Research

Medical Sciences

Title :

Development of nanocomposite based wearable sensors and machine learning algorithm for the remote monitoring of post stroke rehabilitation exercises

Area of research :

Medical Sciences

Focus area :

Wearable Sensors

Principal Investigator :

Dr. Pramod Kesavan Namboothiri, Manipal Academy Of Higher Education, Karnataka

Timeline Start Year :

2022

Timeline End Year :

2025

Contact info :

Equipments :

Details

Executive Summary :

Stroke is a major cause of disability worldwide, and patients undergo rehabilitation therapies in acute stages at specialized health care facilities and after discharge in chronic stages at home or communities. However, the provision available in specialized hospitals during acute stages may not be available in chronic stages, making it difficult to monitor, evaluate, and ensure treatment quality and efficiency. Wireless wearable sensors can provide more objective evaluation of patients' condition with quantifiable data, reducing evaluation times, replicable, and potentially reducing diagnostic errors. The additional details captured by these sensors can be used to categorize patients into finer specific groups and provide personalized treatment. Physiotherapists can use these sensors to understand variations in motor functions during daily life activities and for remote monitoring. A promising study involves stretchable sensors with low Young's modulus (E) mismatch between sensor and skin, which enables conformal contacts with the human body without significant interference. Nano sensors consist of stretchable polymer thin layer coated cotton matrix or substrate and cotton matrix coated with conducting nano material filler or surface coating by spray coating. The movement of the body part will be sensed based on piezoresistive/capacitive property of the nanocomposite sensor. The electrical percolation of nanofillers depends on factors like size, aspect ratio, and volume percentage of the filler in the matrix. To design an efficient sensor, these factors will be studied in detail and optimized. Signals acquired from these sensors can be collected by a transmitter unit attached to the body and sent wirelessly to a nearby mobile phone. Machine learning-based prediction modals will be developed to support clinicians in monitoring and managing post-stroke rehabilitation.

Co-PI:

Dr. Manikandan Natarajan, Manipal Academy Of Higher Education, Karnataka-576104, Dr. Mathew Peter, Manipal Academy Of Higher Education, Karnataka-576104, Dr. M Jeevan, Manipal Academy Of Higher Education, Karnataka-576104

Total Budget (INR):

31,47,657

Organizations involved