A Robust Deep Transfer Learning Model for Early Parkinson’s Disease Diagnosis

Abstract

Parkinson’s disease (PD) is one of the chronic neurological diseases whose progressions slowand symptoms have similarities with other diseases. Early detection and diagnosis of PD iscrucial to prescribe proper treatment for patients productive and healthy lives. The diseasessymptoms are characterized by tremors, muscle rigidity,slownessinmovements, balancingalongwithotherpsychiatricsymptoms. The dynamics of handwritten records served as one of the dominant mechanisms which support PD detection and assessment. Several machine learning methods have been investigated for the early detection of this disease. But most of these handcrafted feature extraction techniques predominantly suffer from low performance accuracy issues. This cannot be tolerable for dealing with detection of such a chronic ailment. To this end, an efficient deep learning model is proposed which can assist to have early detection of Parkinson’s disease. The significant contribution of the proposed model is to select the most optimum features which have the effect of getting the high- performance accuracies. The feature optimization is done through genetic algorithm wherein K-Nearest Neighbor technique. The proposed novel model results into detection accuracy higher than 95%, precision of98%, area under curve of0.90 with a loss of0.12 only. The performance of proposed model is compared with some state-of-the-art machine learning and deep learning-based PD detection approaches to demonstrate the better detection ability of our model.

Introduction

Parkinson’s disease (PD) is a long-term neurological disorder caused by the loss of dopamine-producing neurons in the brain. This leads to motor symptoms such as tremors, rigidity, slow movement (bradykinesia), and posture problems. Early detection is difficult because symptoms appear gradually and may resemble other neurological conditions. One early sign is micrographia, a handwriting abnormality where patients produce small, shaky, and irregular strokes.

This study proposes a hybrid artificial intelligence framework to detect Parkinson’s disease using handwriting images. The approach combines deep transfer learning, genetic algorithm–based feature optimization, and K-Nearest Neighbor (KNN) classification to improve accuracy and efficiency.

Earlier research mainly used machine learning methods like Support Vector Machines, Random Forest, Artificial Neural Networks, and Decision Trees with speech or sensor data. However, these methods rely on manually selected features, which can reduce accuracy. Deep learning models such as CNNs with transfer learning architectures (VGG16, ResNet50, InceptionV3) have shown better performance in medical image analysis.

The proposed methodology includes four main steps:

1. Image Preprocessing – resizing and normalizing handwriting images.

2. Deep Feature Extraction – using pretrained CNN models to extract important features.

3. Feature Optimization – applying a Genetic Algorithm (GA) to select the most relevant features and reduce dimensionality.

4. Classification – using KNN to classify whether a sample indicates Parkinson’s disease.

The system was implemented in Python using libraries such as TensorFlow, Keras, Scikit-learn, and OpenCV, and tested on spiral and wave handwriting datasets. Performance was evaluated using metrics like accuracy, precision, recall, F1-score, and confusion matrix.

Results show that the hybrid model achieves higher accuracy, reduced training time, and better performance on small datasets compared to traditional machine learning methods. It also provides a non-invasive method for early Parkinson’s screening.

Future improvements may include mobile applications, real-time diagnosis using tablets, multimodal data integration (speech, handwriting, sensors), and cloud-based telemedicine systems.

Conclusion

This research presents an automated Parkinson’s disease detection system using deep transfer learning and genetic feature optimization. The hybrid CNN GA KNN model improves early diagnosis accuracy while reducing computational cost. The system can assist clinicians in screening and monitoring patients efficiently and affordably.

References

[1] Bloem et al., Parkinson’s disease, Lancet, 2021 [2] Bakator & Radosav, Deep learning in medical diagnosis, 2018 [3] Kaplan et al., Automated Parkinson detection using MRI, 2022 [4] Chakraborty et al., Spiral drawing classification using CNN, 2020 [5] Das et al., Machine learning comparison for PD detection [2] Benba, A., Jilbab, A. &Hammouch, A. Analysis of multiple types of voice recordings in cepstral domain using MFCC for discriminating between patients with Parkinson’s disease and healthy people. Int J Speech Technol 19, 449–456 (2016). [3] Ö.Esk?dere, A. Karatutlu and C. Ünal, \"Detection of Parkinson\'s disease from vocal features using random subspace classifier ensemble,\" 2015 Twelve International Conference on Electronics Computer and Computation (ICECCO), doi: 10.1109/ICECCO.2015.7416886. [4] Nissar, Iqra & Rizvi, Danish & Masood, Sarfaraz & Mir, Aqib. (2018). Voice-Based Detection of Parkinson’s Disease through Ensemble Machine Learning Approach: A Performance Study. EAI Endorsed Transactions on Pervasive Health and Technology. 5. 162806. 10.4108/eai.13-7-2018.162806. [5] Y. Li, C. Zhang, Y. Jia, P. Wang, X. Zhang and T. Xie, \"Simultaneous learning of speech feature and segment for classification of Parkinson disease,\" 2017 IEEE 19th International Conference on e-Health Networking, Applications and Services (Healthcom), Dalian, 2017, pp. 1-6, doi: 10.1109/HealthCom.2017.8210820. [6] Caliskan, Abdullah & Badem, Hasan &Basturk, Alper & Yüksel, Meltem. (2017). Diagnosis of the Parkinson disease by using deep neural network classifier. Istanbul University - Journal of Electrical and Electronics Engineering. 17. 3311-3318. [7] Das R. (2010) “A comparison of multiple classification methods for diagnosis of Parkinson disease”. Expert Systems with Applications”; 37:1568-1572.

Copyright

Copyright © 2026 P. Venkateswara Reddy, CH. Padma. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.