FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2907519982> ?p ?o ?g. }

• W2907519982 abstract "A clinically meaningful distance metric, which is learned from measuring patient similarity, plays an important role in clinical decision support applications. Several metric learning approaches have been proposed to measure patient similarity, but they are mostly designed for learning the metric at only one time point/interval. It leads to a problem that those approaches cannot reflect the similarity variations among patients with the progression of diseases. In order to capture similarity information from multiple future time points simultaneously, we formulate a multi-task metric learning approach to identify patient similarity. However, it is challenging to directly apply traditional multi-task metric learning methods to learn such similarities due to the high dimensional, complex and noisy nature of healthcare data. Besides, the disease labels often have clinical relationships, which should not be treated as independent. Unfortunately, traditional formulation of the loss function ignores the degree of labels' similarity. To tackle the aforementioned challenges, we propose mtTSML, a multi-task triplet constrained sparse metric learning method, to monitor the similarity progression of patient pairs. In the proposed model, the distance for each task can be regarded as the combination of a common part and a task-specific one in the transformed low-rank space. We then perform sparse feature selection for each individual task to select the most discriminative information. Moreover, we use triplet constraints to guarantee the margin between similar and less similar pairs according to the ordered information of disease severity levels (i.e. labels). The experimental results on two real-world healthcare datasets show that the proposed multi-task metric learning method significantly outperforms the state-of-the-art baselines, including both single-task and multi-task metric learning methods." @default.
• W2907519982 created "2019-01-11" @default.
• W2907519982 creator A5001030192 @default.
• W2907519982 creator A5013588572 @default.
• W2907519982 creator A5014346487 @default.
• W2907519982 creator A5016035883 @default.
• W2907519982 creator A5033311476 @default.
• W2907519982 creator A5053419913 @default.
• W2907519982 date "2018-11-01" @default.
• W2907519982 modified "2023-10-16" @default.
• W2907519982 title "Multi-task Sparse Metric Learning for Monitoring Patient Similarity Progression" @default.
• W2907519982 cites W1965701254 @default.
• W2907519982 cites W1998396170 @default.
• W2907519982 cites W1999802986 @default.
• W2907519982 cites W2031250362 @default.
• W2907519982 cites W2048110836 @default.
• W2907519982 cites W2053226533 @default.
• W2907519982 cites W2054110507 @default.
• W2907519982 cites W2058046352 @default.
• W2907519982 cites W2116453957 @default.
• W2907519982 cites W2134982367 @default.
• W2907519982 cites W2155012713 @default.
• W2907519982 cites W2162003701 @default.
• W2907519982 cites W2169495281 @default.
• W2907519982 cites W2358113125 @default.
• W2907519982 cites W236448318 @default.
• W2907519982 cites W2401999504 @default.
• W2907519982 cites W2583115687 @default.
• W2907519982 cites W2584780866 @default.
• W2907519982 cites W2585971786 @default.
• W2907519982 cites W2743780043 @default.
• W2907519982 cites W2767391771 @default.
• W2907519982 cites W2775102587 @default.
• W2907519982 cites W2801388832 @default.
• W2907519982 cites W2801461046 @default.
• W2907519982 cites W2809398771 @default.
• W2907519982 cites W2809627483 @default.
• W2907519982 cites W2886951144 @default.
• W2907519982 cites W2963094609 @default.
• W2907519982 doi "https://doi.org/10.1109/icdm.2018.00063" @default.
• W2907519982 hasPublicationYear "2018" @default.
• W2907519982 type Work @default.
• W2907519982 sameAs 2907519982 @default.
• W2907519982 citedByCount "15" @default.
• W2907519982 countsByYear W29075199822018 @default.
• W2907519982 countsByYear W29075199822019 @default.
• W2907519982 countsByYear W29075199822020 @default.
• W2907519982 countsByYear W29075199822021 @default.
• W2907519982 countsByYear W29075199822022 @default.
• W2907519982 countsByYear W29075199822023 @default.
• W2907519982 crossrefType "proceedings-article" @default.
• W2907519982 hasAuthorship W2907519982A5001030192 @default.
• W2907519982 hasAuthorship W2907519982A5013588572 @default.
• W2907519982 hasAuthorship W2907519982A5014346487 @default.
• W2907519982 hasAuthorship W2907519982A5016035883 @default.
• W2907519982 hasAuthorship W2907519982A5033311476 @default.
• W2907519982 hasAuthorship W2907519982A5053419913 @default.
• W2907519982 hasConcept C103278499 @default.
• W2907519982 hasConcept C114614502 @default.
• W2907519982 hasConcept C115961682 @default.
• W2907519982 hasConcept C119857082 @default.
• W2907519982 hasConcept C124101348 @default.
• W2907519982 hasConcept C138885662 @default.
• W2907519982 hasConcept C153180895 @default.
• W2907519982 hasConcept C154945302 @default.
• W2907519982 hasConcept C162324750 @default.
• W2907519982 hasConcept C164226766 @default.
• W2907519982 hasConcept C176217482 @default.
• W2907519982 hasConcept C187736073 @default.
• W2907519982 hasConcept C21547014 @default.
• W2907519982 hasConcept C2776401178 @default.
• W2907519982 hasConcept C2780451532 @default.
• W2907519982 hasConcept C33923547 @default.
• W2907519982 hasConcept C41008148 @default.
• W2907519982 hasConcept C41895202 @default.
• W2907519982 hasConcept C774472 @default.
• W2907519982 hasConcept C97931131 @default.
• W2907519982 hasConceptScore W2907519982C103278499 @default.
• W2907519982 hasConceptScore W2907519982C114614502 @default.
• W2907519982 hasConceptScore W2907519982C115961682 @default.
• W2907519982 hasConceptScore W2907519982C119857082 @default.
• W2907519982 hasConceptScore W2907519982C124101348 @default.
• W2907519982 hasConceptScore W2907519982C138885662 @default.
• W2907519982 hasConceptScore W2907519982C153180895 @default.
• W2907519982 hasConceptScore W2907519982C154945302 @default.
• W2907519982 hasConceptScore W2907519982C162324750 @default.
• W2907519982 hasConceptScore W2907519982C164226766 @default.
• W2907519982 hasConceptScore W2907519982C176217482 @default.
• W2907519982 hasConceptScore W2907519982C187736073 @default.
• W2907519982 hasConceptScore W2907519982C21547014 @default.
• W2907519982 hasConceptScore W2907519982C2776401178 @default.
• W2907519982 hasConceptScore W2907519982C2780451532 @default.
• W2907519982 hasConceptScore W2907519982C33923547 @default.
• W2907519982 hasConceptScore W2907519982C41008148 @default.
• W2907519982 hasConceptScore W2907519982C41895202 @default.
• W2907519982 hasConceptScore W2907519982C774472 @default.
• W2907519982 hasConceptScore W2907519982C97931131 @default.
• W2907519982 hasLocation W29075199821 @default.
• W2907519982 hasOpenAccess W2907519982 @default.
• W2907519982 hasPrimaryLocation W29075199821 @default.

• next