Parkinson's Disease, a frequently diagnosed neurodegenerative condition, poses a major global challenge. Early diagnosis and intervention are crucial for Parkinson disease treatment. This study proposes a diagnostic model for Parkinson disease that analyzes volatile organic compounds from ear canal secretions. Using gas chromatography-mass spectrometry to examine ECS samples from patients, four VOC components were identified as biomarkers with statistically significant differences between Parkinson disease and non-Parkinson disease patients. Diagnostic models based on these VOC components demonstrate strong capability in identifying and classifying Parkinson disease patients. To enhance the accuracy and efficiency of the Parkinson disease diagnostic model, this study introduces a protocol for extracting features from chromatographic data. By integrating gas chromatography-surface acoustic wave sensors with a convolutional neural network model, the system achieves an accuracy of up to 94.4%. Further enhancements to the diagnostic model could pave the way for a promising new Parkinson disease diagnostic solution and the clinical use of a bedside Parkinson disease diagnostic device.
