Research Projects

Parkinson's disease (PD) is a progressive neurodegenerative disorder affecting over 10 million people worldwide. The prevalence of PD in India is estimated at 0.58 million, with the numbers expected to rise significantly due to an aging population. PD results in 5.8 million disability-adjusted life years (DALYs) and 329,000 deaths annually worldwide, placing a substantial economic and social burden on individuals and healthcare systems. Existing solutions for PD management include pharmacological treatments, such as levodopa/carbidopa, which remain the gold standard for symptom management. Additionally, deep brain stimulation (DBS) has shown promise in reducing motor symptoms, though its high cost and invasive nature often limit it. Physiotherapy and occupational therapy are also commonly employed to improve mobility and functional abilities. In India, however, access to these treatments can be limited by socioeconomic factors and the availability of specialized care. Robotic-assisted rehabilitation is emerging as a promising avenue for PD management. Devices such as the Lokomat and EksoGT provide robotic exoskeletons to support and enhance gait training, demonstrating significant improvements in mobility and muscle strength. Despite these advancements, the high cost and limited availability of such devices pose challenges to widespread adoption, particularly in low- and middle-income countries like India. Despite the advances in pharmacological treatments and robotic-assisted rehabilitation, there remains a significant need for innovative solutions that are both cost-effective and accessible. This project proposes the development of a hybrid AI-integrated wearable suit designed for early disease prediction, assisting Parkinson's patients with locomotion, and preventing freezing of gait events. By utilizing multiple input signals, including Electroencephalogram (EEG), Electromyogram (EMG), and Inertial measurement Units (IMU) sensors, this wearable suit aims to provide real-time assistance tailored to the patient's specific needs. The hybrid system uses EEG signals processed by AI algorithms to identify the patient's locomotion intentions, while EMG signals estimate the muscle force generated by the lower limb muscles. Additionally, IMU sensors are employed to gait phases and gait events during walking. An AI module is developed to predict the freezing of gait events and trigger control signals that activate actuators on the leg joints, providing the necessary assistance to avoid these episodes and facilitate seamless walking. The modular and cost-effective nature of the solution ensures that it can be scaled and adapted for broader use, making it an asset in the global fight against neurodegenerative diseases. This initiative not only promises to deliver clinical benefits but also holds the potential to make a substantial societal impact, fostering a healthier and more inclusive world.