FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2913694856> ?p ?o ?g. }

• W2913694856 endingPage "103122" @default.
• W2913694856 startingPage "103122" @default.
• W2913694856 abstract "Phenotyping algorithms can efficiently and accurately identify patients with a specific disease phenotype and construct electronic health records (EHR)-based cohorts for subsequent clinical or genomic studies. Previous studies have introduced unsupervised EHR-based feature selection methods that yielded algorithms with high accuracy. However, those selection methods still require expert intervention to tweak the parameter settings according to the EHR data distribution for each phenotype. To further accelerate the development of phenotyping algorithms, we propose a fully automated and robust unsupervised feature selection method that leverages only publicly available medical knowledge sources, instead of EHR data. SEmantics-Driven Feature Extraction (SEDFE) collects medical concepts from online knowledge sources as candidate features and gives them vector-form distributional semantic representations derived with neural word embedding and the Unified Medical Language System Metathesaurus. A number of features that are semantically closest and that sufficiently characterize the target phenotype are determined by a linear decomposition criterion and are selected for the final classification algorithm. SEDFE was compared with the EHR-based SAFE algorithm and domain experts on feature selection for the classification of five phenotypes including coronary artery disease, rheumatoid arthritis, Crohn’s disease, ulcerative colitis, and pediatric pulmonary arterial hypertension using both supervised and unsupervised approaches. Algorithms yielded by SEDFE achieved comparable accuracy to those yielded by SAFE and expert-curated features. SEDFE is also robust to the input semantic vectors. SEDFE attains satisfying performance in unsupervised feature selection for EHR phenotyping. Both fully automated and EHR-independent, this method promises efficiency and accuracy in developing algorithms for high-throughput phenotyping." @default.
• W2913694856 created "2019-02-21" @default.
• W2913694856 creator A5008454615 @default.
• W2913694856 creator A5009822037 @default.
• W2913694856 creator A5018662278 @default.
• W2913694856 creator A5025181406 @default.
• W2913694856 creator A5026870387 @default.
• W2913694856 creator A5040501126 @default.
• W2913694856 creator A5060000892 @default.
• W2913694856 creator A5071353174 @default.
• W2913694856 creator A5077007622 @default.
• W2913694856 creator A5078003862 @default.
• W2913694856 creator A5088509061 @default.
• W2913694856 date "2019-03-01" @default.
• W2913694856 modified "2023-10-16" @default.
• W2913694856 title "Feature extraction for phenotyping from semantic and knowledge resources" @default.
• W2913694856 cites W1081873870 @default.
• W2913694856 cites W153781075 @default.
• W2913694856 cites W1579185617 @default.
• W2913694856 cites W1590194639 @default.
• W2913694856 cites W1607892368 @default.
• W2913694856 cites W1759667598 @default.
• W2913694856 cites W1969208427 @default.
• W2913694856 cites W1983578042 @default.
• W2913694856 cites W1989668072 @default.
• W2913694856 cites W1990965188 @default.
• W2913694856 cites W2004198484 @default.
• W2913694856 cites W2012487908 @default.
• W2913694856 cites W2016104730 @default.
• W2913694856 cites W2024582227 @default.
• W2913694856 cites W202767273 @default.
• W2913694856 cites W2029119894 @default.
• W2913694856 cites W2046844528 @default.
• W2913694856 cites W2051743300 @default.
• W2913694856 cites W2057913811 @default.
• W2913694856 cites W2064337796 @default.
• W2913694856 cites W2071311382 @default.
• W2913694856 cites W2075490785 @default.
• W2913694856 cites W2076766778 @default.
• W2913694856 cites W2079691202 @default.
• W2913694856 cites W2083680351 @default.
• W2913694856 cites W2084525236 @default.
• W2913694856 cites W2104919320 @default.
• W2913694856 cites W2105637130 @default.
• W2913694856 cites W2109056977 @default.
• W2913694856 cites W2113105800 @default.
• W2913694856 cites W2113952938 @default.
• W2913694856 cites W2114584591 @default.
• W2913694856 cites W2118338230 @default.
• W2913694856 cites W2118669252 @default.
• W2913694856 cites W2122825543 @default.
• W2913694856 cites W2123556395 @default.
• W2913694856 cites W2134731454 @default.
• W2913694856 cites W2138162199 @default.
• W2913694856 cites W2145555242 @default.
• W2913694856 cites W2147152072 @default.
• W2913694856 cites W2149600008 @default.
• W2913694856 cites W2151068025 @default.
• W2913694856 cites W2154048976 @default.
• W2913694856 cites W2165456953 @default.
• W2913694856 cites W2187005605 @default.
• W2913694856 cites W2279992407 @default.
• W2913694856 cites W2292270531 @default.
• W2913694856 cites W2327091741 @default.
• W2913694856 cites W2337688125 @default.
• W2913694856 cites W2356882517 @default.
• W2913694856 cites W2395889391 @default.
• W2913694856 cites W2509406088 @default.
• W2913694856 cites W2520392019 @default.
• W2913694856 cites W2625154504 @default.
• W2913694856 cites W2765693998 @default.
• W2913694856 cites W2792604504 @default.
• W2913694856 cites W2882319491 @default.
• W2913694856 cites W2997522493 @default.
• W2913694856 doi "https://doi.org/10.1016/j.jbi.2019.103122" @default.
• W2913694856 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/6424621" @default.
• W2913694856 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/30738949" @default.
• W2913694856 hasPublicationYear "2019" @default.
• W2913694856 type Work @default.
• W2913694856 sameAs 2913694856 @default.
• W2913694856 citedByCount "21" @default.
• W2913694856 countsByYear W29136948562019 @default.
• W2913694856 countsByYear W29136948562020 @default.
• W2913694856 countsByYear W29136948562021 @default.
• W2913694856 countsByYear W29136948562022 @default.
• W2913694856 crossrefType "journal-article" @default.
• W2913694856 hasAuthorship W2913694856A5008454615 @default.
• W2913694856 hasAuthorship W2913694856A5009822037 @default.
• W2913694856 hasAuthorship W2913694856A5018662278 @default.
• W2913694856 hasAuthorship W2913694856A5025181406 @default.
• W2913694856 hasAuthorship W2913694856A5026870387 @default.
• W2913694856 hasAuthorship W2913694856A5040501126 @default.
• W2913694856 hasAuthorship W2913694856A5060000892 @default.
• W2913694856 hasAuthorship W2913694856A5071353174 @default.
• W2913694856 hasAuthorship W2913694856A5077007622 @default.
• W2913694856 hasAuthorship W2913694856A5078003862 @default.
• W2913694856 hasAuthorship W2913694856A5088509061 @default.
• W2913694856 hasBestOaLocation W29136948562 @default.

• next