Learning vector representation of medical objects via EMR-driven nonnegative restricted Boltzmann machines (eNRBM)
MetadataShow full item record
Electronic 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.
Showing items related by title, author, creator and subject.
Kerr, Thor (2013)A consortium of property developers set out to occupy 345 hectares of sea bed near Fremantle Port by claiming that their project, North Port Quay, would demonstrate that the community of Western Australia could ‘lead the ...
Claessen, Mary; Leitao, Suze (2012)It has been hypothesized that children with specific language impairment (SLI) have difficulty processing sound-based information, including storing and accessing phonological representations in the lexicon. Tasks are ...
Hussain, Omar; Dillon, Tharam S.; Hussain, Farookh Khadeer; Chang, Elizabeth (2010)Business activities are a result of carefully formed associations between different users in order to achieve certain pre-decided outcomes. Decision-making in such associations is an important step and transactional risk ...