Let's Draw: Detecting and Measuring Parkinson's Disease on Smartphones

Kuosmanen, Elina; Kan, Valerii; Visuri, Aku; Hosio, Simo; Ferreira, Denzil

doi:10.1145/3313831.3376864

Cited by 11 publications

(7 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Using SVMs, Random Forests, and Naive Bayes classifiers, they achieve up to 92% prediction accuracy with features, such as average number of pen strokes, total writing time, stroke distance, duration, pressure, and speed. Similar techniques have been used to diagnose other cognitive impairments, such as Parkinson's disease (Drotár et al, 2014 ; Kuosmanen et al, 2020 ), or to predict task difficulty and user performance of cognitive tests (Barz et al, 2020 ). This shows that the ML-based digital pen features approach considered in this work can be applied to a variety of application domains and use cases.…”

Section: Related Workmentioning

confidence: 99%

Modeling Users' Cognitive Performance Using Digital Pen Features

Prange

Sonntag

2022

Front. Artif. Intell.

View full text Add to dashboard Cite

Digital pen features model characteristics of sketches and user behavior, and can be used for various supervised machine learning (ML) applications, such as multi-stroke sketch recognition and user modeling. In this work, we use a state-of-the-art set of more than 170 digital pen features, which we implement and make publicly available. The feature set is evaluated in the use case of analyzing paper-pencil-based neurocognitive assessments in the medical domain. Most cognitive assessments, for dementia screening for example, are conducted with a pen on normal paper. We record these tests with a digital pen as part of a new interactive cognitive assessment tool with automatic analysis of pen input. The physician can, first, observe the sketching process in real-time on a mobile tablet, e.g., in telemedicine settings or to follow Covid-19 distancing regulations. Second, the results of an automatic test analysis are presented to the physician in real-time, thereby reducing manual scoring effort and producing objective reports. As part of our evaluation we examine how accurately different feature-based, supervised ML models can automatically score cognitive tests, with and without semantic content analysis. A series of ML-based sketch recognition experiments is conducted, evaluating 10 modern off-the-shelf ML classifiers (i.e., SVMs, Deep Learning, etc.) on a sketch data set which we recorded with 40 subjects from a geriatrics daycare clinic. In addition, an automated ML approach (AutoML) is explored for fine-tuning and optimizing classification performance on the data set, achieving superior recognition accuracies. Using standard ML techniques our feature set outperforms all previous approaches on the cognitive tests considered, i.e., the Clock Drawing Test, the Rey-Osterrieth Complex Figure Test, and the Trail Making Test, by automatically scoring cognitive tests with up to 87.5% accuracy in a binary classification task.

show abstract

Section: Related Workmentioning

confidence: 99%

Modeling Users' Cognitive Performance Using Digital Pen Features

Prange

Sonntag

2022

Front. Artif. Intell.

View full text Add to dashboard Cite

show abstract

“…Les travaux sont orientés selon différents intérêts sur la MP. Certains travaux ont été réalisés pour le diagnostic de la MP [37], [11], [34], [15]. Dans l'approche centrée utilisateur utilisée, des entretiens et des ateliers [37], avec des personnes atteintes de la MP et aides-soignants ont été menées pour impliquer les utilisateurs.…”

Section: La Conception Des Logiciels Sur La Maladie De Parkinsonunclassified

“…• Les différents changements que peuvent connaître les symptômes ayant un impact sur les besoins • Les informations sur les symptômes qui évoluent plus vite (ex. le tremblement [15] évolue plus vite que d'autres symptômes tels que le trouble de la communication [1]. • Les proches et les aidants qui devront s'adapter à l'évolution de la solution technologique • les changements environnementaux • Les changements de ses capacités (physiques et mentales) • Les tâches qu'il aura à exécuter et qui auront à évoluer en fonction de son profil.…”

Section: Le Processus Ccu-peunclassified

Vers une conception centrée sur l’utilisateur ayant un profil évolutif: Une étude de cas avec des personnes atteintes de la maladie de Parkinson

Lepreux

Apedo

Oliveira

2021

32e Conférence Francophone Sur l'Interaction Homme-Machine

View full text Add to dashboard Cite

Providing assistance to people with progressive diseases, such as Parkinson's disease, is a major challenge. The needs of these users change from moment to moment over a short, medium or long period. Our study focuses on communication disorders in people with Parkinson's disease. In order to implement a technology solution to meet their needs, it is essential that the end users of evolving profiles are at the center of the design. For this, we realized the need to adapt the user-centered approach presented in the IS0 / IEC 9241-210 standard to consider the evolving profile. In addition, we explicitly integrate the principles of participatory design into the approach. The proposed approach is being used to develop a useful and scalable communication tool for different user profile. CCS CONCEPTS• Human-centered computing → HCI design and evaluation methods; HCI theory, concepts and models.

show abstract

“…A number of digital tools for assessing one's cognitive abilities have been proposed [5,25,39,40,38] as an alternative to traditional pen and paper based approach where a trained expert (clinician) is required to examine the test results manually. For instance, Prange et al [39] proposed a multimodal speech-based dialogue system for a questionnaire-based cognitive test called the Mini-Mental State Examination (MMSE).…”

Section: Digital Tools For Cognitive Assessmentsmentioning

confidence: 99%

“…They showed that their system can reduce the scoring time automating the process and that the its results are clinically reliable. Similarly, Kuosmanen et al [25] developed a smartphone-based clinical tool to detect symptoms of Parkinson's disease with the spiral drawing test. Researchers also focused on Trail Making Test (TMT) for assessing one's cognitive performance.…”

Section: Digital Tools For Cognitive Assessmentsmentioning

confidence: 99%

Dot-to-Dot: Pre-reading Assessment of Literacy Risk via a Visual-Motor Mechanism on Touchscreen Devices

Park¹,

Revés

Esteves

et al. 2021

Human-Computer Interaction – INTERACT 2021

View full text Add to dashboard Cite

While early identification of children with dyslexia is crucial, it is difficult to assess literacy risks of these children early on before they learn to read. In this study, we expand early work on Dot-to-Dot (DtD), a non-linguistic visual-motor mechanism aimed at facilitating the detection of the potential reading difficulties of children at pre-reading age.To investigate the effectiveness of this approach on touchscreen devices, we conducted a user study with 33 children and examined their task performance logs as well as language test results. Our findings suggest that there is a significant correlation among DtD task and series of language tests. We conclude the work by suggesting different ways in which DtD could be seamlessly embedded into everyday mobile use cases.

show abstract

Let's Draw: Detecting and Measuring Parkinson's Disease on Smartphones

Cited by 11 publications

References 14 publications

Modeling Users' Cognitive Performance Using Digital Pen Features

Modeling Users' Cognitive Performance Using Digital Pen Features

Vers une conception centrée sur l’utilisateur ayant un profil évolutif: Une étude de cas avec des personnes atteintes de la maladie de Parkinson

Dot-to-Dot: Pre-reading Assessment of Literacy Risk via a Visual-Motor Mechanism on Touchscreen Devices

Contact Info

Product

Resources

About