Wearable Sensors for Parkinson’s Disease Detection

Abstract

Parkinson’s Disease (PD) is a progressive neurological disorder characterized by motor impairments such as tremors, rigidity, and bradykinesia, making early detection crucial for effective management. This paper presents a framework utilizing wearable sensors for Parkinson’s Disease detection through continuous monitoring of physiological and movement-based signals. The proposed system employs sensors such as accelerometers, gyroscopes, and inertial measurement units to capture gait patterns, tremor frequency, and motion irregularities. Machine learning algorithms are applied to analyze the collected data and identify early signs of the disease. Feature extraction and selection techniques are incorporated to improve model accuracy and computational efficiency. The framework is further enhanced using hybrid and ensemble learning approaches to ensure robustness and generalization across diverse patient data. Experimental results demonstrate that the proposed system achieves reliable performance in detecting Parkinson’s symptoms and supports real-time monitoring. Integration with prior research in disease prediction strengthens the effectiveness of the model. The study highlights the potential of wearable technology in enabling non-invasive, continuous, and cost-effective Parkinson’s Disease detection, particularly in remote and resource-constrained healthcare environments.