Few-Shot Personalized Blood Pressure Estimation from Photoplethysmography and Physiological Priors via Low-Rank Adaptation

Noninvasive continuous blood pressure (BP) monitoring has become a critical requirement for effective health management in the general population. To address the challenge of accurate few-shot personalized BP estimation, a photoplethysmography (PPG)-based framework built on the unified multi-task time series model with a Transformer backbone is proposed. The framework comprises population-level pretraining and personalized fine tuning with a pulse pressure segmented penalty (PPSP) loss. The PPSP couples systolic BP (SBP) and diastolic BP (DBP) outputs by penalizing pulse pressure values outside clinically accepted ranges, which enforces physiological consistency. In addition, a sampling-rate-robust low-rank adaptation (SRR-LoRA) is introduced to improve estimation accuracy when low-frequency PPG signals are employed. After rate alignment, SRR-LoRA prioritizes measurements over interpolated points, suppresses interpolation noise, and preserves cross-device generalization. Model performance was evaluated on the UCI cuffless BP estimation dataset, the University of Queensland vital signs dataset, and the CAS-BP dataset. 113,812 samples from 2,405 subjects were used for pretraining, and data from 316 subjects (each with 50 samples) were included for few-shot fine tuning. The proposed method achieved mean absolute errors of 1.52/1.07 mmHg for SBP/DBP. These results fulfill the Association for the Advancement of Medical Instrumentation BP standard and correspond to Grade A performance according to the British Hypertension Society standard and IEEE 1708 standard, which demonstrates the framework's potential for practical personalized wearable BP monitoring.