{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"submitter":["Rehman RZU"],"funding":["Innovative Medicines Initiative","Parkinsonis UK","Newcastle upon Tyne Hospitals NHS Foundation Trust","H2020 Marie Skłodowska-Curie Actions","Parkinson's UK"],"pagination":["65-73"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC8979631"],"repository":["biostudies-literature"],"omics_type":["Unknown"],"volume":["1"],"pubmed_abstract":["<i>Objective:</i> Gait may be a useful biomarker that can be objectively measured with wearable technology to classify Parkinson's disease (PD). This study aims to: (i) comprehensively quantify a battery of commonly utilized gait digital characteristics (spatiotemporal and signal-based), and (ii) identify the best discriminative characteristics for the optimal classification of PD. <i>Methods:</i> Six partial least square discriminant analysis (PLS-DA) models were trained on subsets of 210 characteristics measured in 142 subjects (81 people with PD, 61 controls (CL)). <i>Results:</i> Models accuracy ranged between 70.42-88.73% (AUC: 78.4-94.5%) with a sensitivity of 72.84-90.12% and a specificity of 60.3-86.89%. Signal-based digital gait characteristics independently gave 87.32% accuracy. "],"journal":["IEEE open journal of engineering in medicine and biology"],"pubmed_title":["Accelerometry-Based Digital Gait Characteristics for Classification of Parkinson's Disease: What Counts?"],"pmcid":["PMC8979631"],"funding_grant_id":["G-1301","09/H0906/82","820820","J-0802","721577"],"pubmed_authors":["Kirk C","Rochester L","Dunne-Willows M","Mazza C","Buckley C","Del Din S","Rehman RZU","Alcock L","Mico-Amigo ME","Shi JQ"],"additional_accession":[]},"is_claimable":false,"name":"Accelerometry-Based Digital Gait Characteristics for Classification of Parkinson's Disease: What Counts?","description":"<i>Objective:</i> Gait may be a useful biomarker that can be objectively measured with wearable technology to classify Parkinson's disease (PD). This study aims to: (i) comprehensively quantify a battery of commonly utilized gait digital characteristics (spatiotemporal and signal-based), and (ii) identify the best discriminative characteristics for the optimal classification of PD. <i>Methods:</i> Six partial least square discriminant analysis (PLS-DA) models were trained on subsets of 210 characteristics measured in 142 subjects (81 people with PD, 61 controls (CL)). <i>Results:</i> Models accuracy ranged between 70.42-88.73% (AUC: 78.4-94.5%) with a sensitivity of 72.84-90.12% and a specificity of 60.3-86.89%. Signal-based digital gait characteristics independently gave 87.32% accuracy. ","dates":{"release":"2020-01-01T00:00:00Z","publication":"2020","modification":"2025-04-04T12:57:51.898Z","creation":"2025-04-04T12:57:51.898Z"},"accession":"S-EPMC8979631","cross_references":{"pubmed":["35402938"],"doi":["10.1109/OJEMB.2020.2966295"]}}