FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385302721> ?p ?o ?g. }

• W4385302721 endingPage "1946" @default.
• W4385302721 startingPage "1941" @default.
• W4385302721 abstract "Abstract We investigated whether human preferences hold the potential to improve diagnostic artificial intelligence (AI)-based decision support using skin cancer diagnosis as a use case. We utilized nonuniform rewards and penalties based on expert-generated tables, balancing the benefits and harms of various diagnostic errors, which were applied using reinforcement learning. Compared with supervised learning, the reinforcement learning model improved the sensitivity for melanoma from 61.4% to 79.5% (95% confidence interval (CI): 73.5–85.6%) and for basal cell carcinoma from 79.4% to 87.1% (95% CI: 80.3–93.9%). AI overconfidence was also reduced while simultaneously maintaining accuracy. Reinforcement learning increased the rate of correct diagnoses made by dermatologists by 12.0% (95% CI: 8.8–15.1%) and improved the rate of optimal management decisions from 57.4% to 65.3% (95% CI: 61.7–68.9%). We further demonstrated that the reward-adjusted reinforcement learning model and a threshold-based model outperformed naïve supervised learning in various clinical scenarios. Our findings suggest the potential for incorporating human preferences into image-based diagnostic algorithms." @default.
• W4385302721 created "2023-07-28" @default.
• W4385302721 creator A5000215116 @default.
• W4385302721 creator A5004712523 @default.
• W4385302721 creator A5011182804 @default.
• W4385302721 creator A5011768850 @default.
• W4385302721 creator A5018897159 @default.
• W4385302721 creator A5033462323 @default.
• W4385302721 creator A5035102732 @default.
• W4385302721 creator A5050063952 @default.
• W4385302721 creator A5056955219 @default.
• W4385302721 creator A5071595948 @default.
• W4385302721 creator A5071822275 @default.
• W4385302721 creator A5072653864 @default.
• W4385302721 creator A5073027533 @default.
• W4385302721 creator A5079760997 @default.
• W4385302721 creator A5083011959 @default.
• W4385302721 creator A5085409073 @default.
• W4385302721 creator A5086926559 @default.
• W4385302721 date "2023-07-27" @default.
• W4385302721 modified "2023-10-09" @default.
• W4385302721 title "A reinforcement learning model for AI-based decision support in skin cancer" @default.
• W4385302721 cites W2087230523 @default.
• W4385302721 cites W2145339207 @default.
• W4385302721 cites W2581082771 @default.
• W4385302721 cites W2753047523 @default.
• W4385302721 cites W2806853752 @default.
• W4385302721 cites W2952971376 @default.
• W4385302721 cites W2998175747 @default.
• W4385302721 cites W3003375105 @default.
• W4385302721 cites W3036298167 @default.
• W4385302721 cites W3102785203 @default.
• W4385302721 cites W3196396697 @default.
• W4385302721 cites W4210545395 @default.
• W4385302721 cites W4211195874 @default.
• W4385302721 cites W4224242326 @default.
• W4385302721 cites W4226269440 @default.
• W4385302721 cites W4283313052 @default.
• W4385302721 cites W4308516851 @default.
• W4385302721 doi "https://doi.org/10.1038/s41591-023-02475-5" @default.
• W4385302721 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37501017" @default.
• W4385302721 hasPublicationYear "2023" @default.
• W4385302721 type Work @default.
• W4385302721 citedByCount "1" @default.
• W4385302721 crossrefType "journal-article" @default.
• W4385302721 hasAuthorship W4385302721A5000215116 @default.
• W4385302721 hasAuthorship W4385302721A5004712523 @default.
• W4385302721 hasAuthorship W4385302721A5011182804 @default.
• W4385302721 hasAuthorship W4385302721A5011768850 @default.
• W4385302721 hasAuthorship W4385302721A5018897159 @default.
• W4385302721 hasAuthorship W4385302721A5033462323 @default.
• W4385302721 hasAuthorship W4385302721A5035102732 @default.
• W4385302721 hasAuthorship W4385302721A5050063952 @default.
• W4385302721 hasAuthorship W4385302721A5056955219 @default.
• W4385302721 hasAuthorship W4385302721A5071595948 @default.
• W4385302721 hasAuthorship W4385302721A5071822275 @default.
• W4385302721 hasAuthorship W4385302721A5072653864 @default.
• W4385302721 hasAuthorship W4385302721A5073027533 @default.
• W4385302721 hasAuthorship W4385302721A5079760997 @default.
• W4385302721 hasAuthorship W4385302721A5083011959 @default.
• W4385302721 hasAuthorship W4385302721A5085409073 @default.
• W4385302721 hasAuthorship W4385302721A5086926559 @default.
• W4385302721 hasBestOaLocation W43853027211 @default.
• W4385302721 hasConcept C105795698 @default.
• W4385302721 hasConcept C119857082 @default.
• W4385302721 hasConcept C121608353 @default.
• W4385302721 hasConcept C126322002 @default.
• W4385302721 hasConcept C154945302 @default.
• W4385302721 hasConcept C15744967 @default.
• W4385302721 hasConcept C2777789703 @default.
• W4385302721 hasConcept C2778804307 @default.
• W4385302721 hasConcept C3019992690 @default.
• W4385302721 hasConcept C33923547 @default.
• W4385302721 hasConcept C41008148 @default.
• W4385302721 hasConcept C44249647 @default.
• W4385302721 hasConcept C51110983 @default.
• W4385302721 hasConcept C67203356 @default.
• W4385302721 hasConcept C71924100 @default.
• W4385302721 hasConcept C77805123 @default.
• W4385302721 hasConcept C97541855 @default.
• W4385302721 hasConceptScore W4385302721C105795698 @default.
• W4385302721 hasConceptScore W4385302721C119857082 @default.
• W4385302721 hasConceptScore W4385302721C121608353 @default.
• W4385302721 hasConceptScore W4385302721C126322002 @default.
• W4385302721 hasConceptScore W4385302721C154945302 @default.
• W4385302721 hasConceptScore W4385302721C15744967 @default.
• W4385302721 hasConceptScore W4385302721C2777789703 @default.
• W4385302721 hasConceptScore W4385302721C2778804307 @default.
• W4385302721 hasConceptScore W4385302721C3019992690 @default.
• W4385302721 hasConceptScore W4385302721C33923547 @default.
• W4385302721 hasConceptScore W4385302721C41008148 @default.
• W4385302721 hasConceptScore W4385302721C44249647 @default.
• W4385302721 hasConceptScore W4385302721C51110983 @default.
• W4385302721 hasConceptScore W4385302721C67203356 @default.
• W4385302721 hasConceptScore W4385302721C71924100 @default.
• W4385302721 hasConceptScore W4385302721C77805123 @default.
• W4385302721 hasConceptScore W4385302721C97541855 @default.
• W4385302721 hasIssue "8" @default.

• next