Jaslok Hospital & Research Centre in Mumbai has unveiled a groundbreaking AI-driven clinical study to predict Freezing of Gait (FOG) episodes in Parkinson’s disease patients. Led by Dr. Paresh Doshi, Director of Neurosurgery, the project partners with Dr. Carine Karachi from France’s Paris Brain Institute and will launch formally on World Parkinson’s Day.
FOG affects up to 80% of advanced Parkinson’s patients, causing sudden “glued feet” sensations that lead to falls, injuries, and loss of independence. With Parkinson’s, the world’s second most common neurodegenerative disorder, rising rapidly in India, this scalable AI tool aims to fill a critical gap by forecasting both FOG risk and timing without expensive wearables or diagnostics.
How the AI System Works
The system analyzes routine walking videos via computer vision and machine learning to detect subtle gait changes signaling FOG vulnerability. It leverages Jaslok’s unique 25+ years of longitudinal data from over 750 Deep Brain Stimulation (DBS) patients.
The study unfolds in two phases:
- Phase 1: Retrospective training on data and videos from 150+ patients who developed FOG.
- Phase 2: Prospective validation in 337 patients over up to three years.
This wearable-free approach suits resource-limited Indian hospitals, clinics, and telemedicine, enabling early interventions like motor training to delay onset.
Expert Insights and International Collaboration
Dr. Paresh Doshi emphasized the need: “Parkinson’s is steadily increasing in India, placing greater pressure on neurological care systems. This collaboration strengthens early identification of motor changes in real-world settings, helping clinicians act before disability escalates.”
Dr. Carine Karachi, a global FOG expert, praised the dataset: “Prof. Doshi’s 30-year data is unique worldwide. We’re excited to collaborate via CEFIPRA funding (under review) to advance this essential research.”
Dr. Doshi added on recent advances: “FOG is a core Parkinson’s challenge. Our institute’s novel DBS programming paper complements this AI effort.”
Jitendra Haryan, CEO of Jaslok Hospital, highlighted the impact: “We’re committed to practical AI for clinical use, simplifying neurological detection to improve outcomes across India.”
Path to Open-Access Tool
The long-term goal: A user-friendly, open-access app for clinicians to spot at-risk patients early, predict timelines, and reduce falls and caregiver burden. This India-France tie-up blends neuroscience, AI, and accessible tech to transform Parkinson’s management globally.
