Abstract
In this paper, we propose to use a weakly supervised machine learning framework for automatic detection of Parkinson's Disease motor symptoms in daily living environments. Our primary goal is to develop a monitoring system capable of being used outside of controlled laboratory settings. Such a system would enable us to track medication cycles at home and provide valuable clinical feedback. Most of the relevant prior works involve supervised learning frameworks (e.g., Support Vector Machines). However, in-home monitoring provides only coarse ground truth information about symptom occurrences, making it very hard to adapt and train supervised learning classifiers for symptom detection. We address this challenge by formulating symptom detection under incomplete ground truth information as a multiple instance learning (MIL) problem. MIL is a weakly supervised learning framework that does not require exact instances of symptom occurrences for training; rather, it learns from approximate time intervals within which a symptom might or might not have occurred on a given day. Once trained, the MIL detector was able to spot symptom-prone time windows on other days and approximately localize the symptom instances. We monitored two Parkinson's disease (PD) patients, each for four days with a set of five triaxial accelerometers and utilized a MIL algorithm based on axis parallel rectangle (APR) fitting in the feature space. We were able to detect subject specific symptoms (e.g. dyskinesia) that conformed with a daily log maintained by the patients.
Highlights
There has been an increased interest in developing wearable sensing systems for patient-centric healthcare.The ultimate goal of these collaborative efforts between the healthcare and engineering communities is to enable unobtrusive autonomous monitoring of the patients’ state and generate valuable clinical feedback
Motor symptom monitoring in Parkinson’s Disease (PD) has gained significant attention over the years [11], [15]. These symptoms fluctuate during daily living depending on the medication intake. The knowledge of these medication cycles could be very useful for Parkinson’s disease (PD) treatments including: a) evaluation of the potential benefit of deep brain stimulation (DBS), b) patient adapted drug therapy and c) tracking disease progression over time
The inherent problem lies in the fact that accurate labeling of human behavior is error prone, subjective and time consuming. These issues are accentuated when self-report is the only form of measurement available. We address these by using a weakly supervised learning framework known as multiple instance learning (MIL) [5]
Summary
There has been an increased interest in developing wearable sensing systems for patient-centric healthcare. Motor symptom monitoring in Parkinson’s Disease (PD) has gained significant attention over the years [11], [15] In most cases, these symptoms (e.g. tremors, dyskinesia) fluctuate during daily living depending on the medication intake. These symptoms (e.g. tremors, dyskinesia) fluctuate during daily living depending on the medication intake The knowledge of these medication cycles could be very useful for PD treatments including: a) evaluation of the potential benefit of deep brain stimulation (DBS), b) patient adapted drug therapy and c) tracking disease progression over time. There is a need for sensing systems capable of unobtrusive continuous monitoring of the motor symptoms in uncontrolled daily living environments. The inherent problem lies in the fact that accurate labeling of human behavior is error prone, subjective and time consuming These issues are accentuated when self-report is the only form of measurement available. Our detector was able to spot the subject specific motor symptoms that conformed with the daily log maintained by the patients
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
