This study will investigate new, non-invasive methods to help diagnose Parkinson's disease. Researchers will use advanced eye imaging (hyperspectral retinal photography and OCT), computerized memory and thinking tests, and voice analysis to identify patterns linked to Parkinson's. The goal is to improve early and accurate diagnosis of Parkinson's disease without the need for spinal taps or invasive tests.
This study aims to improve how Parkinson's disease is diagnosed by testing new, non-invasive techniques that do not require spinal taps or other invasive procedures. Researchers are investigating whether changes in the eye's retina, detected with hyperspectral imaging and optical coherence tomography (OCT), can help pinpoint Parkinson's disease. These methods use special photographs and scans, similar to those performed at an eye clinic or optometrist, to analyze patterns linked to nerve cells and blood vessels in the retina. Additionally, participants will take computerized tests to measure memory, attention, and thinking skills. Since Parkinson's disease can also affect speech, the study will analyze voice recordings for specific changes that are common in the disease, such as reduced volume and strength. By combining information from eye images, cognitive tests, and voice analysis, the project hopes to develop a faster and more accurate way to diagnose Parkinson's disease at an earlier stage. The study is open to both people with Parkinson's disease and healthy volunteers, and the new diagnostic tools being tested could make future diagnosis simpler, more comfortable, and accessible to a wider population
Study Type
OBSERVATIONAL
Enrollment
60
Performance of combined model, retinal, voice and cognitive data
To assess the performance (AUC) of an optimized diagnostic model that combines HSI, OCT, and angio-OCT data with computerized cognitive testing and voice analysis for identifying Parkinson's disease
Time frame: Through study completion, an average of 6 months
Performance retinal biomarkers
To evaluate the performance (AUC) of a diagnostic model that combines hyperspectral retinal imaging (HSI), and optimally selected data from OCT and angio-OCT, for classifying patients with Parkinson's disease
Time frame: Through study completion, an average of 6 months
Diagnostic performance of each modality on its own.
Diagnostic performance for each diagnostic modality, HSI, OCT, voice and cognitive testing
Time frame: Through study completion, an average of 6 months
Correlational analyses
Correlation measures for each retinal modality with cognition and functional scale for Parkinson's disease
Time frame: Through study completion, an average of 6 months
This platform is for informational purposes only and does not constitute medical advice. Always consult a qualified healthcare professional.