High-Resolution Motor State Detection in Parkinson’s Disease Using Convolutional Neural Networks

Abstract

patients with advanced parkinson's disease regularly experience unstable motor states. objective and reliable monitoring of these fluctuations is an unmet need. We used deep learning to classify motion data from a single wrist-worn iMU sensor recording in unscripted environments. for validation purposes, patients were accompanied by a movement disorder expert, and their motor state was passively evaluated every minute. We acquired a dataset of 8,661 minutes of IMU data from 30 patients, with annotations about the motor state (off,on, DYSKinetic) based on MDS-UpDRS global bradykinesia item and the AIMS upper limb dyskinesia item. Using a 1-minute window size as an input for a convolutional neural network trained on data from a subset of patients, we achieved a three-class balanced accuracy of 0.654 on data from previously unseen subjects. This corresponds to detecting the OFF, ON, or DYSKINETIC motor state at a sensitivity/specificity of 0.64/0.89, 0.67/0.67 and 0.64/0.89, respectively. on average, the model outputs were highly correlated with the annotation on a per subject scale (r = 0.83/0.84; p < 0.0001), and sustained so for the highly resolved time windows of 1 minute (r = 0.64/0.70; p < 0.0001). Thus, we demonstrate the feasibility of long-term motor-state detection in a free-living setting with deep learning using motion data from a single iMU. Parkinson's disease (PD) is characterized by slowness of movement, decremented small amplitude, and loss of movement spontaneity that are dramatically relieved when dopamine is orally restituted 1. Due to the pharmacokinetic properties of the main medication, i.e. L-DOPA, motor fluctuations may occur and complicate the symptomatic treatment 2-4. Troughs in dopaminergic therapy are accompanied by parkinsonistic phases, so-called OFF-states, while peaks can lead to phases with excessive (hyperkinetic) spontaneous movements, the dyskinetic (DYS), or ON + motor state 5. Ideally, patients with PD (PwP) experience neither OFF nor dyskinetic motor states but maintain a state resembling normal motor function, i.e. the ON state. These motor fluctuations are a major limiting factor for patients' quality of life, especially in later disease stages 6. Consequently, therapeutic innovations have to demonstrate superiority in terms of their ability to reduce motor fluctuations in order to be licensed by health agencies e.g. 7-9. The current standard for assessing motor fluctuations relies on patient self-reporting in the form of diaries (e.g. 10), or expert ratings using standardized scales (e.g. 11 , see 12 for a review). Both approaches have their merits. But they are prone to rater bias and placebo effects, and they can capture the motor state only with coarse temporal resolutions 13,14. In the past, clinically relevant features in motion data has been extracted to quantify motor states of PwP over long periods of time in free-living setups 15-17. Those approaches were not capable of a dynamic detection of typical motion patterns and failed, for example, when the sensor data we...

Sensing of joint and spinal bending or stretching via a retractable and wearable badge reel

“…Current clinical investigations into the spine are lacking of wearable and real-time technologies and mainly based on X-ray film, which is time-consuming and harmful. IMU technique could be applied, however, it requires complicated body parameters to build the individual body model, and the measuring is indirect 34 – 37 . As our proposed stretch sensor is thin and attachable, we utilized it to qualitatively analyze the displacement change of the spine during bending or stretching, by fixing it at the positions along the spinous process joints, including cervical, thoracic, and lumbar spine (Fig.…”

An MRI-based Deep Learning Model to Predict Parkinson’s Disease Stages

“…Franz et al . 9 used a dataset of 8,661 minutes of IMU data from 30 patients, and defined the motor state (off, on, dyskinetic) based on MDS-UPDRS global bradykinesia item as well as the AIMS upper limb dyskinesia item. Having used a 1-minute window size as an input for a CNN trained model on the data from a subset of patients, they achieved a three-class balanced accuracy of 0.654 on data from previously unseen subjects.…”

“…To overcome such drawbacks in clinical evaluation, diagnosis and disease follow up in patients with AD, some studies have proposed methods towards the prediction of PD severity using machine learning methods on different datasets such as voice and UPDRS to distinguish the stages of the disease and healthy people. 6,9,10 The present investigation used MRI data to diagnose stages of PD using deep neural networks.…”

Wearable Magnetic Induction-based Approach Toward 3D Motion Tracking

“…For example, [21] presents the development of a smart wearable jumpsuit with multiple built-in IMU sensors for automatic posture and movement tracking of infants. The work in [22] investigates the reliability and validity of IMUs for clinical movement analysis, and [23] presents a single wrist-worn IMU sensor for high-resolution motor state detection in Parkinson's disease. Inertial sensing can track limb movements by integrating over sensor measurements, though it is subject to drift since the estimation errors caused by the intrinsic noise can grow unbounded with time [1].…”