Objective quantification of the severity of postural tremor based on kinematic parameters: A multi-sensory fusion study. (June 2022)

• Record Type: Journal Article
• Authors: Ma, Chenbin; Zhang, Peng; Wang, Jiachen; Zhang, Jian; Pan, Longsheng; Li, Xuemei; Yin, Chunyu; Li, Ailing; Zong, Rui; Zhang, Zhengbo
• Is Part Of: Computer methods and programs in biomedicine. Volume 219(2022)
• Publication Date: 2022-06
• Subjects: Essential tremor -- Wearable sensor -- Multi-sensory fusion -- Rating of Severity -- Machine learning; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2022.106741
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: Building the first database of three types of postural tremors in patients with essential tremors. It used wearable devices that integrate high-dimensional information under laboratory examination. These model labels combined consensus scores used for supervised learning through independent scoring by three neural experts. Combining multi-sensory fusion features to build multiple machine learning models and perform comprehensive performance evaluation. This experiment's optimal ensemble model provides state-of-the-art results for five classifications of tremor severity. Abstract: Background: Current clinical assessments of essential tremor (ET) are primarily based on expert consultation combined with reviewing patient complaints, physician expertise, and diagnostic experience. Thus, traditional evaluation methods often lead to biased diagnostic results. There is a clinical demand for a method that can objectively quantify the severity of the patient's disease. Methods: This study aims to develop an artificial intelligence-aided diagnosis method based on multi-sensory fusion wearables. The experiment relies on a rigorous clinical trial paradigm to collect multi-modal fusion of signals from 98 ET patients. At the same time, three clinicians scored independently, and the consensus score obtained was used as the ground truth for the machine learning models. Results: Sixty kinematic parameters were extracted from the signals recorded by the nine-axis inertial measurement unit (IMU). The results showed that most of the features obtained by IMU could effectively characterize the severity of the tremors. The accuracy of the optimal model for three tasks classifying five severity levels was 97.71%, 97.54%, and 97.72%, respectively. Conclusions: This paper reports the first attempt to combine multiple feature selection and machine learning algorithms for fine-grained automatic quantification of postural tremor in ET patients. The promising results showed the potential of the proposed approach to quantify the severity of ET objectively.