Artur Chudzik

Selected publications

Selected publications and forthcoming work on machine learning, digital biomarkers, and neurodegenerative disease detection.

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

This review explains how digital biomarkers such as online cognitive tests, eye tracking, and movement data can be combined with AI to spot early signs of Parkinson's and Alzheimer's before symptoms become obvious.

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

This study uses standard T1 MRI scans and interpretable machine-learning features based on brain-region volumes and spatial relationships to distinguish healthy controls, prodromal cases, and Parkinson's disease.

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

This paper shows that online MoCA results become much more useful when timing information is added. Response-time measures helped machine-learning models better separate Parkinson's disease from healthy controls.

Recognizing Patterns of Parkinson's Disease Using Online Trail Making Test and Response Dynamics

This study evaluates an online version of the Trail Making Test and shows that timing-based measures can capture both cognitive and motor changes linked to Parkinson's disease severity.

Investigating the Impact of Parkinson's Disease on Brain Computations: An Online Study of Healthy Controls and PD Patients

This paper uses an online testing platform and neuropsychological tasks to compare healthy controls and Parkinson's patients. The results suggest that subtle cognitive and behavioral changes can be detected before clear clinical symptoms appear.

Eye-Tracking and Machine Learning Significance in Parkinson's Disease Symptoms Prediction

This work combines eye-tracking and neuropsychological testing to predict symptom progression in Parkinson's disease, showing that eye movements can serve as a useful digital biomarker.

Machine Learning and Eye Movements Give Insights into Neurodegenerative Disease Mechanisms

This review looks at how eye-movement tests such as saccades, antisaccades, and pursuit tasks can be analyzed with machine learning to better understand disease mechanisms in Parkinson's and Alzheimer's disease.

Comparison of Different Data Mining Methods to Determine Disease Progression in Dissimilar Groups of Parkinson's Patients

This paper compares rough-set models and other machine-learning methods for predicting changes in Parkinson's disease severity across patient groups receiving different treatments, including deep brain stimulation.

DTI Helps to Predict Parkinson's Patient's Symptoms Using Data Mining Techniques

This early study uses diffusion tensor imaging and data mining to estimate how symptoms may develop after deep brain stimulation by analyzing connections between the stimulated brain region and the cortex.

Symbolic AI for Parkinson's Severity Classification Using MRI In press

This study investigates interpretable AI for classifying Parkinson's disease severity using MRI-derived spatial biomarkers. It shows that symbolic, rule-based models can achieve strong performance while remaining transparent and clinically interpretable.

How Can AI Help to Prevent Dementia In press

This paper explores how explainable AI can identify early dementia risk by analyzing cognitive test results and genetic markers. The goal is to detect subtle signs of Alzheimer's-related decline long before clear clinical symptoms appear.

Preliminary Analysis of Nonlinear Stability in Human Gait Using Marker-Based Largest Lyapunov Exponent Estimation In press

This work studies human gait using nonlinear dynamics and motion-capture data. By measuring frame-by-frame stability changes during walking, it explores whether subtle motor abnormalities could support early screening for neurodegenerative disease.

About

Dr. Artur Chudzik (PhD), is an AI engineer and researcher specializing in medical artificial intelligence and computational neuroscience. His research focuses on explainable machine learning methods for the early detection and monitoring of neurodegenerative diseases, including Parkinson's and Alzheimer's disease.

He holds a PhD in Computer Science from the Polish-Japanese Academy of Information Technology in Warsaw. He earned both his M.Sc. and B.Sc. degrees in Computer Engineering from Rzeszow University of Technology, where he developed an eye-tracking system that enabled individuals with severe disabilities to communicate using eye movements - a project that received positive media coverage.

Currently, his research explores digital biomarkers derived from brain imaging, online cognitive testing, eye-tracking, and movement analysis. By combining interpretable machine learning with accessible digital tools, his work aims to enable earlier and more reliable detection of neurological disorders.

He also contributes to the academic community through peer review and has been recognized as a Reviewer of the Month by the journal Quantitative Imaging in Medicine and Surgery.

Alongside academic research, he has more than a decade of experience in software engineering and applied AI, building intelligent systems that are transparent, reliable, and clinically useful.

As a scientific side interest, he explores questions in cosmology and theoretical physics, including numerical studies of the relationship between cosmic time and the expansion of the universe and the analysis of gamma-ray bursts as cosmological probes.

Research interests

Artificial intelligence

I work on building machine learning systems for biomedical data that are not only accurate, but also understandable. I am especially interested in explainable AI - models that clinicians can trust and interpret. When AI is transparent, it can reveal meaningful patterns in data and make it easier to bring these tools into real healthcare settings.

Neuroscience

My research explores how computational models can help us better understand the brain, particularly in neurodegenerative diseases. By connecting data analysis with biological processes, I aim to identify early changes in the brain and contribute to earlier detection and intervention strategies.

Complex systems

I am fascinated by complex systems - from high-dimensional data to mathematical models that describe how patterns emerge. Using tools from applied mathematics and data science, I study how structure and behavior arise in complicated systems, with the goal of improving both prediction and understanding.

Artificial Intelligence & Neuroscience