At Starlab, we’re passionate about pushing the boundaries of neuroscience and transforming the way we understand and diagnose neurodegenerative diseases. Over the past decade, our work on predicting the conversion to Parkinson's Disease (PD) and Dementia with Lewy Bodies (DLB) using EEG biomarkers has yielded groundbreaking results. Here’s a detailed look at our journey and the incredible discoveries we’ve made along the way.
The Beginning: Two Grants from the Michael J. Fox Foundation
We received two crucial grants from the Michael J. Fox Foundation aimed at developing a machine learning system for characterizing the prodromal phase of Parkinson’s Disease based on EEG biomarkers. These grants enabled us to conduct an initial study with 118 participants and subsequently validate our findings in a multi-site study involving 212 participants.
Collecting and Analyzing the Data
Our research involved collecting EEG data from patients with REM Behavior Disorder (RBD), a condition where individuals act out their dreams during sleep. RBD is recognized as an early indicator of various alpha-synucleinopathies, including Parkinson's Disease and Dementia with Lewy Bodies. Over an eight-year period, some of these patients developed PD or DLB, while others remained with RBD. Healthy controls were also included for comparison.
Predictive Power of EEG Markers
The results were compelling. Our spectral EEG markers were able to objectively predict which patients would convert to PD or DLB. The attached image illustrates the power spectral density of participants, collected eight years before their diagnosis. Even at this early stage, clear differences were visible between those who would develop PD and those who would develop DLB.
Advanced EEG Features and Machine Learning
Beyond basic spectral analysis, we extracted complex features from the EEG data, such as:
Connectivity Patterns: Examining how different brain regions communicate.
Correlating Dipoles: Linking EEG data with PET images to gain a comprehensive understanding of brain activity.
Cross-Frequency Coupling: Analyzing interactions between different frequency bands in the brain.
Using these spectral features, we trained a machine learning model to predict disease conversion. The model achieved an impressive AUC score of 0.82 and an accuracy of 91%. The second image provides detailed insights into the model’s performance.
A New Era for EEG in Neurodegenerative Diseases
Our research underscores the potential of EEG beyond traditional uses in epilepsy and sleep disorders. EEG offers a non-invasive, cost-effective method for diagnosing and understanding neurodegenerative diseases. This technology can revolutionize how we predict disease progression, assess stages, and evaluate outcomes in pharmacological clinical trials. It also aids in stratifying and selecting patients based on brain activity profiles.
Leading the Change
At Starlab, we are proud to be at the forefront of this scientific revolution. Our work continues to advance the possibilities of EEG in clinical settings, offering new hope for early diagnosis and improved management of neurodegenerative diseases.
We are excited to lead this transformative change and remain committed to enhancing patient outcomes through innovative research.
Stay tuned for more updates as we continue our journey to revolutionize neuroscience and improve patient outcomes.
Are you interested in learning how EEG can improve the treatment and monitoring of patients with cognitive complaints at your clinic?
Discover our EEG reporting services: https://www.starlab.es/services/eeg-clinical-reporting
Curious about the impact of EEG as outcome measures for your clinical trials?
Explore our EEG Clinical Support services: https://www.starlab.es/services/clinical-trial-support
Want to learn more?
Get in touch with us at info@starlab.es!
My partner was diagnosed with Parkinson's disease at the age of 66.. His symptoms included excruciating calf pain, muscular aches, tremors, slurred speech, frequent falls, loss of balance, and trouble standing up from a seated posture. After six months on Senemet, Siferol was given to him in place of the Senemet. It was also at this period that he was diagnosed with dementia. He began seeing hallucinations and became detached from reality. With the doctor's approval, we stopped giving him Siferol and chose to try the Natural Herbs Center PD-5 protocol, which we had already looked into. After three months of therapy, he has made significant progress. The illness has been completely contained. There are no symptoms of persistent twitching, weakness, tremors, hallucinations, or muscle soreness. The PD-5 Protocol was obtained…