Search

Introduction: ChatGPT, a large‐scale language model, is a notable example of AI's potential in health care. However, its effectiveness in clinical settings, especially when compared to human physicians, is not fully understood. This study evaluates ChatGPT's capabilities and limitations in answering questions for Japanese internal medicine specialists, aiming to clarify its accuracy and tendencies in both correct and incorrect responses. Methods: We utilized ChatGPT's answers on four sets of self‐training questions for internal medicine specialists in Japan from 2020 to 2023. We ran three trials for each set to evaluate its overall accuracy and performance on nonimage questions. Subsequently, we categorized the questions into two groups: those ChatGPT consistently answered correctly (Confirmed Correct Answer, CCA) and those it consistently answered incorrectly (Confirmed Incorrect Answer, CIA). For these groups, we calculated the average accuracy rates and 95% confidence intervals based on the actual performance of internal medicine physicians on each question and analyzed the statistical significance between the two groups. This process was then similarly applied to the subset of nonimage CCA and CIA questions. Results: ChatGPT's overall accuracy rate was 59.05%, increasing to 65.76% for nonimage questions. 24.87% of the questions had answers that varied between correct and incorrect in the three trials. Despite surpassing the passing threshold for nonimage questions, ChatGPT's accuracy was lower than that of human specialists. There was a significant variance in accuracy between CCA and CIA groups, with ChatGPT mirroring human physician patterns in responding to different question types. Conclusion: This study underscores ChatGPT's potential utility and limitations in internal medicine. While effective in some aspects, its dependence on question type and context suggests that it should supplement, not replace, professional medical judgment. Further research is needed to integrate Artificial Intelligence tools like ChatGPT more effectively into specialized medical practices. [ABSTRACT FROM AUTHOR]

Regulatory authorities must balance ensuring evidence of efficacy and safety of new drugs. Various regulatory pathways, such as the accelerated approval program in the United States (US), allow authorities to quickly approve drugs for severely ill patients by granting market authorization based on surrogate end points and pending confirmatory trials. In this cross‐sectional study, we considered 23 indications of cancer drugs that received accelerated approval by the US Food and Drug Administration (FDA) but were subsequently withdrawn as of April 2023. Our investigation extended to assessing the regulatory status of these accelerated approvals in the European Union (EU) and Japan, examining relevant regulatory documents and identifying factors contributing to the withdrawal in the United States. Comparing regions, we found that for 52% (12/23) and 30% (7/23) of withdrawn accelerated approvals in the United States, sponsors had also sought marketing authorization from the European Medicines Agency (EMA) and Japan's Pharmaceuticals and Medical Devices Agency (PMDA), respectively. As of the April 30, 2023 study cutoff date, 83% (10/12) of drug–indication pairs remained approved by the EMA, while the PMDA retained 100% (7/7). For these indications, the time from FDA withdrawal until the study cutoff date ranged from 0.23 years to 11.45 years for EMA approvals (median: 1.28 years) and 1.10 years to 11.45 years for PMDA approvals (median: 3.22 years). These findings highlight substantial regulatory discrepancies concerning cancer drugs with unconfirmed benefits. Addressing these discrepancies may involve requiring pharmaceutical companies to confirm clinical benefits using more robust end points and fostering international harmonization in regulators' assessment. [ABSTRACT FROM AUTHOR]

The current pandemic of the coronavirus disease 2019 (COVID-19) has negatively impacted medical workers' mental health in many countries including Japan. Although research identified poor mental health of medical workers in COVID-19, protective factors for their mental health remain to be appraised. Accordingly, this study aimed to investigate relationships between mental health problems, loneliness, hope and self-compassion among Japanese medical workers, and compare with the general population. Online self-report measures regarding those four constructs were completed by 142 medical workers and 138 individuals in the general population. T-tests and multiple regression analysis were performed. Medical workers had higher levels of mental health problems and loneliness, and lower levels of hope and self-compassion than the general population. Loneliness was the strongest predictor of mental health problems in the medical workers. Findings suggest that Japanese medical workplaces may benefit from targeting workplace loneliness to prevent mental health problems among the medical staff., Author(s): Yasuhiro Kotera [sup.1] , Akihiko Ozaki [sup.2] [sup.3] , Hirotomo Miyatake [sup.4] , Chie Tsunetoshi [sup.4] , Yoshitaka Nishikawa [sup.5] , Tetsuya Tanimoto [sup.3] Author Affiliations: (1) grid.57686.3a, 0000 [...]

Risk and uncertainty can destabilise and reconstruct the relationships between medicine, policy and publics. Through semi-structured interviews with medical staff following the Fukushima 3.11 Disaster, this paper demonstrates the way in which disruption (caused by disaster), coupled with uncertainty (in this case, around radiation risk) can serve to transform medical practices. After Fukushima, a deficit in publicly-trusted approaches to disaster management meant that the role and status of key medical professionals was transformed. This reorganisation of medical work included the development of new forms of expertise, the stretching of expertise beyond previously well-defined professional boundaries, and shifts in the way in which medical professionals understand and interact with publics. These changes signified the rise of new relationships between the medical workers and their community, as well as adjustments in what were regarded as the boundaries of medical work. Given both the ubiquitous threat of disasters and calls for increased engagement between the medicine and the public, this case study provides insight into the forms which such engagements can take, especially when bound by conditions of uncertainty. The paper draws upon the theoretical literature around the impact of uncertainty on policy, and combines this with medical sociological literature on the nature of medical expertise. The paper examines the shifting of medical expertise towards mode 2 forms, and evidences the impact of a democratised science of risk on the roles and functions of medical practice.