Program
Speech in Health II (HEALTH II)
Thu-3-1-10 Assessment of Parkinson’s Disease Medication State through Automatic Speech Analysis
Anna Pompili(INESC-ID), Rubén Solera-Ureña(INESC-ID), Alberto Abad(INESC-ID, Instituto Superior Técnico, Universidade de Lisboa), Rita Cardoso(Laboratory of Clinical Pharmacology and therapeutics, Faculdade de Medicina, Universidade de Lisboa, Instituto de Medicina Molecular, CNS - Campus Neurológico Sénior), Isabel Guimarães(Laboratory of Clinical Pharmacology and therapeutics, Faculdade de Medicina, Universidade de Lisboa, Instituto de Medicina Molecular, Alcoitão Schoool of Health Sciences, Santa Casa da Misericórida de Lisboa), Margherita Fabbri(Clinical Investigation Center CIC1436, Departments of Clinical Pharmacology and Neurosciences, NS-Park/FCRIN network and NeuroToul Center of Excellence for Neurodegeneration, INSERM, University Hospital of Toulouse and University of Toulouse), Isabel Pavão Martins(Laboratório de Estudos de Linguagem, Faculty of Medicine, University of Lisbon, Instituto de Medicina Molecular) and Joaquim Ferreira(Laboratory of Clinical Pharmacology and therapeutics, Faculdade de Medicina, Universidade de Lisboa, Instituto de Medicina Molecular, CNS - Campus Neurológico Sénior)
Abstract:
Parkinson's disease (PD) is a progressive degenerative disorder of the central nervous system characterized by motor and non-motor symptoms. As the disease progresses, patients alternate periods in which motor symptoms are mitigated due to medication intake (ON state) and periods with motor complications (OFF state). The time that patients spend in the OFF condition is currently the main parameter employed to assess pharmacological interventions and to evaluate the efficacy of different active principles. In this work, we present a system that combines automatic speech processing and deep learning techniques to classify the medication state of PD patients by leveraging personal speech-based bio-markers. We devise a speaker-dependent approach and investigate the relevance of different acoustic-prosodic feature sets. Results show an accuracy of 90.54% in a test task with mixed speech and an accuracy of 95.27% in a semi-spontaneous speech task. Overall, the experimental assessment shows the potentials of this approach towards the development of reliable, remote daily monitoring and scheduling of medication intake of PD patients.
Calls
Program