The primary objective of this study was to develop a smartphone-based system for the quantitative assessment of motor symptoms in Parkinson’s disease (PD), with a focus on tremor and freezing of gait (FOG). The system employed inertial sensors embedded in iOS devices to capture motion data at 50 Hz and integrated signal processing with machine learning techniques for symptom quantification. For FOG assessment, a Random Forest classifier achieved 90% accuracy using time- and frequency-domain features. Tremor analysis relied on spectral methods to identify characteristic oscillations within the 4 – 6 ~ Hz range typically associated with PD. Technical validation with five healthy control subjects demonstrated consistent system performance, supporting its applicability in clinical settings. All controls exhibited a Freezing Index (FI < 2.5) and a Tremor Index (T I < 25%). These findings highlight the potential of the proposed system as a portable solution for the objective monitoring of Parkinson’s disease symptoms, complementing clinical evaluations and supporting personalized therapeutic approaches.
Autor(es):Armoa, Guillermo J.
Abarca, Victoria E.
Elias, Dante A.
Año: 2026
Título de la revista: IEEE Xplore
Ciudad: Lima, Perú
Url: https://doi.org/10.1109/ICIIBMS66230.2025.11316764