FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4297140909> ?p ?o ?g. }

• W4297140909 endingPage "102408" @default.
• W4297140909 startingPage "102408" @default.
• W4297140909 abstract "The adoption of electronic health records in hospitals has ensured the availability of large datasets that can be used to predict medical complications. The trajectories of patients in real-world settings are highly variable, making longitudinal data modeling challenging. In recent years, significant progress has been made in the study of deep learning models applied to time series; however, the application of these models to irregular medical time series (IMTS) remains limited. To address this issue, we developed a generic deep-learning-based framework for modeling IMTS that facilitates the comparative studies of sequential neural networks (transformers and long short-term memory) and irregular time representation techniques. A validation study to predict retinopathy complications was conducted on 1207 patients with type 1 diabetes in a French database using their historical glycosylated hemoglobin measurements, without any data aggregation or imputation. The transformer-based model combined with the soft one-hot representation of time gaps achieved the highest score: an area under the receiver operating characteristic curve of 88.65%, specificity of 85.56%, sensitivity of 83.33% and an improvement of 11.7% over the same architecture without time information. This is the first attempt to predict retinopathy complications in patients with type 1 diabetes using deep learning and longitudinal data collected from patient visits. This study highlighted the significance of modeling time gaps between medical records to improve prediction performance and the utility of a generic framework for conducting extensive comparative studies." @default.
• W4297140909 created "2022-09-27" @default.
• W4297140909 creator A5003796615 @default.
• W4297140909 creator A5017537989 @default.
• W4297140909 creator A5030151382 @default.
• W4297140909 creator A5034736630 @default.
• W4297140909 creator A5038662752 @default.
• W4297140909 creator A5047878606 @default.
• W4297140909 creator A5080592332 @default.
• W4297140909 creator A5086414408 @default.
• W4297140909 date "2022-11-01" @default.
• W4297140909 modified "2023-10-16" @default.
• W4297140909 title "Temporal deep learning framework for retinopathy prediction in patients with type 1 diabetes" @default.
• W4297140909 cites W1574458575 @default.
• W4297140909 cites W2027106132 @default.
• W4297140909 cites W2064675550 @default.
• W4297140909 cites W2262322820 @default.
• W4297140909 cites W2396881363 @default.
• W4297140909 cites W2404901863 @default.
• W4297140909 cites W2481271618 @default.
• W4297140909 cites W2511950764 @default.
• W4297140909 cites W2518582440 @default.
• W4297140909 cites W2533800772 @default.
• W4297140909 cites W2559646245 @default.
• W4297140909 cites W2560773370 @default.
• W4297140909 cites W2566079294 @default.
• W4297140909 cites W2607113351 @default.
• W4297140909 cites W2610304972 @default.
• W4297140909 cites W2612292012 @default.
• W4297140909 cites W2738975713 @default.
• W4297140909 cites W2739805805 @default.
• W4297140909 cites W2754051771 @default.
• W4297140909 cites W2791485417 @default.
• W4297140909 cites W2803894793 @default.
• W4297140909 cites W2807893746 @default.
• W4297140909 cites W2884001105 @default.
• W4297140909 cites W2892035503 @default.
• W4297140909 cites W2897007327 @default.
• W4297140909 cites W2912390055 @default.
• W4297140909 cites W2913240367 @default.
• W4297140909 cites W2921671163 @default.
• W4297140909 cites W2930139824 @default.
• W4297140909 cites W2945583287 @default.
• W4297140909 cites W2949676527 @default.
• W4297140909 cites W2964010366 @default.
• W4297140909 cites W2964335123 @default.
• W4297140909 cites W2972530371 @default.
• W4297140909 cites W2990000777 @default.
• W4297140909 cites W2997353686 @default.
• W4297140909 cites W2998880869 @default.
• W4297140909 cites W3006961624 @default.
• W4297140909 cites W3080967847 @default.
• W4297140909 cites W3082762715 @default.
• W4297140909 cites W3098949126 @default.
• W4297140909 cites W3099136959 @default.
• W4297140909 cites W3108251697 @default.
• W4297140909 cites W3108717672 @default.
• W4297140909 cites W3111488276 @default.
• W4297140909 cites W3119612757 @default.
• W4297140909 cites W3122022143 @default.
• W4297140909 cites W3159265489 @default.
• W4297140909 cites W3169849584 @default.
• W4297140909 cites W3173035603 @default.
• W4297140909 cites W3194761804 @default.
• W4297140909 cites W3200618987 @default.
• W4297140909 doi "https://doi.org/10.1016/j.artmed.2022.102408" @default.
• W4297140909 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36328668" @default.
• W4297140909 hasPublicationYear "2022" @default.
• W4297140909 type Work @default.
• W4297140909 citedByCount "3" @default.
• W4297140909 countsByYear W42971409092023 @default.
• W4297140909 crossrefType "journal-article" @default.
• W4297140909 hasAuthorship W4297140909A5003796615 @default.
• W4297140909 hasAuthorship W4297140909A5017537989 @default.
• W4297140909 hasAuthorship W4297140909A5030151382 @default.
• W4297140909 hasAuthorship W4297140909A5034736630 @default.
• W4297140909 hasAuthorship W4297140909A5038662752 @default.
• W4297140909 hasAuthorship W4297140909A5047878606 @default.
• W4297140909 hasAuthorship W4297140909A5080592332 @default.
• W4297140909 hasAuthorship W4297140909A5086414408 @default.
• W4297140909 hasConcept C108583219 @default.
• W4297140909 hasConcept C119857082 @default.
• W4297140909 hasConcept C124101348 @default.
• W4297140909 hasConcept C134018914 @default.
• W4297140909 hasConcept C141071460 @default.
• W4297140909 hasConcept C154945302 @default.
• W4297140909 hasConcept C160735492 @default.
• W4297140909 hasConcept C162324750 @default.
• W4297140909 hasConcept C195910791 @default.
• W4297140909 hasConcept C2779829184 @default.
• W4297140909 hasConcept C3019952477 @default.
• W4297140909 hasConcept C41008148 @default.
• W4297140909 hasConcept C50522688 @default.
• W4297140909 hasConcept C50644808 @default.
• W4297140909 hasConcept C555293320 @default.
• W4297140909 hasConcept C58471807 @default.
• W4297140909 hasConcept C71924100 @default.
• W4297140909 hasConceptScore W4297140909C108583219 @default.

• next