FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2890434320> ?p ?o ?g. }

• W2890434320 endingPage "37" @default.
• W2890434320 startingPage "27" @default.
• W2890434320 abstract "Patients who are readmitted to an intensive care unit (ICU) usually have a high risk of mortality and an increased length of stay. ICU readmission risk prediction may help physicians to re-evaluate the patient’s physical conditions before patients are discharged and avoid preventable readmissions. ICU readmission prediction models are often built based on physiological variables. Intuitively, snapshot measurements, especially the last measurements, are effective predictors that are widely used by researchers. However, methods that only use snapshot measurements neglect predictive information contained in the trends of physiological and medication variables. Mean, maximum or minimum values take multiple time points into account and capture their summary statistics, however, these statistics are not able to catch the detailed picture of temporal trends. In this study, we find strong predictors with ability of capturing detailed temporal trends of variables for 30-day readmission risk and build prediction models with high accuracy. We study physiological measurements and medications from the Multiparameter Intelligent Monitoring in Intensive Care II (MIMIC-II) clinical dataset. Time series of each variable are converted into trend graphs with nodes being discretized measurements of each variable. Then we extract important temporal trends by applying frequent subgraph mining on the trend graphs. The frequency of a subgraph is a good cue to find important temporal trends since similar patients often share similar trends regarding their pathophysiological evolution under medical interventions. Important temporal trends are then grouped automatically by non-negative matrix factorization. The grouped trends could be considered as an approximate representation of patients’ pathophysiological states and medication profiles. We train a logistic regression model to predict 30-day ICU readmission risk based on snapshot measurements, grouped physiological trends and medication trends. Our dataset consists of 1170 patients who are alive 30 days after discharge from ICU and have at least 12 h of data. In the dataset, 860 patients were not readmitted and 310 were readmitted, within 30 days after discharge. Our model outperforms all comparison models, and shows an improvement in the area under the receiver operating characteristic curve (AUC) of almost 4% from the best comparison model. Grouped physiological and medication trends carry predictive information for ICU readmission risk. In order to build predictive models with higher accuracy, we should add grouped physiological and medication trends as complementary features to snapshot measurements." @default.
• W2890434320 created "2018-09-27" @default.
• W2890434320 creator A5013049879 @default.
• W2890434320 creator A5077991508 @default.
• W2890434320 creator A5084810789 @default.
• W2890434320 date "2019-04-01" @default.
• W2890434320 modified "2023-10-14" @default.
• W2890434320 title "Predicting ICU readmission using grouped physiological and medication trends" @default.
• W2890434320 cites W1522684182 @default.
• W2890434320 cites W1567583613 @default.
• W2890434320 cites W1855722232 @default.
• W2890434320 cites W1983198306 @default.
• W2890434320 cites W1990801176 @default.
• W2890434320 cites W1991915618 @default.
• W2890434320 cites W1997423414 @default.
• W2890434320 cites W1998428198 @default.
• W2890434320 cites W2012391498 @default.
• W2890434320 cites W2013771610 @default.
• W2890434320 cites W2016851014 @default.
• W2890434320 cites W2021644127 @default.
• W2890434320 cites W2034128975 @default.
• W2890434320 cites W2036742971 @default.
• W2890434320 cites W2046788142 @default.
• W2890434320 cites W2056102627 @default.
• W2890434320 cites W2065610092 @default.
• W2890434320 cites W2071303398 @default.
• W2890434320 cites W2072492033 @default.
• W2890434320 cites W2076038013 @default.
• W2890434320 cites W2082285428 @default.
• W2890434320 cites W2083093865 @default.
• W2890434320 cites W2087859259 @default.
• W2890434320 cites W2095526444 @default.
• W2890434320 cites W2116680794 @default.
• W2890434320 cites W2119191765 @default.
• W2890434320 cites W2125449110 @default.
• W2890434320 cites W2129997990 @default.
• W2890434320 cites W2155045550 @default.
• W2890434320 cites W2160865775 @default.
• W2890434320 cites W2162949830 @default.
• W2890434320 cites W2164274563 @default.
• W2890434320 cites W2396881363 @default.
• W2890434320 cites W2469640527 @default.
• W2890434320 cites W2614504311 @default.
• W2890434320 cites W2980443998 @default.
• W2890434320 cites W4230533278 @default.
• W2890434320 cites W4230962320 @default.
• W2890434320 cites W4301424780 @default.
• W2890434320 cites W47062518 @default.
• W2890434320 doi "https://doi.org/10.1016/j.artmed.2018.08.004" @default.
• W2890434320 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/6474661" @default.
• W2890434320 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/30213670" @default.
• W2890434320 hasPublicationYear "2019" @default.
• W2890434320 type Work @default.
• W2890434320 sameAs 2890434320 @default.
• W2890434320 citedByCount "39" @default.
• W2890434320 countsByYear W28904343202018 @default.
• W2890434320 countsByYear W28904343202019 @default.
• W2890434320 countsByYear W28904343202020 @default.
• W2890434320 countsByYear W28904343202021 @default.
• W2890434320 countsByYear W28904343202022 @default.
• W2890434320 countsByYear W28904343202023 @default.
• W2890434320 crossrefType "journal-article" @default.
• W2890434320 hasAuthorship W2890434320A5013049879 @default.
• W2890434320 hasAuthorship W2890434320A5077991508 @default.
• W2890434320 hasAuthorship W2890434320A5084810789 @default.
• W2890434320 hasBestOaLocation W28904343202 @default.
• W2890434320 hasConcept C105795698 @default.
• W2890434320 hasConcept C111919701 @default.
• W2890434320 hasConcept C118552586 @default.
• W2890434320 hasConcept C124101348 @default.
• W2890434320 hasConcept C142724271 @default.
• W2890434320 hasConcept C159110408 @default.
• W2890434320 hasConcept C177713679 @default.
• W2890434320 hasConcept C194828623 @default.
• W2890434320 hasConcept C27415008 @default.
• W2890434320 hasConcept C2776289891 @default.
• W2890434320 hasConcept C2776376669 @default.
• W2890434320 hasConcept C2987404301 @default.
• W2890434320 hasConcept C33923547 @default.
• W2890434320 hasConcept C41008148 @default.
• W2890434320 hasConcept C534262118 @default.
• W2890434320 hasConcept C55282118 @default.
• W2890434320 hasConcept C71924100 @default.
• W2890434320 hasConceptScore W2890434320C105795698 @default.
• W2890434320 hasConceptScore W2890434320C111919701 @default.
• W2890434320 hasConceptScore W2890434320C118552586 @default.
• W2890434320 hasConceptScore W2890434320C124101348 @default.
• W2890434320 hasConceptScore W2890434320C142724271 @default.
• W2890434320 hasConceptScore W2890434320C159110408 @default.
• W2890434320 hasConceptScore W2890434320C177713679 @default.
• W2890434320 hasConceptScore W2890434320C194828623 @default.
• W2890434320 hasConceptScore W2890434320C27415008 @default.
• W2890434320 hasConceptScore W2890434320C2776289891 @default.
• W2890434320 hasConceptScore W2890434320C2776376669 @default.
• W2890434320 hasConceptScore W2890434320C2987404301 @default.
• W2890434320 hasConceptScore W2890434320C33923547 @default.
• W2890434320 hasConceptScore W2890434320C41008148 @default.
• W2890434320 hasConceptScore W2890434320C534262118 @default.

• next