EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

From PPG to Blood Pressure at the Edge: Quantization-Aware Architecture Selection and On-MCU Validation

Elisabetta Leogrande iD, Emanuele De Luca iD, Francesco Dell'Olio iD

Sensors · 25.04.2026 · 26 (9) · 2674

DOI: 10.3390/s26092674 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 25.04.2026. Verfasst von Elisabetta Leogrande und 2 weiteren Autor:innen. Beteiligte Einrichtung: Micro Nano Sensor Group, Polytechnic University of Bari, Via Edoardo Orabona 4, 70126 Bari, Italy. Hauptthemen laut MEDLINE: Photoplethysmography, Blood Pressure, Blood Pressure Determination. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 25 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Blood pressure is a central marker of cardiovascular risk, but continuous monitoring remains difficult because cuff-based measurements are intermittent and uncomfortable. Photoplethysmography (PPG) is already ubiquitous in wearables and can, in principle, enable cuffless blood pressure estimation from a single optical signal. However, many deep learning approaches that perform well in floating-point are impractical for microcontroller-class devices, where memory budgets, latency, and integer-only arithmetic constrain what can be deployed. A key open question is which neural architectures retain accuracy after full-integer quantization, rather than only under desktop inference. Here, we show an end-to-end, microcontroller-oriented evaluation framework that benchmarks multiple 1D convolutional models for cuffless systolic and diastolic pressure estimation from single-channel PPG, jointly optimizing estimation error, model footprint, and quantization robustness. We find that floating-point accuracy alone is a poor predictor of deployability: some lightweight CNNs exhibit substantial performance drift after INT8 conversion, whereas a compact residual 1D CNN preserves its predictions with near-identical error statistics after integer quantization. We then deploy the selected integer-only model on an STM32N6 microcontroller using an industrial toolchain and confirm that on-device inference maintains low bias and limited error dispersion while meeting real-time constraints for continuous operation. These results highlight architecture-dependent quantization stability as a critical design dimension for sensor-edge intelligence and support the feasibility of fully on-device cuffless blood pressure monitoring without multimodal sensing or cloud processing.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

PhotoplethysmographyBlood PressureBlood Pressure DeterminationHumansConvolutional Neural NetworksSignal Processing, Computer-AssistedAlgorithmsDeep LearningNeural Networks, Computer

Stichwörter der Autor:innen

STM32N6TinyMLcuffless blood pressure estimationembedded neural networksphotoplethysmographyquantization-aware design

Autor:innen und Institutionen

  • Micro Nano Sensor Group, Polytechnic University of Bari, Via Edoardo Orabona 4, 70126 Bari, Italy.

ORCID-Profile: Elisabetta Leogrande, Emanuele De Luca, Francesco Dell'Olio

Zitieren

APA

Leogrande, E., Luca, E., & Dell'Olio, F. (2026). From PPG to Blood Pressure at the Edge: Quantization-Aware Architecture Selection and On-MCU Validation. Sensors, 26(9), 2674. https://doi.org/10.3390/s26092674

Vancouver

Leogrande E, Luca E, Dell'Olio F. From PPG to Blood Pressure at the Edge: Quantization-Aware Architecture Selection and On-MCU Validation. Sensors. 2026;26(9):2674. doi:10.3390/s26092674

BibTeX
@article{Leogrande2026,
  author = {Leogrande, Elisabetta and Luca, Emanuele De and Dell'Olio, Francesco},
  title = {From PPG to Blood Pressure at the Edge: Quantization-Aware Architecture Selection and On-MCU Validation},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {9},
  pages = {2674},
  doi = {10.3390/s26092674}
}
Kostenlos starten →