OBJECTIVE: Recording of knee vibroarthrographic (VAG) activity during activities of daily living (ADL) can contribute to diagnose knee osteoarthritis (KOA). However, classifying KOA patients based on knee VAG during ADL has been an elusive problem not related to knee pain. Therefore, the aims of this study was to classify KOA patients based on (1) VAG during ADL and (2) knee pain sensitivity and then compare their results. APPROACH: The experimental procedure consisted of the recording of VAG signals during four ADLs (over-ground gait, stairs descent, stairs ascent and sit-to-stand) from eight patellar and peri-patellar locations in 20 KOA and 20 asymptomatic participants. Pressure pain thresholds (PPT) were obtained from eight locations around the knee joint to quantify pain sensitivity. A random forest classifier was utilized to identify KOA patients based on VAG signal features and PPTs. The most important features contributing to the classification accuracy were determined. The KOA patients participated in a second identical experimental session to examine the day-to-day reproducibility. MAIN RESULTS: The participants were classified with accuracy of 90%, 70%, 64% and 82% during over-ground gait, stairs descent, stairs ascent and sit to stand, respectively. However, the accuracy of the classifier was reduced by about 10%-25% due to a systematic bias in the extracted features across days. Features of the VAG signals in time and frequency domains as well as nonlinear features were found importantly contributing towards the classification accuracy. The VAG features extracted from the lateral side of the knee was found to be more informative than other locations. The classification based on PPT reached 77%. Medial and proximal knee PPT points contributed to the classification accuracy. SIGNIFICANCE: This study showed that using multichannel VAG signals to identify KOA patients allows better accuracy than the use of PPTs. However, VAG setup must be standardized to avoid day-to-day bias.
OBJECTIVE: Recording of knee vibroarthrographic (VAG) activity during activities of daily living (ADL) can contribute to diagnose knee osteoarthritis (KOA). However, classifying KOA patients based on knee VAG during ADL has been an elusive problem not related to knee pain. Therefore, the aims of this study was to classify KOA patients based on (1) VAG during ADL and (2) knee pain sensitivity and then compare their results. APPROACH: The experimental procedure consisted of the recording of VAG signals during four ADLs (over-ground gait, stairs descent, stairs ascent and sit-to-stand) from eight patellar and peri-patellar locations in 20 KOA and 20 asymptomatic participants. Pressure pain thresholds (PPT) were obtained from eight locations around the knee joint to quantify pain sensitivity. A random forest classifier was utilized to identify KOA patients based on VAG signal features and PPTs. The most important features contributing to the classification accuracy were determined. The KOA patients participated in a second identical experimental session to examine the day-to-day reproducibility. MAIN RESULTS: The participants were classified with accuracy of 90%, 70%, 64% and 82% during over-ground gait, stairs descent, stairs ascent and sit to stand, respectively. However, the accuracy of the classifier was reduced by about 10%-25% due to a systematic bias in the extracted features across days. Features of the VAG signals in time and frequency domains as well as nonlinear features were found importantly contributing towards the classification accuracy. The VAG features extracted from the lateral side of the knee was found to be more informative than other locations. The classification based on PPT reached 77%. Medial and proximal knee PPT points contributed to the classification accuracy. SIGNIFICANCE: This study showed that using multichannel VAG signals to identify KOA patients allows better accuracy than the use of PPTs. However, VAG setup must be standardized to avoid day-to-day bias.