FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313339620> ?p ?o ?g. }

• W4313339620 endingPage "226" @default.
• W4313339620 startingPage "218" @default.
• W4313339620 abstract "Abstract Background and Purpose Intracranial hemorrhage (ICH) is a common life‐threatening condition that must be rapidly diagnosed and treated. However, there is still a lack of consensus regarding treatment, driven to some extent by prognostic uncertainty. While several prediction models for ICH detection have already been published, here we present a deep learning predictive model for ICH prognosis. Methods We included patients with ICH ( n = 262), and we trained a custom model for the classification of patients into poor prognosis and good prognosis, using a hybrid input consisting of brain CT images and other clinical variables. We compared it with two other models, one trained with images only (I‐model) and the other with tabular data only (D‐model). Results Our hybrid model achieved an area under the receiver operating characteristic curve (AUC) of .924 (95% confidence interval [CI]: .831‐.986), and an accuracy of .861 (95% CI: .760‐.960). The I‐ and D‐models achieved an AUC of .763 (95% CI: .622‐.902) and .746 (95% CI: .598‐.876), respectively. Conclusions The proposed hybrid model was able to accurately classify patients into good and poor prognosis. To the best of our knowledge, this is the first ICH prognosis prediction deep learning model. We concluded that deep learning can be applied for prognosis prediction in ICH that could have a great impact on clinical decision‐making. Further, hybrid inputs could be a promising technique for deep learning in medical imaging." @default.
• W4313339620 created "2023-01-06" @default.
• W4313339620 creator A5041913847 @default.
• W4313339620 creator A5045579152 @default.
• W4313339620 creator A5046081835 @default.
• W4313339620 creator A5053517181 @default.
• W4313339620 creator A5053720982 @default.
• W4313339620 creator A5057931227 @default.
• W4313339620 creator A5061377409 @default.
• W4313339620 creator A5076635347 @default.
• W4313339620 creator A5082671819 @default.
• W4313339620 date "2022-12-31" @default.
• W4313339620 modified "2023-10-18" @default.
• W4313339620 title "A deep learning model for prognosis prediction after intracranial hemorrhage" @default.
• W4313339620 cites W1971847944 @default.
• W4313339620 cites W1997840342 @default.
• W4313339620 cites W2026669237 @default.
• W4313339620 cites W2112161237 @default.
• W4313339620 cites W2135533213 @default.
• W4313339620 cites W2136587148 @default.
• W4313339620 cites W2610332124 @default.
• W4313339620 cites W2795774310 @default.
• W4313339620 cites W2795959543 @default.
• W4313339620 cites W2896817483 @default.
• W4313339620 cites W2908763778 @default.
• W4313339620 cites W2943644689 @default.
• W4313339620 cites W2995143015 @default.
• W4313339620 cites W3007935259 @default.
• W4313339620 cites W3013294478 @default.
• W4313339620 cites W3023284086 @default.
• W4313339620 cites W3108582022 @default.
• W4313339620 cites W3123553354 @default.
• W4313339620 cites W3129167842 @default.
• W4313339620 cites W3150367798 @default.
• W4313339620 cites W3161263649 @default.
• W4313339620 cites W3181637650 @default.
• W4313339620 cites W3187675958 @default.
• W4313339620 cites W3210570170 @default.
• W4313339620 cites W3216182232 @default.
• W4313339620 cites W4206010335 @default.
• W4313339620 cites W4211064847 @default.
• W4313339620 doi "https://doi.org/10.1111/jon.13078" @default.
• W4313339620 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36585957" @default.
• W4313339620 hasPublicationYear "2022" @default.
• W4313339620 type Work @default.
• W4313339620 citedByCount "3" @default.
• W4313339620 countsByYear W43133396202023 @default.
• W4313339620 crossrefType "journal-article" @default.
• W4313339620 hasAuthorship W4313339620A5041913847 @default.
• W4313339620 hasAuthorship W4313339620A5045579152 @default.
• W4313339620 hasAuthorship W4313339620A5046081835 @default.
• W4313339620 hasAuthorship W4313339620A5053517181 @default.
• W4313339620 hasAuthorship W4313339620A5053720982 @default.
• W4313339620 hasAuthorship W4313339620A5057931227 @default.
• W4313339620 hasAuthorship W4313339620A5061377409 @default.
• W4313339620 hasAuthorship W4313339620A5076635347 @default.
• W4313339620 hasAuthorship W4313339620A5082671819 @default.
• W4313339620 hasBestOaLocation W43133396201 @default.
• W4313339620 hasConcept C108583219 @default.
• W4313339620 hasConcept C119857082 @default.
• W4313339620 hasConcept C126322002 @default.
• W4313339620 hasConcept C126838900 @default.
• W4313339620 hasConcept C154945302 @default.
• W4313339620 hasConcept C41008148 @default.
• W4313339620 hasConcept C44249647 @default.
• W4313339620 hasConcept C58471807 @default.
• W4313339620 hasConcept C71924100 @default.
• W4313339620 hasConceptScore W4313339620C108583219 @default.
• W4313339620 hasConceptScore W4313339620C119857082 @default.
• W4313339620 hasConceptScore W4313339620C126322002 @default.
• W4313339620 hasConceptScore W4313339620C126838900 @default.
• W4313339620 hasConceptScore W4313339620C154945302 @default.
• W4313339620 hasConceptScore W4313339620C41008148 @default.
• W4313339620 hasConceptScore W4313339620C44249647 @default.
• W4313339620 hasConceptScore W4313339620C58471807 @default.
• W4313339620 hasConceptScore W4313339620C71924100 @default.
• W4313339620 hasIssue "2" @default.
• W4313339620 hasLocation W43133396201 @default.
• W4313339620 hasLocation W43133396202 @default.
• W4313339620 hasOpenAccess W4313339620 @default.
• W4313339620 hasPrimaryLocation W43133396201 @default.
• W4313339620 hasRelatedWork W2795261237 @default.
• W4313339620 hasRelatedWork W3014300295 @default.
• W4313339620 hasRelatedWork W3164822677 @default.
• W4313339620 hasRelatedWork W4223943233 @default.
• W4313339620 hasRelatedWork W4225161397 @default.
• W4313339620 hasRelatedWork W4312200629 @default.
• W4313339620 hasRelatedWork W4360585206 @default.
• W4313339620 hasRelatedWork W4364306694 @default.
• W4313339620 hasRelatedWork W4380075502 @default.
• W4313339620 hasRelatedWork W4380086463 @default.
• W4313339620 hasVolume "33" @default.
• W4313339620 isParatext "false" @default.
• W4313339620 isRetracted "false" @default.
• W4313339620 workType "article" @default.