Stabilized sparse ordinal regression for medical risk stratification Tran, Truyen, Phung, Quoc-Dinh, Luo, Wei and Venkatesh, Svetha 2015, Stabilized sparse ordinal regression for medical risk stratification, Knowledge and information systems: an international journal, vol. 43, no. 3, pp. 555-582, doi: 10.1007/s10115-014-0740-4. Attached Files Name Description MIMEType Size Downloads Title Stabilized sparse ordinal regression for medical risk stratification Author(s) Tran, Truyen orcid.org/0000-0001-6531-8907 Phung, Quoc-Dinh orcid.org/0000-0002-9977-8247 Luo, Wei orcid.org/0000-0002-4711-7543 Venkatesh, Svetha orcid.org/0000-0001-8675-6631 Journal name Knowledge and information systems: an international journal Volume number 43 Issue number 3 Start page 555 End page 582 Total pages 28 Publisher Springer Place of publication Berlin, Germany Publication date 2015-06 ISSN 0219-1377 0219-3116 Keyword(s) electronic medical record feature graph medical risk stratification sparse ordinal regression stability Science & Technology Technology Computer Science, Artificial Intelligence Computer Science, Information Systems Computer Science VARIABLE SELECTION MENTAL-HEALTH LOGISTIC-REGRESSION SUICIDE MODELS CLASSIFICATION REGULARIZATION PREVALENCE CONTACT LASSO stat.AP stat.ME Summary The recent wide adoption of electronic medical records (EMRs) presents great opportunities and challenges for data mining. The EMR data are largely temporal, often noisy, irregular and high dimensional. This paper constructs a novel ordinal regression framework for predicting medical risk stratification from EMR. First, a conceptual view of EMR as a temporal image is constructed to extract a diverse set of features. Second, ordinal modeling is applied for predicting cumulative or progressive risk. The challenges are building a transparent predictive model that works with a large number of weakly predictive features, and at the same time, is stable against resampling variations. Our solution employs sparsity methods that are stabilized through domain-specific feature interaction networks. We introduces two indices that measure the model stability against data resampling. Feature networks are used to generate two multivariate Gaussian priors with sparse precision matrices (the Laplacian and Random Walk). We apply the framework on a large short-term suicide risk prediction problem and demonstrate that our methods outperform clinicians to a large margin, discover suicide risk factors that conform with mental health knowledge, and produce models with enhanced stability. © 2014 Springer-Verlag London. Language eng DOI 10.1007/s10115-014-0740-4 Field of Research 080109 Pattern Recognition and Data Mining 0801 Artificial Intelligence And Image Processing Socio Economic Objective 970108 Expanding Knowledge in the Information and Computing Sciences HERDC Research category C1 Refereed article in a scholarly journal ERA Research output type C Journal article Copyright notice ©2014, Springer Persistent URL http://hdl.handle.net/10536/DRO/DU:30080058 Document type: Journal Article Collections: Faculty of Science, Engineering and Built Environment Centre for Pattern Recognition and Data Analytics (PRADA) Duplicates 2018 ERA Submission Related Links Link Description Link to the original record Go to link with your DU access privileges   Connect to published version Go to link with your DU access privileges     Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved. Versions Version Filter Type Thu, 03 Dec 2015, 15:37:46 EST Fri, 04 Dec 2015, 04:02:37 EST Fri, 09 Mar 2018, 09:53:15 EST Fri, 09 Mar 2018, 13:50:13 EST Fri, 09 Mar 2018, 14:07:36 EST Fri, 19 Oct 2018, 14:20:48 EST Tue, 23 Oct 2018, 08:18:51 EST Filtered Full Citation counts:   Cited 14 times in TR Web of Science Cited 17 times in Scopus Search Google Scholar Access Statistics: 331 Abstract Views, 3 File Downloads  -  Detailed Statistics Created: Fri, 09 Mar 2018, 09:53:15 EST

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.