How can we detect disease
before it destroys the brain?

Artur Chudzik, PhD, is an AI engineer and scientist building explainable AI for earlier detection of Parkinson's and Alzheimer's disease. His work turns subtle patterns in cognition, gait, facial expression, eye movements, and brain imaging into interpretable digital biomarkers for monitoring disease and guiding treatment decisions. He holds a PhD in Computer Science from the Polish-Japanese Academy of Information Technology and is a member of the Digital Biomarkers in Neurodegenerative Diseases research group. He also has more than a decade of experience in software engineering and applied AI, which helps him turn research ideas into reliable, transparent, and practical systems.

My work asks a simple question: can we detect neurodegenerative disease earlier by learning from subtle patterns in behavior, cognition, and the brain?

Neurodegenerative diseases are brain diseases in which nerve cells gradually lose function and die. Timing matters because visible motor symptoms in Parkinson's disease often appear only after many dopamine-producing neurons in the substantia nigra are already dead. In Alzheimer's disease, damaging brain changes can begin decades before dementia is diagnosed. The disease process can be underway while the evidence still looks incomplete, ambiguous, or too late to act on confidently. Earlier signals can help clinicians monitor risk, choose interventions, and adjust treatment before the disease trajectory becomes harder to change.

The methodological challenge is not only to classify disease, but to make the evidence behind a prediction understandable. That is why this work combines brain imaging, online cognitive testing, eye tracking, movement analysis, facial expression analysis, and other digital biomarkers with interpretable machine-learning methods.