shoulder complaints may have limitations to perform daily activities and pain, even with negative image findings...

JUSTIFICATIVA E OBJETIVOS: O quadro doloroso do ombro limita o paciente de realizar suas tarefas diárias, assim como de realizar atividades dentro da sua jornada de trabalho. O objetivo deste estudo foi avaliar a relação entre a intensidade da dor, a incapacidade e os achados no exame de imagem de pacientes com dor no ombro. MÉTODOS: Foi realizado um estudo observacional analítico em 54 pacientes com possível lesão de ombro. Os participantes responderam um questionário de incapacidade, uma escala de intensidade de dor e em seguida foram submetidos ao exame de imagem. Foi realizada a análise de correlação entre a incapacidade, a intensidade de dor e o diagnóstico por imagem, além da comparação da intensidade da dor e do nível de incapacidade entre os participantes com e sem anormalidade no exame de imagem. RESULTADOS: A intensidade de dor média encontrada foi de 7,4±2,52. Houve alto grau de incapacidade (média de 57,2%). Nos exames de imagem analisados foram encontradas anormalidades em 59,3% dos laudos. Não houve correlação entre os achados na imagem e a intensidade de dor, assim como não houve correlação entre os achados na imagem e a incapacidade. Observou-se alta correlação entre intensidade de dor e o nível de incapacidade (Rho=0,67; p<0,001). A intensidade de dor e incapacidade não foram diferentes entre os participantes com ou sem algum tipo de anormalidade nos exames de imagem. CONCLUSÃO: Pacientes com queixas na região do ombro podem apresentar limitações nas atividades de vida diária e presença de dor, mesmo sem achados no exame de imagem...

Condom use during sexual assault.

This study examines questions about forced unprotected sex. Study objectives include assessing the prevalence of condom use in sexual assault and improving our understanding of the correlates of condom use in sexual assault. We analyze 841 sexual assault complaints reported to three law enforcement agencies. Descriptive data are used to assess the prevalence of condom use in sexual assault and to examine the contextual factors associated with condom use in sexual assault. We conduct logistic regression analysis to examine motivations for condom use during sexual assault. Condom use prevalence rates across the sites range from 11.7% to 15.6%. Few differences exist across jurisdictions regarding the correlates of condom use. Condom use during sexual assault appears to be motivated by three contextual factors. Younger suspects and suspects who use a weapon during assaults are more likely to use a condom. The suspect's use of alcohol is negatively related to condom use. The low rates of condom use found in this study, coupled with the dangers of unprotected sexual contact, suggest that public health efforts must address the needs of victims of sexual assault more carefully.