mdh.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • 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
First-principle data-driven models for assessment of motor disorders in Parkinson’s disease
Mälardalen University, School of Innovation, Design and Engineering, Embedded Systems. Dalarna University.
2014 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

Parkinson’s disease (PD) is an increasing neurological disorder in an aging society. The motor and non-motor symptoms of PD advance with the disease progression and occur in varying frequency and duration. In order to affirm the full extent of a patient’s condition, repeated assessments are necessary to adjust medical prescription. In clinical studies, symptoms are assessed using the unified Parkinson’s disease rating scale (UPDRS). On one hand, the subjective rating using UPDRS relies on clinical expertise. On the other hand, it requires the physical presence of patients in clinics which implies high logistical costs. Another limitation of clinical assessment is that the observation in hospital may not accurately represent a patient’s situation at home. For such reasons, the practical frequency of tracking PD symptoms may under-represent the true time scale of PD fluctuations and may result in an overall inaccurate assessment. Current technologies for at-home PD treatment are based on data-driven approaches for which the interpretation and reproduction of results are problematic. 

The overall objective of this thesis is to develop and evaluate unobtrusive computer methods for enabling remote monitoring of patients with PD. It investigates first-principle data-driven model based novel signal and image processing techniques for extraction of clinically useful information from audio recordings of speech (in texts read aloud) and video recordings of gait and finger-tapping motor examinations. The aim is to map between PD symptoms severities estimated using novel computer methods and the clinical ratings based on UPDRS part-III (motor examination). A web-based test battery system consisting of self-assessment of symptoms and motor function tests was previously constructed for a touch screen mobile device. A comprehensive speech framework has been developed for this device to analyze text-dependent running speech by: (1) extracting novel signal features that are able to represent PD deficits in each individual component of the speech system, (2) mapping between clinical ratings and feature estimates of speech symptom severity, and (3) classifying between UPDRS part-III severity levels using speech features and statistical machine learning tools. A novel speech processing method called cepstral separation difference showed stronger ability to classify between speech symptom severities as compared to existing features of PD speech. In the case of finger tapping, the recorded videos of rapid finger tapping examination were processed using a novel computer-vision (CV) algorithm that extracts symptom information from video-based tapping signals using motion analysis of the index-finger which incorporates a face detection module for signal calibration. This algorithm was able to discriminate between UPDRS part III severity levels of finger tapping with high classification rates. Further analysis was performed on novel CV based gait features constructed using a standard human model to discriminate between a healthy gait and a Parkinsonian gait.

The findings of this study suggest that the symptom severity levels in PD can be discriminated with high accuracies by involving a combination of first-principle (features) and data-driven (classification) approaches. The processing of audio and video recordings on one hand allows remote monitoring of speech, gait and finger-tapping examinations by the clinical staff. On the other hand, the first-principles approach eases the understanding of symptom estimates for clinicians. We have demonstrated that the selected features of speech, gait and finger tapping were able to discriminate between symptom severity levels, as well as, between healthy controls and PD patients with high classification rates. The findings support suitability of these methods to be used as decision support tools in the context of PD assessment.

Place, publisher, year, edition, pages
Sweden: Mälardalen University , 2014. , 102 p.
Series
Mälardalen University Press Dissertations, ISSN 1651-4238 ; 153
National Category
Engineering and Technology
Research subject
Computer Science
Identifiers
URN: urn:nbn:se:mdh:diva-24647ISBN: 978-91-7485-142-7 (print)OAI: oai:DiVA.org:mdh-24647DiVA: diva2:705205
Public defence
2014-04-16, Clas Ohlson, Studenternas Hus Tenoren, Campus Borlänge, 13:00 (English)
Opponent
Supervisors
Funder
Knowledge Foundation
Available from: 2014-03-17 Created: 2014-03-14 Last updated: 2015-07-15Bibliographically approved
List of papers
1. Methods for Detection of Speech Impairment Using Mobile Devices
Open this publication in new window or tab >>Methods for Detection of Speech Impairment Using Mobile Devices
2011 (English)In: Recent Patents on Signal Processing, ISSN 1877-6124, Vol. 11, no 2, 163-171 p.Article in journal (Refereed) Published
Abstract [en]

Speech impairment is an important symptom of Parkinson’s disease (PD). This paper presents a detailed systematic literature review on speech impairment assessment through mobile devices. A two-tier review methodology is utilized. The first tier focuses on real-time problems in speech detection. In the second tier, acoustics features that respond to medication changes in Levodopa responsive PD patients are investigated for recognition of speech symptoms. The investigation of the patents reveals that speech disorder assessment can be made by a comparative analysis between pathological acoustic patterns and the normal acoustic patterns saved in a database. The review depicts that vowel and consonant formants are the most relevant acoustic parameters to reflect PD medication changes. Since consonants have high zero-crossing rate (ZCR) whereas vowels have low ZCR, enhancements in voice segmentation can be done by inducing ZCR. Our synthesis further suggests that wavelet transforms have potential for being useful in real-time voice analysis for detection and quantification of symptoms at home.

Place, publisher, year, edition, pages
Netherlands: Bentham Science, 2011
Keyword
Parkinson’s disease, hypokinetic dysarthria, voice recognition, speech impairment, telemedicine.
National Category
Engineering and Technology
Identifiers
urn:nbn:se:mdh:diva-23610 (URN)10.2174/2210686311101020163 (DOI)
Projects
E-MOTIONS
Available from: 2013-12-16 Created: 2013-12-16 Last updated: 2015-07-15Bibliographically approved
2. Running-speech MFCC are better markers of Parkinsonian speech deficits than vowel phonation and diadochokinetic
Open this publication in new window or tab >>Running-speech MFCC are better markers of Parkinsonian speech deficits than vowel phonation and diadochokinetic
(English)Manuscript (preprint) (Other academic)
Abstract [en]

Background:The mel-frequency cepstral coefficients (MFCC) are relied for their capability to identify pathological speech. The literature suggests that triangular mel-filters that are used in the MFCC calculation provide an approximation of the human auditory perception. This approximation allows quantifying the clinician’s perception of the intelligibility of the patient’s speech that allows mapping between the clinician’s score of the severity of speech symptoms and the actual symptom severity of the patient’s speech. Previous research on speech impairment in Parkinson’s disease(PD) used sustained-phonation and diadochokinesis tests to score symptoms using the unified Parkinson’s disease rating scale motor speech examination (UPDRS-S).

Objectives:The paper aims to utilize MFCC computed from the recordings of running speech examination for classification of the severity of speech symptoms based on the UPDRS-S. The secondary aim was to compare the performance of the MFCC from running-speech, and the MFCC from sustained-phonation and diadochokinesis recordings, in classifying the UPDRS-S levels.

Method:The study involved audio recordings of motor speech examination of 80 subjects, including 60 PD patients and 20 normal controls. Three different running-speech tests, four different sustained-phonation tests and two different diadochokinesis tests were recorded in different occasions from each subject. The vocal performance of each subject was rated by a clinician using the UPDRS-S. A total of 16 MFCC computed separately from the recordings of running-speech, sustained-phonation and diadochokinesis tests were used to train a support vector machine (SVM) for classifying the levels of UPDRS-S severity. The area under the ROC curve (AoC) was used to compare the feasibility of classification models. Additionally, the Guttman correlation coefficient (μ2) and intra-class correlation coefficient (ICC) were used for feature validation.

Results:The experiments on the SVM trained using the MFCC from running-speech samples produced higher AoC (84%and 85%) in classifying the severity levels of UPDRS-S as compared to the AoC produced by the MFCC from sustained-phonation (88% and 77%) and diadochokinesis (77% and 77%) samples in 10-fold cross validation and training-testing schemes respectively. The μ2 between the MFCC from running speech samples and clinical ratings was stronger (μ2 up to 0.7) than the μ2 between the clinical ratings and the MFCC from sustained-phonation and diadochokinesis samples. The ICC of the MFCC from the running-speech samples recorded in different test occasions was stronger as compared to the ICC of the MFCC from sustained-phonation and diadochokinesis samples recorded in different test occasions.

Conclusions:The strong classification ability of running-speech MFCC and SVM, on one hand, supports suitability of this scheme to monitor speech symptoms in PD. Besides, the values of μ2 and ICC suggest that the MFCC from running speech signals are more reliable for scoring speech symptoms as compared to the MFCC from sustained-phonation and diadochokinesis signals

National Category
Engineering and Technology
Research subject
Care Sciences
Identifiers
urn:nbn:se:mdh:diva-24645 (URN)
Projects
PAULINA
Funder
Knowledge Foundation
Note

The article has been submitted to a journal for publication.

Available from: 2014-03-14 Created: 2014-03-14 Last updated: 2015-07-15Bibliographically approved
3. Cepstral separation difference: A novel approach for speech impairment quantification in Parkinson's disease
Open this publication in new window or tab >>Cepstral separation difference: A novel approach for speech impairment quantification in Parkinson's disease
2014 (English)In: Biocybernetics and Biomedical Engineering BBE, ISSN 0208-5216, Vol. 34, no 1, 25-34 p.Article in journal (Refereed) Published
Abstract [en]

This paper introduces a novel approach, Cepstral Separation Difference (CSD), for quantification of speech impairment in Parkinson's disease (PD). CSD represents a ratio between the magnitudes of glottal (source) and supra-glottal (filter) log-spectrums acquired using the source-filter speech model. The CSD-based features were tested on a database consisting of 240 clinically rated running speech samples acquired from 60 PD patients and 20 healthy controls. The Guttmann (mu2) monotonic correlations between the CSD features and the speech symptom severity ratings were strong (up to 0.78). This correlation increased with the increasing textual difficulty in different speech tests. CSD was compared with some non-CSD speech features (harmonic ratio, harmonic-to-noise ratio and Mel-frequency cepstral coefficients) for speech symptom characterization in terms of consistency and reproducibility. The high intra-class correlation coefficient (>0.9) and analysis of variance indicates that CSD features can be used reliably to distinguish between severity levels of speech impairment. Results motivate the use of CSD in monitoring speech symptoms in PD

Place, publisher, year, edition, pages
Elsevier, 2014
Keyword
Parkinson's disease, Speech processing, Dysarthria, Acoustic analysis, Speech cepstrum
National Category
Engineering and Technology
Identifiers
urn:nbn:se:mdh:diva-23606 (URN)10.1016/j.bbe.2013.06.001 (DOI)000333226500005 ()2-s2.0-84894594187 (Scopus ID)
Projects
E-MOTIONS
Available from: 2013-12-16 Created: 2013-12-16 Last updated: 2015-07-15Bibliographically approved
4. Classification of speech intelligibility in Parkinson's disease
Open this publication in new window or tab >>Classification of speech intelligibility in Parkinson's disease
2014 (English)In: Biocybernetics and Biomedical Engineering BBE, ISSN 0208-5216, Vol. 34, no 1, 34-45 p.Article in journal (Refereed) Published
Abstract [en]

A problem in the clinical assessment of running speech in Parkinson's disease (PD) is to track underlying deficits in a number of speech components including respiration, phonation, articulation and prosody, each of which disturbs the speech intelligibility. A set of 13 features, including the cepstral separation difference and Mel-frequency cepstral coefficients were computed to represent deficits in each individual speech component. These features were then used in training a support vector machine (SVM) using n-fold cross validation. The dataset used for method development and evaluation consisted of 240 running speech samples recorded from 60 PD patients and 20 healthy controls. These speech samples were clinically rated using the Unified Parkinson's Disease Rating Scale Motor Examination of Speech (UPDRS-S). The classification accuracy of SVM was 85% in 3 levels of UPDRS-S scale and 92% in 2 levels with the average area under the ROC (receiver operating characteristic) curves of around 91%. The strong classification ability of selected features and the SVM model supports suitability of this scheme to monitor speech symptoms in PD.

Keyword
Parkinson's disease, Speech processing, Dysarthria, Support vector machine, Tele-monitoring
National Category
Engineering and Technology
Identifiers
urn:nbn:se:mdh:diva-23607 (URN)10.1016/j.bbe.2013.10.003 (DOI)000333226500006 ()2-s2.0-84894547177 (Scopus ID)
Projects
E-MOTIONS
Available from: 2013-12-16 Created: 2013-12-16 Last updated: 2015-07-15Bibliographically approved
5. A computer vision framework for finger-tapping evaluation in Parkinson's disease
Open this publication in new window or tab >>A computer vision framework for finger-tapping evaluation in Parkinson's disease
2014 (English)In: Artificial Intelligence in Medicine, ISSN 0933-3657, E-ISSN 1873-2860, Vol. 60, no 1, 27-40 p.Article in journal (Refereed) Published
Abstract [en]

Objectives: The rapid finger-tapping test (RFT) is an important method for clinical evaluation of movement disorders, including Parkinson's disease (PD). In clinical practice, the naked-eye evaluation of RFT results in a coarse judgment of symptom scores. We introduce a novel computer-vision (CV) method for quantification of tapping symptoms through motion analysis of index-fingers. The method is unique as it utilizes facial features to calibrate tapping amplitude for normalization of distance variation between the camera and subject.

Methods: The study involved 387 video footages of RFT recorded from 13 patients diagnosed with advanced PD. Tapping performance in these videos was rated by two clinicians between the symptom severity levels (‘0: normal’ to ‘3: severe’) using the unified Parkinson's disease rating scale motor examination of finger-tapping (UPDRS-FT). Another set of recordings in this study consisted of 84 videos of RFT recorded from 6 healthy controls. These videos were processed by a CV algorithm that tracks the index-finger motion between the video-frames to produce a tapping time-series. Different features were computed from this time series to estimate speed, amplitude, rhythm and fatigue in tapping. The features were trained in a support vector machine (1) to categorize the patient group between UPDRS-FT symptom severity levels, and (2) to discriminate between PD patients and healthy controls.

Results: A new representative feature of tapping rhythm, ‘cross-correlation between the normalized peaks’ showed strong Guttman correlation (mu2 = -0.80) with the clinical ratings. The classification of tapping features using the support vector machine classifier and 10-fold cross validation categorized the patient samples between UPDRS-FT levels with an accuracy of 88%. The same classification scheme discriminated between RFT samples of healthy controls and PD patients with an accuracy of 95%.

Conclusion: The work supports the feasibility of the approach, which is presumed suitable for PD monitoring in the home environment. The system offers advantages over other technologies (e.g. magnetic sensors, accelerometers, etc.) previously developed for objective assessment of tapping symptoms.

Place, publisher, year, edition, pages
Elsevier, 2014
Keyword
Computer vision, Motion analysis, Face detection, Parkinson's disease, Finger-tapping
National Category
Engineering and Technology
Identifiers
urn:nbn:se:mdh:diva-23608 (URN)10.1016/j.artmed.2013.11.004 (DOI)000331506200003 ()2-s2.0-84892883460 (Scopus ID)
Projects
E-MOTIONS
Available from: 2013-12-16 Created: 2013-12-16 Last updated: 2015-07-15Bibliographically approved
6. Computer Vision Methods for Parkinsonian Gait Analysis: A Review on Patents
Open this publication in new window or tab >>Computer Vision Methods for Parkinsonian Gait Analysis: A Review on Patents
2013 (English)In: Recent Patents on Biomedical Engineering RPBE, ISSN 2211-3320, Vol. 6, no 2, 97-108 p.Article in journal (Refereed) Published
Abstract [en]

Gait disturbance is an important symptom of Parkinson’s disease (PD). This paper presents a review of patents reported in the area of computerized gait disorder analysis. The feasibility of marker-less vision based systems has been examined for ‘at-home’ self-evaluation of gait taking into account the physical restrictions of patients arising due to PD. A three tier review methodology has been utilized to synthesize gait applications to investigate PD related gait features and to explore methods for gait classification based on symptom severities. A comparison between invasive and non-invasive methods for gait analysis revealed that marker-free approach can provide resource efficient, convenient and accurate gait measurements through the use of image processing methods. Image segmentation of human silhouette is the major challenge in the marker-free systems which can possibly be comprehended through the use of Microsoft Kinect application and motion estimation algorithms. Our synthesis further suggests that biorhythmic features in gait patterns have potential to discriminate gait anomalies based on the clinical scales.

Place, publisher, year, edition, pages
Bentham Science, 2013
Keyword
Gait Impairment, Parkinson’s disease, Gait Video Analysis, and Image Processing.
National Category
Engineering and Technology
Identifiers
urn:nbn:se:mdh:diva-23611 (URN)10.2174/1874764711306020004 (DOI)2-s2.0-84882764035 (Scopus ID)
Projects
E-MOTIONS
Available from: 2013-12-16 Created: 2013-12-16 Last updated: 2015-07-15Bibliographically approved
7. Motion Cue Analysis for Parkinsonian Gait Recognition
Open this publication in new window or tab >>Motion Cue Analysis for Parkinsonian Gait Recognition
2013 (English)In: Open Biomedical Engineering Journal, ISSN 1874-1207, Vol. 7, no 1, 1-8 p.Article in journal (Refereed) Published
Abstract [en]

This paper presents a computer-vision based marker-free method for gait-impairment detection in Patients with Parkinson’s disease (PWP). The system is based upon the idea that a normal human body attains equilibrium during the gait by aligning the body posture with Axis-of-Gravity (AOG) using feet as the base of support. In contrast, PWP appear to be falling forward as they are less-able to align their body with AOG due to rigid muscular tone. A normal gait exhibits periodic stride-cycles with stride-angle around 45o between the legs, whereas PWP walk with shortened stride-angle with high variability between the stride-cycles. In order to analyze Parkinsonian-gait (PG), subjects were videotaped with several gait-cycles. The subject’s body was segmented using a color-segmentation method to form a silhouette. The silhouette was skeletonized for motion cues extraction. The motion cues analyzed were stride-cycles (based on the cyclic leg motion of skeleton) and posture lean (based on the angle between leaned torso of skeleton and AOG). Cosine similarity between an imaginary perfect gait pattern and the subject gait patterns produced 100% recognition rate of PG for 4 normal-controls and 3 PWP. Results suggested that the method is a promising tool to be used for PG assessment in home-environment.

Place, publisher, year, edition, pages
Netherlands: Bentham Science, 2013
Keyword
Gait impairment, Parkinson’s disease, Gait video analysis, Image processing.
National Category
Engineering and Technology
Identifiers
urn:nbn:se:mdh:diva-23612 (URN)10.2174/1874120701307010001 (DOI)2-s2.0-84876092108 (Scopus ID)
Projects
E-MOTIONS
Available from: 2013-12-16 Created: 2013-12-16 Last updated: 2015-07-15Bibliographically approved

Open Access in DiVA

fulltext(2213 kB)600 downloads
File information
File name FULLTEXT03.pdfFile size 2213 kBChecksum SHA-512
b733805f475121ba381f5eca4c3bc96c3d3f6c3e49c688fd24af6f625ecbf8d7377181256129c1b70b9d1962199ccbdfb110c3d094c284eeae760579cd04fa69
Type fulltextMimetype application/pdf

Search in DiVA

By author/editor
Khan, Taha
By organisation
Embedded Systems
Engineering and Technology

Search outside of DiVA

GoogleGoogle Scholar
Total: 600 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

Total: 820 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • 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