Ryan S. Hsi, MD.

J Urol

Department of Urology, Vanderbilt University Medical Center, Nashville, Tennessee.

Published: May 2024

Download full-text PDF

Source
http://dx.doi.org/10.1097/JU.0000000000003905DOI Listing

Publication Analysis

Top Keywords

ryan hsi
4
ryan
1

Similar Publications

Article Synopsis
  • Developed a nonbiohazardous simulator for ultrasound-guided percutaneous nephrolithotomy using expert feedback and modern education theory.
  • A prototype was created with realistic anatomical features through 3D printing and hydrogel molding, and validated by expert surgeons and participants in multicenter trials.
  • The simulator showed high satisfaction ratings and significant skill improvements for residents, making it an effective training tool for urologic education.
View Article and Find Full Text PDF

Background: Recent advancements of large language models (LLMs) like Generative Pre-trained Transformer 4 (GPT-4) have generated significant interest among the scientific community. Yet, the potential of these models to be utilized in clinical settings remains largely unexplored. This study investigated the abilities of multiple LLMs and traditional machine learning models to analyze emergency department (ED) reports and determine if the corresponding visits were caused by symptomatic kidney stones.

View Article and Find Full Text PDF
Article Synopsis
  • This study investigates the genetic factors contributing to kidney stone disease using a large-scale analysis of electronic health records from over 5,000 cases and 83,000 controls.
  • The research identified ten significant genetic loci related to kidney stones, with the most notable one being rs28544423, which influences urinary excretion and is linked to calcium oxalate stones.
  • While important genetic associations were found, the study noted some limitations including potential biases and concluded that genetic variants influence stone composition but not the severity of the disease.
View Article and Find Full Text PDF
Article Synopsis
  • PheMIME is an interactive visualization tool developed to analyze and characterize multimorbidity patterns across different populations using data from large-scale electronic health record (EHR) systems.
  • It integrates data from institutions like Vanderbilt University and Mass General Brigham, allowing users to explore complex disease relationships through dynamic, multi-faceted visualizations and analyses.
  • The tool enhances our understanding of patient health by making it easier to identify disease associations, ultimately contributing to more personalized healthcare strategies.
View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!