du.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • chicago-author-date
  • chicago-note-bibliography
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Multisensor data-driven methods for automated quantification of motor symptoms in Parkinson’s disease
Dalarna University, School of Technology and Business Studies, Microdata Analysis.ORCID iD: 0000-0002-1548-5077
2019 (English)Doctoral thesis, comprehensive summary (Other academic)
Description
Abstract [en]

The overall aim of this thesis was to develop and evaluate new data-driven methods for supporting treatment and providing information for better management of Parkinson’s disease (PD).

This disease is complex and progressive. There is a large amount of inter- and intra-variability in motor symptoms of patients with PD (PwPD). Current evaluation of motor symptoms which is done at clinics by using clinical rating scales provides limited and only part of the health status of PwPD. PD requires an accurate assessment that is approved by clinics. Therefore frequent evaluation of symptoms at micro-level is required.

Sensor systems including smartphone and motion sensors were employed to collect data from PwPD and the recruited healthy controls. Repeated measures consisting of subjective assessment of symptoms and objective assessment of motor functions were collected.

First, the smartphone-based data-driven methods were developed to quantify the dexterity presented in fine motor tests of spiral drawing and alternate tapping. The upper extremities temporal irregularity measure presented in spiral drawing tests of PwPD was further analyzed by the approximate entropy (ApEn) method. Second, tri-axial motion sensor data were collected from various tests like leg agility, walking, and rapid alternating movements of hands of PwPD during a full cycled levodopa challenge. Data driven methods for quantification of leg agility tests and a combination of multiple motor tests were developed. The clinimetric properties of the methods such as reliability, validity, and responsiveness were evaluated. In addition, the feasibility of using smartphone inertial measurement unit (IMU) sensors in comparison to motion sensors for quantifying the motor states in PD during rapid alternating movements of hands tests was investigated.

Results of the developed methods for quantification of PD motor symptoms via dexterity tests in a smartphone can be used for measuring treatment related changes in PwPD. Investigation of the ApEn method showed good sensitivity and test-retest reliability indicating that this method is useful in measuring upper limb temporal irregularity at micro-level. High convergence validity resulted from using motion sensors during leg agility tests which led to valid and reliable objective measures of PD motor symptoms. The results of fusion of sensor data gathered during standardized motor tests were promising and led to highly valid, reliable and sensitive objective measures of PD motor symptoms. The results of the analyzing acceleration IMU data showed that smartphone IMU is capable of capturing symptom information from hand rotation tests. It can provide sufficient data for quantification of the motor states.

The findings from the data-driven methodology in this thesis can be used in development of systems for follow up of the effects of treatment and individualizing treatments in PD.

Place, publisher, year, edition, pages
Borlänge: Dalarna University, 2019.
Series
Dalarna Doctoral Dissertations ; 10
Keywords [en]
Parkinson’s disease, motor symptoms, motion sensors, smartphone, microdata, multivariate analysis, data-driven, support vector machine, stepwise regression, predictive models
National Category
Medical Laboratory and Measurements Technologies Biomedical Laboratory Science/Technology Computer Sciences
Research subject
Complex Systems – Microdata Analysis
Identifiers
URN: urn:nbn:se:du-29583ISBN: 978-91-88679-00-0 (print)OAI: oai:DiVA.org:du-29583DiVA, id: diva2:1292235
Public defence
2019-04-26, Clas Ohlson, Borlänge, 13:00 (English)
Opponent
Supervisors
Available from: 2019-03-28 Created: 2019-02-27 Last updated: 2019-03-28Bibliographically approved
List of papers
1. A smartphone-based system to quantify dexterity in Parkinson's disease patients
Open this publication in new window or tab >>A smartphone-based system to quantify dexterity in Parkinson's disease patients
Show others...
2017 (English)In: Informatics in Medicine Unlocked, ISSN 2352-9148, Vol. 9, p. 11-17Article in journal (Refereed) Published
Abstract [en]

Objectives: The aim of this paper is to investigate whether a smartphone-based system can be used to quantify dexterity in Parkinson’s disease (PD). More specifically, the aim was to develop data-driven methods to quantify and characterize dexterity in PD. Methods: Nineteen advanced PD patients and 22 healthy controls participated in a clinical trial in Uppsala, Sweden. The subjects were asked to perform tapping and spiral drawing tests using a smartphone. Patients performed the tests before, and at pre-specified time points after they received 150% of their usual levodopa morning dose. Patients were video recorded and their motor symptoms were assessed by three movement disorder specialists using three Unified PD Rating Scale (UPDRS) motor items from part III, the dyskinesia scoring and the treatment response scale (TRS). The raw tapping and spiral data were processed and analyzed with time series analysis techniques to extract 37 spatiotemporal features. For each of the five scales, separate machine learning models were built and tested by using principal components of the features as predictors and mean ratings of the three specialists as target variables. Results: There were weak to moderate correlations between smartphone-based scores and mean ratings of UPDRS item #23 (0.52; finger tapping), UPDRS #25 (0.47; rapid alternating movements of hands), UPDRS #31 (0.57; body bradykinesia and hypokinesia), sum of the three UPDRS items (0.46), dyskinesia (0.64), and TRS (0.59). When assessing the test-retest reliability of the scores it was found that, in general, the clinical scores had better test-retest reliability than the smartphone-based scores. Only the smartphone-based predicted scores on the TRS and dyskinesia scales had good repeatability with intra-class correlation coefficients of 0.51 and 0.84, respectively. Clinician-based scores had higher effect sizes than smartphone-based scores indicating a better responsiveness in detecting changes in relation to treatment interventions. However, the first principal component of the 37 features was able to capture changes throughout the levodopa cycle and had trends similar to the clinical TRS and dyskinesia scales. Smartphone-based scores differed significantly between patients and healthy controls. Conclusions: Quantifying PD motor symptoms via instrumented, dexterity tests employed in a smartphone is feasible and data from such tests can also be used for measuring treatment-related changes in patients.

Keywords
Parkinson's disease; motor assessment; spiral tests; tapping tests; smartphone; dyskinesia; bradykinesia; objective measures; telemedicine
National Category
Electrical Engineering, Electronic Engineering, Information Engineering
Research subject
Complex Systems – Microdata Analysis
Identifiers
urn:nbn:se:du-25034 (URN)10.1016/j.imu.2017.05.005 (DOI)
Funder
Knowledge Foundation
Available from: 2017-05-19 Created: 2017-05-19 Last updated: 2019-02-27Bibliographically approved
2. A method for measuring Parkinson's disease related temporal irregularity in spiral drawings
Open this publication in new window or tab >>A method for measuring Parkinson's disease related temporal irregularity in spiral drawings
2016 (English)In: 2016 IEEE International Conference on Biomedical and Health Informatics, 2016, p. 410-413Conference paper, Published paper (Refereed)
Abstract [en]

The objective of this paper was to develop and evaluate clinimetric properties of a method for measuring Parkinson's disease (PD)-related temporal irregularities using digital spiral analysis. In total, 108 (98 patients in different stages of PD and 10 healthy elderly subjects) performed repeated spiral drawing tasks in their home environments using a touch screen device. A score was developed for representing the amount of temporal irregularity during spiral drawing tasks, using Approximate Entropy (ApEn) technique. In addition, two previously published spiral scoring methods were adapted and their scores were analyzed. The mean temporal irregularity score differed significantly between healthy elderly subjects and advanced PD patients (P<0.005). The ApEn-based method had a better responsiveness and test-retest reliability when compared to the other two methods. In contrast to the other methods, the mean scores of the ApEn-based method improved significantly during a 3 year clinical study, indicating a possible impact of pathological basal ganglia oscillations in temporal control during spiral drawing tasks. In conclusion, the ApEn-based method could be used for differentiating between patients in different stages of PD and healthy subjects. The responsiveness and test-retest reliability were good for the ApEn-based method indicating that this method is useful for measuring upper limb temporal irregularity at a micro-level.

National Category
Computer Systems Signal Processing
Research subject
Complex Systems – Microdata Analysis, FLOAT - Flexible Levodopa Optimizing Assistive Technology
Identifiers
urn:nbn:se:du-21183 (URN)10.1109/BHI.2016.7455921 (DOI)000381398000102 ()978-1-5090-2455-1 (ISBN)
Conference
Biomedical and Health Informatics 2016, Las Vegas, 24-27 February
Available from: 2016-03-01 Created: 2016-03-01 Last updated: 2019-02-27Bibliographically approved
3. Verification of a method for measuring Parkinson’s disease related temporal irregularity in spiral drawings
Open this publication in new window or tab >>Verification of a method for measuring Parkinson’s disease related temporal irregularity in spiral drawings
Show others...
2017 (English)In: Sensors, ISSN 1424-8220, E-ISSN 1424-8220, Vol. 17, no 10, article id 2341Article in journal (Refereed) Published
Abstract [en]

Parkinson's disease (PD) is a progressive movement disorder caused by the death of dopamine-producing cells in the midbrain. There is a need for frequent symptom assessment, since the treatment needs to be individualized as the disease progresses. The aim of this paper was to verify and further investigate the clinimetric properties of an entropy-based method for measuring PD-related upper limb temporal irregularities during spiral drawing tasks. More specifically, properties of a temporal irregularity score (TIS) for patients at different stages of PD, and medication time points were investigated. Nineteen PD patients and 22 healthy controls performed repeated spiral drawing tasks on a smartphone. Patients performed the tests before a single levodopa dose and at specific time intervals after the dose was given. Three movement disorder specialists rated videos of the patients based on the unified PD rating scale (UPDRS) and the Dyskinesia scale. Differences in mean TIS between the groups of patients and healthy subjects were assessed. Test-retest reliability of the TIS was measured. The ability of TIS to detect changes from baseline (before medication) to later time points was investigated. Correlations between TIS and clinical rating scores were assessed. The mean TIS was significantly different between healthy subjects and patients in advanced groups (p-value = 0.02). Test-retest reliability of TIS was good with Intra-class Correlation Coefficient of 0.81. When assessing changes in relation to treatment, TIS contained some information to capture changes from Off to On and wearing off effects. However, the correlations between TIS and clinical scores (UPDRS and Dyskinesia) were weak. TIS was able to differentiate spiral drawings drawn by patients in an advanced stage from those drawn by healthy subjects, and TIS had good test-retest reliability. TIS was somewhat responsive to single-dose levodopa treatment. Since TIS is an upper limb high-frequency-based measure, it cannot be detected during clinical assessment.

Keywords
Parkinson's disease; smartphone; spiral tests; temporal irregularity; timing variability; motor assessment; approximate entropy; complexity
National Category
Other Medical Engineering Probability Theory and Statistics
Research subject
Complex Systems – Microdata Analysis
Identifiers
urn:nbn:se:du-29318 (URN)10.3390/s17102341 (DOI)29027941 (PubMedID)2-s2.0-85032855199 (Scopus ID)
Available from: 2019-01-21 Created: 2019-01-21 Last updated: 2019-02-27Bibliographically approved
4. Motion sensor-based assessment of Parkinson’s disease motor symptoms during leg agility tests: results from levodopa challenge
Open this publication in new window or tab >>Motion sensor-based assessment of Parkinson’s disease motor symptoms during leg agility tests: results from levodopa challenge
Show others...
2019 (English)In: IEEE journal of biomedical and health informatics, ISSN 2168-2194, E-ISSN 2168-2208Article in journal (Refereed) Epub ahead of print
Abstract [en]

Parkinson’s disease (PD) is a degenerative, progressive disorder of the central nervous system that mainly affects motor control. The aim of this study was to develop data-driven methods and test their clinimetric properties to detect and quantify PD motor states using motion sensor data from leg agility tests. Nineteen PD patients were recruited in a levodopa single dose challenge study. PD patients performed leg agility tasks while wearing motion sensors on their lower extremities. Clinical evaluation of video recordings was performed by three movement disorder specialists who used four items from the motor section of the Unified PD Rating Scale (UPDRS), the treatment response scale (TRS) and a dyskinesia score. Using the sensor data, spatiotemporal features were calculated and relevant features were selected by feature selection. Machine learning methods like support vector machines (SVM), decision trees and linear regression, using 10-fold cross validation were trained to predict motor states of the patients. SVM showed the best convergence validity with correlation coefficients of 0.81 to TRS, 0.83 to UPDRS #31 (body bradykinesia and hypokinesia), 0.78 to SUMUPDRS (the sum of the UPDRS items: #26-leg agility, #27-arising from chair and #29-gait), and 0.67 to dyskinesia. Additionally, the SVM-based scores had similar test-retest reliability in relation to clinical ratings. The SVM-based scores were less responsive to treatment effects than the clinical scores, particularly with regards to dyskinesia. In conclusion, the results from this study indicate that using motion sensors during leg agility tests may lead to valid and reliable objective measures of PD motor symptoms.

Place, publisher, year, edition, pages
IEEE, 2019
National Category
Physiotherapy Other Medical Engineering
Research subject
Complex Systems – Microdata Analysis
Identifiers
urn:nbn:se:du-29542 (URN)10.1109/JBHI.2019.2898332 (DOI)
Available from: 2019-02-21 Created: 2019-02-21 Last updated: 2019-02-27Bibliographically approved
5. Treatment response index from a multi-modal sensor fusion platform for assessment of motor states in Parkinson's disease
Open this publication in new window or tab >>Treatment response index from a multi-modal sensor fusion platform for assessment of motor states in Parkinson's disease
Show others...
2019 (English)Manuscript (preprint) (Other academic)
Abstract [en]

The aim of this paper is to develop and evaluate a multi-sensor data fusion platform for quantifying Parkinson’s disease (PD) motor states. More specifically, the aim is to evaluate the clinimetric properties (validity, reliability, and responsiveness to treatment) of the method, using data from motion sensors during lower- and upper-limb tests.

Methods: Nineteen PD patients and 22 healthy controls were recruited in a single center study. Subjects performed standardized motor tasks of Unified PD Rating Scale (UPDRS), including leg agility, hand rotation, and walking after wearing motion sensors on ankles and wrists. PD patients received a single levodopa dose before and at follow-up time points after the dose administration. Patients were video recorded and their motor symptoms were rated by three movement disorder experts. Experts rated each and every test occasions based on the six items of UPDRS-III (motor section), the treatment response scale (TRS) and the dyskinesia score. Spatiotemporal features were extracted from the sensor data. Features from lower limbs and upper limbs were fused. Feature selection methods of stepwise regression (SR), Lasso regression and principle component analysis (PCA) were used to select the most important features. Different machine learning methods of linear regression (LR), decision trees, and support vector machines were examined and their clinimetric properties were assessed.

Results: Treatment response index from multimodal motion sensors (TRIMMS) scores obtained from the most valid method of LR when using data from all tests. Features were selected by SR, and this method resulted in r=0.95 to TRS. The test-retest reliability of TRIMMS was good with intra-class correlation coefficient of 0.82. Responsiveness of the TRIMMS to levodopa treatment was similar to the responsiveness of TRS.

Conclusions: The results from this study indicate that fusing motion sensors data gathered during standardized motor tasks leads to valid, reliable and sensitive objective measurements of PD motor symptoms. These measurements could be further utilized in studies for individualized optimization of treatments in PD.

National Category
Medical Engineering
Research subject
Complex Systems – Microdata Analysis
Identifiers
urn:nbn:se:du-29546 (URN)
Available from: 2019-02-21 Created: 2019-02-21 Last updated: 2019-02-27Bibliographically approved
6. Feasibility of using smartphones for quantification of Parkinson’s disease motor states during hand rotation tests
Open this publication in new window or tab >>Feasibility of using smartphones for quantification of Parkinson’s disease motor states during hand rotation tests
2019 (English)Conference paper, Published paper (Refereed)
National Category
Medical Engineering
Research subject
Complex Systems – Microdata Analysis
Identifiers
urn:nbn:se:du-29543 (URN)
Conference
41st International Engineering in Medicine and Biology Conference, Berlin, Germany, July 23–27, 2019
Available from: 2019-02-21 Created: 2019-02-21 Last updated: 2019-02-27Bibliographically approved

Open Access in DiVA

fulltext(813 kB)46 downloads
File information
File name FULLTEXT01.pdfFile size 813 kBChecksum SHA-512
853b5b1f996f44b89a17306219916790aea2ee212df51b13b239f15e5d86bdf7479fdb9159ec9b4e1011113b69d99a2e6a299085c7fb05b08754d7dcffb4e1ed
Type fulltextMimetype application/pdf

Authority records BETA

Aghanavesi, Somayeh

Search in DiVA

By author/editor
Aghanavesi, Somayeh
By organisation
Microdata Analysis
Medical Laboratory and Measurements TechnologiesBiomedical Laboratory Science/TechnologyComputer Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 46 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

isbn
urn-nbn

Altmetric score

isbn
urn-nbn
Total: 1187 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • chicago-author-date
  • chicago-note-bibliography
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf