Matches in SemOpenAlex for { <https://semopenalex.org/work/W2188015611> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W2188015611 abstract "Electronic Medical Records (EMR) are increasingly used for risk prediction. EMR analysis is complicated by missing entries. There are two reasons — the “primary reason for admission” is included in EMR, but the co-morbidities (other chronic diseases) are left uncoded, and, many zero values in the data are accurate, reflecting that a patient has not accessed medical facilities. A key challenge is to deal with the peculiarities of this data — unlike many other datasets, EMR is sparse, reflecting the fact that patients have some, but not all diseases. We propose a novel model to fill-in these missing values, and use the new representation for prediction of key hospital events. To “fill-in” missing values, we represent the feature-patient matrix as a product of two low rank factors, preserving the sparsity property in the product. Intuitively, the product regularization allows sparse imputation of patient conditions reflecting common comorbidities across patients. We develop a scalable optimization algorithm based on Block coordinate descent method to find an optimal solution. We evaluate the proposed framework on two real world EMR cohorts: Cancer (7000 admissions) and Acute Myocardial Infarction (2652 admissions). Our result shows that the AUC for 3 months admission prediction is improved significantly from (0.741 to 0.786) for Cancer data and (0.678 to 0.724) for AMI data. We also extend the proposed method to a supervised model for predicting of multiple related risk outcomes (e.g. emergency presentations and admissions in hospital over 3, 6 and 12 months period) in an integrated framework. For this model, the AUC averaged over outcomes is improved significantly from (0.768 to 0.806) for Cancer data and (0.685 to 0.748) for AMI data." @default.
- W2188015611 created "2016-06-24" @default.
- W2188015611 creator A5011012522 @default.
- W2188015611 creator A5037997498 @default.
- W2188015611 creator A5045540854 @default.
- W2188015611 date "2015-10-01" @default.
- W2188015611 modified "2023-09-26" @default.
- W2188015611 title "Improved risk predictions via sparse imputation of patient conditions in electronic medical records" @default.
- W2188015611 cites W1494192010 @default.
- W2188015611 cites W1969116741 @default.
- W2188015611 cites W1969698720 @default.
- W2188015611 cites W1975900269 @default.
- W2188015611 cites W1983866540 @default.
- W2188015611 cites W1995243833 @default.
- W2188015611 cites W1998249118 @default.
- W2188015611 cites W2004910511 @default.
- W2188015611 cites W2012451988 @default.
- W2188015611 cites W2042759724 @default.
- W2188015611 cites W2068548513 @default.
- W2188015611 cites W2103972604 @default.
- W2188015611 cites W2114157572 @default.
- W2188015611 cites W2121382432 @default.
- W2188015611 cites W2130903752 @default.
- W2188015611 cites W2137245235 @default.
- W2188015611 cites W2143995004 @default.
- W2188015611 cites W2146130798 @default.
- W2188015611 cites W2164278908 @default.
- W2188015611 cites W2165238043 @default.
- W2188015611 cites W2401999504 @default.
- W2188015611 cites W2404638125 @default.
- W2188015611 cites W2611328865 @default.
- W2188015611 cites W2952066970 @default.
- W2188015611 cites W2963173886 @default.
- W2188015611 cites W807207105 @default.
- W2188015611 doi "https://doi.org/10.1109/dsaa.2015.7344790" @default.
- W2188015611 hasPublicationYear "2015" @default.
- W2188015611 type Work @default.
- W2188015611 sameAs 2188015611 @default.
- W2188015611 citedByCount "0" @default.
- W2188015611 crossrefType "proceedings-article" @default.
- W2188015611 hasAuthorship W2188015611A5011012522 @default.
- W2188015611 hasAuthorship W2188015611A5037997498 @default.
- W2188015611 hasAuthorship W2188015611A5045540854 @default.
- W2188015611 hasConcept C119857082 @default.
- W2188015611 hasConcept C124101348 @default.
- W2188015611 hasConcept C126838900 @default.
- W2188015611 hasConcept C154945302 @default.
- W2188015611 hasConcept C195910791 @default.
- W2188015611 hasConcept C41008148 @default.
- W2188015611 hasConcept C48044578 @default.
- W2188015611 hasConcept C58041806 @default.
- W2188015611 hasConcept C71924100 @default.
- W2188015611 hasConcept C77088390 @default.
- W2188015611 hasConcept C9357733 @default.
- W2188015611 hasConceptScore W2188015611C119857082 @default.
- W2188015611 hasConceptScore W2188015611C124101348 @default.
- W2188015611 hasConceptScore W2188015611C126838900 @default.
- W2188015611 hasConceptScore W2188015611C154945302 @default.
- W2188015611 hasConceptScore W2188015611C195910791 @default.
- W2188015611 hasConceptScore W2188015611C41008148 @default.
- W2188015611 hasConceptScore W2188015611C48044578 @default.
- W2188015611 hasConceptScore W2188015611C58041806 @default.
- W2188015611 hasConceptScore W2188015611C71924100 @default.
- W2188015611 hasConceptScore W2188015611C77088390 @default.
- W2188015611 hasConceptScore W2188015611C9357733 @default.
- W2188015611 hasLocation W21880156111 @default.
- W2188015611 hasOpenAccess W2188015611 @default.
- W2188015611 hasPrimaryLocation W21880156111 @default.
- W2188015611 hasRelatedWork W1562433567 @default.
- W2188015611 hasRelatedWork W178422781 @default.
- W2188015611 hasRelatedWork W2065189618 @default.
- W2188015611 hasRelatedWork W2072939266 @default.
- W2188015611 hasRelatedWork W2107098692 @default.
- W2188015611 hasRelatedWork W2137283541 @default.
- W2188015611 hasRelatedWork W2607618013 @default.
- W2188015611 hasRelatedWork W2620924547 @default.
- W2188015611 hasRelatedWork W2782925919 @default.
- W2188015611 hasRelatedWork W2889721888 @default.
- W2188015611 hasRelatedWork W2909388807 @default.
- W2188015611 hasRelatedWork W2952547388 @default.
- W2188015611 hasRelatedWork W2963267245 @default.
- W2188015611 hasRelatedWork W2968883412 @default.
- W2188015611 hasRelatedWork W3029856140 @default.
- W2188015611 hasRelatedWork W3042102985 @default.
- W2188015611 hasRelatedWork W3048898492 @default.
- W2188015611 hasRelatedWork W3103471119 @default.
- W2188015611 hasRelatedWork W3157807213 @default.
- W2188015611 hasRelatedWork W3207770250 @default.
- W2188015611 isParatext "false" @default.
- W2188015611 isRetracted "false" @default.
- W2188015611 magId "2188015611" @default.
- W2188015611 workType "article" @default.