Transformer model ProQ-BERT advances CKD prognosis prediction

Researchers have developed a transformer-based framework called ProQ-BERT to predict the progression of Chronic Kidney Disease (CKD). This model utilizes multi-modal electronic health records, including demographic, clinical, and laboratory data, employing novel tokenization for continuous values and attention mechanisms for interpretability. Tested on over 91,000 patients, ProQ-BERT demonstrated superior performance compared to CEHR-BERT, achieving an ROC-AUC of up to 0.995 and PR-AUC of 0.989 for short-term predictions. The study highlights the potential of transformer architectures in advancing personalized CKD care. AI

IMPACT Enhances clinical decision-making for CKD patients by improving prediction accuracy.

RANK_REASON The cluster describes a research paper detailing a new model for disease prognosis. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• CEHR-BERT
• Chronic Kidney Disease
• Dong Gyun Kang
• Observational Medical Outcomes Partnership Common Data Model
• ProQ-BERT
• Seoul National University Hospital
• transformer

• paper
• model release

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