PrimSeq: a deep learning-based pipeline to quantitate rehabilitation training

TL;DR

PrimSeq is a novel deep learning pipeline that accurately classifies and counts functional motions in stroke rehabilitation using wearable sensors, enabling efficient measurement of training content and quantity.

Contribution

This work introduces PrimSeq, the first practical tool combining wearable sensors and deep learning to quantify rehabilitation motions, facilitating quantitative dosing in stroke therapy.

Findings

PrimSeq outperforms existing machine learning methods in classifying motions.

It accurately quantifies motions with less time and labor than human experts.

Demonstrated effectiveness on unseen stroke patients with various impairments.

Abstract

Stroke rehabilitation seeks to increase neuroplasticity through the repeated practice of functional motions, but may have minimal impact on recovery because of insufficient repetitions. The optimal training content and quantity are currently unknown because no practical tools exist to measure them. Here, we present PrimSeq, a pipeline to classify and count functional motions trained in stroke rehabilitation. Our approach integrates wearable sensors to capture upper-body motion, a deep learning model to predict motion sequences, and an algorithm to tally motions. The trained model accurately decomposes rehabilitation activities into component functional motions, outperforming competitive machine learning methods. PrimSeq furthermore quantifies these motions at a fraction of the time and labor costs of human experts. We demonstrate the capabilities of PrimSeq in previously unseen stroke patients with a range of upper extremity motor impairment. We expect that these advances will support the rigorous measurement required for quantitative dosing trials in stroke rehabilitation.