This project is undertaken by a master’s student at the Responsible Artificial Intelligence Lab. Bladder volume estimation is crucial for patients with spinal cord injury (SCI) as their neuro-urological functions are impaired, often leading to an inability to sense bladder fullness.
This can result in complications such as urinary tract infections (UTIs), bladder distension, autonomic dysreflexia, and urinary incontinence. Traditional methods like catheterization and ultrasound are either invasive or require skilled personnel, making them unsuitable for continuous, home-based monitoring.
Continuous bladder monitoring using sensors offers a non-invasive solution. However, estimation algorithms trained on able-bodied individuals may produce inaccurate results when applied to the sedentary lifestyle typical of SCI patients. Therefore, validating and adapting these algorithms for the SCI population is essential.
Additionally, electrode-based sensors are prone to artefacts due to posture changes and motion, necessitating the development of specific artefact suppression techniques tailored to the unique movements of SCI individuals.
