FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4328103228> ?p ?o ?g. }

• W4328103228 endingPage "105050" @default.
• W4328103228 startingPage "105050" @default.
• W4328103228 abstract "Stroke is the second leading cause of death worldwide and has a significantly high recurrence rate. We aimed to identify risk factors for stroke recurrence and develop an interpretable machine learning model to predict 30-day readmissions after stroke.Stroke patients deposited in electronic health records (EHRs) in Xuzhou Medical University Hospital between February 1, 2021, and November 30, 2021, were included in the study, and deceased patients were excluded. We extracted 74 features from EHRs, and the top 20 features (chi-2 value) were used to build machine learning models. 80% of the patients were used for pre-training. Subsequently, a 20% holdout dataset was used for verification. The Shapley Additive exPlanations (SHAP) method was used to explore the interpretability of the model.The cohort included 6,558 patients, of whom the mean (SD) age was 65 (11) years, 3,926 were males (59.86 %), and 132 (2.01 %) were readmitted within 30 days. The area under the receiver operating characteristic curve (AUROC) for the optimized model was 0.80 (95 % CI 0.68-0.80). We used the SHAP method to identify the top 10 risk factors (i.e., severe carotid artery stenosis, weak, homocysteine, glycosylated hemoglobin, sex, lymphocyte percentage, neutrophilic granulocyte percentage, urine glucose, fresh cerebral infarction, and red blood cell count). The AUROC of a model with the 10 features was 0.80 (95 % CI 0.69-0.80) and was not significantly different from that of the model with 20 risk factors.Our methods not only showed good performance in predicting 30-day readmissions after stroke but also revealed risk factors that provided valuable insights for treatments." @default.
• W4328103228 created "2023-03-22" @default.
• W4328103228 creator A5006818966 @default.
• W4328103228 creator A5024467493 @default.
• W4328103228 creator A5032770198 @default.
• W4328103228 creator A5043485598 @default.
• W4328103228 creator A5070527587 @default.
• W4328103228 creator A5073568638 @default.
• W4328103228 creator A5077042443 @default.
• W4328103228 creator A5078328036 @default.
• W4328103228 creator A5089707927 @default.
• W4328103228 date "2023-06-01" @default.
• W4328103228 modified "2023-10-14" @default.
• W4328103228 title "An interpretable machine learning approach for predicting 30-day readmission after stroke" @default.
• W4328103228 cites W1710286707 @default.
• W4328103228 cites W1994810045 @default.
• W4328103228 cites W1999402245 @default.
• W4328103228 cites W2015983646 @default.
• W4328103228 cites W2078063083 @default.
• W4328103228 cites W2078271269 @default.
• W4328103228 cites W2094701432 @default.
• W4328103228 cites W2097457623 @default.
• W4328103228 cites W2164294116 @default.
• W4328103228 cites W2164335974 @default.
• W4328103228 cites W2518098335 @default.
• W4328103228 cites W2527824850 @default.
• W4328103228 cites W2605001986 @default.
• W4328103228 cites W2889961932 @default.
• W4328103228 cites W2906137209 @default.
• W4328103228 cites W2920989721 @default.
• W4328103228 cites W2928741313 @default.
• W4328103228 cites W2969569798 @default.
• W4328103228 cites W2999615587 @default.
• W4328103228 cites W3033794693 @default.
• W4328103228 cites W3117504162 @default.
• W4328103228 cites W3124410225 @default.
• W4328103228 cites W3131987456 @default.
• W4328103228 cites W3144601772 @default.
• W4328103228 cites W3157892075 @default.
• W4328103228 cites W3158744978 @default.
• W4328103228 cites W3178880675 @default.
• W4328103228 cites W3197231066 @default.
• W4328103228 cites W3207601856 @default.
• W4328103228 cites W3209217280 @default.
• W4328103228 cites W4206738083 @default.
• W4328103228 cites W4211186001 @default.
• W4328103228 cites W4220693124 @default.
• W4328103228 cites W4281552718 @default.
• W4328103228 cites W4281703125 @default.
• W4328103228 cites W659565176 @default.
• W4328103228 cites W66857733 @default.
• W4328103228 doi "https://doi.org/10.1016/j.ijmedinf.2023.105050" @default.
• W4328103228 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36965404" @default.
• W4328103228 hasPublicationYear "2023" @default.
• W4328103228 type Work @default.
• W4328103228 citedByCount "2" @default.
• W4328103228 countsByYear W43281032282023 @default.
• W4328103228 crossrefType "journal-article" @default.
• W4328103228 hasAuthorship W4328103228A5006818966 @default.
• W4328103228 hasAuthorship W4328103228A5024467493 @default.
• W4328103228 hasAuthorship W4328103228A5032770198 @default.
• W4328103228 hasAuthorship W4328103228A5043485598 @default.
• W4328103228 hasAuthorship W4328103228A5070527587 @default.
• W4328103228 hasAuthorship W4328103228A5073568638 @default.
• W4328103228 hasAuthorship W4328103228A5077042443 @default.
• W4328103228 hasAuthorship W4328103228A5078328036 @default.
• W4328103228 hasAuthorship W4328103228A5089707927 @default.
• W4328103228 hasConcept C119857082 @default.
• W4328103228 hasConcept C126322002 @default.
• W4328103228 hasConcept C127413603 @default.
• W4328103228 hasConcept C2780645631 @default.
• W4328103228 hasConcept C2781067378 @default.
• W4328103228 hasConcept C41008148 @default.
• W4328103228 hasConcept C58471807 @default.
• W4328103228 hasConcept C71924100 @default.
• W4328103228 hasConcept C72563966 @default.
• W4328103228 hasConcept C78519656 @default.
• W4328103228 hasConceptScore W4328103228C119857082 @default.
• W4328103228 hasConceptScore W4328103228C126322002 @default.
• W4328103228 hasConceptScore W4328103228C127413603 @default.
• W4328103228 hasConceptScore W4328103228C2780645631 @default.
• W4328103228 hasConceptScore W4328103228C2781067378 @default.
• W4328103228 hasConceptScore W4328103228C41008148 @default.
• W4328103228 hasConceptScore W4328103228C58471807 @default.
• W4328103228 hasConceptScore W4328103228C71924100 @default.
• W4328103228 hasConceptScore W4328103228C72563966 @default.
• W4328103228 hasConceptScore W4328103228C78519656 @default.
• W4328103228 hasLocation W43281032281 @default.
• W4328103228 hasLocation W43281032282 @default.
• W4328103228 hasOpenAccess W4328103228 @default.
• W4328103228 hasPrimaryLocation W43281032281 @default.
• W4328103228 hasRelatedWork W1986582023 @default.
• W4328103228 hasRelatedWork W2603773853 @default.
• W4328103228 hasRelatedWork W2883749686 @default.
• W4328103228 hasRelatedWork W2966218717 @default.
• W4328103228 hasRelatedWork W3102363003 @default.
• W4328103228 hasRelatedWork W3166531723 @default.
• W4328103228 hasRelatedWork W4315864862 @default.

• next