Micheal Abimbola Oladosu1, Moses Adondua Abah2, Loveth Agbo3 and Olaide Ayokunmi Oladosu4

 1Department of Chemical Sciences, Faculty of Science, Anchor University Lagos, Ayobo-Ipaja, Lagos, Nigeria.

2Department of Biochemistry, Faculty of Pure and Applied Sciences, Federal University of Wukari, Wukari, Taraba State, Nigeria.

3Department of Pharmacy, Faculty of Pharmaceutical Sciences, University of Porth Harcourt, River State, Nigeria

4Department of Computer Science, Faculty of Science and Technology, Babcock University,

Ilishan, Nigeria.

() Corresponding Author

 Received: April 26, 2026/ Revised: May 28, 2026/Accepted: June 3, 2026

Highlights

  • Reviews AI-driven biomedical signal processing for diagnosis and remote patient monitoring.
  • Explores integration of pneumatic sensors, IoT, and intelligent healthcare systems.
  • Evaluates machine learning and deep learning methods for physiological signal analysis.
  • Highlights applications in respiratory, cardiovascular, and wearable health monitoring.
  • Discusses challenges related to sensor reliability, privacy, and clinical implementation.
 Abstract

 Air-powered biomedical technologies represent an emerging paradigm in healthcare monitoring, combining pneumatic sensing mechanisms with advanced signal processing techniques for non-invasive diagnostic applications. This review examines the integration of air-powered sensors, including pneumatic tactile sensors, respiratory monitoring devices, and soft robotic systems, with biomedical signal processing algorithms for real-time patient monitoring and disease diagnosis. The synthesis of pneumatic sensing technology with machine learning algorithms, edge computing, and Internet of Things (IoT) infrastructures has enabled continuous, wireless monitoring of vital physiological parameters, including respiratory patterns, cardiovascular signals, and biomechanical activities. Key applications discussed include respiratory disease monitoring, cardiac signal analysis, tumour detection through robotic palpation, and remote patient monitoring systems. Signal processing methodologies encompassing wavelet transforms, entropy-based analysis, and deep learning architectures are critically evaluated for their efficacy in extracting clinically relevant features from air-powered sensor data. Current challenges, including sensor drift, environmental interference, data privacy, and standardisation, are addressed alongside emerging solutions through adaptive filtering and federated learning frameworks. This review underscores the transformative potential of air-powered biomedical signal processing in advancing personalised, accessible, and efficient healthcare delivery systems.

Keywords: Air-powered sensors, pneumatic sensing, biomedical signal processing, remote patient monitoring, respiratory monitoring, machine learning, soft robotics, wearable sensors

How to cite this article

Oladosu, M. A., Abah, M. A., Agbo, L., & Oladosu, O. A. (2026). AI-powered biomedical signal processing applications in diagnosis and remote patient monitoring. Science Archives, 7(2), 74–85. https://doi.org/10.47587/SA.2026.7206

This work is licensed under a Creative Commons Attribution 4.0 International License


 

View Details