FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3081483181> ?p ?o ?g. }

• W3081483181 endingPage "e0237911" @default.
• W3081483181 startingPage "e0237911" @default.
• W3081483181 abstract "Electronic health records (EHRs) contain rich documentation regarding disease symptoms and progression, but EHR data is challenging to use for diagnosis prediction due to its high dimensionality, relative scarcity, and substantial level of noise. We investigated how to best represent EHR data for predicting cervical cancer, a serious disease where early detection is beneficial for the outcome of treatment. A case group of 1321 patients with cervical cancer were matched to ten times as many controls, and for both groups several types of events were extracted from their EHRs. These events included clinical codes, lab results, and contents of free text notes retrieved using a LSTM neural network. Clinical events are described with great variation in EHR texts, leading to a very large feature space. Therefore, an event hierarchy inferred from the textual events was created to represent the clinical texts. Overall, the events extracted from free text notes contributed the most to the final prediction, and the hierarchy of textual events further improved performance. Four classifiers were evaluated for predicting a future cancer diagnosis where Random Forest achieved the best results with an AUC of 0.70 from a year before diagnosis up to 0.97 one day before diagnosis. We conclude that our approach is sound and had excellent discrimination at diagnosis, but only modest discrimination capacity before this point. Since our study objective was earlier disease prediction than such, we propose further work should consider extending patient histories through e.g. the integration of primary health records preceding referral to hospital." @default.
• W3081483181 created "2020-09-01" @default.
• W3081483181 creator A5001810790 @default.
• W3081483181 creator A5028278998 @default.
• W3081483181 date "2020-08-21" @default.
• W3081483181 modified "2023-10-15" @default.
• W3081483181 title "Using machine learning for predicting cervical cancer from Swedish electronic health records by mining hierarchical representations" @default.
• W3081483181 cites W129507607 @default.
• W3081483181 cites W1541954861 @default.
• W3081483181 cites W1550258693 @default.
• W3081483181 cites W1956509155 @default.
• W3081483181 cites W2004910511 @default.
• W3081483181 cites W2015168986 @default.
• W3081483181 cites W2041888817 @default.
• W3081483181 cites W2057443209 @default.
• W3081483181 cites W2111698097 @default.
• W3081483181 cites W2120539430 @default.
• W3081483181 cites W2121382432 @default.
• W3081483181 cites W2126502509 @default.
• W3081483181 cites W2167101736 @default.
• W3081483181 cites W2395172628 @default.
• W3081483181 cites W2403510108 @default.
• W3081483181 cites W2404901863 @default.
• W3081483181 cites W2473152724 @default.
• W3081483181 cites W2511950764 @default.
• W3081483181 cites W2594685110 @default.
• W3081483181 cites W2612374874 @default.
• W3081483181 cites W2911964244 @default.
• W3081483181 cites W2995950854 @default.
• W3081483181 cites W3099136959 @default.
• W3081483181 doi "https://doi.org/10.1371/journal.pone.0237911" @default.
• W3081483181 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/7444577" @default.
• W3081483181 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/32822401" @default.
• W3081483181 hasPublicationYear "2020" @default.
• W3081483181 type Work @default.
• W3081483181 sameAs 3081483181 @default.
• W3081483181 citedByCount "16" @default.
• W3081483181 countsByYear W30814831812021 @default.
• W3081483181 countsByYear W30814831812022 @default.
• W3081483181 countsByYear W30814831812023 @default.
• W3081483181 crossrefType "journal-article" @default.
• W3081483181 hasAuthorship W3081483181A5001810790 @default.
• W3081483181 hasAuthorship W3081483181A5028278998 @default.
• W3081483181 hasBestOaLocation W30814831811 @default.
• W3081483181 hasConcept C119857082 @default.
• W3081483181 hasConcept C121608353 @default.
• W3081483181 hasConcept C126322002 @default.
• W3081483181 hasConcept C148524875 @default.
• W3081483181 hasConcept C154945302 @default.
• W3081483181 hasConcept C160735492 @default.
• W3081483181 hasConcept C162324750 @default.
• W3081483181 hasConcept C169258074 @default.
• W3081483181 hasConcept C199360897 @default.
• W3081483181 hasConcept C204321447 @default.
• W3081483181 hasConcept C2776135927 @default.
• W3081483181 hasConcept C2778220009 @default.
• W3081483181 hasConcept C2779134260 @default.
• W3081483181 hasConcept C3019952477 @default.
• W3081483181 hasConcept C3020144179 @default.
• W3081483181 hasConcept C41008148 @default.
• W3081483181 hasConcept C50522688 @default.
• W3081483181 hasConcept C512399662 @default.
• W3081483181 hasConcept C56666940 @default.
• W3081483181 hasConcept C71924100 @default.
• W3081483181 hasConceptScore W3081483181C119857082 @default.
• W3081483181 hasConceptScore W3081483181C121608353 @default.
• W3081483181 hasConceptScore W3081483181C126322002 @default.
• W3081483181 hasConceptScore W3081483181C148524875 @default.
• W3081483181 hasConceptScore W3081483181C154945302 @default.
• W3081483181 hasConceptScore W3081483181C160735492 @default.
• W3081483181 hasConceptScore W3081483181C162324750 @default.
• W3081483181 hasConceptScore W3081483181C169258074 @default.
• W3081483181 hasConceptScore W3081483181C199360897 @default.
• W3081483181 hasConceptScore W3081483181C204321447 @default.
• W3081483181 hasConceptScore W3081483181C2776135927 @default.
• W3081483181 hasConceptScore W3081483181C2778220009 @default.
• W3081483181 hasConceptScore W3081483181C2779134260 @default.
• W3081483181 hasConceptScore W3081483181C3019952477 @default.
• W3081483181 hasConceptScore W3081483181C3020144179 @default.
• W3081483181 hasConceptScore W3081483181C41008148 @default.
• W3081483181 hasConceptScore W3081483181C50522688 @default.
• W3081483181 hasConceptScore W3081483181C512399662 @default.
• W3081483181 hasConceptScore W3081483181C56666940 @default.
• W3081483181 hasConceptScore W3081483181C71924100 @default.
• W3081483181 hasIssue "8" @default.
• W3081483181 hasLocation W30814831811 @default.
• W3081483181 hasLocation W30814831812 @default.
• W3081483181 hasLocation W30814831813 @default.
• W3081483181 hasOpenAccess W3081483181 @default.
• W3081483181 hasPrimaryLocation W30814831811 @default.
• W3081483181 hasRelatedWork W1641026212 @default.
• W3081483181 hasRelatedWork W187932805 @default.
• W3081483181 hasRelatedWork W2078646730 @default.
• W3081483181 hasRelatedWork W2087134418 @default.
• W3081483181 hasRelatedWork W2323588885 @default.
• W3081483181 hasRelatedWork W2911135505 @default.
• W3081483181 hasRelatedWork W2920854314 @default.
• W3081483181 hasRelatedWork W3027078461 @default.

• next