Dr. Artur Chudzik

Computational Neuroscientist
PhD in Computer Science | Independent Researcher | Rotterdam, Netherlands

Specializing in digital biomarkers and explainable AI for brain longevity
and early Alzheimer's and Parkinson's detection

Research Focus

Digital Biomarkers

Developing accessible tools for remote neurocognitive data collection using AI-powered analysis. Digital biomarkers enable early detection and intervention before clinical symptoms appear, preserving cognitive function and healthspan.

MRI Analysis

Using interpretable machine learning to analyze structural brain changes and aging patterns in T1-weighted MRI scans. MRI provides objective assessment without requiring neurocognitive testing, enabling detection of pathological changes and disease staging before clinical symptoms emerge.

Cognitive Assessment

Applying machine learning to online cognitive tests (MoCA, Trail Making Test) combined with temporal response dynamics. Response patterns significantly improve diagnostic accuracy while maintaining accessibility for remote assessment.

Eye Tracking

Analyzing eye movement patterns and oculomotor dynamics using machine learning methods. Eye tracking biomarkers reveal neurodegeneration in early disease stages through non-invasive, accessible measurement.

Movement & Gait Analysis

Utilizing motion capture and complexity analysis to study gait patterns and the concept of healthy chaos in walking. Movement biomarkers reveal subtle changes in motor control that precede clinical symptoms in neurodegenerative diseases.

Online Neurocognitive Testing

Creating web-based platforms for remote neurocognitive assessment using standard home equipment. Investigating VR-based serious games and Trail Making Tests to assess spatial orientation and hippocampal function in immersive 3D environments.

Recent Publications

Machine Learning Methods for Parkinson's Disease Datasets

Springer Nature, 2025 | Book Chapter: Intelligent Technologies Vol. 4 | DOI: 10.1007/978-981-96-5585-4_6

A guide to building AI systems that doctors can actually understand and trust. Shows how to predict disease progression using methods that explain their reasoning, not black boxes that return unexplainable answers.

View publication →

How to Cure Alzheimer's Disease

Journal of Alzheimer's Disease, 2024 | DOI: 10.3233/JAD-240231

Brain changes begin 20-30 years before symptoms appear. By using machine learning and rough set theory to analyze cognitive data backwards in time, we can predict who will develop dementia years before clinical diagnosis—when intervention might still work.

View publication →

Machine Learning Recognizes Stages of Parkinson's Disease Using Magnetic Resonance Imaging

Sensors, 2024 | DOI: 10.3390/s24248152

Standard brain scans can reveal where someone is in disease progression without any cognitive testing. This means objective staging using equipment already available in most hospitals.

View publication →

Classification of Parkinson's Disease Using Machine Learning with MoCA Response Dynamics

Applied Sciences, 2024 | DOI: 10.3390/app14072979

It's not just what answers people give on cognitive tests, but how long they take to respond. Adding timing data to a simple online test dramatically improves detection accuracy.

View publication →

Machine Learning and Digital Biomarkers Can Detect Early Stages of Neurodegenerative Diseases

Sensors, 2024 | DOI: 10.3390/s24051572 | Review Article | Popular

A comprehensive look at how everyday technology can catch brain diseases early. Reviews the current state of digital tools for spotting problems before symptoms appear.

View publication →

Machine Learning and Eye Movements Give Insights into Neurodegenerative Disease Mechanisms

Sensors, 2023 | DOI: 10.3390/s23042145 | Review Article | Popular

The way your eyes move reveals early brain changes. Eye tracking provides a non-invasive window into neurological health that can catch problems years before other symptoms.

View publication →

About

Dr. Artur Chudzik

The brain begins to change decades before symptoms appear. By the time someone notices memory loss or tremor, much of the damage is irreversible. My work asks: can we see these changes earlier, when intervention is still possible?

I develop explainable AI methods that turn digital tools into windows on brain health. Online cognitive tests, standard MRI scans, eye tracking: these accessible technologies can reveal early changes when combined with interpretable machine learning. The approach emphasizes transparency. Clinicians should be able to understand why a diagnosis is made, not just accept an algorithm's output.

Working with collaborators across Europe and the US, I focus on making brain longevity research practical and deployable. Methods that can reach people before it's too late to intervene.

Education

  • PhD in Computer Science
    Polish-Japanese Academy of Information Technology, Warsaw
  • M.Sc. Computer Engineering
    Rzeszow University of Technology
  • B.Sc. Computer Engineering
    Rzeszow University of Technology

Research Areas

  • Machine Learning & AI
  • Digital Biomarkers
  • Neurodegenerative Diseases
  • Brain Aging & Cognitive Longevity
  • Digital Phenotyping
  • Computational Neuroscience
  • Medical Data Mining

Impact

Contact & Collaboration

I am open to remote research positions, grant collaborations, and partnerships in computational neuroscience, machine learning for healthcare, and brain longevity research.

Email: artur.chudzik@pjwstk.edu.pl