File(s) under permanent embargo
Improved risk predictions via sparse imputation of patient conditions in electronic medical records
conference contribution
posted on 2015-10-19, 00:00 authored by Budhaditya Saha, Sunil GuptaSunil Gupta, Svetha VenkateshSvetha VenkateshElectronic 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.
History
Event
Data Science and Advanced Analytics. Conference (2015 : Paris, France)Pagination
1 - 10Publisher
IEEELocation
Paris, FrancePlace of publication
Piscataway, N.J.Publisher DOI
Start date
2015-10-19End date
2015-10-21ISBN-13
9781467382724Language
engPublication classification
E Conference publication; E1 Full written paper - refereedCopyright notice
2015, IEEEEditor/Contributor(s)
E Gaussier, L Cao, P Gallinari, J Kwok, G Pasi, O ZaianeTitle of proceedings
DSAA 2015: IEEE International Conference on Data Science and Advanced AnalyticsUsage metrics
Categories
No categories selectedKeywords
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC