北海道大学 · 医学
Yudai Kaneda教授の研究室は、人工知能(AI)の医療応用に焦点を当てており、特にChatGPTをはじめとする大規模言語モデルが日本語の医療・看護・保育分野における意思決定支援や情報提供の有効性を検証しています。臨床的推論力や正答率、共感性といった観点から、GPT-3.5とGPT-4の性能差を分析し、医療現場での実用的応用可能性と限界を明らかにしています。また、医療記録作成や診断の補助といったAIの業務効率化の可能性についても実証的研究を進めています。
Figures are computed from collected data and may differ slightly.
Purpose The purpose of this study was to evaluate the changes in capabilities between the Generative Pre-trained Transformer (GPT)-3.5 and GPT-4 versions of the large-scale language model ChatGPT within a Japanese medical context. Methods The study involved ChatGPT versions 3.5 and 4 responding to questions from the 112th Japanese National Nursing Examination (JNNE). The study comprised three analyses: correct answer rate and score rate calculations, comparisons between GPT-3.5 and GPT-4, and co
We have attempted to develop a system for specific enhancement of transgene expression, which has been one of the most important issues in human gene therapy. When an Epstein-Barr virus (EBV) nuclear antigen 1 (EBNA-1) expression vector, pCMV-trEBNA-1, was cotransfected with an origin of latent viral DNA replication (oriP)-harboring plasmid, poriP-CMV-luciferase, luciferase gene expression was up to 20 times greater than in the absence of EBNA-1. This enhancement was regulated mainly at the tran
ChatGPT is gaining widespread acceptance for its ability to generate natural language sentences in response to various inputs and is expected to become a supplementary tool for diagnosing and determining treatment policies in clinical settings. ChatGPT was used to evaluate its ability to perform clinical inference and accuracy in answering questions on the 117th Japanese National Medical Licensing Examination held in February 2023. The exam questions were manually inputted into ChatGPT's window,
Artificial intelligence (AI), particularly ChatGPT, developed by OpenAI (San Francisco, CA, USA), is making significant strides in the medical field. In a simulated case study, a 66-year-old Japanese female patient's dialogue with a physician was transcribed and inputted into ChatGPT to assess its efficacy in drafting medical records, formulating differential diagnoses, and establishing treatment plans. The results showed a high similarity between the medical summaries generated by ChatGPT and t
Purpose This study aimed to evaluate the performance and acceptance of responses generated by ChatGPT-3.5 and GPT-4 to Japanese childcare-related questions to assess their potential applicability and limitations in the childcare field, specifically focusing on the accuracy, usefulness, and empathy of the generated answers. Methods We evaluated answers in Japanese generated by GPT-3.5 and GPT-4 for two types of childcare-related questions. ① For the written examination questions of Japan's childc
The "infallibility principle" in Japanese government bureaucracy has led to conservative responses in handling the COVID-19 pandemic, with adherence to initial methods, like the 3Cs (crowded places, close-contact settings, and confined and enclosed spaces), and resistance to policy changes, despite evolving scientific findings on airborne transmission. This inflexible approach resulted in multiple states of emergency, social and economic losses, and increased health challenges. Although claims h
The acceptance of foreign tourists in Japan was suspended for more than two years as a countermeasure against coronavirus disease 2019 (COVID-19), and was resumed on October 11, 2022.However, the temporal and spatial spread of infectious diseases is greatly influenced by human mobility, with air travel, in particular, having the potential to accelerate the dissemination of these diseases [1].Indeed, multiple infection have been reported in Japan after resuming acceptance of foreign visitors.The
Journal Article In the era of prominent AI, what role will physicians be expected to play? Get access Yudai Kaneda Yudai Kaneda Conceptualization, Data curation, Writing - original draft School of Medicine, Hokkaido University, Kita-ku, Kita 15, Nishi 7, Sapporo, Hokkaido 0608638, Japan Address correspondence to Y. Kaneda, School of Medicine, Hokkaido University, Kita-ku, Kita 15, Nishi 7, Sapporo, Hokkaido 0608638, Japan. email: nature271828@gmail.com https://orcid.org/0000-0001-8302-9439 Searc
In recent years, Japan has faced a significant demographic crisis, which was further exacerbated by the coronavirus disease 2019 (COVID-19) pandemic. By 2022, the country experienced a 1.5% decrease in population, which is in contrast to other G7 nations, and had the highest rate of excess mortality among Organization for Economic Co-operation and Development (OECD) countries. This crisis is mainly attributed to aging population, with Japan's aging rate reaching 29.9%, the highest among its peer
The Importance of the Taliban and the International Community Collaboration in Building Support Systems for Experts Working in Earthquake-Affected Areas in Afghanistan—Perspectives from a Triple Disaster Experience in Fukushima - Volume 17
The 7.8 magnitude earthquake that occurred in southern Turkey on February 6, 2023, has resulted in over 40,000 and 5,000 confirmed deaths in Turkey and Syria, respectively, including substantial infrastructure damage. While Turkey has received assistance from various countries and international organizations, the level of support Syria has received remains unclear. The Assad regime has demanded that aid be sent to the capital Damascus, but this may hinder the delivery of assistance to the areas
Abstract Little is known on how different types of disasters interact in their impacts on patient care. We experienced a breast cancer patient whose initial presentation was delayed for 2 years due to the COVID‐19 pandemic and Typhoon Hagibis. Increasing awareness is needed on the combined impacts of disasters on breast cancer management.
Open papers in the app to read, cite, and organize with AI.