Human Activity Recognition for People with Knee Osteoarthritis-A Proof-of-Concept

Abstract

Clinicians lack objective means for monitoring if their knee osteoarthritis patients are improving outside of the clinic (e.g., at home). Previous human activity recognition (HAR) models using wearable sensor data have only used data from healthy people and such models are typically imprecise for people who have medical conditions affecting movement. HAR models designed for people with knee osteoarthritis have classified rehabilitation exercises but not the clinically relevant activities of transitioning from a chair, negotiating stairs and walking, which are commonly monitored for improvement during therapy for this condition. Therefore, it is unknown if a HAR model trained on data from people who have knee osteoarthritis can be accurate in classifying these three clinically relevant activities. Therefore, we collected inertial measurement unit (IMU) data from 18 participants with knee osteoarthritis and trained convolutional neural network models to identify chair, stairs and walking activities, and phases. The model accuracy was 85% at the first level of classification (activity), 89-97% at the second (direction of movement) and 60-67% at the third level (phase). This study is the first proof-of-concept that an accurate HAR system can be developed using IMU data from people with knee osteoarthritis to classify activities and phases of activities.

Keywords: human activity recognition; inertial measurement units; knee osteoarthritis; machine learning; physical activity monitoring.

Figure 1

Placement of IMUs (purple) used for training the CNN models and Vicon marker (blue) placement for recording start and end times for each trial.

Figure 2

Architecture of the proposed human activity recognition system.

Figure 3

Visual representation of Level 1 activity ‘image’ patterns.

Figure 4

Decision tree for three levels of activity classification—Level 1 Activity, Level 2 Direction, Level 3 Phase.

Figure 5

Illustration of the segmented window sliding in 10 ms increments for each level of classification. Level 1—200 ms; Level 2—100 ms; Level 3—40 ms.

Figure 6

Confusion matrices for classification of activities/phases per classification level. Green cells represent correct classification and arrows represent the classification pathway from activities to phases of activities.