biostudies-literatureRehman RZUInnovative Medicines InitiativeParkinsonis UKNewcastle upon Tyne Hospitals NHS Foundation TrustH2020 Marie Skłodowska-Curie ActionsParkinson's UK65-73https://www.ebi.ac.uk/biostudies/studies/S-EPMC8979631biostudies-literatureUnknown1<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. IEEE open journal of engineering in medicine and biologyAccelerometry-Based Digital Gait Characteristics for Classification of Parkinson's Disease: What Counts?PMC8979631G-130109/H0906/82820820J-0802721577Kirk CRochester LDunne-Willows MMazza CBuckley CDel Din SRehman RZUAlcock LMico-Amigo MEShi JQfalseAccelerometry-Based Digital Gait Characteristics for Classification of Parkinson's Disease: What Counts?<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. 2020-01-01T00:00:00Z20202025-04-04T12:57:51.898Z2025-04-04T12:57:51.898ZS-EPMC89796313540293810.1109/OJEMB.2020.2966295