Application of Inertial Measurement Units and Machine Learning Classification in Cerebral Palsy (Preprint)
BACKGROUND Cerebral palsy (CP) is a physical disability that affects movement and posture. About 17 million people worldwide and 34000 people in Australia are living with CP. In clinical and kinematic research, goniometers and inclinometers are the most commonly used clinical tools to measure joint angles and position in children with CP. OBJECTIVE This paper presents collaborative research between department of Electrical Engineering and Computing at Curtin University and the investigator team of a multi-centre randomised controlled trial involving children with CP. The main objective of this paper was to develop a digital solution for mass data collection and application of machine learning to classify the movement features associated with CP without the need to measure Euler, Quaternion, and joint measurement calculation and help determine the effectiveness of therapy. METHODS Custom, low-cost Inertial Measurement Units (IMUs) were developed to record the usual wrist movements of participants aged 5 to 15 years old with CP. The IMU data were used to calculate the joint angle of the wrist movement to determine the range of motion. Nine different machine learning algorithms were used to classify the movement features associated with CP. RESULTS Upon completion of the project, the wrist joint angle was successfully calculated, and CP movement was classified as a feature using machine learning on raw IMU data, with Random Forrest algorithm showing the highest accuracy at 85.75%. CONCLUSIONS Anecdotal feedback from MIT researchers were positive about the potential for IMUs to contribute accurate data about active ROM, especially in children for whom goniometric methods are challenging. There may also be potential to use IMUs for continued monitoring of hand movement throughout the day. CLINICALTRIAL The trial is registered with the ANZ Clinical Trials Registry (ACTRN12614001276640).