Maarten De Vos1, John Prince1, Tim Buchanan2, James J FitzGerald3, Chrystalina A Antoniades4. 1. Department of Engineering Science, Institute of Biomedical Engineering, University of Oxford, Old Road Campus Research Building, OX3 7DQ, Oxford, UK. 2. UCB Biopharma SPRL, Brussels, Belgium. 3. Nuffield Department of Surgical Sciences, University of Oxford, Oxford, OX3 9DU, UK; Nuffield Department of Clinical Neurosciences, NeuroMetrology Lab, University of Oxford, Oxford, OX3 9DU, UK. 4. Nuffield Department of Clinical Neurosciences, NeuroMetrology Lab, University of Oxford, Oxford, OX3 9DU, UK. Electronic address: chrystalina.antoniades@ndcn.ox.ac.uk.
Abstract
BACKGROUND: Progressive supranuclear palsy (PSP), a neurodegenerative conditions may be difficult to discriminate clinically from idiopathic Parkinson's disease (PD). It is critical that we are able to do this accurately and as early as possible in order that future disease modifying therapies for PSP may be deployed at a stage when they are likely to have maximal benefit. Analysis of gait and related tasks is one possible means of discrimination. RESEARCH QUESTION: Here we investigate a wearable sensor array coupled with machine learning approaches as a means of disease classification. METHODS: 21 participants with PSP, 20 with PD, and 39 healthy control (HC) subjects performed a two minute walk, static sway test, and timed up-and-go task, while wearing an array of six inertial measurement units. The data were analysed to determine what features discriminated PSP from PD and PSP from HC. Two machine learning algorithms were applied, Logistic Regression (LR) and Random Forest (RF). RESULTS: 17 features were identified in the combined dataset that contained independent information. The RF classifier outperformed the LR classifier, and allowed discrimination of PSP from PD with 86 % sensitivity and 90 % specificity, and PSP from HC with 90 % sensitivity and 97 % specificity. Using data from the single lumbar sensor only resulted in only a modest reduction in classification accuracy, which could be restored using 3 sensors (lumbar, right arm and foot). However for maximum specificity the full six sensor array was needed. SIGNIFICANCE: A wearable sensor array coupled with machine learning methods can accurately discriminate PSP from PD. Choice of array complexity depends on context; for diagnostic purposes a high specificity is needed suggesting the more complete array is advantageous, while for subsequent disease tracking a simpler system may suffice. Crown
BACKGROUND:Progressive supranuclear palsy (PSP), a neurodegenerative conditions may be difficult to discriminate clinically from idiopathic Parkinson's disease (PD). It is critical that we are able to do this accurately and as early as possible in order that future disease modifying therapies for PSP may be deployed at a stage when they are likely to have maximal benefit. Analysis of gait and related tasks is one possible means of discrimination. RESEARCH QUESTION: Here we investigate a wearable sensor array coupled with machine learning approaches as a means of disease classification. METHODS: 21 participants with PSP, 20 with PD, and 39 healthy control (HC) subjects performed a two minute walk, static sway test, and timed up-and-go task, while wearing an array of six inertial measurement units. The data were analysed to determine what features discriminated PSP from PD and PSP from HC. Two machine learning algorithms were applied, Logistic Regression (LR) and Random Forest (RF). RESULTS: 17 features were identified in the combined dataset that contained independent information. The RF classifier outperformed the LR classifier, and allowed discrimination of PSP from PD with 86 % sensitivity and 90 % specificity, and PSP from HC with 90 % sensitivity and 97 % specificity. Using data from the single lumbar sensor only resulted in only a modest reduction in classification accuracy, which could be restored using 3 sensors (lumbar, right arm and foot). However for maximum specificity the full six sensor array was needed. SIGNIFICANCE: A wearable sensor array coupled with machine learning methods can accurately discriminate PSP from PD. Choice of array complexity depends on context; for diagnostic purposes a high specificity is needed suggesting the more complete array is advantageous, while for subsequent disease tracking a simpler system may suffice. Crown
Authors: Miracle Ozzoude; Brenda Varriano; Derek Beaton; Joel Ramirez; Melissa F Holmes; Christopher J M Scott; Fuqiang Gao; Kelly M Sunderland; Paula McLaughlin; Jennifer Rabin; Maged Goubran; Donna Kwan; Angela Roberts; Robert Bartha; Sean Symons; Brian Tan; Richard H Swartz; Agessandro Abrahao; Gustavo Saposnik; Mario Masellis; Anthony E Lang; Connie Marras; Lorne Zinman; Christen Shoesmith; Michael Borrie; Corinne E Fischer; Andrew Frank; Morris Freedman; Manuel Montero-Odasso; Sanjeev Kumar; Stephen Pasternak; Stephen C Strother; Bruce G Pollock; Tarek K Rajji; Dallas Seitz; David F Tang-Wai; John Turnbull; Dar Dowlatshahi; Ayman Hassan; Leanne Casaubon; Jennifer Mandzia; Demetrios Sahlas; David P Breen; David Grimes; Mandar Jog; Thomas D L Steeves; Stephen R Arnott; Sandra E Black; Elizabeth Finger; Maria Carmela Tartaglia Journal: Geroscience Date: 2022-03-16 Impact factor: 7.581
Authors: Jamie L Adams; Karlo J Lizarraga; Emma M Waddell; Taylor L Myers; Stella Jensen-Roberts; Joseph S Modica; Ruth B Schneider Journal: Curr Neurol Neurosci Rep Date: 2021-03-03 Impact factor: 6.030
Authors: Marta F Pereira; Tim Buchanan; Günter U Höglinger; Marko Bogdanovic; George Tofaris; Simon Prangnell; Nagaraja Sarangmat; James J FitzGerald; Chrystalina A Antoniades Journal: BMJ Neurol Open Date: 2022-01-21