AI-Driven Remote Parkinson's Diagnosis with BPNN Framework and Cloud-Based Data Security

• Published in: 2024 International Conference on Knowledge Engineering and Communication Systems (ICKECS) Vol. 1; pp. 1 - 6
• Main Authors: Raman, Ramakrishnan, Kumar, Vikram, Pillai, Biju G., Rabadiya, Dhaval, Patre, Smruti, Meenakshi, R.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 18.04.2024
• Subjects: Access control; Accuracy; Artificial Intelligence; Back Propagation Neural Network; Backpropagation; Cloud-Based Security; Computer architecture; Data privacy; Data security; Neural networks; Parkinson's Diagnosis
• DOI: 10.1109/ICKECS61492.2024.10616436

In the realm of medical diagnostics, the integration of Artificial Intelligence (AI) has shown promising advancements, especially in the diagnosis and management of chronic diseases such as Parkinson's Disease (PD). This paper presents a novel AI-Driven approach for Remote Parkinson's Diagnosis utilizing a Back Propagation Neural Network (BPNN) framework, coupled with a secure cloud-based data handling mechanism. The primary focus is to harness the computational prowess of BPNNs to analyze and interpret the subtle and complex patterns associated with Parkinson's symptoms, thus facilitating an accurate and early diagnosis. To address the critical concern of data privacy and security, which is paramount in the healthcare domain, we implement a robust cloud-based architecture ensuring the confidentiality, integrity, and availability of patient data. This architecture employs state-of-the-art encryption techniques alongside access control mechanisms to safeguard sensitive information against unauthorized access and potential cyber threats. The proposed system is evaluated through extensive experiments involving real-world datasets, demonstrating its effectiveness in diagnosing Parkinson's with high accuracy and efficiency. Furthermore, the implementation of this system on a cloud platform ensures scalability, making it accessible to a wider range of healthcare providers and patients. Through this study, we aim to contribute to the improvement of remote healthcare services for Parkinson's patients, offering a secure, accurate, and user-friendly diagnostic tool.