Wearable-based Parkinson's Disease Severity Monitoring using Deep Learning
This work addresses the problem of inaccessible biomarkers for Parkinson's disease severity monitoring for patients and medical staff, representing an incremental advancement in applying deep learning to medical time series data.
The paper tackled the challenge of monitoring Parkinson's disease severity by developing deep learning models using wearable sensor data, finding that these models outperform classical machine learning and that regression tasks are most appropriate, with transfer learning improving performance substantially.
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.