Skip to main content

LUP Student Papers

LUND UNIVERSITY LIBRARIES

Classification of hyperkinesia in Parkinson patients using mobile sensors

von Grothusen, Gustaf LU (2022) In Master's Theses in Matematical Sciences FMSM01 20222
Mathematical Statistics
Abstract
In this thesis, we explore the possibility to monitoring hyperkinesia in people who suffer from Parkinson's disease (PD) using sensors in mobile phones. This is done by first collecting data from 25 patients diagnosed with PD by using a sensor-recording smartphone in a bag attached to the stomach, and at the same time let trained professionals make assessments of the degree of which they show signs of hyperkinesia, on the clinical dyskinesia rating scale, CDRS. Given the labels and the sensor data, a set of models has been trained. Both models for binary classification, i.e., predicting the presence of hyperkinesia vs no hyperkinesia, as well as models aiming to estimate the CDRS score were investigated. As the available data is a mere 429... (More)
In this thesis, we explore the possibility to monitoring hyperkinesia in people who suffer from Parkinson's disease (PD) using sensors in mobile phones. This is done by first collecting data from 25 patients diagnosed with PD by using a sensor-recording smartphone in a bag attached to the stomach, and at the same time let trained professionals make assessments of the degree of which they show signs of hyperkinesia, on the clinical dyskinesia rating scale, CDRS. Given the labels and the sensor data, a set of models has been trained. Both models for binary classification, i.e., predicting the presence of hyperkinesia vs no hyperkinesia, as well as models aiming to estimate the CDRS score were investigated. As the available data is a mere 429 samples, a key part of the work has been to self-engineer features descriptive to signs of hyperkinesia. The proposed models are kernel support vector machines for both the binary classification and for the regression. The proposed method provides results that are in line with what can be expected of an assessment by a trained professional. (Less)
Please use this url to cite or link to this publication:
author
von Grothusen, Gustaf LU
supervisor
organization
course
FMSM01 20222
year
type
H2 - Master's Degree (Two Years)
subject
keywords
Dyskinesia, hyperkinesia, Parkinson's disease, support vector machine, SVM, SVR, SVC, feature engineering, digital phenotyping, CDRS, smartphone, accelerometer
publication/series
Master's Theses in Matematical Sciences
report number
LUTFMS-3463-2023
ISSN
1404-6342
other publication id
2023:E3
language
English
id
9107609
date added to LUP
2023-01-19 13:39:58
date last changed
2023-01-23 15:06:40
@misc{9107609,
  abstract     = {{In this thesis, we explore the possibility to monitoring hyperkinesia in people who suffer from Parkinson's disease (PD) using sensors in mobile phones. This is done by first collecting data from 25 patients diagnosed with PD by using a sensor-recording smartphone in a bag attached to the stomach, and at the same time let trained professionals make assessments of the degree of which they show signs of hyperkinesia, on the clinical dyskinesia rating scale, CDRS. Given the labels and the sensor data, a set of models has been trained. Both models for binary classification, i.e., predicting the presence of hyperkinesia vs no hyperkinesia, as well as models aiming to estimate the CDRS score were investigated. As the available data is a mere 429 samples, a key part of the work has been to self-engineer features descriptive to signs of hyperkinesia. The proposed models are kernel support vector machines for both the binary classification and for the regression. The proposed method provides results that are in line with what can be expected of an assessment by a trained professional.}},
  author       = {{von Grothusen, Gustaf}},
  issn         = {{1404-6342}},
  language     = {{eng}},
  note         = {{Student Paper}},
  series       = {{Master's Theses in Matematical Sciences}},
  title        = {{Classification of hyperkinesia in Parkinson patients using mobile sensors}},
  year         = {{2022}},
}