Matches in SemOpenAlex for { <https://semopenalex.org/work/W4381301343> ?p ?o ?g. }
Showing items 1 to 57 of
57
with 100 items per page.
- W4381301343 endingPage "481" @default.
- W4381301343 startingPage "469" @default.
- W4381301343 abstract "In the last decade, many AI-based CAD models were developed which hardly could convince the high-stake decision makers to accept the machine-specified decisions. In this research work, it was attempted to unbox a supervised AI model built using XGBoost on lung cancer detection by using XAI tools—two post-hoc methods (LIME and SHAP) and one ante-hoc method, to provide satisfactory explanations to medical practitioners, thereby minimize the AI risk factor in implementation of the model and reinforce the trust to the medical experts and patients in accepting such model. In this paper, the results of all three XAI tools were illustrated using heat maps to select important input biomarkers that contributed more in detection of the benign or malignancy state of the pulmonary nodules. Finally, the supervised AI model was rebuilt using only those important input features and it was found out that the metrics like specificity, precision and the AUC of the newer model under the ROC curve were giving better results in prediction of the detection of lung cancer. It is a study to explore how XAI tools highlight the contributions of input features in a CAD AI model for the prediction of lung cancer detection and how that AI model’s performance can be fine-tuned based on the outputs of XAI methods." @default.
- W4381301343 created "2023-06-21" @default.
- W4381301343 creator A5054981700 @default.
- W4381301343 creator A5069823069 @default.
- W4381301343 date "2023-01-01" @default.
- W4381301343 modified "2023-09-23" @default.
- W4381301343 title "Explainable AI Model to Minimize AI Risk and Maximize Trust in Malignancy Detection of the Pulmonary Nodules" @default.
- W4381301343 cites W2282821441 @default.
- W4381301343 cites W2295107390 @default.
- W4381301343 cites W2962858109 @default.
- W4381301343 cites W2980895398 @default.
- W4381301343 cites W2982109562 @default.
- W4381301343 cites W3036319923 @default.
- W4381301343 cites W4200596050 @default.
- W4381301343 doi "https://doi.org/10.1007/978-981-99-0085-5_38" @default.
- W4381301343 hasPublicationYear "2023" @default.
- W4381301343 type Work @default.
- W4381301343 citedByCount "0" @default.
- W4381301343 crossrefType "book-chapter" @default.
- W4381301343 hasAuthorship W4381301343A5054981700 @default.
- W4381301343 hasAuthorship W4381301343A5069823069 @default.
- W4381301343 hasConcept C119857082 @default.
- W4381301343 hasConcept C127413603 @default.
- W4381301343 hasConcept C142724271 @default.
- W4381301343 hasConcept C154945302 @default.
- W4381301343 hasConcept C194789388 @default.
- W4381301343 hasConcept C199639397 @default.
- W4381301343 hasConcept C2779399171 @default.
- W4381301343 hasConcept C41008148 @default.
- W4381301343 hasConcept C71924100 @default.
- W4381301343 hasConceptScore W4381301343C119857082 @default.
- W4381301343 hasConceptScore W4381301343C127413603 @default.
- W4381301343 hasConceptScore W4381301343C142724271 @default.
- W4381301343 hasConceptScore W4381301343C154945302 @default.
- W4381301343 hasConceptScore W4381301343C194789388 @default.
- W4381301343 hasConceptScore W4381301343C199639397 @default.
- W4381301343 hasConceptScore W4381301343C2779399171 @default.
- W4381301343 hasConceptScore W4381301343C41008148 @default.
- W4381301343 hasConceptScore W4381301343C71924100 @default.
- W4381301343 hasLocation W43813013431 @default.
- W4381301343 hasOpenAccess W4381301343 @default.
- W4381301343 hasPrimaryLocation W43813013431 @default.
- W4381301343 hasRelatedWork W2961085424 @default.
- W4381301343 hasRelatedWork W3046775127 @default.
- W4381301343 hasRelatedWork W3170094116 @default.
- W4381301343 hasRelatedWork W3209574120 @default.
- W4381301343 hasRelatedWork W4205958290 @default.
- W4381301343 hasRelatedWork W4285260836 @default.
- W4381301343 hasRelatedWork W4286629047 @default.
- W4381301343 hasRelatedWork W4306321456 @default.
- W4381301343 hasRelatedWork W4306674287 @default.
- W4381301343 hasRelatedWork W4224009465 @default.
- W4381301343 isParatext "false" @default.
- W4381301343 isRetracted "false" @default.
- W4381301343 workType "book-chapter" @default.