tran-learningvector-2015.pdf (2.9 MB)
Learning vector representation of medical objects via EMR-driven nonnegative restricted Boltzmann machines (eNRBM)
journal contribution
posted on 2015-04-01, 00:00 authored by Truyen TranTruyen Tran, Tu Dinh Nguyen, Quoc-Dinh Phung, Svetha VenkateshSvetha VenkateshElectronic medical record (EMR) offers promises for novel analytics. However, manual feature engineering from EMR is labor intensive because EMR is complex - it contains temporal, mixed-type and multimodal data packed in irregular episodes. We present a computational framework to harness EMR with minimal human supervision via restricted Boltzmann machine (RBM). The framework derives a new representation of medical objects by embedding them in a low-dimensional vector space. This new representation facilitates algebraic and statistical manipulations such as projection onto 2D plane (thereby offering intuitive visualization), object grouping (hence enabling automated phenotyping), and risk stratification. To enhance model interpretability, we introduced two constraints into model parameters: (a) nonnegative coefficients, and (b) structural smoothness. These result in a novel model called eNRBM (EMR-driven nonnegative RBM). We demonstrate the capability of the eNRBM on a cohort of 7578 mental health patients under suicide risk assessment. The derived representation not only shows clinically meaningful feature grouping but also facilitates short-term risk stratification. The F-scores, 0.21 for moderate-risk and 0.36 for high-risk, are significantly higher than those obtained by clinicians and competitive with the results obtained by support vector machines.
History
Journal
Journal of biomedical informaticsVolume
54Pagination
96 - 105Publisher
ElsevierLocation
Amsterdam, The NetherlandsPublisher DOI
Link to full text
eISSN
1532-0480Language
engPublication classification
C Journal article; C1 Refereed article in a scholarly journalCopyright notice
2015, ElsevierUsage metrics
Categories
No categories selectedKeywords
Electronic medical recordsFeature groupingMedical objects embeddingSuicide risk stratificationVector representationElectronic Health RecordsFemaleHumansMaleMarkov ChainsMedical InformaticsMental DisordersModels, StatisticalNeoplasmsNeural Networks (Computer)Risk AssessmentSuicideSupport Vector MachineScience & TechnologyTechnologyLife Sciences & BiomedicineComputer Science, Interdisciplinary ApplicationsComputer ScienceSUICIDAL-BEHAVIORMENTAL-HEALTHRISK-FACTORSCOMORBIDITYRECORDSPREVALENCEDEPRESSIONDISORDERVALIDITYDISEASE
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC