Key result
A longitudinal mixed-effects model with Gaussian process prior using wrist-worn accelerometer data predicted clinical stroke rehabilitation scores with an RMSE of 5.75 for acute patients and 3.12 for chronic patients.
Why the study?
Traditional stroke rehabilitation assessment methods can be subjective, expensive, and inconvenient due to the need for frequent clinic visits.
Does an automated system using wearable accelerometers and a longitudinal mixed-effects model accurately predict clinical rehabilitation assessment scores in stroke survivors?
Observational (n=59)
Does an automated system using wearable accelerometers and a longitudinal mixed-effects model accurately predict clinical rehabilitation assessment scores in stroke survivors?
An automated system using wrist-worn accelerometers and a longitudinal mixed-effects model can objectively monitor stroke rehabilitation by predicting clinical assessment scores in free-living environments.
May support remote monitoring of stroke rehab; hypothesis-generating and requires prospective validation before practice change.
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.
No takes yet. Share an insight, caveat, or question.
Chen et al. (2023) conducted an observational in Stroke (n=59). Wrist-worn accelerometer monitoring and LMGP predictive modeling vs. Linear fixed-effects model was evaluated on Root mean square error (RMSE) of predicted CAHAI score. A longitudinal mixed-effects model with Gaussian process prior using wrist-worn accelerometer data predicted clinical stroke rehabilitation scores with an RMSE of 5.75 for acute patients and 3.12 for chronic patients.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: