記述言語：日本語   出版者・発行元：(一社)日本臨床救急医学会  

researchmap

記述言語：英語   掲載種別：研究論文（学術雑誌）  

Background Emergency physicians need a broad range of knowledge and skills to address critical medical, traumatic, and environmental conditions. Artificial intelligence (AI), including large language models (LLMs), has potential applications in healthcare settings; however, the performance of LLMs in emergency medicine remains unclear.Methods To evaluate the reliability of information provided by ChatGPT, an LLM was given the questions set by the Japanese Association of Acute Medicine in its board certification examinations over a period of 5 years (2018-2022) and programmed to answer them twice. Statistical analysis was used to assess agreement of the two responses.Results The LLM successfully answered 465 of the 475 text-based questions, achieving an overall correct response rate of 62.3%. For questions without images, the rate of correct answers was 65.9%. For questions with images that were not explained to the LLM, the rate of correct answers was only 52.0%. The annual rates of correct answers to questions without images ranged from 56.3% to 78.8%. Accuracy was better for scenario-based questions (69.1%) than for stand-alone questions (62.1%). Agreement between the two responses was substantial (kappa = 0.70). Factual error accounted for 82% of the incorrectly answered questions.Conclusion An LLM performed satisfactorily on an emergency medicine board certification examination in Japanese and without images. However, factual errors in the responses highlight the need for physician oversight when using LLMs.

DOI： 10.1272/jnms.JNMS.2024_91-205

PubMed

researchmap

記述言語：日本語   出版者・発行元：日本救急医学会-関東地方会  

researchmap

記述言語：日本語   出版者・発行元：日本救急医学会-関東地方会  

researchmap

記述言語：日本語   出版者・発行元：(一社)日本救急医学会  

researchmap

記述言語：日本語   出版者・発行元：(一社)日本救急医学会  

researchmap

記述言語：英語   掲載種別：研究論文（学術雑誌）  

BACKGROUND: Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) pneumonia is reportedly associated with air leak syndrome (ALS), including mediastinal emphysema and pneumothorax, and has a high mortality rate. In this study, we compared values obtained every minute from ventilators to clarify the relationship between ventilator management and risk of developing ALS. METHODS: This single-center, retrospective, observational study was conducted at a tertiary care hospital in Tokyo, Japan, over a 21-month period. Information on patient background, ventilator data, and outcomes was collected from adult patients with SARS-CoV-2 pneumonia on ventilator management. Patients who developed ALS within 30 days of ventilator management initiation (ALS group) were compared with those who did not (non-ALS group). RESULTS: Of the 105 patients, 14 (13%) developed ALS. The median positive-end expiratory pressure (PEEP) difference was 0.20 cmH2O (95% confidence interval [CI], 0.20-0.20) and it was higher in the ALS group than in the non-ALS group (9.6 [7.8-20.2] vs. 9.3 [7.3-10.2], respectively). For peak pressure, the median difference was -0.30 cmH2O (95% CI, -0.30 - -0.20) (20.4 [17.0-24.4] in the ALS group vs. 20.9 [16.7-24.6] in the non-ALS group). The mean pressure difference of 0.0 cmH2O (95% CI, 0.0-0.0) (12.7 [10.9-14.6] vs. 13.0 [10.3-15.0], respectively) was also higher in the non-ALS group than in the ALS group. The difference in single ventilation volume per ideal body weight was 0.71 mL/kg (95% CI, 0.70-0.72) (8.17 [6.79-9.54] vs. 7.43 [6.03-8.81], respectively), and the difference in dynamic lung compliance was 8.27 mL/cmH2O (95% CI, 12.76-21.95) (43.8 [28.2-68.8] vs. 35.7 [26.5-41.5], respectively); both were higher in the ALS group than in the non-ALS group. CONCLUSIONS: There was no association between higher ventilator pressures and the development of ALS. The ALS group had higher dynamic lung compliance and tidal volumes than the non-ALS group, which may indicate a pulmonary contribution to ALS. Ventilator management that limits tidal volume may prevent ALS development.

DOI： 10.1186/s12890-023-02549-7

PubMed

researchmap

記述言語：日本語   出版者・発行元：(一社)日本災害医学会  

researchmap

記述言語：英語  

BACKGROUND: Diabetic ketoacidosis (DKA) is associated with a high mortality rate, especially if cerebral edema develops during the disease course. It is rarer and more severe in adults than in children. We present cases of two patients with cerebral edema-related DKA. CASE PRESENTATION: The first patient was a 38-year-old man with diabetes mellitus who presented with DKA-related disturbed consciousness. Although glycemic correction was performed slowly, he showed pupil dilation 11 h later. He underwent emergency ventricular drainage, but died of cerebral herniation. The second patient was a 25-year-old woman who presented with impaired consciousness secondary to DKA. Head computed tomography showed subarachnoid hemorrhage and cerebral edema. No related intraoperative findings were observed; it was concluded that the first computed tomography scan revealed pseudo-subarachnoid hemorrhage. CONCLUSION: Diabetic ketoacidosis-related cerebral edema develops despite treatment according to guidelines and is difficult to predict. Therefore, adult patients should be treated cautiously during DKA management.

DOI： 10.1002/ams2.860

PubMed

researchmap

記述言語：日本語   出版者・発行元：(一社)日本災害医学会  

researchmap

記述言語：日本語   出版者・発行元：(一社)日本災害医学会  

researchmap

掲載種別：研究論文（学術雑誌）   出版者・発行元：Elsevier BV  

DOI： 10.1016/j.tcr.2022.100625

researchmap

記述言語：日本語   出版者・発行元：(一社)日本救急医学会  

researchmap

記述言語：日本語   出版者・発行元：(一社)日本救急医学会  

researchmap

記述言語：英語   掲載種別：研究論文（学術雑誌）  

BACKGROUND: The coronavirus disease (COVID-19) poses an urgent threat to global public health and is characterized by rapid disease progression even in mild cases. In this study, we investigated whether machine learning can be used to predict which patients will have a deteriorated condition and require oxygenation in asymptomatic or mild cases of COVID-19. METHODS: This single-center, retrospective, observational study included COVID-19 patients admitted to the hospital from February 1, 2020, to May 31, 2020, and who were either asymptomatic or presented with mild symptoms and did not require oxygen support on admission. Data on patient characteristics and vital signs were collected upon admission. We used seven machine learning algorithms, assessed their capability to predict exacerbation, and analyzed important influencing features using the best algorithm. RESULTS: In total, 210 patients were included in the study. Among them, 43 (19%) required oxygen therapy. Of all the models, the logistic regression model had the highest accuracy and precision. Logistic regression analysis showed that the model had an accuracy of 0.900, precision of 0.893, and recall of 0.605. The most important parameter for predictive capability was SpO2, followed by age, respiratory rate, and systolic blood pressure. CONCLUSION: In this study, we developed a machine learning model that can be used as a triage tool by clinicians to detect high-risk patients and disease progression earlier. Prospective validation studies are needed to verify the application of the tool in clinical practice.

DOI： 10.1272/jnms.JNMS.2022_89-210

PubMed

researchmap

記述言語：日本語   出版者・発行元：(一社)日本集中治療医学会  

researchmap

記述言語：日本語   出版者・発行元：(一社)日本臨床救急医学会  

researchmap

記述言語：日本語   出版者・発行元：(一社)日本救急医学会  

researchmap

記述言語：日本語   出版者・発行元：(一社)日本外傷学会  

researchmap

記述言語：日本語   出版者・発行元：(一社)日本救急医学会  

researchmap

記述言語：日本語   出版者・発行元：日本医科大学医学会  

researchmap

記述言語：日本語   出版者・発行元：日本医科大学医学会  

researchmap

記述言語：日本語   出版者・発行元：(株)へるす出版  

researchmap

担当区分：筆頭著者   記述言語：日本語  

researchmap

記述言語：日本語   出版者・発行元：(一社)日本集中治療医学会  

researchmap

記述言語：日本語   出版者・発行元：(一社)日本救急医学会  

researchmap

記述言語：日本語   出版者・発行元：(一社)日本救急医学会  

researchmap

記述言語：日本語   出版者・発行元：(一社)日本救急医学会  

researchmap

記述言語：日本語   出版者・発行元：(株)へるす出版  

researchmap

記述言語：日本語   出版者・発行元：(一社)日本外傷学会  

researchmap

記述言語：日本語   出版者・発行元：日本医科大学医学会  

researchmap

その他リンク： https://search-tp.jamas.or.jp/index.php?module=Default&action=Link&pub_year=2022&ichushi_jid=J04260&link_issn=&doc_id=20220307420007&doc_link_id=10.1272%2Fmanms.18.41&url=https%3A%2F%2Fdoi.org%2F10.1272%2Fmanms.18.41&type=J-STAGE&icon=https%3A%2F%2Fjk04.jamas.or.jp%2Ficon%2F00007_3.gif

記述言語：日本語   出版者・発行元：日本医科大学医学会  

researchmap

開催年月日： 2023年1月

記述言語：英語   会議種別：ポスター発表  

researchmap

開催年月日： 2022年11月

会議種別：シンポジウム・ワークショップ パネル（公募）  

researchmap

開催年月日： 2022年10月

会議種別：口頭発表（一般）  

researchmap

開催年月日： 2022年3月

会議種別：口頭発表（一般）  

researchmap

開催年月日： 2021年11月

記述言語：日本語   会議種別：口頭発表（一般）  

researchmap

開催年月日： 2021年2月

記述言語：日本語   会議種別：口頭発表（一般）  

researchmap

開催年月日： 2020年11月

記述言語：日本語   会議種別：ポスター発表  

researchmap

開催年月日： 2020年

記述言語：日本語   会議種別：口頭発表（一般）  

researchmap

開催年月日： 2018年

記述言語：日本語   会議種別：ポスター発表  

researchmap

開催年月日： 2018年

記述言語：日本語   会議種別：口頭発表（一般）  

researchmap

開催年月日： 2017年

記述言語：日本語   会議種別：ポスター発表  

researchmap

開催年月日： 2017年

記述言語：日本語   会議種別：ポスター発表  

researchmap

開催年月日： 2017年

記述言語：日本語   会議種別：ポスター発表  

researchmap

開催年月日： 2017年

記述言語：日本語   会議種別：口頭発表（一般）  

researchmap

開催年月日： 2016年

記述言語：日本語   会議種別：口頭発表（一般）  

researchmap

開催年月日： 2016年

記述言語：日本語   会議種別：口頭発表（一般）  

researchmap

開催年月日： 2015年

会議種別：ポスター発表  

researchmap