Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385482594> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W4385482594 abstract "Health risk refers to the probability of the occurrence of a specific health outcome for a specific patient. Interest in health risk prediction has been increasing, especially with the availability of a large amount of electronic health records (EHR). An EHR contains multivariate time series data that records meaningful information associated with a chronological set of clinical events for each patient. Recurrent neural networks (RNN) and hidden Markov models (HMM) have been widely used as generative models of time series data. RNN-based models have strong prediction performance but lack transparency. HMMs have a simple functional form and the ability to provide an intuitive probabilistic interpretation, but their state dynamics are 'memoryless', making it difficult to thoroughly take into account the irregularity in patients' health trajectory. This paper proposes a novel deep Markov network for health risk prediction. The method integrates two modules, a GRU (Gated Recurrent Unit) with attention mechanism and a Neural HMM, into a single network. The GRU generates the inputs required for health risk predictions and uses an attention mechanism to create memorable state dynamics for the Neural HMM. The Neural HMM then provides interpretable structured representations through training. Mixture Density Networks are incorporated in the Neural HMM, which contribute to the modeling of complex patterns found in the transition process. Furthermore, an inference network is designed to embed hidden state representations of GRU and Neural HMM into the same space. The inference network enables the two types of representations to learn from each other during the decoding process of Neural HMM, thereby improving the quality of interpretable structured representations. Experimental results on MIMIC-III and eICU datasets demonstrate that our method can outperform state-of-the-art methods and provide transparency of the model decisions." @default.
- W4385482594 created "2023-08-03" @default.
- W4385482594 creator A5000633755 @default.
- W4385482594 creator A5001608625 @default.
- W4385482594 creator A5067376850 @default.
- W4385482594 date "2023-06-18" @default.
- W4385482594 modified "2023-09-26" @default.
- W4385482594 title "NeuralHMM: A Deep Markov Network for Health Risk Prediction using Electronic Health Records" @default.
- W4385482594 cites W1677182931 @default.
- W4385482594 cites W2064675550 @default.
- W4385482594 cites W2150845035 @default.
- W4385482594 cites W2157331557 @default.
- W4385482594 cites W2396881363 @default.
- W4385482594 cites W2769215776 @default.
- W4385482594 cites W2891400669 @default.
- W4385482594 cites W2964010366 @default.
- W4385482594 cites W2964232608 @default.
- W4385482594 cites W2997653844 @default.
- W4385482594 cites W3015593438 @default.
- W4385482594 cites W3016032135 @default.
- W4385482594 cites W3038139858 @default.
- W4385482594 cites W3080987150 @default.
- W4385482594 cites W3101973032 @default.
- W4385482594 cites W3160263899 @default.
- W4385482594 cites W4296175910 @default.
- W4385482594 doi "https://doi.org/10.1109/ijcnn54540.2023.10191594" @default.
- W4385482594 hasPublicationYear "2023" @default.
- W4385482594 type Work @default.
- W4385482594 citedByCount "0" @default.
- W4385482594 crossrefType "proceedings-article" @default.
- W4385482594 hasAuthorship W4385482594A5000633755 @default.
- W4385482594 hasAuthorship W4385482594A5001608625 @default.
- W4385482594 hasAuthorship W4385482594A5067376850 @default.
- W4385482594 hasConcept C107673813 @default.
- W4385482594 hasConcept C119857082 @default.
- W4385482594 hasConcept C147168706 @default.
- W4385482594 hasConcept C154945302 @default.
- W4385482594 hasConcept C160735492 @default.
- W4385482594 hasConcept C162324750 @default.
- W4385482594 hasConcept C163836022 @default.
- W4385482594 hasConcept C23224414 @default.
- W4385482594 hasConcept C2776214188 @default.
- W4385482594 hasConcept C3019952477 @default.
- W4385482594 hasConcept C41008148 @default.
- W4385482594 hasConcept C50522688 @default.
- W4385482594 hasConcept C50644808 @default.
- W4385482594 hasConcept C82142266 @default.
- W4385482594 hasConcept C98763669 @default.
- W4385482594 hasConceptScore W4385482594C107673813 @default.
- W4385482594 hasConceptScore W4385482594C119857082 @default.
- W4385482594 hasConceptScore W4385482594C147168706 @default.
- W4385482594 hasConceptScore W4385482594C154945302 @default.
- W4385482594 hasConceptScore W4385482594C160735492 @default.
- W4385482594 hasConceptScore W4385482594C162324750 @default.
- W4385482594 hasConceptScore W4385482594C163836022 @default.
- W4385482594 hasConceptScore W4385482594C23224414 @default.
- W4385482594 hasConceptScore W4385482594C2776214188 @default.
- W4385482594 hasConceptScore W4385482594C3019952477 @default.
- W4385482594 hasConceptScore W4385482594C41008148 @default.
- W4385482594 hasConceptScore W4385482594C50522688 @default.
- W4385482594 hasConceptScore W4385482594C50644808 @default.
- W4385482594 hasConceptScore W4385482594C82142266 @default.
- W4385482594 hasConceptScore W4385482594C98763669 @default.
- W4385482594 hasLocation W43854825941 @default.
- W4385482594 hasOpenAccess W4385482594 @default.
- W4385482594 hasPrimaryLocation W43854825941 @default.
- W4385482594 hasRelatedWork W1581104981 @default.
- W4385482594 hasRelatedWork W2114483795 @default.
- W4385482594 hasRelatedWork W2146143523 @default.
- W4385482594 hasRelatedWork W2226204588 @default.
- W4385482594 hasRelatedWork W2574982804 @default.
- W4385482594 hasRelatedWork W2696198890 @default.
- W4385482594 hasRelatedWork W2989726406 @default.
- W4385482594 hasRelatedWork W4281386417 @default.
- W4385482594 hasRelatedWork W4327831767 @default.
- W4385482594 hasRelatedWork W4385482594 @default.
- W4385482594 isParatext "false" @default.
- W4385482594 isRetracted "false" @default.
- W4385482594 workType "article" @default.