New Transformer model estimates blood pressure from PPG signals

Researchers have developed a new Transformer-based model called DMT for estimating blood pressure from PPG signals without a cuff. This model incorporates demographic information through feature modulation within its attention layers and includes an auxiliary head to focus on BP-relevant waveform morphology. On the PulseDB dataset, DMT achieved a 47% reduction in systolic BP error and a 50% reduction in diastolic BP error compared to previous demographic-enhanced baselines. AI

IMPACT Introduces a novel approach for cuffless blood pressure estimation, potentially improving wearable health monitoring.

RANK_REASON This is a research paper detailing a new model and its performance on a specific dataset. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• PPG
• PulseDB
• Transformer

• paper
• model release

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