Publication detail

Analysis of in-air movement in handwriting:A novel marker for Parkinsons disease

DROTÁR, P. MEKYSKA, J. REKTOROVÁ, I. MASAROVÁ, L. SMÉKAL, Z. FAÚNDEZ ZANUY, M.

Original Title

Analysis of in-air movement in handwriting:A novel marker for Parkinsons disease

English Title

Analysis of in-air movement in handwriting:A novel marker for Parkinsons disease

Type

journal article in Web of Science

Language

en

Original Abstract

Background and objective: Parkinsons disease (PD) is the second most common neurodegen-erative disease affecting significant portion of elderly population. One of the most frequenthallmarks and usually also the first manifestation of PD is deterioration of handwriting char-acterized by micrographia and changes in kinematics of handwriting. There is no objectivequantitative method of clinical diagnosis of PD. It is thought that PD can only be definitivelydiagnosed at postmortem, which further highlights the complexities of diagnosis.Methods: We exploit the fact that movement during handwriting of a text consists not onlyfrom the on-surface movements of the hand, but also from the in-air trajectories performedwhen the hand moves in the air from one stroke to the next. We used a digitizing tablet toassess both in-air and on-surface kinematic variables during handwriting of a sentence in37 PD patients on medication and 38 age- and gender-matched healthy controls.Results: By applying feature selection algorithms and support vector machine learning meth-ods to separate PD patients from healthy controls, we demonstrated that assessing thein-air/on-surface hand movements led to accurate classifications in 84% and 78% of sub-jects, respectively. Combining both modalities improved the accuracy by another 1% over theevaluation of in-air features alone and provided medically relevant diagnosis with 85.61%prediction accuracy.Conclusions: Assessment of in-air movements during handwriting has a major impact on dis-ease classification accuracy. This study confirms that handwriting can be used as a markerfor PD and can be with advance used in decision support systems for differential diagnosisof PD.

English abstract

Background and objective: Parkinsons disease (PD) is the second most common neurodegen-erative disease affecting significant portion of elderly population. One of the most frequenthallmarks and usually also the first manifestation of PD is deterioration of handwriting char-acterized by micrographia and changes in kinematics of handwriting. There is no objectivequantitative method of clinical diagnosis of PD. It is thought that PD can only be definitivelydiagnosed at postmortem, which further highlights the complexities of diagnosis.Methods: We exploit the fact that movement during handwriting of a text consists not onlyfrom the on-surface movements of the hand, but also from the in-air trajectories performedwhen the hand moves in the air from one stroke to the next. We used a digitizing tablet toassess both in-air and on-surface kinematic variables during handwriting of a sentence in37 PD patients on medication and 38 age- and gender-matched healthy controls.Results: By applying feature selection algorithms and support vector machine learning meth-ods to separate PD patients from healthy controls, we demonstrated that assessing thein-air/on-surface hand movements led to accurate classifications in 84% and 78% of sub-jects, respectively. Combining both modalities improved the accuracy by another 1% over theevaluation of in-air features alone and provided medically relevant diagnosis with 85.61%prediction accuracy.Conclusions: Assessment of in-air movements during handwriting has a major impact on dis-ease classification accuracy. This study confirms that handwriting can be used as a markerfor PD and can be with advance used in decision support systems for differential diagnosisof PD.

Keywords

Handwriting; Disease classification; Parkinsons disease; Micrographia; In-air movement; Decision support systems

RIV year

2014

Released

17.09.2014

Publisher

Elsevier

Pages from

405

Pages to

411

Pages count

7

BibTex


@article{BUT110177,
  author="Peter {Drotár} and Jiří {Mekyska} and Irena {Rektorová} and Lucia {Masarová} and Zdeněk {Smékal} and Marcos {Faúndez Zanuy}",
  title="Analysis of in-air movement in handwriting:A novel marker for Parkinsons disease",
  annote="Background and objective: Parkinsons disease (PD) is the second most common neurodegen-erative disease affecting significant portion of elderly population. One of the most frequenthallmarks and usually also the first manifestation of PD is deterioration of handwriting char-acterized by micrographia and changes in kinematics of handwriting. There is no objectivequantitative method of clinical diagnosis of PD. It is thought that PD can only be definitivelydiagnosed at postmortem, which further highlights the complexities of diagnosis.Methods: We exploit the fact that movement during handwriting of a text consists not onlyfrom the on-surface movements of the hand, but also from the in-air trajectories performedwhen the hand moves in the air from one stroke to the next. We used a digitizing tablet toassess both in-air and on-surface kinematic variables during handwriting of a sentence in37 PD patients on medication and 38 age- and gender-matched healthy controls.Results: By applying feature selection algorithms and support vector machine learning meth-ods to separate PD patients from healthy controls, we demonstrated that assessing thein-air/on-surface hand movements led to accurate classifications in 84% and 78% of sub-jects, respectively. Combining both modalities improved the accuracy by another 1% over theevaluation of in-air features alone and provided medically relevant diagnosis with 85.61%prediction accuracy.Conclusions: Assessment of in-air movements during handwriting has a major impact on dis-ease classification accuracy. This study confirms that handwriting can be used as a markerfor PD and can be with advance used in decision support systems for differential diagnosisof PD.",
  address="Elsevier",
  chapter="110177",
  doi="10.1016/j.cmpb.2014.08.007",
  institution="Elsevier",
  number="3",
  volume="117",
  year="2014",
  month="september",
  pages="405--411",
  publisher="Elsevier",
  type="journal article in Web of Science"
}