EUVIMEDEUVIMED entdecken
Crossref

Integrating Clinical Indicators and DaTSCAN SPECT Biomarkers Using Transfer Learning Ensemble Models for Early Parkinson’s Disease Diagnosis with SWEDD Cohort

Bakaraniya Parul V., Mamta C. Padole

Journal of Trends in Computer Science and Smart Technology · 18.05.2026 · 8 (2) · 389-412

DOI: 10.36548/jtcsst.2026.2.010 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Trends in Computer Science and Smart Technology, online erschienen am 18.05.2026. Verfasst von Bakaraniya Parul V. und 1 weiteren Autor:innen. Die Arbeit nennt 36 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Zitieren

APA

V., B. P., & Padole, M. C. (2026). Integrating Clinical Indicators and DaTSCAN SPECT Biomarkers Using Transfer Learning Ensemble Models for Early Parkinson’s Disease Diagnosis with SWEDD Cohort. Journal of Trends in Computer Science and Smart Technology, 8(2), 389-412. https://doi.org/10.36548/jtcsst.2026.2.010

Vancouver

V. BP, Padole MC. Integrating Clinical Indicators and DaTSCAN SPECT Biomarkers Using Transfer Learning Ensemble Models for Early Parkinson’s Disease Diagnosis with SWEDD Cohort. Journal of Trends in Computer Science and Smart Technology. 2026;8(2):389-412. doi:10.36548/jtcsst.2026.2.010

BibTeX
@article{V2026,
  author = {V., Bakaraniya Parul and Padole, Mamta C.},
  title = {Integrating Clinical Indicators and DaTSCAN SPECT Biomarkers Using Transfer Learning Ensemble Models for Early Parkinson’s Disease Diagnosis with SWEDD Cohort},
  journal = {Journal of Trends in Computer Science and Smart Technology},
  year = {2026},
  volume = {8},
  number = {2},
  pages = {389--412},
  doi = {10.36548/jtcsst.2026.2.010}
}
Kostenlos starten →