Data Efficient Cuffless Blood Pressure Classification from PPG using Foundation Model Embeddings and Few-Shot Learning
Mahdi Pirayesh Shirazi Nejad, Elahe Hosseini, Mohammadnavid Tarighat, Ning Miao, Zequan Liang, Edwin Kay, Hossein Sayadi, Javier E. Lopez, Houman Homayoun
Summary
A pretrained wearable-physiology FM (not named in the abstract) is used as a frozen feature extractor; a lightweight few-shot classifier conditioned on 3 labeled PPG–SBP context pairs predicts the AHA BP category (6 classes) of a query segment. Adaptation pool 2,400 pairs; held-out test 15,000 pairs from PulseDB/VitalDB. Accuracy 82.4%, weighted F1 0.832 from PPG alone.
Key facts
- Form Factor
- clinical_finger
- License
- Not stated
Reported benchmarks
Cuffless blood pressure
pulsedb-vitaldb-aha6 · Accuracy ↑
AHA 6-class category, 3-shot; weighted F1 0.832; classification — not comparable to MAE rows
Updated: Oct 11, 2026
Related Research
- Cuffless blood pressure leaderboard
Benchmark results for cuffless blood pressure
- LIMA-Mamba: A lightweight and distribution-robust Mamba network for PPG-based biometrics
Research paper
- A Comparative Study of Signal Representations Methods and Deep Learning Architectures for PPG-Based Cuffless Blood Pressure Estimation
Seven 1D→2D transforms × several CNN variants on the UCI BP database. Best: CWT, errors reported as
- A Decodability-Grounded Audit of Clinical Prediction Claims in PPG Foundation Models
Audits frozen representations of four encoders on 37,784 MC-MED encounters via concept decodability,