Integrative approach for early detection of Parkinson’s disease and atypical Parkinsonian syndromes leveraging hemodynamic parameters, motion data & advanced AI models

• Published in: Computer methods and programs in biomedicine Vol. 271; p. 108989
• Main Authors: Singh, Rishit, Malhotra, Yugnanda, Parikh, Jolly
• Format: Journal Article
• Language: English
• Published: Ireland Elsevier B.V 01.11.2025
• Subjects: Algorithms; Artificial Intelligence; Deep Learning; Detection; Diagnosis, Computer-Assisted; Disease; Early Diagnosis; Heart Rate; Hemodynamics; Humans; MLP; Motion; Parkinson; Parkinson Disease - diagnosis; Parkinson Disease - physiopathology; Parkinsonian Disorders - diagnosis; Parkinsonian Disorders - physiopathology; Photoplethysmography; Wearable Electronic Devices; MLP; Disease; PD; AI; Detection; Parkinson; ML
• ISSN: 0169-2607; 1872-7565; 1872-7565
• DOI: 10.1016/j.cmpb.2025.108989

•Parkinson’s disease (PD) is a progressive neurological disorder affecting motor and non-motor functions. Early detection of PD is essential for improving patient outcomes and quality of life.•This study proposes a multimodal hardware based wearable integrated with a novel machine learning framework for early, accurate and remote diagnosis of Parkinson’s disease.•Analyzes diverse data sets, including hemodynamic parameters, gait patterns, and hand tremor metrics including bradykinesia and rigidity.•Achieves high accuracy through advanced algorithms, integrating artificial intelligence and intuitive user interface, thus providing a robust diagnostic tool. Parkinson's disease (PD) and other atypical Parkinsonian syndromes, including Multiple Systems Atrophies (MSAs) and Progressive Supranuclear Palsies (PSPs) are progressive neurodegenerative disorders that are often present with motor and non-motor symptoms. Early stage diagnosis is crucial to initiate timely intervention and manage disease progression while mitigating patient health. This study proposes a wearable, multi-modal sensor driven framework integrated with AI models for accurate classification of PD. A multi sensor hardware platform is developed incorporating photoplethysmography (PPG), Heart Rate Variability (HRV) using MAX30102 for peripheral oxygen saturation and perfusion along with, temperature sensor (DS18B20) and inertial sensor (MPU6050), to detect tremor amplitudes, rigidity and bradykinesia. Data is collected from real time recording and publicly available datasets. Using a set of preprocessing filters, relevant temporal and statistical features are extracted to train a Multi-Layer Perceptron (MLP) & ensemble model enabling AI and deep learning classifiers. The model is trained using deep learning techniques and evaluated using stratified k-fold class validation. Model performance is assessed using accuracy, precision, sensitivity and specificity metrics. The proposed model demonstrated high diagnostic performance. The ensemble classifier achieved over 96% accuracy in identifying early stage PD symptoms, while the ensemble classifier presented with an accuracy of over 96.7%. The models consistently reported over 95% accuracy with minimal variance across folds, confirming robustness across datasets and sensor modalities. The novel integration of multi modal physiological and hemodynamic parameters amalgamating AI algorithms offer a scalable, remote and non-invasive approach to early detection of Parkinson’s disease and other atypical Parkinsonian syndromes. The proposed framework demonstrated key potential for clinical transition with implication for improving timeline of patient diagnoses, reduction in healthcare burden and costs along with enhancing patient quality of life and outcome.