Limitations of Low-Cost PPG Sensors for Cuffless Blood Pressure Estimation Using IoT and Machine Learning

DOI

10.2991/978-94-6239-664-7_15How to use a DOI?

Keywords

Photoplethysmography; Blood Pressure Estimation; IoT; Machine Learning; Feature Extraction; Sensor Limitations

Abstract

One of the health issues that has attracted much attention in the world is high blood pressure (BP), which requires consistent blood pressure measurements. The traditional cuff devices, however dependable, cannot be used regularly and are inconvenient; as a result, Photoplethysmography (PPG) cuffless BP has become a popular topic in studies on Internet-of-Things (IoT) health systems. This paper gives a design and analysis of an IoT BP estimation pipeline with the use of the MAX30102 PPG sensor and an ESP32 microcontroller. Raw PPG signals were processed to eliminate noise, and then morphological, spectral, entropy, and nonlinear dynamics features were extracted. Other demographic features were also added to increase the accuracy. Mutual information, recursive feature elimination (RFE), and SHAP analysis were used to select the features. Several machine-learning models were trained and tested, such as Random Forest, CatBoost,. Through extensive feature-engineering, the highest results found were MAE = 9.08 and R² = 0.24 with Random Forest (Tuned). Due to the low sampling rate (5.6 Hz), the signal quality was poor, producing noisy and unreliable features, which could not reliably estimate the BP. This report thus indicates that cheap PPG sensors are inappropriate for clinically reliable cuffless BP prediction.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Ridwan Sharif
AU  - Arif Mahmud
PY  - 2026
DA  - 2026/06/08
TI  - Limitations of Low-Cost PPG Sensors for Cuffless Blood Pressure Estimation Using IoT and Machine Learning
BT  - Proceedings of the International Conference on Intelligent Data Analysis and Applications (IDAA 2025)
PB  - Atlantis Press
SP  - 191
EP  - 205
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6239-664-7_15
DO  - 10.2991/978-94-6239-664-7_15
ID  - Sharif2026
ER  -