Classification of iRBD and Parkinson's disease patients based on eye movements during sleep

Gitte Julie Christensen; Henriette Koch; Rune Asger Vestergaard Frandsen; Jacob Kempfner; Lars Arvastson; Soren R Christensen; Helge B D Sorensen; Poul Jennum

doi:10.1109/embc.2013.6609531

Classification of iRBD and Parkinson's disease patients based on eye movements during sleep

Gitte Julie Christensen, Henriette Koch, Rune Asger Vestergaard Frandsen, Jacob Kempfner, Lars Arvastson, Soren R Christensen, Helge B D Sorensen, Poul Jennum

Institut for Klinisk Medicin

14 Citationer (Scopus)

Abstract

Patients suffering from the sleep disorder idiopathic rapid-eye-movement sleep behavior disorder (iRBD) have been observed to be in high risk of developing Parkinson's disease (PD). This makes it essential to analyze them in the search for PD biomarkers. This study aims at classifying patients suffering from iRBD or PD based on features reflecting eye movements (EMs) during sleep. A Latent Dirichlet Allocation (LDA) topic model was developed based on features extracted from two electrooculographic (EOG) signals measured as parts in full night polysomnographic (PSG) recordings from ten control subjects. The trained model was tested on ten other control subjects, ten iRBD patients and ten PD patients, obtaining a EM topic mixture diagram for each subject in the test dataset. Three features were extracted from the topic mixture diagrams, reflecting 'certainty', 'fragmentation' and 'stability' in the timely distribution of the EM topics. Using a Naive Bayes (NB) classifier and the features 'certainty' and 'stability' yielded the best classification result and the subjects were classified with a sensitivity of 95 %, a specificity of 80% and an accuracy of 90 %. This study demonstrates in a data-driven approach, that iRBD and PD patients may exhibit abnorm form and/or timely distribution of EMs during sleep.

Originalsprog	Engelsk
Tidsskrift	Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference
Vol/bind	2013
Sider (fra-til)	441-4
Antal sider	4
ISSN	1557-170X
DOI	https://doi.org/10.1109/embc.2013.6609531
Status	Udgivet - 2013

Adgang til dokumentet

10.1109/embc.2013.6609531

Citationsformater

Christensen, G. J., Koch, H., Frandsen, R. A. V., Kempfner, J., Arvastson, L., Christensen, S. R., Sorensen, H. B. D., & Jennum, P. (2013). Classification of iRBD and Parkinson's disease patients based on eye movements during sleep. Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference, 2013, 441-4. https://doi.org/10.1109/embc.2013.6609531

Classification of iRBD and Parkinson's disease patients based on eye movements during sleep. / Christensen, Gitte Julie; Koch, Henriette; Frandsen, Rune Asger Vestergaard et al.

I: Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference, Bind 2013, 2013, s. 441-4.

Publikation: Bidrag til tidsskrift › Konferenceartikel › Forskning › peer review

Christensen, GJ, Koch, H, Frandsen, RAV, Kempfner, J, Arvastson, L, Christensen, SR, Sorensen, HBD & Jennum, P 2013, 'Classification of iRBD and Parkinson's disease patients based on eye movements during sleep', Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference, bind 2013, s. 441-4. https://doi.org/10.1109/embc.2013.6609531

Christensen GJ, Koch H, Frandsen RAV, Kempfner J, Arvastson L, Christensen SR et al. Classification of iRBD and Parkinson's disease patients based on eye movements during sleep. Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference. 2013;2013:441-4. doi: 10.1109/embc.2013.6609531

Christensen, Gitte Julie ; Koch, Henriette ; Frandsen, Rune Asger Vestergaard et al. / Classification of iRBD and Parkinson's disease patients based on eye movements during sleep. I: Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference. 2013 ; Bind 2013. s. 441-4.

@inproceedings{d5f8415ee2ba45f6ba2aa796a2d7fa80,

title = "Classification of iRBD and Parkinson's disease patients based on eye movements during sleep",

abstract = "Patients suffering from the sleep disorder idiopathic rapid-eye-movement sleep behavior disorder (iRBD) have been observed to be in high risk of developing Parkinson's disease (PD). This makes it essential to analyze them in the search for PD biomarkers. This study aims at classifying patients suffering from iRBD or PD based on features reflecting eye movements (EMs) during sleep. A Latent Dirichlet Allocation (LDA) topic model was developed based on features extracted from two electrooculographic (EOG) signals measured as parts in full night polysomnographic (PSG) recordings from ten control subjects. The trained model was tested on ten other control subjects, ten iRBD patients and ten PD patients, obtaining a EM topic mixture diagram for each subject in the test dataset. Three features were extracted from the topic mixture diagrams, reflecting 'certainty', 'fragmentation' and 'stability' in the timely distribution of the EM topics. Using a Naive Bayes (NB) classifier and the features 'certainty' and 'stability' yielded the best classification result and the subjects were classified with a sensitivity of 95 %, a specificity of 80% and an accuracy of 90 %. This study demonstrates in a data-driven approach, that iRBD and PD patients may exhibit abnorm form and/or timely distribution of EMs during sleep.",

author = "Christensen, {Gitte Julie} and Henriette Koch and Frandsen, {Rune Asger Vestergaard} and Jacob Kempfner and Lars Arvastson and Christensen, {Soren R} and Sorensen, {Helge B D} and Poul Jennum",

year = "2013",

doi = "10.1109/embc.2013.6609531",

language = "English",

volume = "2013",

pages = "441--4",

journal = "Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings",

issn = "0589-1019",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Classification of iRBD and Parkinson's disease patients based on eye movements during sleep

AU - Christensen, Gitte Julie

AU - Koch, Henriette

AU - Frandsen, Rune Asger Vestergaard

AU - Kempfner, Jacob

AU - Arvastson, Lars

AU - Christensen, Soren R

AU - Sorensen, Helge B D

AU - Jennum, Poul

PY - 2013

Y1 - 2013

N2 - Patients suffering from the sleep disorder idiopathic rapid-eye-movement sleep behavior disorder (iRBD) have been observed to be in high risk of developing Parkinson's disease (PD). This makes it essential to analyze them in the search for PD biomarkers. This study aims at classifying patients suffering from iRBD or PD based on features reflecting eye movements (EMs) during sleep. A Latent Dirichlet Allocation (LDA) topic model was developed based on features extracted from two electrooculographic (EOG) signals measured as parts in full night polysomnographic (PSG) recordings from ten control subjects. The trained model was tested on ten other control subjects, ten iRBD patients and ten PD patients, obtaining a EM topic mixture diagram for each subject in the test dataset. Three features were extracted from the topic mixture diagrams, reflecting 'certainty', 'fragmentation' and 'stability' in the timely distribution of the EM topics. Using a Naive Bayes (NB) classifier and the features 'certainty' and 'stability' yielded the best classification result and the subjects were classified with a sensitivity of 95 %, a specificity of 80% and an accuracy of 90 %. This study demonstrates in a data-driven approach, that iRBD and PD patients may exhibit abnorm form and/or timely distribution of EMs during sleep.

AB - Patients suffering from the sleep disorder idiopathic rapid-eye-movement sleep behavior disorder (iRBD) have been observed to be in high risk of developing Parkinson's disease (PD). This makes it essential to analyze them in the search for PD biomarkers. This study aims at classifying patients suffering from iRBD or PD based on features reflecting eye movements (EMs) during sleep. A Latent Dirichlet Allocation (LDA) topic model was developed based on features extracted from two electrooculographic (EOG) signals measured as parts in full night polysomnographic (PSG) recordings from ten control subjects. The trained model was tested on ten other control subjects, ten iRBD patients and ten PD patients, obtaining a EM topic mixture diagram for each subject in the test dataset. Three features were extracted from the topic mixture diagrams, reflecting 'certainty', 'fragmentation' and 'stability' in the timely distribution of the EM topics. Using a Naive Bayes (NB) classifier and the features 'certainty' and 'stability' yielded the best classification result and the subjects were classified with a sensitivity of 95 %, a specificity of 80% and an accuracy of 90 %. This study demonstrates in a data-driven approach, that iRBD and PD patients may exhibit abnorm form and/or timely distribution of EMs during sleep.

U2 - 10.1109/embc.2013.6609531

DO - 10.1109/embc.2013.6609531

M3 - Conference article

C2 - 24109718

SN - 0589-1019

VL - 2013

SP - 441

EP - 444

JO - Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings

JF - Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings

ER -

Classification of iRBD and Parkinson's disease patients based on eye movements during sleep

Abstract

Adgang til dokumentet

Fingeraftryk

Citationsformater