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...

No abstract

No abstract

One major challenge in the medication of Parkinson's disease is that the severity of the disease, reflected in the patients' motor state, cannot be measured using accessible biomarkers. Therefore, we develop and examine a variety of statistical models to detect the motor state of such patients based on sensor data from a wearable device. We find that deep learning models consistently outperform a classical machine learning model applied on hand-crafted features in this time series classification task. Furthermore, our results suggest that treating this problem as a regression instead of an ordinal regression or a classification task is most appropriate. For consistent model evaluation and training, we adopt the leave-one-subject-out validation scheme to the training of deep learning models. We also employ a class-weighting scheme to successfully mitigate the problem of high multi-class imbalances in this domain. In addition, we propose a customized performance measure that reflects the requirements of the involved medical staff on the model. To solve the problem of limited availability of high quality training data, we propose a transfer learning technique which helps to improve model performance substantially. Our results suggest that deep learning techniques offer a high potential to autonomously detect motor states of patients with Parkinson's disease.

One of the promising opportunities of digital health is its potential to lead to more holistic understandings of diseases by interacting with the daily life of patients and through the collection of large amounts of real world data. Validating and benchmarking indicators of disease severity in the home setting is difficult, however, given the large number of confounders present in the real world and the challenges in collecting ground truth data in the home. Here we leverage two datasets with continuous wrist-worn accelerometer data coupled with frequent symptom reports in the home setting, to develop digital biomarkers of symptom severity. Using these data, we performed a public benchmarking challenge in which participants were asked to build measures of severity across 3 symptoms (on/off medication, dyskinesia, and tremor). 42 teams participated and performance was improved over baseline models for each subchallenge. Additional ensemble modeling across submissions further improved performance, and the top models validated in a subset of patients whose symptoms were observed and rated by trained clinicians.