In a retrospective cross-sectional analysis of clinical registry data from 2,106 maintenance hemodialysis patients, explainable machine learning models successfully distinguished prevalent arteriovenous fistula use from alternative vascular access types based entirely on routinely collected patient variables. The investigation, conducted using records from the Wuhan Hemodialysis Quality Control Center covering the 2025 calendar year, demonstrate…
This story is only covered by news sources that have yet to be evaluated by the independent media monitoring agencies we use to assess the quality and reliability of news outlets on our platform. Learn more here.