IRO Journals
Journal of Trends in Computer Science and Smart Technology

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

Open Access
Published: 18 May, 2026
Pages: 389-412
  • Bakaraniya Parul V. , Bakaraniya Parul V.
    Research Scholar, Department of Computer Science and Engineering, The M. S. University, Vadodara, India
    Research Scholar, Department of Computer Science and Engineering, The M. S. University, Vadodara, India
  • Mamta C. Padole Mamta C. Padole
    Associate Professor, Department of Computer Science and Engineering, The M. S. University, Vadodara, India
    Associate Professor, Department of Computer Science and Engineering, The M. S. University, Vadodara, India
view PDF
view PDF

How to Cite

V., Bakaraniya Parul, and Mamta C. Padole. 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.
ACM ACS APA ABNT Chicago Harvard IEEE MLA Turabian Vancouver AMA

Download Citation

Endnote/Zotero/Mendeley (RIS) BibTeX

Keywords

Transfer Learning
Parkinson Disease Progression
SWEDD
Random Forest
Ensemble Model

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.

References

  1. Tolosa, Eduardo, Gregor Wenning, and Werner Poewe. "The Diagnosis of Parkinson's Disease." The Lancet Neurology 5, no. 1 (2006): 75-86.
  2. Jankovic, Joseph. "Parkinson’s Disease: Clinical Features and Diagnosis." Journal of neurology, neurosurgery & psychiatry 79, no. 4 (2008): 368-376.
  3. Schrag, A1, C. D. Good, K. Miszkiel, H. R. Morris, C. J. Mathias, A. J. Lees, and N. P. Quinn. "Differentiation of Atypical Parkinsonian Syndromes with Routine MRI." Neurology 54, no. 3 (2000): 697-697.
  4. Hayes, Michael T. "Parkinson's Disease and Parkinsonism." The American journal of medicine 132, no. 7 (2019): 802-807.
  5. Das, Samarjit, Laura Trutoiu, Akihiko Murai, Dunbar Alcindor, Michael Oh, Fernando De la Torre, and Jessica Hodgins. "Quantitative Measurement of Motor Symptoms in Parkinson's Disease: A Study with Full-Body Motion Capture Data." In 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, IEEE, 2011, 6789-6792.
  6. Thobois, Stéphane, Stéphane Prange, Christian Scheiber, and Emmanuel Broussolle. "What a Neurologist Should Know About PET and SPECT Functional Imaging for Parkinsonism: A Practical Perspective." Parkinsonism & related disorders 59 (2019): 93-100.
  7. Marek, Kenneth, John Seibyl, Shirley Eberly, David Oakes, Ira Shoulson, Anthony E. Lang, Chris Hyson, Danna Jennings, and Parkinson Study Group PRECEPT Investigators. "Longitudinal Follow-Up of SWEDD Subjects in the PRECEPT Study." Neurology 82, no. 20 (2014): 1791-1797.
  8. De Rosa, Anna, Claudia Carducci, Carla Carducci, Silvio Peluso, Maria Lieto, Andrea Mazzella, Francesco Saccà et al. "Screening for Dopa-Responsive Dystonia in Patients with Scans Without Evidence of Dopaminergic Deficiency (SWEDD)." Journal of neurology 261, no. 11 (2014): 2204-2208.
  9. Taylor, Jonathan Christopher, and John Wesley Fenner. "Comparison of Machine Learning and Semi-Quantification Algorithms For (I123) FP-CIT Classification: The Beginning of the End for Semi-Quantification?." EJNMMI physics 4, no. 1 (2017): 29.
  10. Jalalian, Afsaneh, Syamsiah BT Mashohor, Hajjah Rozi Mahmud, M. Iqbal B. Saripan, Abdul Rahman B. Ramli, and Babak Karasfi. "Computer-Aided Detection/Diagnosis of Breast Cancer in Mammography and Ultrasound: A Review." Clinical imaging 37, no. 3 (2013): 420-426.
  11. Roth, Holger R., Le Lu, Jiamin Liu, Jianhua Yao, Ari Seff, Kevin Cherry, Lauren Kim, and Ronald M. Summers. "Improving Computer-Aided Detection Using Convolutional Neural Networks and Random View Aggregation." IEEE transactions on medical imaging 35, no. 5 (2015): 1170-1181.
  12. Ayech, Marouane Ben Haj, and Hamid Amiri. "Texture Description Using Statistical Feature Extraction." In 2016 2nd International Conference on Advanced Technologies for Signal and Image Processing (ATSIP), IEEE, 2016, 223-227.
  13. Firmino, Macedo, Giovani Angelo, Higor Morais, Marcel R. Dantas, and Ricardo Valentim. "Computer-Aided Detection (CADe) and Diagnosis (CADx) System for Lung Cancer with Likelihood of Malignancy." Biomedical engineering online 15, no. 1 (2016): 2.
  14. Aboudi, Noura, Ramzi Guetari, and Nawres Khlifa. "Multi‐Objectives Optimisation of Features Selection for the Classification of Thyroid Nodules in Ultrasound Images." IET Image Processing 14, no. 9 (2020): 1901-1908.
  15. Mastouri, Rekka, Nawres Khlifa, Henda Neji, and Saoussen Hantous-Zannad. "A Bilinear Convolutional Neural Network for Lung Nodules Classification on CT Images." International Journal of Computer Assisted Radiology and Surgery 16, no. 1 (2021): 91-101.
  16. Prashanth, Rꎬ, Sumantra Dutta Roy, Pravat K. Mandal, and Shantanu Ghosh. "Automatic Classification and Prediction Models for Early Parkinson’s Disease Diagnosis from SPECT Imaging." Expert Systems with Applications 41, no. 7 (2014): 3333-3342.
  17. Mabrouk, Rostom, Belkacem Chikhaoui, and Layachi Bentabet. "Machine Learning Based Classification Using Clinical and Datscan SPECT Imaging Features: A Study on Parkinson’s Disease and SWEDD." IEEE Transactions on Radiation and Plasma Medical Sciences 3, no. 2 (2018): 170-177.
  18. Segovia, F., J. M. Górriz, J. Ramírez, J. Levin, M. Schuberth, M. Brendel, A. Rominger, G. Garraux, and C. Phillips. "Analysis of 18F-DMFP PET Data Using Multikernel Classification in Order to Assist the Diagnosis of Parkinsonism." In 2015 IEEE Nuclear Science Symposium and Medical Imaging Conference (NSS/MIC), IEEE, 2015, 1-4.
  19. Segovia, Fermín, Juan Manuel Górriz, J. Ramırez, and Diego Salas-Gonzalez. "Multiclass Classification of 18 F-DMFP-PET Data to Assist the Diagnosis of Parkinsonism." In 2016 International Workshop on Pattern Recognition in Neuroimaging (PRNI), IEEE, 2016, 1-4.
  20. Khachnaoui, Hajer, Nawres Khlifa, and Rostom Mabrouk. "Machine Learning for Early Parkinson’s Disease Identification Within SWEDD Group Using Clinical and Datscan SPECT Imaging Features." Journal of Imaging 8, no. 4 (2022): 97.
  21. Parkinson's Progression Markers Initiative. (n.d.). PPMI – Parkinson's Progression Markers Initiative. Laboratory of Neuro Imaging, USC. https://ida.loni.usc.edu/home/projectPage.jsp?project=PPMI
  22. Kurmi, Ankit, Shreya Biswas, Shibaprasad Sen, Aleksandr Sinitca, Dmitrii Kaplun, and Ram Sarkar. "An Ensemble of CNN Models for Parkinson’s Disease Detection Using DaTscan Images." Diagnostics 12, no. 5 (2022): 1173.
  23. Prashant, R. "Accurate Early Detection of Parkinson’s Disease from Single Photon Emission Computed Tomography Imaging Through Convolutional Neural Networks." Artificial Intelligence in Health 2, no. 4 (2025): 22.
  24. Majhi, Babita, Aarti Kashyap, Siddhartha Suprasad Mohanty, Sujata Dash, Saurav Mallik, Aimin Li, and Zhongming Zhao. "An Improved Method for Diagnosis of Parkinson’s Disease Using Deep Learning Models Enhanced with Metaheuristic Algorithm." BMC medical imaging 24, no. 1 (2024): 156.
  25. Dentamaro, Vincenzo, Donato Impedovo, Luca Musti, Giuseppe Pirlo, and Paolo Taurisano. "Enhancing Early Parkinson’s Disease Detection Through Multimodal Deep Learning and Explainable AI: Insights from the PPMI Database." Scientific reports 14, no. 1 (2024): 20941.
  26. Chang, Yan, Jiajin Liu, Shuwei Sun, Tong Chen, and Ruimin Wang. "Deep Learning for Parkinson’s Disease Classification Using Multimodal and Multi-Sequences PET/MR Images." EJNMMI research 15, no. 1 (2025): 55.
  27. Cao, Jiangbo, and Xiaojing Long. "Racf: A Multimodal Deep Learning Framework for Parkinson’s Disease Diagnosis Using Snp and MRI Data." Applied Sciences 15, no. 8 (2025): 4513.
  28. Majhi, Babita, Aarti Kashyap, Siddhartha Suprasad Mohanty, Sujata Dash, Saurav Mallik, Aimin Li, and Zhongming Zhao. "An Improved Method for Diagnosis of Parkinson’s Disease Using Deep Learning Models Enhanced with Metaheuristic Algorithm." BMC medical imaging 24, no. 1 (2024): 156.
  29. Sar, Ayan, Pranav Singh Puri, Huma Naz, Sumit Aich, Tanupriya Choudhury, and Lubna Abdelkhreim Gabralla. "Multi-Modal Deep Learning Framework for Early Detection of Parkinson’s Disease Using Neurological and Physiological Data for High-Fidelity Diagnosis." Scientific Reports 15, no. 1 (2025): 34835.
  30. Chowdhury, Nishu, Utpol Kanti Das, and Amit Chowdhury. "Multimodal Approach for Early Diagnosis of Parkinson’s Disease Using PET Imaging, Tremor Detection, and Machine Learning." Psychiatry Research: Neuroimaging (2025): 112063.
  31. Suo, Xueling, Mengyao Chen, Li Chen, Chunyan Luo, Graham J. Kemp, Su Lui, and Huaiqiang Sun. "Automatic Identification of Parkinsonism Using Clinical Multi-Contrast Brain MRI: A Large Self-Supervised Vision Foundation Model Strategy." EBioMedicine 116 (2025).
  32. Welton, Thomas, Septian Hartono, Weiling Lee, Peik Yen Teh, Wenlu Hou, Robert Chun Chen, Celeste Chen et al. "Classification of Parkinson’s Disease by Deep Learning on Midbrain MRI." Frontiers in Aging Neuroscience 16 (2024): 1425095.
  33. Khalil, Rana M., Lisa M. Shulman, Ann L. Gruber-Baldini, Stephen G. Reich, Joseph M. Savitt, Jeffrey M. Hausdorff, Rainer von Coelln, and Michael P. Cummings. "Applying Wearable Sensors and Machine Learning to the Diagnostic Challenge of Distinguishing Parkinson’s Disease from Other Forms of Parkinsonism." Biomedicines 13, no. 3 (2025): 572.
  34. Shokrpour, Sahar, AmirMehdi MoghadamFarid, Sepideh Bazzaz Abkenar, Mostafa Haghi Kashani, Mohammad Akbari, and Mostafa Sarvizadeh. "Machine Learning for Parkinson’s Disease: A Comprehensive Review of Datasets, Algorithms, And Challenges." npj Parkinson's Disease 11, no. 1 (2025): 187.
  35. Ling, Ronghua, Xingxing Cen, Shaoyou Wu, Min Wang, Ying Zhang, Juanjuan Jiang, Jiaying Lu et al. "Explainable Graph Neural Network Based on Metabolic Brain Imaging for Differential Diagnosis of Parkinsonism." Frontiers in Aging Neuroscience 17 (2025): 1580910.
  36. Bakaraniya Parul V., Dr. Mamta C. Padole. (2025). Multimodal Deep Learning Framework Integrating Clinical and DaTSCAN SPECT Features for Early Parkinson’s Disease Detection in SWEDD Cohort. Journal of Applied Bioanalysis, 11(S2), 269-284. https://doi.org/10.53555/jab.v11si2.539