New AI Model Mr.Dec Predicts Hospital Readmissions Using Daily EHR and X-ray Data

Researchers have developed Mr.Dec, a novel multimodal model designed to predict 30-day hospital readmissions by analyzing longitudinal patient data. Unlike previous methods that condense patient history, Mr.Dec processes daily electronic health record updates and chest X-ray findings in a time-aligned sequence, mimicking the clinical workflow. The model utilizes a Transformer Decoder architecture and Disease-Specific Supervised Contrastive Learning to capture dynamic patient trajectories and identify critical days within an admission for real-time risk stratification. Evaluations on the MIMIC-IV and MIMIC-CXR datasets demonstrate that Mr.Dec achieves state-of-the-art performance by preserving the integrity of the clinical sequence. AI

IMPACT This model could improve patient care by enabling more accurate and timely risk stratification for hospital readmissions.

RANK_REASON The cluster contains a research paper detailing a new AI model for a specific application. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• arXiv
• chest radiograph
• Disease-Specific Supervised Contrastive Learning
• electronic health records
• MIMIC-CXR
• MIMIC-IV
• Mr.Dec
• Transformer Decoder

• paper
• model release
• other

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