Background: The diagnostic accuracy of differential diagnoses generated by artificial intelligence chatbots, including ChatGPT models, for complex clinical vignettes derived from general internal medicine (GIM) department case reports is unknown. Objective: This study aims to evaluate the accuracy of the differential diagnosis lists generated by both third-generation ChatGPT (ChatGPT-3.5) and fourth-generation ChatGPT (ChatGPT-4) by using case vignettes from case reports published by the Department of GIM of Dokkyo Medical University Hospital, Japan. Methods: We searched PubMed for case reports. Upon identification, physicians selected diagnostic cases, determined the final diagnosis, and displayed them into clinical vignettes. Physicians typed the determined text with the clinical vignettes in the ChatGPT-3.5 and ChatGPT-4 prompts to generate the top 10 differential diagnoses. The ChatGPT models were not specially trained or further reinforced for this task. Three GIM physicians from other medical institutions created differential diagnosis lists by reading the same clinical vignettes. We measured the rate of correct diagnosis within the top 10 differential diagnosis lists, top 5 differential diagnosis lists, and the top diagnosis. Results: In total, 52 case reports were analyzed. The rates of correct diagnosis by ChatGPT-4 within the top 10 differential diagnosis lists, top 5 differential diagnosis lists, and top diagnosis were 83% (43/52), 81% (42/52), and 60% (31/52), respectively. The rates of correct diagnosis by ChatGPT-3.5 within the top 10 differential diagnosis lists, top 5 differential diagnosis lists, and top diagnosis were 73% (38/52), 65% (34/52), and 42% (22/52), respectively. The rates of correct diagnosis by ChatGPT-4 were comparable to those by physicians within the top 10 (43/52, 83% vs 39/52, 75%, respectively; P=.47) and within the top 5 (42/52, 81% vs 35/52, 67%, respectively; P=.18) differential diagnosis lists and top diagnosis (31/52, 60% vs 26/52, 50%, respectively; P=.43) although the difference was not significant. The ChatGPT models’ diagnostic accuracy did not significantly vary based on open access status or the publication date (before 2011 vs 2022). Conclusions: This study demonstrates the potential diagnostic accuracy of differential diagnosis lists generated using ChatGPT-3.5 and ChatGPT-4 for complex clinical vignettes from case reports published by the GIM department. The rate of correct diagnoses within the top 10 and top 5 differential diagnosis lists generated by ChatGPT-4 exceeds 80%. Although derived from a limited data set of case reports from a single department, our findings highlight the potential utility of ChatGPT-4 as a supplementary tool for physicians, particularly for those affiliated with the GIM department. Further investigations should explore the diagnostic accuracy of ChatGPT by using distinct case materials beyond its training data. Such efforts will provide a comprehensive insight into the role of artificial intelligence in enhancing clinical decision-making.

Background: The COVID-19 pandemic has negatively affected medical education. However, little data are available about medical students’ distress during the pandemic. Objective: This study aimed to provide details on how medical students have been affected by the pandemic. Methods: A cross-sectional study was conducted. A total of 717 medical students participated in the web-based survey. The survey included questions about how the participants’ mental status had changed from before to after the Japanese nationwide state of emergency (SOE). Results: Out of 717 medical students, 473 (66.0%) participated in the study. In total, 29.8% (141/473) of the students reported concerns about the shift toward online education, mostly because they thought online education would be ineffective compared with in-person learning. The participants’ subjective mental health status significantly worsened after the SOE was lifted (P<.001). Those who had concerns about a shift toward online education had higher odds of having generalized anxiety and being depressed (odds ratio [OR] 1.97, 95% CI 1.19-3.28) as did those who said they would request food aid (OR 1.99, 95% CI 1.16-3.44) and mental health care resources (OR 3.56, 95% CI 2.07-6.15). Conclusions: Given our findings, the sudden shift to online education might have overwhelmed medical students. Thus, we recommend that educators inform learners that online learning is not inferior to in-person learning, which could attenuate potential depression and anxiety.

Background: In the evolving field of health care, multimodal generative artificial intelligence (AI) systems, such as ChatGPT-4 with vision (ChatGPT-4V), represent a significant advancement, as they integrate visual data with text data. This integration has the potential to revolutionize clinical diagnostics by offering more comprehensive analysis capabilities. However, the impact on diagnostic accuracy of using image data to augment ChatGPT-4 remains unclear. Objective: This study aims to assess the impact of adding image data on ChatGPT-4’s diagnostic accuracy and provide insights into how image data integration can enhance the accuracy of multimodal AI in medical diagnostics. Specifically, this study endeavored to compare the diagnostic accuracy between ChatGPT-4V, which processed both text and image data, and its counterpart, ChatGPT-4, which only uses text data. Methods: We identified a total of 557 case reports published in the American Journal of Case Reports from January 2022 to March 2023. After excluding cases that were nondiagnostic, pediatric, and lacking image data, we included 363 case descriptions with their final diagnoses and associated images. We compared the diagnostic accuracy of ChatGPT-4V and ChatGPT-4 without vision based on their ability to include the final diagnoses within differential diagnosis lists. Two independent physicians evaluated their accuracy, with a third resolving any discrepancies, ensuring a rigorous and objective analysis. Results: The integration of image data into ChatGPT-4V did not significantly enhance diagnostic accuracy, showing that final diagnoses were included in the top 10 differential diagnosis lists at a rate of 85.1% (n=309), comparable to the rate of 87.9% (n=319) for the text-only version (P=.33). Notably, ChatGPT-4V’s performance in correctly identifying the top diagnosis was inferior, at 44.4% (n=161), compared with 55.9% (n=203) for the text-only version (P=.002, χ2 test). Additionally, ChatGPT-4’s self-reports showed that image data accounted for 30% of the weight in developing the differential diagnosis lists in more than half of cases. Conclusions: Our findings reveal that currently, ChatGPT-4V predominantly relies on textual data, limiting its ability to fully use the diagnostic potential of visual information. This study underscores the need for further development of multimodal generative AI systems to effectively integrate and use clinical image data. Enhancing the diagnostic performance of such AI systems through improved multimodal data integration could significantly benefit patient care by providing more accurate and comprehensive diagnostic insights. Future research should focus on overcoming these limitations, paving the way for the practical application of advanced AI in medicine.

Background and Objectives: COVID-19 can be serious not only in the acute phase but also after the acute phase and some patients develop ME/CFS. There have been few studies on patients with long COVID in whom ME/CFS was diagnosed by physicians based on standardized criteria after examinations and exclusion diagnosis and not based on only subjective symptoms. The purpose of this study was to elucidate the detailed characteristics of ME/CFS in patients with long COVID. Materials and Methods: A retrospective descriptive study was performed for patients who visited a COVID-19 aftercare clinic established in Okayama University Hospital during the period was from February 2021 to April 2022. Results: Clinical data were obtained from medical records for 281 patients, and 279 patients who met the definition of long COVID were included. The overall prevalence rate of ME/CFS diagnosed by three sets of ME/CFS criteria (Fukuda, Canadian and IOM criteria) was 16.8% (48.9% in male and 51.1% in females). The most frequent symptoms in ME/CFS patients were general fatigue and post-exertional malaise (89.4% of the patients), headache (34.0%), insomnia (23.4%), dysosmia (21.3%) and dysgeusia (19.1%). Dizziness, chest pain, insomnia and headache were characteristic symptoms related to ME/CFS. The male to female ratio in ME/CFS patients was equal in the present study, although ME/CFS was generally more common in women in previous studies. Given that patients with ME/CFS had more severe conditions in the acute phase of COVID-19, the severity of the acute infectious state might be involved in the pathophysiology of ME/CFS. Conclusions: The prevalence rate of ME/CFS and the characteristic sequelae in the long COVID condition were revealed in this study.

Background: The potential of artificial intelligence (AI) chatbots, particularly ChatGPT with GPT-4 (OpenAI), in assisting with medical diagnosis is an emerging research area. However, it is not yet clear how well AI chatbots can evaluate whether the final diagnosis is included in differential diagnosis lists. Objective: This study aims to assess the capability of GPT-4 in identifying the final diagnosis from differential-diagnosis lists and to compare its performance with that of physicians for case report series. Methods: We used a database of differential-diagnosis lists from case reports in the American Journal of Case Reports, corresponding to final diagnoses. These lists were generated by 3 AI systems: GPT-4, Google Bard (currently Google Gemini), and Large Language Models by Meta AI 2 (LLaMA2). The primary outcome was focused on whether GPT-4’s evaluations identified the final diagnosis within these lists. None of these AIs received additional medical training or reinforcement. For comparison, 2 independent physicians also evaluated the lists, with any inconsistencies resolved by another physician. Results: The 3 AIs generated a total of 1176 differential diagnosis lists from 392 case descriptions. GPT-4’s evaluations concurred with those of the physicians in 966 out of 1176 lists (82.1%). The Cohen κ coefficient was 0.63 (95% CI 0.56-0.69), indicating a fair to good agreement between GPT-4 and the physicians’ evaluations. Conclusions: GPT-4 demonstrated a fair to good agreement in identifying the final diagnosis from differential-diagnosis lists, comparable to physicians for case report series. Its ability to compare differential diagnosis lists with final diagnoses suggests its potential to aid clinical decision-making support through diagnostic feedback. While GPT-4 showed a fair to good agreement for evaluation, its application in real-world scenarios and further validation in diverse clinical environments are essential to fully understand its utility in the diagnostic process.

The long-term clinical course, prognosis, and optimal management of symptoms and conditions after the acute phase of coronavirus disease 2019 (COVID-19) remain to be elucidated. The purpose of this study was to clarify the characteristics of patients referred to a COVID-19 aftercare (CAC) clinic established at a tertiary academic hospital in Japan. This study was a descriptive case series study. All patients who visited the CAC clinic between February 15 and September 17 in 2021 were included. Patients’ background, chief complaints, and clinical courses after the onset of COVID-19 were described. A total of 87 Japanese patients (median age, 40.0 years; interquartile range [IQR], 26.5-53.0 years; 52.9% women) were referred to the CAC clinic. The median interval between the onset of COVID-19 and the visit to the clinic was 79.0 (IQR, 52.5-112.0) days. Referral sources were hospitals (36 patients), clinics (47 patients), a local healthcare center (3 patients), and other (1 patient). The most common chief complaint was general fatigue (50.4%) followed by dysosmia (28.7%), dysgeusia (26.4%), hair loss (18.4%), headache (17.2%), dyspnea (16.1%), and dyssomnia (13.1%). Respiratory symptoms were common in the early stages of the disease but were less common as the chief complaints when visiting the clinic. On the other hand, neurological, psychiatric, and extremity symptoms were predominant one month after the onset of COVID-19. Regardless of the severity in the acute phase, patients visiting our CAC clinic suffered from a variety of symptoms. General physicians skilled in using a comprehensive approach would be optimal to see patients with such complex symptoms.