Application of artificial intelligence for kinematic signal processing in diagnostics of Parkinson's disease and atypical parkinsonisms: doctoral dissertation
Year: 2023
Type: dissertation
Study design: Observational Study
Abstract: Clinical diagnosis of Parkinson’s disease (PD) and atypical parkinsonisms remains a\nchallenging and time-consuming task. This study sought to utilize AI to provide quick support in\ndifferential diagnostics, relying on kinematic data obtained from two modalities: repetitive finger tapping\nand gait.\nThe main study focus was on finger tapping data obtained by a custom low-weight, low-cost inertial\nsensor setup. Three groups of patients were recruited, including individuals suffering from PD,\nProgressive Supranuclear Palsy (PSP), and Multiple System Atrophy (MSA), and a group of healthy\ncontrols (HC) without neurological disorders. Statistical analysis of obtained signals showed differences\nin certain trends between the tested groups, and the utilization of AI models allowed the PD group to be\ndiscerned from the controls with accuracy of 92%, whereas all participant groups discerned in a\nmulticlass setting with overall accuracy of 85.18%.\nThis work also tackled PD diagnostics through the use of AI in analysis of gait, using a sensorized\nelectronic walkway. De novo PD patients and a HC group were tested in a series of dual-task tests, where\nthe interference task was of motor or mental type. We were able to programmatically select a subset of\ngait parameters that best help in PD diagnostics and use the selected parameters to classify PD vs HC\ngroup with accuracy of 85%.\nFuture work should tackle the effect of possible noise in the labels (non-autopsy-confirmed diagnoses),\nand standardized multi-center data collection that would allow further refinement of the system’s\npredictive power. Recruitment of patients with atypical parkinsonisms for gait-based tests should assess\nthe ability of the proposed analyses to aid in differential diagnostics among these neurological disorders\nwith similar clinical presentations
Author: Belić, Minja
Language: English
Field: Health Professions
Domain: Health Sciences
Open Access status: green
Funder: NIH Clinical Center
OpenAlex ID: W7045440602