The Science of Recovery

How Sync Works

Stroke can sever the brain's motor pathways overnight. Sync applies the same biological rules the brain uses to learn — precisely, consistently, and from home.

Hebbian Plasticity

Practice Together, Connect Together

Your brain learns by repetition. When you think about moving your hand and actually move it at the same time, the brain cells involved form stronger connections — like a path that gets wider the more you walk on it. Neuroscientist Donald Hebb described this in 1949: neurons that fire together, wire together.

After a stroke, these pathways are damaged. Sync helps rebuild them by making sure your intention to move and the actual movement happen within half a second of each other — the sweet spot where the brain is most ready to rewire itself.

[1] Hebb, D.O. (1949). The Organization of Behavior. Wiley.

[2] Takeuchi, N. & Izumi, S-I. (2015). Combinations of stroke neurorehabilitation to facilitate motor recovery: perspectives on Hebbian plasticity and homeostatic metaplasticity. Frontiers in Human Neuroscience, 9:349.

Computer Vision

Webcam-Guided Movement Practice

When you sit down for a Sync session, all you see is your exercise on screen and a camera watching your movement. There is no suit to put on, no sensor to clip to your wrist, and no technician required. Behind that simplicity, the camera is tracking 33 points across your body and 21 points on each hand, updating in real time at research-grade precision.

This level of detail, made possible by advances in markerless pose estimation, lets Sync give you immediate feedback during each exercise — whether your affected arm is reaching the right range of motion, whether your posture is correct, and how your performance is changing over days and weeks.

[3] Amprimo, G. et al. (2024). Hand tracking for clinical applications: Validation of the Google MediaPipe Hand (GMH) and the depth-enhanced GMH-D frameworks. Computer Methods and Programs in Biomedicine.

[4] Markerless Human Pose Estimation for Biomedical Applications (2023). Frontiers in Computer Science.

33 Body Landmarks

21 Hand Landmarks

Mirror Therapy

See It, Move It, Recover It

Here is something remarkable about the human brain: it does not fully distinguish between doing something and watching it being done. When researchers discovered this in 1992, they found a class of brain cells — now called mirror neurons — that fire both when you perform an action and when you observe someone else performing the same action. Rizzolatti & Craighero (2004) later showed this system is woven throughout the motor and premotor cortex, deep in the machinery of how we move and learn.

Ramachandran & Altschuler (2009) put this to practical use, showing that mirror visual feedback — reflecting the healthy limb to appear as the affected one — can reduce phantom pain and accelerate motor recovery after stroke. Sync digitizes this: your webcam captures your good side and reflects it in real-time, creating the illusion of bilateral movement and giving the brain's mirror system something meaningful to work with.

[5] Di Pellegrino, G. et al. (1992). Understanding Motor Events. Experimental Brain Research, 91, 176-180.

[6] Rizzolatti, G. & Craighero, L. (2004). The Mirror-Neuron System. Annual Review of Neuroscience, 27.

[7] Ramachandran, V.S. & Altschuler, E.L. (2009). Brain, 132(7).

Gamification

Play to Recover

Repetition is the engine of motor recovery, but traditional rehabilitation exercises are often monotonous, leading to low adherence. Games work in rehabilitation not simply because they are more enjoyable, but because they generate the volume of repetitions that recovery demands without the psychological grind of doing the same movement for its own sake. Gamified neurorehabilitation transforms repetitive movements into engaging game mechanics — turning shoulder flexions into paddle strokes, finger taps into musical notes, and weight shifts into farm tasks.

Research shows that game-based approaches significantly increase exercise frequency, session duration, and patient motivation compared to conventional therapy. By providing real-time scoring, progress tracking, and adaptive difficulty, Sync keeps patients engaged through the hundreds of repetitions needed for neural rewiring.

[8] Gamified Neurorehabilitation Strategies for Post-stroke Motor Recovery (2022). Current Neurology & Neuroscience Reports.

Scoring

Progress

Repetition

Adaptive

Speech Therapy

AI-Powered Speech Recovery

For roughly one in three stroke survivors, the words that were once easy to find simply stop coming. Aphasia — the loss of ability to understand or produce speech — can be one of the most isolating consequences of stroke, and progress requires more daily practice than a weekly clinic visit can provide. Traditional speech therapy is valuable but constrained: the hours are limited, and the practice stops when the session ends.

AI-powered speech assessment can now evaluate pronunciation accuracy, fluency, and prosody in real-time, enabling guided speech exercises that patients can practice independently at home. Sync integrates AI speech technology to provide immediate feedback across 12 exercise types including pronunciation, articulation, sentence building, and picture naming.

[9] AI-Assisted Assessment and Treatment of Aphasia (2024). Frontiers in Public Health.

Technology

Just a Webcam. Nothing Else.

No wearables, no expensive equipment. Sync uses computer vision through your browser's webcam.

Pose Detection

33 body landmarks tracked in real-time for gross motor exercises

Hand Tracking

21 hand landmarks per hand for fine motor exercises

Key References

[1] Hebbian Plasticity

Hebb, D.O. (1949). The Organization of Behavior. Wiley.

[2] Activity-Dependent Neuroplasticity

Takeuchi, N. & Izumi, S-I. (2015). Combinations of stroke neurorehabilitation to facilitate motor recovery: perspectives on Hebbian plasticity and homeostatic metaplasticity. Frontiers in Human Neuroscience, 9:349.

[3] Clinical Validation of MediaPipe

Amprimo, G. et al. (2024). Hand tracking for clinical applications: Validation of the Google MediaPipe Hand (GMH) and the depth-enhanced GMH-D frameworks. Computer Methods and Programs in Biomedicine.

[4] Pose Estimation

Markerless Human Pose Estimation for Biomedical Applications (2023). Frontiers in Computer Science.

[5] Mirror Neurons

Di Pellegrino, G. et al. (1992). Understanding Motor Events. Experimental Brain Research, 91, 176-180.

[6] Mirror-Neuron System

Rizzolatti, G. & Craighero, L. (2004). The Mirror-Neuron System. Annual Review of Neuroscience, 27.

[7] Mirror Therapy

Ramachandran, V.S. & Altschuler, E.L. (2009). Brain, 132(7).

[8] Gamification

Gamified Neurorehabilitation Strategies for Post-stroke Motor Recovery (2022). Current Neurology & Neuroscience Reports.

[9] AI Speech

AI-Assisted Assessment and Treatment of Aphasia (2024). Frontiers in Public Health.