Author
Listed:
- Bakaraniya Parul V.
- Mamta C. Padole
Abstract
One of the most crucial issues nowadays is the initial detection of Parkinson's disease (PD) to improve patient treatment and diagnosis. The objective of this research is to classify PD patients at an early stage among the healthy controls (HC) and the Scan without Evidence of Dopaminergic Deficit (SWEDD) group, which has a combination of symptoms from the PD and HC control groups. Accurate classification is necessary and challenging to identify Parkinson's disease in these hybrid cases. To address the aforementioned issues, the current study focuses on a novel deep neural network (DNN) architecture that can distinguish between participants in SWEDD, healthy controls, and people with PD. The data consists of clinical information and DaTSCAN single-photon emission computed tomography (SPECT) scans from 589 participants, including 62 SWEDD subjects, 135 healthy controls, and 392 PD patients. The original PPMI datasets were used. The proposed framework incorporates DNN and numerous transfer learning models, including ResNet50, DenseNet121, Xception, ResNet152, InceptionV3, VGG16, and EfficientNetV2B0.We have used Random Forest (RF) and Support Vector Machine (SVM) to create ensemble models that are comparable to all of the previously mentioned transfer learning models to improve optimization. In comparison to the estimations from hybrid model practices and conventional clustering algorithms like DBSCAN and K-Means, DNN produced distinguishing scores of 91.8% accuracy, ResNet50 with SVM produced 0.94 accuracy, ResNet152 with SVM produced 0.97 accuracy, and Xception with SVM produced 0.99 accuracy. The Xception with SVM model also yielded better results, with F1 scores of 0.98 for class 0 (HC), 1.00 for class 1 (PD), and 0.93 for class 2 (SWEDD) subjects. These results show that the proposed deep learning and transfer learning ensemble model configuration is valid for identifying PD cases alongside healthy ones in the SWEDD population.
Suggested Citation
Handle:
RePEc:gvu:tcsst0:v:8:y:2026:i:2:id:2224
DOI: 10.36548/jtcsst.2026.2.010
Download full text from publisher
Corrections
All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:gvu:tcsst0:v:8:y:2026:i:2:id:2224. See general information about how to correct material in RePEc.
If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.
We have no bibliographic references for this item. You can help adding them by using this form .
If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.
For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Journal Manager (email available below). General contact details of provider: https://irojournals.com/tcsst .
Please note that corrections may take a couple of weeks to filter through
the various RePEc services.