Matches in SemOpenAlex for { <https://semopenalex.org/work/W3054397274> ?p ?o ?g. }
- W3054397274 abstract "Machine learning (ML) is increasingly used to support decision-making in the healthcare sector. While ML approaches provide promising results with regard to their classification performance, most share a central limitation, namely their black-box character. Motivated by the interest to understand the functioning of ML models, methods from the field of Explainable Artificial Intelligence (XAI) have recently become important. This article investigates the usefulness of XAI methods in clinical gait classification. For this purpose, predictions of state-of-the-art classification methods are explained with an established XAI method, i.e., Layer-wise Relevance Propagation (LRP). We propose to evaluate the obtained explanations with two complementary approaches: a statistical analysis of the underlying data using Statistical Parametric Mapping and a qualitative evaluation by a clinical expert. A gait dataset comprising ground reaction force measurements from 132 patients with different lower-body gait disorders and 62 healthy controls is utilized. We investigate several gait classification tasks, employ multiple classification methods, and analyze the impact of data normalization and different signal components for classification performance and explanation quality. Our experiments show that explanations obtained by LRP exhibit promising statistical properties concerning inter-class discriminativity and are also in line with clinically relevant biomechanical gait characteristics." @default.
- W3054397274 created "2020-08-24" @default.
- W3054397274 creator A5006306235 @default.
- W3054397274 creator A5016465792 @default.
- W3054397274 creator A5017608155 @default.
- W3054397274 creator A5026451495 @default.
- W3054397274 creator A5052704769 @default.
- W3054397274 creator A5055814440 @default.
- W3054397274 creator A5060926433 @default.
- W3054397274 creator A5081508168 @default.
- W3054397274 creator A5081850574 @default.
- W3054397274 date "2020-08-19" @default.
- W3054397274 modified "2023-10-18" @default.
- W3054397274 title "On the Explanation of Machine Learning Predictions in Clinical Gait Analysis" @default.
- W3054397274 cites W1504118426 @default.
- W3054397274 cites W1787224781 @default.
- W3054397274 cites W1906985535 @default.
- W3054397274 cites W1997022053 @default.
- W3054397274 cites W2005230922 @default.
- W3054397274 cites W2031240554 @default.
- W3054397274 cites W2051552261 @default.
- W3054397274 cites W2062156755 @default.
- W3054397274 cites W2073790636 @default.
- W3054397274 cites W2077228124 @default.
- W3054397274 cites W2083231156 @default.
- W3054397274 cites W2084347472 @default.
- W3054397274 cites W2089563340 @default.
- W3054397274 cites W2109943925 @default.
- W3054397274 cites W2150165932 @default.
- W3054397274 cites W2161843739 @default.
- W3054397274 cites W2187089797 @default.
- W3054397274 cites W2240067561 @default.
- W3054397274 cites W2332488709 @default.
- W3054397274 cites W2420245003 @default.
- W3054397274 cites W2546344052 @default.
- W3054397274 cites W2581082771 @default.
- W3054397274 cites W2590082389 @default.
- W3054397274 cites W2591954064 @default.
- W3054397274 cites W2605409611 @default.
- W3054397274 cites W2618851150 @default.
- W3054397274 cites W2657631929 @default.
- W3054397274 cites W2736217281 @default.
- W3054397274 cites W2738293192 @default.
- W3054397274 cites W2778796877 @default.
- W3054397274 cites W2784570262 @default.
- W3054397274 cites W2786497292 @default.
- W3054397274 cites W2799793144 @default.
- W3054397274 cites W2806853752 @default.
- W3054397274 cites W2847270913 @default.
- W3054397274 cites W2887949497 @default.
- W3054397274 cites W2891489434 @default.
- W3054397274 cites W2891503716 @default.
- W3054397274 cites W2891612330 @default.
- W3054397274 cites W2906295032 @default.
- W3054397274 cites W2908201961 @default.
- W3054397274 cites W2914484425 @default.
- W3054397274 cites W2927351257 @default.
- W3054397274 cites W2953012738 @default.
- W3054397274 cites W2958089299 @default.
- W3054397274 cites W2962851944 @default.
- W3054397274 cites W2963464195 @default.
- W3054397274 cites W2972059645 @default.
- W3054397274 cites W2973136764 @default.
- W3054397274 cites W2981565374 @default.
- W3054397274 cites W2989553303 @default.
- W3054397274 cites W2998175747 @default.
- W3054397274 cites W3012234327 @default.
- W3054397274 cites W3016748229 @default.
- W3054397274 cites W3025598645 @default.
- W3054397274 cites W3101609372 @default.
- W3054397274 cites W3121556506 @default.
- W3054397274 cites W3204445786 @default.
- W3054397274 hasPublicationYear "2020" @default.
- W3054397274 type Work @default.
- W3054397274 sameAs 3054397274 @default.
- W3054397274 citedByCount "2" @default.
- W3054397274 countsByYear W30543972742021 @default.
- W3054397274 crossrefType "posted-content" @default.
- W3054397274 hasAuthorship W3054397274A5006306235 @default.
- W3054397274 hasAuthorship W3054397274A5016465792 @default.
- W3054397274 hasAuthorship W3054397274A5017608155 @default.
- W3054397274 hasAuthorship W3054397274A5026451495 @default.
- W3054397274 hasAuthorship W3054397274A5052704769 @default.
- W3054397274 hasAuthorship W3054397274A5055814440 @default.
- W3054397274 hasAuthorship W3054397274A5060926433 @default.
- W3054397274 hasAuthorship W3054397274A5081508168 @default.
- W3054397274 hasAuthorship W3054397274A5081850574 @default.
- W3054397274 hasConcept C102366305 @default.
- W3054397274 hasConcept C105795698 @default.
- W3054397274 hasConcept C117251300 @default.
- W3054397274 hasConcept C119857082 @default.
- W3054397274 hasConcept C121332964 @default.
- W3054397274 hasConcept C136886441 @default.
- W3054397274 hasConcept C144024400 @default.
- W3054397274 hasConcept C151800584 @default.
- W3054397274 hasConcept C153180895 @default.
- W3054397274 hasConcept C154945302 @default.
- W3054397274 hasConcept C158154518 @default.
- W3054397274 hasConcept C173906292 @default.
- W3054397274 hasConcept C17744445 @default.