Deep learning model KFDeep dynamically predicts kidney failure

Researchers have developed KFDeep, a deep learning model designed to dynamically predict kidney failure using longitudinal electronic health record data. The model demonstrated strong performance across internal and three external validation cohorts, achieving AUROCs ranging from 0.8141 to 0.9359. KFDeep provides continuously updated predictions without increasing clinical examination costs and has been integrated into hospital systems as a decision-support tool for physicians. AI

IMPACT This model offers a new tool for early detection of kidney failure, potentially improving patient outcomes and reducing healthcare costs.

RANK_REASON The cluster describes a research paper detailing the development and validation of a new deep learning model. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• arXiv
• CKD-NET-Yinzhou Dataset
• C-STRIDE cohort
• Hugging Face
• iCaReMe cohort
• Jingying Ma
• KFDeep
• PKUFH cohort

• paper
• model release
• product

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →