FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4384652504> ?p ?o ?g. }

• W4384652504 abstract "Non-accidental trauma (NAT) is deadly and difficult to predict. Transformer models pretrained on large datasets have recently produced state of the art performance on diverse prediction tasks, but the optimal pretraining strategies for diagnostic predictions are not known. Here we report the development and external validation of Pretrained and Adapted BERT for Longitudinal Outcomes (PABLO), a transformer-based deep learning model with multitask clinical pretraining, to identify patients who will receive a diagnosis of NAT in the next year. We develop a clinical interface to visualize patient trajectories, model predictions, and individual risk factors. In two comprehensive statewide databases, approximately 1% of patients experience NAT within one year of prediction. PABLO predicts NAT events with area under the receiver operating characteristic curve (AUROC) of 0.844 (95% CI 0.838-0.851) in the California test set, and 0.849 (95% CI 0.846-0.851) on external validation in Florida, outperforming comparator models. Multitask pretraining significantly improves model performance. Attribution analysis shows substance use, psychiatric, and injury diagnoses, in the context of age and racial demographics, as influential predictors of NAT. As a clinical decision support system, PABLO can identify high-risk patients and patient-specific risk factors, which can be used to target secondary screening and preventive interventions at the point-of-care." @default.
• W4384652504 created "2023-07-19" @default.
• W4384652504 creator A5011448190 @default.
• W4384652504 creator A5015656765 @default.
• W4384652504 creator A5015766352 @default.
• W4384652504 creator A5043376508 @default.
• W4384652504 creator A5054705095 @default.
• W4384652504 date "2023-07-19" @default.
• W4384652504 modified "2023-09-27" @default.
• W4384652504 title "Development and external validation of a pretrained deep learning model for the prediction of non-accidental trauma" @default.
• W4384652504 cites W1987087249 @default.
• W4384652504 cites W1994602607 @default.
• W4384652504 cites W2022087132 @default.
• W4384652504 cites W2043488071 @default.
• W4384652504 cites W2090818154 @default.
• W4384652504 cites W2120596490 @default.
• W4384652504 cites W2133619004 @default.
• W4384652504 cites W2137591261 @default.
• W4384652504 cites W2167414941 @default.
• W4384652504 cites W2328176404 @default.
• W4384652504 cites W2444289242 @default.
• W4384652504 cites W2570409301 @default.
• W4384652504 cites W2765101269 @default.
• W4384652504 cites W2770724157 @default.
• W4384652504 cites W2777834684 @default.
• W4384652504 cites W2895936626 @default.
• W4384652504 cites W2897902709 @default.
• W4384652504 cites W2944152776 @default.
• W4384652504 cites W2952863144 @default.
• W4384652504 cites W2955957196 @default.
• W4384652504 cites W2976398475 @default.
• W4384652504 cites W3007453563 @default.
• W4384652504 cites W3012693113 @default.
• W4384652504 cites W3017637887 @default.
• W4384652504 cites W3046113390 @default.
• W4384652504 cites W3098949126 @default.
• W4384652504 cites W3102476541 @default.
• W4384652504 cites W3109426378 @default.
• W4384652504 cites W3160137267 @default.
• W4384652504 cites W3189722576 @default.
• W4384652504 cites W3197057602 @default.
• W4384652504 cites W3204096867 @default.
• W4384652504 cites W4282946251 @default.
• W4384652504 cites W4311539437 @default.
• W4384652504 doi "https://doi.org/10.1038/s41746-023-00875-y" @default.
• W4384652504 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37468526" @default.
• W4384652504 hasPublicationYear "2023" @default.
• W4384652504 type Work @default.
• W4384652504 citedByCount "0" @default.
• W4384652504 crossrefType "journal-article" @default.
• W4384652504 hasAuthorship W4384652504A5011448190 @default.
• W4384652504 hasAuthorship W4384652504A5015656765 @default.
• W4384652504 hasAuthorship W4384652504A5015766352 @default.
• W4384652504 hasAuthorship W4384652504A5043376508 @default.
• W4384652504 hasAuthorship W4384652504A5054705095 @default.
• W4384652504 hasBestOaLocation W43846525041 @default.
• W4384652504 hasConcept C108583219 @default.
• W4384652504 hasConcept C118552586 @default.
• W4384652504 hasConcept C119857082 @default.
• W4384652504 hasConcept C142724271 @default.
• W4384652504 hasConcept C144024400 @default.
• W4384652504 hasConcept C149923435 @default.
• W4384652504 hasConcept C151730666 @default.
• W4384652504 hasConcept C154945302 @default.
• W4384652504 hasConcept C27415008 @default.
• W4384652504 hasConcept C2779343474 @default.
• W4384652504 hasConcept C2780084366 @default.
• W4384652504 hasConcept C41008148 @default.
• W4384652504 hasConcept C534262118 @default.
• W4384652504 hasConcept C58471807 @default.
• W4384652504 hasConcept C71924100 @default.
• W4384652504 hasConcept C86803240 @default.
• W4384652504 hasConceptScore W4384652504C108583219 @default.
• W4384652504 hasConceptScore W4384652504C118552586 @default.
• W4384652504 hasConceptScore W4384652504C119857082 @default.
• W4384652504 hasConceptScore W4384652504C142724271 @default.
• W4384652504 hasConceptScore W4384652504C144024400 @default.
• W4384652504 hasConceptScore W4384652504C149923435 @default.
• W4384652504 hasConceptScore W4384652504C151730666 @default.
• W4384652504 hasConceptScore W4384652504C154945302 @default.
• W4384652504 hasConceptScore W4384652504C27415008 @default.
• W4384652504 hasConceptScore W4384652504C2779343474 @default.
• W4384652504 hasConceptScore W4384652504C2780084366 @default.
• W4384652504 hasConceptScore W4384652504C41008148 @default.
• W4384652504 hasConceptScore W4384652504C534262118 @default.
• W4384652504 hasConceptScore W4384652504C58471807 @default.
• W4384652504 hasConceptScore W4384652504C71924100 @default.
• W4384652504 hasConceptScore W4384652504C86803240 @default.
• W4384652504 hasIssue "1" @default.
• W4384652504 hasLocation W43846525041 @default.
• W4384652504 hasLocation W43846525042 @default.
• W4384652504 hasOpenAccess W4384652504 @default.
• W4384652504 hasPrimaryLocation W43846525041 @default.
• W4384652504 hasRelatedWork W3014300295 @default.
• W4384652504 hasRelatedWork W3164822677 @default.
• W4384652504 hasRelatedWork W4223943233 @default.
• W4384652504 hasRelatedWork W4225161397 @default.
• W4384652504 hasRelatedWork W4309045103 @default.
• W4384652504 hasRelatedWork W4309637067 @default.
• W4384652504 hasRelatedWork W4312200629 @default.

• next