Matches in SemOpenAlex for { <https://semopenalex.org/work/W2321014722> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W2321014722 abstract "Mulitask-Temporal approach to develop predictive models using temporal information in EHR data.Display Omitted We discuss methods to use temporal information in EHR data for predictive modeling.We propose a multitask learning based approach.We use our method to predict short-term progression of renal dysfunction.We show that the importance of different predictors vary over time.Our method was able to use temporal information in EHR data to improve performance. Predictive models built using temporal data in electronic health records (EHRs) can potentially play a major role in improving management of chronic diseases. However, these data present a multitude of technical challenges, including irregular sampling of data and varying length of available patient history. In this paper, we describe and evaluate three different approaches that use machine learning to build predictive models using temporal EHR data of a patient.The first approach is a commonly used non-temporal approach that aggregates values of the predictors in the patient's medical history. The other two approaches exploit the temporal dynamics of the data. The two temporal approaches vary in how they model temporal information and handle missing data. Using data from the EHR of Mount Sinai Medical Center, we learned and evaluated the models in the context of predicting loss of estimated glomerular filtration rate (eGFR), the most common assessment of kidney function.Our results show that incorporating temporal information in patient's medical history can lead to better prediction of loss of kidney function. They also demonstrate that exactly how this information is incorporated is important. In particular, our results demonstrate that the relative importance of different predictors varies over time, and that using multi-task learning to account for this is an appropriate way to robustly capture the temporal dynamics in EHR data. Using a case study, we also demonstrate how the multi-task learning based model can yield predictive models with better performance for identifying patients at high risk of short-term loss of kidney function." @default.
- W2321014722 created "2016-06-24" @default.
- W2321014722 creator A5007282049 @default.
- W2321014722 creator A5047405500 @default.
- W2321014722 creator A5049238181 @default.
- W2321014722 creator A5065704891 @default.
- W2321014722 creator A5071606253 @default.
- W2321014722 creator A5091620204 @default.
- W2321014722 date "2014-11-01" @default.
- W2321014722 modified "2023-09-24" @default.
- W2321014722 title "Incorporating temporal EHR data in predictive models for risk stratification of renal function deterioration" @default.
- W2321014722 cites W2028306794 @default.
- W2321014722 cites W2075825059 @default.
- W2321014722 cites W2090260554 @default.
- W2321014722 cites W2091452510 @default.
- W2321014722 cites W2092433795 @default.
- W2321014722 cites W2096607633 @default.
- W2321014722 cites W2136840691 @default.
- W2321014722 cites W2155965977 @default.
- W2321014722 cites W2157556100 @default.
- W2321014722 cites W2165817472 @default.
- W2321014722 cites W2318315426 @default.
- W2321014722 hasPublicationYear "2014" @default.
- W2321014722 type Work @default.
- W2321014722 sameAs 2321014722 @default.
- W2321014722 citedByCount "0" @default.
- W2321014722 crossrefType "journal-article" @default.
- W2321014722 hasAuthorship W2321014722A5007282049 @default.
- W2321014722 hasAuthorship W2321014722A5047405500 @default.
- W2321014722 hasAuthorship W2321014722A5049238181 @default.
- W2321014722 hasAuthorship W2321014722A5065704891 @default.
- W2321014722 hasAuthorship W2321014722A5071606253 @default.
- W2321014722 hasAuthorship W2321014722A5091620204 @default.
- W2321014722 hasConcept C119857082 @default.
- W2321014722 hasConcept C124101348 @default.
- W2321014722 hasConcept C151730666 @default.
- W2321014722 hasConcept C154945302 @default.
- W2321014722 hasConcept C2779343474 @default.
- W2321014722 hasConcept C41008148 @default.
- W2321014722 hasConcept C45804977 @default.
- W2321014722 hasConcept C77277458 @default.
- W2321014722 hasConcept C86803240 @default.
- W2321014722 hasConcept C9357733 @default.
- W2321014722 hasConceptScore W2321014722C119857082 @default.
- W2321014722 hasConceptScore W2321014722C124101348 @default.
- W2321014722 hasConceptScore W2321014722C151730666 @default.
- W2321014722 hasConceptScore W2321014722C154945302 @default.
- W2321014722 hasConceptScore W2321014722C2779343474 @default.
- W2321014722 hasConceptScore W2321014722C41008148 @default.
- W2321014722 hasConceptScore W2321014722C45804977 @default.
- W2321014722 hasConceptScore W2321014722C77277458 @default.
- W2321014722 hasConceptScore W2321014722C86803240 @default.
- W2321014722 hasConceptScore W2321014722C9357733 @default.
- W2321014722 hasLocation W23210147221 @default.
- W2321014722 hasOpenAccess W2321014722 @default.
- W2321014722 hasPrimaryLocation W23210147221 @default.
- W2321014722 hasRelatedWork W2005464046 @default.
- W2321014722 hasRelatedWork W2015462679 @default.
- W2321014722 hasRelatedWork W2050218819 @default.
- W2321014722 hasRelatedWork W2469019492 @default.
- W2321014722 hasRelatedWork W2560004025 @default.
- W2321014722 hasRelatedWork W2611236118 @default.
- W2321014722 hasRelatedWork W2784168210 @default.
- W2321014722 hasRelatedWork W2902998465 @default.
- W2321014722 hasRelatedWork W2963180539 @default.
- W2321014722 hasRelatedWork W2964225306 @default.
- W2321014722 hasRelatedWork W2986132467 @default.
- W2321014722 hasRelatedWork W3026190971 @default.
- W2321014722 hasRelatedWork W3026992267 @default.
- W2321014722 hasRelatedWork W3036914761 @default.
- W2321014722 hasRelatedWork W3094794737 @default.
- W2321014722 hasRelatedWork W3116608762 @default.
- W2321014722 hasRelatedWork W3133650345 @default.
- W2321014722 hasRelatedWork W3187888585 @default.
- W2321014722 hasRelatedWork W3202070916 @default.
- W2321014722 hasRelatedWork W3202149807 @default.
- W2321014722 isParatext "false" @default.
- W2321014722 isRetracted "false" @default.
- W2321014722 magId "2321014722" @default.
- W2321014722 workType "article" @default.