This study evaluated the accuracy of ChatGPT in translating English patient education materials into Spanish, Mandarin, and Russian. While ChatGPT shows promise for translating Spanish and Russian medical information, Mandarin translations require further refinement, highlighting the need for careful review of AI-generated translations before clinical use.
View Article and Find Full Text PDFEnsuring reliability of Large Language Models (LLMs) in clinical tasks is crucial. Our study assesses two state-of-the-art LLMs (ChatGPT and LlaMA-2) for extracting clinical information, focusing on cognitive tests like MMSE and CDR. Our data consisted of 135,307 clinical notes (Jan 12th, 2010 to May 24th, 2023) mentioning MMSE, CDR, or MoCA.
View Article and Find Full Text PDFBackground: High flow nasal cannula therapy (HFNC) and continuous positive airway pressure (CPAP) are two widely used modes of non-invasive respiratory support in paediatric critical care units. The FIRST-ABC randomised controlled trials (RCTs) evaluated the clinical and cost-effectiveness of HFNC compared with CPAP in two distinct critical care populations: acutely ill children ('step-up' RCT) and extubated children ('step-down' RCT). Clinical effectiveness findings (time to liberation from all forms of respiratory support) showed that HFNC was non-inferior to CPAP in the step-up RCT, but failed to meet non-inferiority criteria in the step-down RCT.
View Article and Find Full Text PDFBACKGROUNDDespite an overall poor prognosis, about 15% of patients with advanced-stage tubo-ovarian high-grade serous carcinoma (HGSC) survive 10 or more years after standard treatment.METHODSWe evaluated the tumor microenvironment of this exceptional, understudied group using a large international cohort enriched for long-term survivors (LTS; 10+ years; n = 374) compared with mid-term (MTS; 5-7.99 years; n = 433) and short-term survivors (STS; 2-4.
View Article and Find Full Text PDF