Acoustic Analysis and Assessment of the Knee in Osteoarthritis During Walking

Yiallourides, Costas; Moore, Alastair H.; Auvinet, Edouard; Straeten, Catherine Van Der; Naylor, Patrick A.

doi:10.1109/icassp.2018.8461622

Cited by 2 publications

(3 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, these observations highlight the importance of the spectrum features that fall within the two identified bands of frequencies and show that these features have a strong impact on the classification performance. In the analysis of our previous work, [35], it was observed that the top performing features obtained from the magnitude spectrum are primarily at the low frequencies. This is further supported here where we have also identified specific bands that carry significantly discriminant information.…”

Section: B Data Acquisition and Test Protocolmentioning

confidence: 95%

“…Table II reports the frame length value that gave the highest AUC per feature set, found using SVM l . A corresponding score, S c , computed as S c = MCC + (1 − E r ) + F 0.5 /3, [35], is also used and consists of the MCC and F 0.5 measures which capture different attributes of the classification result than the AUC and would therefore be useful in the analysis. S c can vary between 0 and 1 (where S c = 1 indicates perfect prediction).…”

Section: Local Search In the Vicinity Of The Best Frame Lengthmentioning

confidence: 99%

“…In particular, discriminative features are sought that are relevant to the analysis and classification of normal (clinically healthy) and abnormal (clinically OA) knee joints. A preliminary version of this work was presented in [35]. Here this work is extended to consider time-frequency representations of the knee acoustic signals as features and examine their discriminatory power.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Time-Frequency Analysis and Parameterisation of Knee Sounds for Non-Invasive Detection of Osteoarthritis

Yiallourides

Naylor

2021

IEEE Trans. Biomed. Eng.

Self Cite

View full text Add to dashboard Cite

In this work the potential of non-invasive detection of knee osteoarthritis is investigated using the sounds generated by the knee joint during walking. Methods: The information contained in the time-frequency domain of these signals and its compressed representations is exploited and their discriminant properties are studied. Their efficacy for the task of normal vs abnormal signal classification is evaluated using a comprehensive experimental framework. Based on this, the impact of the feature extraction parameters on the classification performance is investigated using Classification and Regression Trees, Linear Discriminant Analysis and Support Vector Machine classifiers. Results: It is shown that classification is successful with an area under the Receiver Operating Characteristic curve of 0.92. Conclusion: The analysis indicates improvements in classification performance when using non-uniform frequency scaling and identifies specific frequency bands that contain discriminative features. Significance: Contrary to other studies that focus on sitto-stand movements and knee flexion/extension, this study used knee sounds obtained during walking. The analysis of such signals leads to non-invasive detection of knee osteoarthritis with high accuracy and could potentially extend the range of available tools for the assessment of the disease as a more practical and cost effective method without requiring clinical setups.

show abstract

Section: B Data Acquisition and Test Protocolmentioning

confidence: 95%

Section: Local Search In the Vicinity Of The Best Frame Lengthmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Time-Frequency Analysis and Parameterisation of Knee Sounds for Non-Invasive Detection of Osteoarthritis

Yiallourides

Naylor

2021

IEEE Trans. Biomed. Eng.

Self Cite

View full text Add to dashboard Cite

show abstract

Osteoarthritis Disease Prediction Based on Machine Learning Techniques

Sathya,

Parthiban,

Megavarshini

et al. 2024

Enhancing Medical Imaging With Emerging Technologies

View full text Add to dashboard Cite

The most typical type of arthritis is osteoarthritis. Osteoarthritis is a degenerative joint disease affecting millions of people worldwide. It usually affects the hands, hips, and knees. People with osteoarthritis struggle to perform simple tasks such as walking, standing, or climbing stairs. In osteoarthritis, a joint's cartilage starts to degrade, and the underlying bone starts to alter. One of the main causes of disability and a prevalent disease of the elderly population is osteoarthritis. Moreover, because of the persistent pain and impairment brought on by the condition, osteoarthritis can also result in psychological distress, such as sorrow and anxiety. The advanced deep learning-based convolutional neural network and several machine learning-based techniques are applied in comparison. Using the random forest method, this chapter divides osteoarthritis disease into four categories of severity: Grade-0, Grade-1, Grade-2, Grade-3, Grade-4. Extensive experiments demonstrate that the proposed model outperformed with a 99% accuracy score for predicting osteoarthritis.

show abstract

Acoustic Analysis and Assessment of the Knee in Osteoarthritis During Walking

Cited by 2 publications

References 19 publications

Time-Frequency Analysis and Parameterisation of Knee Sounds for Non-Invasive Detection of Osteoarthritis

Time-Frequency Analysis and Parameterisation of Knee Sounds for Non-Invasive Detection of Osteoarthritis

Osteoarthritis Disease Prediction Based on Machine Learning Techniques

Contact Info

Product

Resources

About