Knee joint osteoarthritis diagnosis based on selected acoustic signal discriminants using machine learning
Artykuł w czasopiśmie
MNiSW
70
Lista 2021
| Status: | |
| Autorzy: | Karpiński Robert |
| Dyscypliny: | |
| Aby zobaczyć szczegóły należy się zalogować. | |
| Rok wydania: | 2022 |
| Wersja dokumentu: | Elektroniczna |
| Język: | angielski |
| Numer czasopisma: | 2 |
| Wolumen/Tom: | 18 |
| Strony: | 71 - 85 |
| Scopus® Cytowania: | 21 |
| Bazy: | Scopus |
| Efekt badań statutowych | NIE |
| Materiał konferencyjny: | NIE |
| Publikacja OA: | TAK |
| Licencja: | |
| Sposób udostępnienia: | Otwarte czasopismo |
| Wersja tekstu: | Ostateczna wersja opublikowana |
| Czas opublikowania: | W momencie opublikowania |
| Data opublikowania w OA: | 27 czerwca 2022 |
| Abstrakty: | angielski |
| This paper presents the results of a preliminary study on simplified diagnosis of osteo- arthritis of the knee joint based on generated vibroacoustic processes. The analysis was based on acoustic signals recorded in a group of 50 people, half of whom were healthy, and the other half – people with previously confirmed degenerative changes. Selected discriminants of the signals were determined and statistical analysis was performed to allow selection of optimal discriminants used at a later stage as input to the classifier. The best results of classification using artificial neural networks (ANN) of RBF (Radial Basis Function) and MLP (Multilevel Perceptron) types are presented. For the problem involving the classification of cases into one of two groups HC (Healthy Control) and OA (Osteoarthritis) an accuracy of 0.9 was obtained, with a sensitivity of 0.885 and a specificity of 0.917. It is shown that vibroacoustic diagnostics has great potential in the non-invasive assessment of damage to joint structures of the knee. |
