RetainVis: Visual Analytics with Interpretable and Interactive Recurrent Neural Networks on Electronic Medical Records

Cited 158 time in webofscience Cited 128 time in scopus
  • Hit : 749
  • Download : 0
DC FieldValueLanguage
dc.contributor.authorKwon, Bum Chulko
dc.contributor.authorChoi, Min-Jeko
dc.contributor.authorKim, Joanne Taeryko
dc.contributor.authorChoi, Edwardko
dc.contributor.authorKim, Young Binko
dc.contributor.authorKwon, Soonwookko
dc.contributor.authorSun, Jimengko
dc.contributor.authorChoo, Jaegulko
dc.date.accessioned2020-03-24T06:20:07Z-
dc.date.available2020-03-24T06:20:07Z-
dc.date.created2020-03-24-
dc.date.created2020-03-24-
dc.date.created2020-03-24-
dc.date.created2020-03-24-
dc.date.created2020-03-24-
dc.date.issued2019-01-
dc.identifier.citationIEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS, v.25, no.1, pp.299 - 309-
dc.identifier.issn1077-2626-
dc.identifier.urihttp://hdl.handle.net/10203/273431-
dc.description.abstractWe have recently seen many successful applications of recurrent neural networks (RNNs) on electronic medical records (EMRs), which contain histories of patients' diagnoses, medications, and other various events, in order to predict the current and future states of patients. Despite the strong performance of RNNs, it is often challenging for users to understand why the model makes a particular prediction. Such black-box nature of RNNs can impede its wide adoption in clinical practice. Furthermore, we have no established methods to interactively leverage users' domain expertise and prior knowledge as inputs for steering the model. Therefore, our design study aims to provide a visual analytics solution to increase interpretability and interactivity of RNNs via a joint effort of medical experts, artificial intelligence scientists, and visual analytics researchers. Following the iterative design process between the experts, we design, implement, and evaluate a visual analytics tool called RetainVis, which couples a newly improved, interpretable, and interactive RNN-based model called RetainEX and visualizations for users' exploration of EMR data in the context of prediction tasks. Our study shows the effective use of RetainVis for gaining insights into how individual medical codes contribute to making risk predictions, using EMRs of patients with heart failure and cataract symptoms. Our study also demonstrates how we made substantial changes to the state-of-the-art RNN model called RETAIN in order to make use of temporal information and increase interactivity. This study will provide a useful guideline for researchers that aim to design an interpretable and interactive visual analytics tool for RNNs.-
dc.languageEnglish-
dc.publisherIEEE COMPUTER SOC-
dc.titleRetainVis: Visual Analytics with Interpretable and Interactive Recurrent Neural Networks on Electronic Medical Records-
dc.typeArticle-
dc.identifier.wosid000452640000029-
dc.identifier.scopusid2-s2.0-85052616093-
dc.type.rimsART-
dc.citation.volume25-
dc.citation.issue1-
dc.citation.beginningpage299-
dc.citation.endingpage309-
dc.citation.publicationnameIEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS-
dc.identifier.doi10.1109/TVCG.2018.2865027-
dc.contributor.localauthorChoi, Edward-
dc.contributor.localauthorChoo, Jaegul-
dc.contributor.nonIdAuthorKwon, Bum Chul-
dc.contributor.nonIdAuthorChoi, Min-Je-
dc.contributor.nonIdAuthorKim, Joanne Taery-
dc.contributor.nonIdAuthorKim, Young Bin-
dc.contributor.nonIdAuthorKwon, Soonwook-
dc.contributor.nonIdAuthorSun, Jimeng-
dc.description.isOpenAccessN-
dc.type.journalArticleArticle-
dc.subject.keywordAuthorInteractive Artificial Intelligence-
dc.subject.keywordAuthorXAI (Explainable Artificial Intelligence)-
dc.subject.keywordAuthorInterpretable Deep Learning-
dc.subject.keywordAuthorHealthcare-
dc.subject.keywordPlusHEART-FAILURE-
dc.subject.keywordPlusCEREBROVASCULAR-DISEASE-
dc.subject.keywordPlusPARAMETERS-
dc.subject.keywordPlusRISK-
Appears in Collection
AI-Journal Papers(저널논문)
Files in This Item
There are no files associated with this item.
This item is cited by other documents in WoS
⊙ Detail Information in WoSⓡ Click to see webofscience_button
⊙ Cited 158 items in WoS Click to see citing articles in records_button

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0