The way people walk, their gait, can reveal early signs of serious neurological conditions such as Parkinson’s disease, cerebral palsy, dementia, and cognitive decline. Subtle differences in stride, balance, and timing often give clues about these conditions, but traditional gait assessments rely heavily on visual observation by doctors. This approach can be subjective, time‑consuming, and limited to controlled environments. However, a new collaboration between tech giant IBM (IBM) and Cleveland Clinic hopes to change this by creating an AI system that can work with many types of neurological conditions and sensor setups, including everyday devices like smartphone cameras and wearables.
Elevate Your Investing Strategy:
Take advantage of TipRanks Premium at 50% off! Unlock powerful investing tools, advanced data, and expert analyst insights to help you invest with confidence.
At the center of this work is an AI foundation model called GaitFM, trained on a mix of real and synthetic data. Most of the training data comes from physics‑based simulations of walking that mimic the effects of age, disease, and different types of sensors. This synthetic data helps solve a major problem in gait research: there is very little gait data available online. By first training on synthetic data and then fine‑tuning with smaller clinical datasets, GaitFM can recognize the gait patterns of different diseases.
Early tests show that GaitFM can estimate key movement features, classify conditions, and even predict disease progression. In studies, models trained on synthetic data alone were able to perform competitively, and combining synthetic with real data provided the best results. The technology is already being piloted at Cleveland Clinic and recently won Best Paper at the 2025 IEEE International Conference on Digital Health. Researchers believe this approach could make gait analysis widely accessible and scalable, especially for rare conditions where collecting real data is difficult.
Is IBM a Buy, Sell, or Hold?
Turning to Wall Street, analysts have a Moderate Buy consensus rating on IBM stock based on seven Buys, four Holds, and one Sell assigned in the past three months, as indicated by the graphic below. Furthermore, the average IBM price target of $297.33 per share implies 14.5% upside potential.
See more IBM analyst ratings
Disclaimer & DisclosureReport an Issue