oru.sePublications
Change search
Link to record
Permanent link

Direct link
BETA
Memedi, Mevludin, PhDORCID iD iconorcid.org/0000-0002-2372-4226
Publications (10 of 39) Show all publications
Javed, F., Thomas, I. & Memedi, M. (2018). A comparison of feature selection methods when using motion sensors data: a case study in Parkinson’s disease. In: : . Paper presented at 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC'18), Honolulu, Hawaii, USA, July 17-21, 2018. IEEE
Open this publication in new window or tab >>A comparison of feature selection methods when using motion sensors data: a case study in Parkinson’s disease
2018 (English)Conference paper, Published paper (Refereed)
Abstract [en]

The objective of this study is to investigate the effects of feature selection methods on the performance of machine learning methods for quantifying motor symptoms of Parkinson’s disease (PD) patients. Different feature selection methods including step-wise regression, Lasso regression and Principal Component Analysis (PCA) were applied on 88 spatiotemporal features that were extracted from motion sensors during hand rotation tests. The selected features were then used in support vector machines (SVM), decision trees (DT), linear regression, and random forests models to calculate a so-called treatment-response index (TRIS). The validity, testretest reliability and sensitivity to treatment were assessed for each combination (feature selection method plus machine learning method). There were improvements in correlation coefficients and root mean squared error (RMSE) for all the machine learning methods, except DTs, when using the selected features from step-wise regression inputs. Using step-wise regression and SVM was found to have better sensitivity to treatment and higher correlation to clinical ratings on the Unified PD Rating Scale as compared to the combination of PCA and SVM. When assessing the ability of the machine learning methods to discriminate between tests performed by PD patients and healthy controls the results were mixed. These results suggest that the choice of feature selection methods is crucial when working with data-driven modelling. Based on our findings the step-wise regression can be considered as the method with the best performance.

Place, publisher, year, edition, pages
IEEE, 2018
Keywords
Feature extraction, Support vector machines, Principal component analysis, Correlation, Machine learning, Predictive models, Sensors
National Category
Computer and Information Sciences
Research subject
Informatics; Statistics
Identifiers
urn:nbn:se:oru:diva-69954 (URN)10.1109/EMBC.2018.8513683 (DOI)
Conference
40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC'18), Honolulu, Hawaii, USA, July 17-21, 2018
Funder
Knowledge Foundation
Available from: 2018-10-30 Created: 2018-10-30 Last updated: 2018-10-31Bibliographically approved
Thomas, I., Westin, J., Alam, M., Bergquist, F., Nyholm, D., Senek, M. & Memedi, M. (2018). A treatment–response index from wearable sensors for quantifying Parkinson's disease motor states. IEEE journal of biomedical and health informatics, 22(5), 1341-1349, Article ID 8119948.
Open this publication in new window or tab >>A treatment–response index from wearable sensors for quantifying Parkinson's disease motor states
Show others...
2018 (English)In: IEEE journal of biomedical and health informatics, ISSN 2168-2194, E-ISSN 2168-2208, Vol. 22, no 5, p. 1341-1349, article id 8119948Article in journal (Refereed) Published
Abstract [en]

The goal of this study was to develop an algorithm that automatically quantifies motor states (off,on,dyskinesia) in Parkinson's disease (PD), based on accelerometry during a hand pronation-supination test. Clinician's ratings using the Treatment Response Scale (TRS), ranging from -3 (very Off) to 0 (On) to +3 (very dyskinetic), was used as target. For that purpose, 19 participants with advanced PD and 22 healthy persons were recruited in a single center open label clinical trial in Uppsala, Sweden. The trial consisted of single levodopa dose experiments for the people with PD (PwP), where participants were asked to perform standardized wrist rotation tests, using each hand, before and at pre-specified time points after the dose. The participants used wrist sensors containing a 3D accelerometer and gyroscope. Features to quantify the level, variation and asymmetry of the sensor signals, three-level Discrete Wavelet Transform features and approximate entropy measures were extracted from the sensors data. At the time of the tests, the PwP were video recorded. Three movement disorder specialists rated the participants’ state on the TRS scale. A Treatment Response Index from Sensors (TRIS) was constructed to quantify the motor states based on the wrist rotation tests. Different machine learning algorithms were evaluated to map the features derived from the sensor data to the ratings provided by the three specialists. Results from cross validation, both in 10-fold and a leave-one-individual out setting, showed good predictive power of a support vector machine model and high correlation to the TRS scale. Values at the end tails of the TRS scale were under and over predicted due to the lack of observations at those values but the model managed to accurately capture the dose - effect profiles of the patients. In addition, the TRIS had good test-retest reliability on the baseline levels of the PD participants (Intraclass correlation coefficient of 0.83) and reasonable sensitivity to levodopa treatment (0.33 for the TRIS). For a series of test occasions the proposed algorithms provided dose - effect time profiles for participants with PD, which could be useful during therapy individualization of people suffering from advanced PD.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers (IEEE), 2018
Keywords
Machine learning, Levodopa response, Signal processing, Parkinson’s disease, Accelerometry, Wearable sensors, Pattern recognition
National Category
Other Medical Engineering Computer Sciences
Research subject
Informatics
Identifiers
urn:nbn:se:oru:diva-62864 (URN)10.1109/JBHI.2017.2777926 (DOI)000441795800002 ()29989996 (PubMedID)2-s2.0-85035809095 (Scopus ID)
Funder
Knowledge FoundationVINNOVA
Note

Funding Agencies:

Acreo (Sweden)  

Cenvigo (Sweden)  

Sensidose (Sweden)  

Uppsala University (Sweden)  

Dalarna University (Sweden) 

Available from: 2017-11-28 Created: 2017-11-28 Last updated: 2018-08-31Bibliographically approved
Kolkowska, E., Scandurra, I., Avatare Nöu, A., Sjölinder, M. & Memedi, M. (2018). A user-centered ethical assessment of welfare technology for elderly. In: Jia Zhou, Gavriel Salvendy (Ed.), Human Aspects of IT for the Aged Population. Applications in Health, Assistance, and Entertainment: . Paper presented at 4th International Conference on Human Aspects of IT for the Aged Population (ITAP 2018), Held as Part of HCI International 2018, Las Vegas, United States, July 15-20, 2018 (pp. 59-73). Springer
Open this publication in new window or tab >>A user-centered ethical assessment of welfare technology for elderly
Show others...
2018 (English)In: Human Aspects of IT for the Aged Population. Applications in Health, Assistance, and Entertainment / [ed] Jia Zhou, Gavriel Salvendy, Springer, 2018, p. 59-73Conference paper, Published paper (Refereed)
Abstract [en]

Welfare technology (WT) is often developed with a technical perspective, and little consideration is taken regarding the involvement of important ethical considerations and different values that come up during the development and implementation of WT. Safety, security and privacy are significant, as well as the usability and overall benefit of the tool, but to date assessments often lack a holistic picture of the WT as seen by the users. This paper suggests a user-centered ethical assessment (UCEA) framework for WT to be able to evaluate ethical consequences as a part of the user-centered aspects. Building on established methodologies from research on ethical considerations, as well as the research domain of human-computer interaction, this assessment framework joins knowledge of ethical consequences with aspects affecting the “digitalization with the individual in the center”, e.g. privacy, safety, well-being, dignity, empowerment and usability. The framework was applied during development of an interface for providing symptom information to Parkinson patients. The results showed that the UCEA framework directs the attention to values emphasized by the patients. Thus, functionality of the system was evaluated in the light of values and expected results of the patients, thereby facilitating follow-up of a user-centered assessment. The framework may be further developed and tested, but in this study it served as a working tool for assessing ethical consequences of WT as a part of user-centered aspects.

Place, publisher, year, edition, pages
Springer, 2018
Series
Lecture Notes in Computer Science, ISSN 0302-9743, E-ISSN 1611-3349 ; 10927
Keywords
Ethical evaluation, Elderly, Welfare technology, Assistive technology, Ambient-assisted living, Health-enabling technology, Framework, User-centered, Assessment
National Category
Human Computer Interaction
Research subject
Informatics
Identifiers
urn:nbn:se:oru:diva-68527 (URN)10.1007/978-3-319-92037-5_6 (DOI)2-s2.0-85050586674 (Scopus ID)978-3-319-92036-8 (ISBN)978-3-319-92037-5 (ISBN)
Conference
4th International Conference on Human Aspects of IT for the Aged Population (ITAP 2018), Held as Part of HCI International 2018, Las Vegas, United States, July 15-20, 2018
Projects
EMPARK
Funder
Knowledge Foundation
Available from: 2018-08-20 Created: 2018-08-20 Last updated: 2018-08-22Bibliographically approved
Memedi, M., Tshering, G., Fogelberg, M., Jusufi, I., Kolkowska, E. & Klein, G. O. (2018). An interface for IoT: feeding back health-related data to Parkinson's disease patients. Journal of Sensor and Actuator Networks, 7(1), Article ID 14.
Open this publication in new window or tab >>An interface for IoT: feeding back health-related data to Parkinson's disease patients
Show others...
2018 (English)In: Journal of Sensor and Actuator Networks, ISSN 1007-7294, E-ISSN 1089-747X, Vol. 7, no 1, article id 14Article in journal (Refereed) Published
Abstract [en]

This paper presents a user-centered design (UCD) process of an interface for Parkinson’s disease (PD) patients for helping them to better manage their symptoms. The interface is designed to visualize symptom and medication information, collected by an Internet of Things (IoT)-based system, which will consist of a smartphone, electronic dosing device, wrist sensor and a bed sensor. In our work, the focus is on measuring data related to some of the main health-related quality of life aspects such as motor function, sleep, medication compliance, meal intake timing in relation to medication intake, and physical exercise. A mock-up demonstrator for the interface was developed using UCD methodology in collaboration with PD patients. The research work was performed as an iterative design and evaluation process based on interviews and observations with 11 PD patients. Additional usability evaluations were conducted with three information visualization experts. Contributions include a list of requirements for the interface, results evaluating the performance of the patients when using the demonstrator during task-based evaluation sessions as well as opinions of the experts. The list of requirements included ability of the patients to track an ideal day, so they could repeat certain activities in the future as well as determine how the scores are related to each other. The patients found the visualizations as clear and easy to understand and could successfully perform the tasks. The evaluation with experts showed that the visualizations are in line with the current standards and guidelines for the intended group of users. In conclusion, the results from this work indicate that the proposed system can be considered as a tool for assisting patients in better management of the disease by giving them insights on their own aggregated symptom and medication information. However, the actual effects of providing such feedback to patients on their health-related quality of life should be investigated in a clinical trial.

Place, publisher, year, edition, pages
Multidisciplinary Digital Publishing Institute (MDPI), 2018
Keywords
Information visualization; user-centered design; internet of things; sensor technology; Parkinson’s disease; patient empowerment; quality of life
National Category
Human Computer Interaction
Research subject
Informatics
Identifiers
urn:nbn:se:oru:diva-65675 (URN)10.3390/jsan7010014 (DOI)000428559500013 ()2-s2.0-85044327671 (Scopus ID)
Projects
EMPARK
Funder
Knowledge Foundation, 20160176
Note

Funding Agencies:

Sensidose AB  

Cenvigo AB  

Nethouse Sverige AB  

Swedish Institute 

Available from: 2018-03-12 Created: 2018-03-12 Last updated: 2018-06-20Bibliographically approved
Karni, L., Memedi, M., Kolkowska, E. & Klein, G. O. (2018). EMPARK: Internet of Things for Empowerment and Improved Treatment of Patients with Parkinson's Disease. In: : . Paper presented at International Congress of Parkinson´s Disease and Movement Disorders, Hong Kong, People's Republic of China, 5-9 October, 2018. John Wiley & Sons
Open this publication in new window or tab >>EMPARK: Internet of Things for Empowerment and Improved Treatment of Patients with Parkinson's Disease
2018 (English)Conference paper, Poster (with or without abstract) (Other (popular science, discussion, etc.))
Abstract [en]

Objective: This study aims to assess the effects of patient-directed feedback from remote symptom, medication, and disease activity monitoring on patient empowerment and treatment in Parkinson’s disease (PD).

Background: There is a need to empower patients with PD to be able to understand better and control their disease using prescribed medication and following recommendations on lifestyle. The research project EMPARK will develop an Internet of Things system of sensors, mobile devices to deliver real-time, 24/7 patient symptom information with the primary goal to support PD patients empowerment and better understanding of their disease. The system will be deployed in patient homes to continuously measure movements, time-in-bed and drug delivery from a micro-dose levodopa system. Subjective symptom scoring, time of meals and physical activities will be reported by the patients via a smartphone application. Interfaces for patients and clinicians are being developed based on the user center design methodology to ensure maximal user acceptance. 

Methods: This is a randomized controlled trial where 30 PD patients from 2 university clinics in Sweden will be randomized to receive (intervention group) or not (control group) continuous feedback from the results of the EMPARK home monitoring for 2 weeks. Disease-specific (UPDRS, PDQ-39), Quality of Life (QoL) (modified EuroQoL EQ-5D) and empowerment questionnaires will be collected prior and after the intervention. The correlation of technology-based objective and patient-reported subjective parameters will be assessed in both groups. Interviews will be conducted with the clinicians and observations will be made about the patient-clinician interaction to assess the potential treatment benefits of the intervention.

Results: Preliminary results from workshops with patients and clinicians show potential to improve patient empowerment and disease control among patients. Completion of the trial will show the degree of patient empowerment, individualized treatment, and patientclinician interactions.

Conclusions: Raising patients’ awareness about disease activity and home medication is possible among PD patients by providing them with feedback from the results of a home monitoring system. This randomized, controlled trial aims to provide evidence that this approach leads to improved patient empowerment and treatment results.

Place, publisher, year, edition, pages
John Wiley & Sons, 2018
National Category
Computer and Information Sciences
Research subject
Informatics
Identifiers
urn:nbn:se:oru:diva-69955 (URN)
Conference
International Congress of Parkinson´s Disease and Movement Disorders, Hong Kong, People's Republic of China, 5-9 October, 2018
Funder
Knowledge Foundation
Available from: 2018-10-30 Created: 2018-10-30 Last updated: 2018-11-14Bibliographically approved
Aghanavesi, S., Filip, B., Nyholm, D., Senek, M. & Memedi, M. (2018). Feasibility of a multi-sensor data fusion method for assessment of Parkinson’s disease motor symptoms. In: : . Paper presented at International Congress of Parkinson’s Disease and Movement Disorders (MDS), Hong Kong, Dept. of Neuroscience, Neurology, Uppsala University, Uppsala, Sweden, 5-9 October, 2018.
Open this publication in new window or tab >>Feasibility of a multi-sensor data fusion method for assessment of Parkinson’s disease motor symptoms
Show others...
2018 (English)Conference paper, Poster (with or without abstract) (Other academic)
Abstract [en]

Title: Feasibility of a multi-sensor data fusion method for assessment of Parkinson’s disease motor symptoms

Objective: To assess the feasibility of measuring Parkinson’s disease (PD) motor symptoms with a multi-sensor data fusion method. More specifically, the aim is to assess validity, reliability and sensitivity to treatment of the methods.

Background: Data from 19 advanced PD patients (Gender: 14 males and 5 females, mean age: 71.4, mean years with PD: 9.7, mean years with levodopa: 9.5) were collected in a single center, open label, single dose clinical trial in Sweden [1].

Methods: The patients performed leg agility and 2-5 meter straight walking tests while wearing motion sensors on their limbs. They performed the tests at baseline, at the time they received the morning dose, and at pre-specified time points until the medication wore off. While performing the tests the patients were video recorded. The videos were observed by three movement disorder specialists who rated the symptoms using a treatment response scale (TRS), ranging from -3 (very off) to 3 (very dyskinetic). The sensor data consisted of lower limb data during leg agility, upper limb data during walking, and lower limb data during walking. Time series analysis was performed on the raw sensor data extracted from 17 patients to derive a set of quantitative measures, which were then used during machine learning to be mapped to mean ratings of the three raters on the TRS scale. Combinations of data were tested during the machine learning procedure.

Results: Using data from both tests, the Support Vector Machines (SVM) could predict the motor states of the patients on the TRS scale with a good agreement in relation to the mean ratings of the three raters (correlation coefficient = 0.92, root mean square error = 0.42, p<0.001). Additionally, there was good test-retest reliability of the SVM scores during baseline and second tests with intraclass-correlation coefficient of 0.84. Sensitivity to treatment for SVM was good (Figure 1), indicating its ability to detect changes in motor symptoms. The upper limb data during walking was more informative than lower limb data during walking since SVMs had higher correlation coefficient to mean ratings.  

Conclusions: The methodology demonstrates good validity, reliability, and sensitivity to treatment. This indicates that it could be useful for individualized optimization of treatments among PD patients, leading to an improvement in health-related quality of life.

National Category
Computer and Information Sciences Physiology
Research subject
Informatics
Identifiers
urn:nbn:se:oru:diva-69855 (URN)
Conference
International Congress of Parkinson’s Disease and Movement Disorders (MDS), Hong Kong, Dept. of Neuroscience, Neurology, Uppsala University, Uppsala, Sweden, 5-9 October, 2018
Available from: 2018-10-25 Created: 2018-10-25 Last updated: 2018-10-29Bibliographically approved
Aghanavesi, S., Bergquist, F., Nyholm, D., Senek, M. & Memedi, M. (2018). Objective assessment of Parkinson’s disease motor symptoms during leg agility test using motion sensors. In: : . Paper presented at International Congress of Parkinson’s Disease and Movement Disorders (MDS), Hong Kong, People's Republic of China, 5-9 October, 2018.
Open this publication in new window or tab >>Objective assessment of Parkinson’s disease motor symptoms during leg agility test using motion sensors
Show others...
2018 (English)Conference paper, Poster (with or without abstract) (Refereed)
Abstract [en]

Title: Objective assessment of Parkinson’s disease motor symptoms during leg agility test using motion sensors

Objective: To develop and evaluate machine learning methods for assessment of Parkinson’s disease (PD) motor symptoms using leg agility (LA) data collected with motion sensors during a single dose experiment.

Background: Nineteen advanced PD patients (Gender: 14 males and 5 females, mean age: 71.4, mean years with PD: 9.7, mean years with levodopa: 9.5) were recruited in a single center, open label, single dose clinical trial in Sweden [1].

Methods: The patients performed up to 15 LA tasks while wearing motions sensors on their foot ankle. They performed tests at pre-defined time points starting from baseline, at the time they received a morning dose (150% of their levodopa equivalent morning dose), and at follow-up time points until the medication wore off. The patients were video recorded while performing the motor tasks. and three movement disorder experts rated the observed motor symptoms using 4 items from the Unified PD Rating Scale (UPDRS) motor section including UPDRS #26 (leg agility), UPDRS #27 (Arising from chair), UPDRS #29 (Gait), UPDRS #31 (Body Bradykinesia and Hypokinesia), and dyskinesia scale. In addition, they rated the overall mobility of the patients using Treatment Response Scale (TRS), ranging from -3 (very off) to 3 (very dyskinetic). Sensors data were processed and their quantitative measures were used to develop machine learning methods, which mapped them to the mean ratings of the three raters. The quality of measurements of the machine learning methods was assessed by convergence validity, test-retest reliability and sensitivity to treatment.

Results: Results from the 10-fold cross validation showed good convergent validity of the machine learning methods (Support Vector Machines, SVM) with correlation coefficients of 0.81 for TRS, 0.78 for UPDRS #26, 0.69 for UPDRS #27, 0.78 for UPDRS #29, 0.83 for UPDRS #31, and 0.67 for dyskinesia scale (P<0.001). There were good correlations between scores produced by the methods during the first (baseline) and second tests with coefficients ranging from 0.58 to 0.96, indicating good test-retest reliability. The machine learning methods had lower sensitivity than mean clinical ratings (Figure. 1).

Conclusions: The presented methodology was able to assess motor symptoms in PD well, comparable to movement disorder experts. The leg agility test did not reflect treatment related changes.

National Category
Computer and Information Sciences Physiology
Research subject
Informatics
Identifiers
urn:nbn:se:oru:diva-69856 (URN)
Conference
International Congress of Parkinson’s Disease and Movement Disorders (MDS), Hong Kong, People's Republic of China, 5-9 October, 2018
Available from: 2018-10-25 Created: 2018-10-25 Last updated: 2018-10-29Bibliographically approved
Jusufi, I., Memedi, M. & Nyholm, D. (2018). TapVis: A Data Visualization Approach for Assessment of Alternating Tapping Performance in Patients with Parkinson’s Disease. In: EuroVis 2018 - Short Papers: . Paper presented at 20th EG/VGTC Conference on Visualization (EuroVis '18), Brno, Czech Republic, June 4-8, 2018 (pp. 55-59). The Eurographics Association
Open this publication in new window or tab >>TapVis: A Data Visualization Approach for Assessment of Alternating Tapping Performance in Patients with Parkinson’s Disease
2018 (English)In: EuroVis 2018 - Short Papers, The Eurographics Association , 2018, p. 55-59Conference paper, Oral presentation with published abstract (Refereed)
Abstract [en]

Advancements in telemedicine have been helpful for frequent monitoring of patients with Parkinson’s disease (PD) from remote locations and assessment of their individual symptoms and treatment-related complications. These data can be useful for helping clinicians to interpret symptom states and individually tailor the treatments by visualizing the physiological information collected by sensor-based systems. In this paper we present a visualization metaphor that represents symptom information of PD patients during tapping tests performed with a smartphone. The metaphor has been developed and evaluated with a clinician. It enabled the clinician to observe fine motor impairments and identify motor fluctuations regarding several movement aspects of patients that perform the tests from their homes.

Place, publisher, year, edition, pages
The Eurographics Association, 2018
National Category
Media and Communication Technology
Research subject
Informatics
Identifiers
urn:nbn:se:oru:diva-68437 (URN)10.2312/eurovisshort.20181078 (DOI)978-3-03868-060-4 (ISBN)
Conference
20th EG/VGTC Conference on Visualization (EuroVis '18), Brno, Czech Republic, June 4-8, 2018
Projects
EMPARK
Funder
Knowledge Foundation
Available from: 2018-08-13 Created: 2018-08-13 Last updated: 2018-08-13Bibliographically approved
Thomas, I., Memedi, M., Westin, J. & Nyholm, D. (2018). The effect of continuous levodopa treatment during the afternoon hours. Acta Neurologica Scandinavica
Open this publication in new window or tab >>The effect of continuous levodopa treatment during the afternoon hours
2018 (English)In: Acta Neurologica Scandinavica, ISSN 0001-6314, E-ISSN 1600-0404Article in journal (Refereed) Epub ahead of print
Abstract [en]

Objective: The aim of this retrospective study was to investigate if patients with PD, who are treated with levodopa‐carbidopa intestinal gel (LCIG), clinically worsen during the afternoon hours and if so, to evaluate whether this occurs in all LCIG‐treated patients or in a sub‐group of patients.

Methods: Three published studies were identified and included in the analysis. All studies provided individual response data assessed on the treatment response scale (TRS) and patients were treated with continuous LCIG. Ninety‐eight patients from the three studies fulfilled the criteria. T‐tests were performed to find differences on the TRS values between the morning and the afternoon hours, linear mixed effect models were fitted on the afternoon hours’ evaluations to find trends of wearing‐off, and patients were classified into three TRS categories (meaningful increase in TRS, meaningful decrease in TRS, non ‐meaningful increase or decrease).

Results: In all three studies significant statistical differences were found between the morning TRS values and the afternoon TRS values (p‐value <= 0.001 in all studies). The linear mixed effect models had significant negative coefficients for time in two studies, and 48 out of 98 patients (49%) showed a meaningful decrease of TRS during the afternoon hours.

Conclusion: The results from all studies were consistent, both in the proportion of patients in the three groups and the value of TRS decrease in the afternoon hours. Based on these findings there seems to be a group of patients with predictable “off” behavior in the later parts of the day.

Place, publisher, year, edition, pages
Munksgaard Forlag, 2018
National Category
Neurology Computer and Information Sciences
Research subject
Informatics
Identifiers
urn:nbn:se:oru:diva-68788 (URN)10.1111/ane.13020 (DOI)30180267 (PubMedID)
Available from: 2018-09-07 Created: 2018-09-07 Last updated: 2018-09-13Bibliographically approved
Aghanavesi, S., Nyholm, D., Senek, M., Bergquist, F. & Memedi, M. (2017). A smartphone-based system to quantify dexterity in Parkinson's disease patients. Informatics in Medicine Unlocked
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 2352-9148Article 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
Computer and Information Sciences
Research subject
Informatics
Identifiers
urn:nbn:se:oru:diva-57657 (URN)10.1016/j.imu.2017.05.005 (DOI)
Available from: 2017-05-15 Created: 2017-05-15 Last updated: 2018-07-31Bibliographically approved
Organisations
Identifiers
ORCID iD: ORCID iD iconorcid.org/0000-0002-2372-4226

Search in DiVA

Show all publications