Designing compact features for remote stroke rehabilitation monitoring using wearable accelerometers

Abstract

Stroke is known as a major global health problem, and for stroke survivors it is key to monitor the recovery levels. However, traditional stroke rehabilitation assessment methods (such as the popular clinical assessment) can be subjective and expensive, and it is also less convenient for patients to visit clinics in a high frequency. To address this issue, in this work based on wearable sensing and machine learning techniques, we develop an automated system that can predict the assessment score in an objective manner. With wrist-worn sensors, accelerometer data is collected from 59 stroke survivors in free-living environments for a duration of 8 weeks, and we map the week-wise accelerometer data (3 days per week) to the assessment score by developing signal processing and predictive model pipeline. To achieve this, we propose two types of new features, which can encode the rehabilitation information from both paralysed and non-paralysed sides while suppressing the high-level noises such as irrelevant daily activities. Based on the proposed features, we further develop the longitudinal mixed-effects model with Gaussian process prior (LMGP), which can model the random effects caused by different subjects and time slots (during the 8 weeks). Comprehensive experiments are conducted to evaluate our system on both acute and chronic patients, and the promising results suggest its effectiveness.

Automatic Post-Stroke Severity Assessment Using Novel Unsupervised Consensus Learning for Wearable and Camera-Based Sensor Datasets

“…Supervised learning predicts severity levels by developing various connections between patient attributes and the effects of interest, which have been investigated the most within the literature [ 46 , 47 ]. The studies developed on the automated assessment of the motor function of the upper extremity are divided into three types, including those on activity recognition [ 15 , 16 , 17 , 18 , 19 , 20 , 21 , 22 , 23 ], measurement classification [ 3 , 24 , 25 , 26 , 27 , 28 , 29 , 30 , 31 , 32 , 33 , 34 ], and clinical assessment simulation [ 1 , 35 , 36 , 37 , 38 , 39 , 40 , 41 , 42 , 43 ]. Additionally, the assessments have been utilized by employing various sensors.…”

“…Additionally, the assessments have been utilized by employing various sensors. Wearable sensor-based systems are greatly used (such as IMUs or accelerometers [ 15 , 16 , 17 , 18 , 19 , 20 , 21 , 22 , 23 ], barometers [ 48 , 49 ], Flex sensors [ 21 ], EMG sensors [ 24 , 25 ], pressure sensors, etc.) [ 21 , 26 , 27 , 28 , 29 , 30 , 31 , 32 ], as are camera-based systems [ 5 , 33 , 34 , 35 , 36 ], to automate the stroke assessment test by reducing barriers and the obligations of experts or physiotherapists [ 1 ].…”

“…The summary of the work conducted using wearable sensors is presented in Table 1 . In the literature, the assessment type has been investigated based on three categories: clinical emulation [ 1 , 19 , 20 , 21 , 22 , 23 , 30 , 38 , 39 , 40 ], movement classification [ 3 , 17 , 18 , 25 , 41 , 42 , 43 , 50 , 51 , 52 , 53 , 54 ], and activity recognition [ 15 , 16 , 24 , 44 , 48 , 49 , 55 , 56 , 57 , 58 , 59 ]. As this study focused on clinical emulation, Table 1 describes only the summary of this category.…”

“…Several studies deployed individual accelerometers [ 19 , 20 , 22 , 37 ], and some studies combined IMUs with different sensors such as flex sensors [ 60 , 61 ]. While some studies used healthy participants [ 20 , 54 , 62 ], others used stroke patients as participants [ 1 , 22 , 23 , 38 , 39 , 40 ]. Support Vector regression (SVR) was the most used classifier [ 21 , 22 , 40 ]; this was primarily used in regression problems for clinical assessments where participants were given clinical scores [ 1 , 19 , 20 , 21 , 22 , 30 , 37 , 38 , 40 ].…”

“…MEMS motion sensors are utilized to develop a sensor fusion structure [ 14 ]. There are several studies focused on using wearable sensors and camera-based systems applying machine learning technology for activity recognition [ 15 , 16 , 17 , 18 , 19 , 20 , 21 , 22 , 23 ] measurement classification [ 24 , 25 , 26 , 27 , 28 , 29 , 30 , 31 , 32 , 33 , 34 ], and clinical assessment simulation [ 35 , 36 , 37 , 38 , 39 , 40 , 41 , 42 , 43 ]. However, the main machine learning technique primarily uses supervised learning to automatically predict assessment scores.…”