Dopaminergic-induced dyskinesia assessment based on a single belt-worn accelerometer

Carlos Pérez-López, Albert Samà, Daniel Rodríguez-Martín, Juan Manuel Moreno-Aróstegui, Joan Cabestany, Angels Bayes, Berta Mestre, Sheila Alcaine, Paola Quispe, Gearóid Laighin, Dean Sweeney, Leo R. Quinlan, Timothy J. Counihan, Patrick Browne, Roberta Annicchiarico, Alberto Costa, Hadas Lewy, Alejandro Rodríguez-Molinero

Research output: Contribution to journalArticle

Abstract

Background: After several years of treatment, patients with Parkinson's disease (PD) tend to have, as a side effect of the medication, dyskinesias. Close monitoring may benefit patients by enabling doctors to tailor a personalised medication regimen. Moreover, dyskinesia monitoring can help neurologists make more informed decisions in patient's care. Objective: To design and validate an algorithm able to be embedded into a system that PD patients could wear during their activities of daily living with the purpose of registering the occurrence of dyskinesia in real conditions. Materials and methods: Data from an accelerometer positioned in the waist are collected at the patient's home and are annotated by experienced clinicians. Data collection is divided into two parts: a main database gathered from 92 patients used to partially train and to evaluate the algorithms based on a leave-one-out approach and, on the other hand, a second database from 10 patients which have been used to also train a part of the detection algorithm. Results: Results show that, depending on the severity and location of dyskinesia, specificities and sensitivities higher than 90% are achieved using a leave-one-out methodology. Although mild dyskinesias presented on the limbs are detected with 95% specificity and 39% sensitivity, the most important types of dyskinesia (any strong dyskinesia and trunk mild dyskinesia) are assessed with 95% specificity and 93% sensitivity. Conclusion: The presented algorithmic method and wearable device have been successfully validated in monitoring the occurrence of strong dyskinesias and mild trunk dyskinesias during activities of daily living.

Original languageEnglish
JournalArtificial Intelligence in Medicine
DOIs
Publication statusAccepted/In press - Jul 9 2015

Fingerprint

Dyskinesias
Accelerometers
Monitoring
Patient treatment
Wear of materials
Activities of Daily Living
Sensitivity and Specificity
Parkinson Disease
Databases
Patient Care
Extremities
Equipment and Supplies

Keywords

  • Ambulatory monitoring
  • Dyskinesia
  • Inertial sensors
  • Parkinson's disease
  • Support vector machine

ASJC Scopus subject areas

  • Artificial Intelligence
  • Medicine (miscellaneous)

Cite this

Pérez-López, C., Samà, A., Rodríguez-Martín, D., Moreno-Aróstegui, J. M., Cabestany, J., Bayes, A., ... Rodríguez-Molinero, A. (Accepted/In press). Dopaminergic-induced dyskinesia assessment based on a single belt-worn accelerometer. Artificial Intelligence in Medicine. https://doi.org/10.1016/j.artmed.2016.01.001

Dopaminergic-induced dyskinesia assessment based on a single belt-worn accelerometer. / Pérez-López, Carlos; Samà, Albert; Rodríguez-Martín, Daniel; Moreno-Aróstegui, Juan Manuel; Cabestany, Joan; Bayes, Angels; Mestre, Berta; Alcaine, Sheila; Quispe, Paola; Laighin, Gearóid; Sweeney, Dean; Quinlan, Leo R.; Counihan, Timothy J.; Browne, Patrick; Annicchiarico, Roberta; Costa, Alberto; Lewy, Hadas; Rodríguez-Molinero, Alejandro.

In: Artificial Intelligence in Medicine, 09.07.2015.

Research output: Contribution to journalArticle

Pérez-López, C, Samà, A, Rodríguez-Martín, D, Moreno-Aróstegui, JM, Cabestany, J, Bayes, A, Mestre, B, Alcaine, S, Quispe, P, Laighin, G, Sweeney, D, Quinlan, LR, Counihan, TJ, Browne, P, Annicchiarico, R, Costa, A, Lewy, H & Rodríguez-Molinero, A 2015, 'Dopaminergic-induced dyskinesia assessment based on a single belt-worn accelerometer', Artificial Intelligence in Medicine. https://doi.org/10.1016/j.artmed.2016.01.001
Pérez-López C, Samà A, Rodríguez-Martín D, Moreno-Aróstegui JM, Cabestany J, Bayes A et al. Dopaminergic-induced dyskinesia assessment based on a single belt-worn accelerometer. Artificial Intelligence in Medicine. 2015 Jul 9. https://doi.org/10.1016/j.artmed.2016.01.001
Pérez-López, Carlos ; Samà, Albert ; Rodríguez-Martín, Daniel ; Moreno-Aróstegui, Juan Manuel ; Cabestany, Joan ; Bayes, Angels ; Mestre, Berta ; Alcaine, Sheila ; Quispe, Paola ; Laighin, Gearóid ; Sweeney, Dean ; Quinlan, Leo R. ; Counihan, Timothy J. ; Browne, Patrick ; Annicchiarico, Roberta ; Costa, Alberto ; Lewy, Hadas ; Rodríguez-Molinero, Alejandro. / Dopaminergic-induced dyskinesia assessment based on a single belt-worn accelerometer. In: Artificial Intelligence in Medicine. 2015.
@article{ff1d8c30a0344e23a0f932ad4ae9a7a1,
title = "Dopaminergic-induced dyskinesia assessment based on a single belt-worn accelerometer",
abstract = "Background: After several years of treatment, patients with Parkinson's disease (PD) tend to have, as a side effect of the medication, dyskinesias. Close monitoring may benefit patients by enabling doctors to tailor a personalised medication regimen. Moreover, dyskinesia monitoring can help neurologists make more informed decisions in patient's care. Objective: To design and validate an algorithm able to be embedded into a system that PD patients could wear during their activities of daily living with the purpose of registering the occurrence of dyskinesia in real conditions. Materials and methods: Data from an accelerometer positioned in the waist are collected at the patient's home and are annotated by experienced clinicians. Data collection is divided into two parts: a main database gathered from 92 patients used to partially train and to evaluate the algorithms based on a leave-one-out approach and, on the other hand, a second database from 10 patients which have been used to also train a part of the detection algorithm. Results: Results show that, depending on the severity and location of dyskinesia, specificities and sensitivities higher than 90{\%} are achieved using a leave-one-out methodology. Although mild dyskinesias presented on the limbs are detected with 95{\%} specificity and 39{\%} sensitivity, the most important types of dyskinesia (any strong dyskinesia and trunk mild dyskinesia) are assessed with 95{\%} specificity and 93{\%} sensitivity. Conclusion: The presented algorithmic method and wearable device have been successfully validated in monitoring the occurrence of strong dyskinesias and mild trunk dyskinesias during activities of daily living.",
keywords = "Ambulatory monitoring, Dyskinesia, Inertial sensors, Parkinson's disease, Support vector machine",
author = "Carlos P{\'e}rez-L{\'o}pez and Albert Sam{\`a} and Daniel Rodr{\'i}guez-Mart{\'i}n and Moreno-Ar{\'o}stegui, {Juan Manuel} and Joan Cabestany and Angels Bayes and Berta Mestre and Sheila Alcaine and Paola Quispe and Gear{\'o}id Laighin and Dean Sweeney and Quinlan, {Leo R.} and Counihan, {Timothy J.} and Patrick Browne and Roberta Annicchiarico and Alberto Costa and Hadas Lewy and Alejandro Rodr{\'i}guez-Molinero",
year = "2015",
month = "7",
day = "9",
doi = "10.1016/j.artmed.2016.01.001",
language = "English",
journal = "Artificial Intelligence in Medicine",
issn = "0933-3657",
publisher = "Elsevier",

}

TY - JOUR

T1 - Dopaminergic-induced dyskinesia assessment based on a single belt-worn accelerometer

AU - Pérez-López, Carlos

AU - Samà, Albert

AU - Rodríguez-Martín, Daniel

AU - Moreno-Aróstegui, Juan Manuel

AU - Cabestany, Joan

AU - Bayes, Angels

AU - Mestre, Berta

AU - Alcaine, Sheila

AU - Quispe, Paola

AU - Laighin, Gearóid

AU - Sweeney, Dean

AU - Quinlan, Leo R.

AU - Counihan, Timothy J.

AU - Browne, Patrick

AU - Annicchiarico, Roberta

AU - Costa, Alberto

AU - Lewy, Hadas

AU - Rodríguez-Molinero, Alejandro

PY - 2015/7/9

Y1 - 2015/7/9

N2 - Background: After several years of treatment, patients with Parkinson's disease (PD) tend to have, as a side effect of the medication, dyskinesias. Close monitoring may benefit patients by enabling doctors to tailor a personalised medication regimen. Moreover, dyskinesia monitoring can help neurologists make more informed decisions in patient's care. Objective: To design and validate an algorithm able to be embedded into a system that PD patients could wear during their activities of daily living with the purpose of registering the occurrence of dyskinesia in real conditions. Materials and methods: Data from an accelerometer positioned in the waist are collected at the patient's home and are annotated by experienced clinicians. Data collection is divided into two parts: a main database gathered from 92 patients used to partially train and to evaluate the algorithms based on a leave-one-out approach and, on the other hand, a second database from 10 patients which have been used to also train a part of the detection algorithm. Results: Results show that, depending on the severity and location of dyskinesia, specificities and sensitivities higher than 90% are achieved using a leave-one-out methodology. Although mild dyskinesias presented on the limbs are detected with 95% specificity and 39% sensitivity, the most important types of dyskinesia (any strong dyskinesia and trunk mild dyskinesia) are assessed with 95% specificity and 93% sensitivity. Conclusion: The presented algorithmic method and wearable device have been successfully validated in monitoring the occurrence of strong dyskinesias and mild trunk dyskinesias during activities of daily living.

AB - Background: After several years of treatment, patients with Parkinson's disease (PD) tend to have, as a side effect of the medication, dyskinesias. Close monitoring may benefit patients by enabling doctors to tailor a personalised medication regimen. Moreover, dyskinesia monitoring can help neurologists make more informed decisions in patient's care. Objective: To design and validate an algorithm able to be embedded into a system that PD patients could wear during their activities of daily living with the purpose of registering the occurrence of dyskinesia in real conditions. Materials and methods: Data from an accelerometer positioned in the waist are collected at the patient's home and are annotated by experienced clinicians. Data collection is divided into two parts: a main database gathered from 92 patients used to partially train and to evaluate the algorithms based on a leave-one-out approach and, on the other hand, a second database from 10 patients which have been used to also train a part of the detection algorithm. Results: Results show that, depending on the severity and location of dyskinesia, specificities and sensitivities higher than 90% are achieved using a leave-one-out methodology. Although mild dyskinesias presented on the limbs are detected with 95% specificity and 39% sensitivity, the most important types of dyskinesia (any strong dyskinesia and trunk mild dyskinesia) are assessed with 95% specificity and 93% sensitivity. Conclusion: The presented algorithmic method and wearable device have been successfully validated in monitoring the occurrence of strong dyskinesias and mild trunk dyskinesias during activities of daily living.

KW - Ambulatory monitoring

KW - Dyskinesia

KW - Inertial sensors

KW - Parkinson's disease

KW - Support vector machine

UR - http://www.scopus.com/inward/record.url?scp=84955565597&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84955565597&partnerID=8YFLogxK

U2 - 10.1016/j.artmed.2016.01.001

DO - 10.1016/j.artmed.2016.01.001

M3 - Article

AN - SCOPUS:84955565597

JO - Artificial Intelligence in Medicine

JF - Artificial Intelligence in Medicine

SN - 0933-3657

ER -