Matches in SemOpenAlex for { <https://semopenalex.org/work/W4297267135> ?p ?o ?g. }
- W4297267135 endingPage "104144" @default.
- W4297267135 startingPage "104144" @default.
- W4297267135 abstract "The application of Artificial Intelligence (AI) on cancer drug recommendation can prompt the development of personalized cancer therapy. However, most of the current AI drug recommendations cannot give explainable inferences, where their prediction procedures are black boxes, and are difficult to earn the trust of doctors or patients. In explainable inference, the key steps during the recommendation procedures can be located easily, facilitating model adjustment for wrong predictions and model generalization for new drugs/samples. In this paper, we analyze the necessity of developing explainable AI drug recommendation, and propose an evaluation metric called traceability rate. The traceability rate is calculated as the proportion of correct predictions that are traceable along the knowledge graph in all the ground truths. We further conduct an experiment on a benchmark drug response dataset to apply the traceability rate as evaluation metric, where the results show a trade-off between model performance and explainability. Therefore, the explainable AI drug recommendation still demands for further improvement to meet the requirement of clinical personalized therapy." @default.
- W4297267135 created "2022-09-28" @default.
- W4297267135 creator A5006085047 @default.
- W4297267135 creator A5010582306 @default.
- W4297267135 creator A5058380236 @default.
- W4297267135 creator A5060178337 @default.
- W4297267135 creator A5066148256 @default.
- W4297267135 date "2023-01-01" @default.
- W4297267135 modified "2023-10-10" @default.
- W4297267135 title "Cancer omic data based explainable AI drug recommendation inference: A traceability perspective for explainability" @default.
- W4297267135 cites W2043398720 @default.
- W4297267135 cites W2046711245 @default.
- W4297267135 cites W2108068107 @default.
- W4297267135 cites W2108933868 @default.
- W4297267135 cites W2117513900 @default.
- W4297267135 cites W2120204563 @default.
- W4297267135 cites W2197241765 @default.
- W4297267135 cites W2328260251 @default.
- W4297267135 cites W2382467334 @default.
- W4297267135 cites W2432718434 @default.
- W4297267135 cites W2461427403 @default.
- W4297267135 cites W2584535601 @default.
- W4297267135 cites W2763729702 @default.
- W4297267135 cites W2772158850 @default.
- W4297267135 cites W2792791113 @default.
- W4297267135 cites W2800484633 @default.
- W4297267135 cites W2891837572 @default.
- W4297267135 cites W2893531376 @default.
- W4297267135 cites W2895035285 @default.
- W4297267135 cites W2896725104 @default.
- W4297267135 cites W2904448411 @default.
- W4297267135 cites W2905483812 @default.
- W4297267135 cites W2913240367 @default.
- W4297267135 cites W2946834067 @default.
- W4297267135 cites W2950063908 @default.
- W4297267135 cites W2958089299 @default.
- W4297267135 cites W2972535098 @default.
- W4297267135 cites W2981731882 @default.
- W4297267135 cites W2995175648 @default.
- W4297267135 cites W2995523160 @default.
- W4297267135 cites W2999615587 @default.
- W4297267135 cites W3000469142 @default.
- W4297267135 cites W3001022866 @default.
- W4297267135 cites W3005380244 @default.
- W4297267135 cites W3008395627 @default.
- W4297267135 cites W3037814715 @default.
- W4297267135 cites W3041880399 @default.
- W4297267135 cites W3044083352 @default.
- W4297267135 cites W3048469615 @default.
- W4297267135 cites W3089488726 @default.
- W4297267135 cites W3099726771 @default.
- W4297267135 cites W3109060525 @default.
- W4297267135 cites W3165195325 @default.
- W4297267135 cites W3171986076 @default.
- W4297267135 cites W3181468676 @default.
- W4297267135 cites W3188005850 @default.
- W4297267135 cites W3200428569 @default.
- W4297267135 cites W3202807692 @default.
- W4297267135 cites W4200265636 @default.
- W4297267135 doi "https://doi.org/10.1016/j.bspc.2022.104144" @default.
- W4297267135 hasPublicationYear "2023" @default.
- W4297267135 type Work @default.
- W4297267135 citedByCount "8" @default.
- W4297267135 countsByYear W42972671352023 @default.
- W4297267135 crossrefType "journal-article" @default.
- W4297267135 hasAuthorship W4297267135A5006085047 @default.
- W4297267135 hasAuthorship W4297267135A5010582306 @default.
- W4297267135 hasAuthorship W4297267135A5058380236 @default.
- W4297267135 hasAuthorship W4297267135A5060178337 @default.
- W4297267135 hasAuthorship W4297267135A5066148256 @default.
- W4297267135 hasConcept C115903868 @default.
- W4297267135 hasConcept C119857082 @default.
- W4297267135 hasConcept C124101348 @default.
- W4297267135 hasConcept C13280743 @default.
- W4297267135 hasConcept C134306372 @default.
- W4297267135 hasConcept C153876917 @default.
- W4297267135 hasConcept C154945302 @default.
- W4297267135 hasConcept C162324750 @default.
- W4297267135 hasConcept C176217482 @default.
- W4297267135 hasConcept C177148314 @default.
- W4297267135 hasConcept C185798385 @default.
- W4297267135 hasConcept C205649164 @default.
- W4297267135 hasConcept C21547014 @default.
- W4297267135 hasConcept C2776214188 @default.
- W4297267135 hasConcept C33923547 @default.
- W4297267135 hasConcept C41008148 @default.
- W4297267135 hasConceptScore W4297267135C115903868 @default.
- W4297267135 hasConceptScore W4297267135C119857082 @default.
- W4297267135 hasConceptScore W4297267135C124101348 @default.
- W4297267135 hasConceptScore W4297267135C13280743 @default.
- W4297267135 hasConceptScore W4297267135C134306372 @default.
- W4297267135 hasConceptScore W4297267135C153876917 @default.
- W4297267135 hasConceptScore W4297267135C154945302 @default.
- W4297267135 hasConceptScore W4297267135C162324750 @default.
- W4297267135 hasConceptScore W4297267135C176217482 @default.
- W4297267135 hasConceptScore W4297267135C177148314 @default.
- W4297267135 hasConceptScore W4297267135C185798385 @default.
- W4297267135 hasConceptScore W4297267135C205649164 @default.