FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4302024654> ?p ?o ?g. }

• W4302024654 endingPage "107175" @default.
• W4302024654 startingPage "107175" @default.
• W4302024654 abstract "Treatment effect estimation, as a fundamental problem in causal inference, focuses on estimating the outcome difference between different treatments. However, in clinical observational data, some patient covariates (such as gender, age) not only affect the outcomes but also affect the treatment assignment. Such covariates, named as confounders, produce distribution discrepancies between different treatment groups, thereby introducing the selection bias for the estimation of treatment effects. The situation is even more complicated in longitudinal data, because the confounders are time-varying that are subject to patient history and meanwhile affect the future outcomes and treatment assignments. Existing methods mainly work on cross-sectional data obtained at a specific time point, but cannot process the time-varying confounders hidden in the longitudinal data.In this study, we address this problem for the first time by disentangled representation learning, which considers the observational data as consisting of three components, including outcome-specific factors, treatment-specific factors, and time-varying confounders. Based on this, the proposed approach adopts a recurrent neural network-based framework to process sequential information and learn the disentangled representations of the components from longitudinal observational sequences, captures the posterior distributions of latent factors by multi-task learning strategy. Moreover, mutual information-based regularization is adopted to eliminate the time-varying confounders. In this way, the association between patient history and treatment assignment is removed and the estimation can be effectively conducted.We evaluate our model in a realistic set-up using a model of tumor growth. The proposed model achieves the best performance over benchmark models for both one-step ahead prediction (0.70% vs 0.74% for the-state-of-the-art model, when γ = 3. Measured by normalized root mean square error, the lower the better) and five-step ahead prediction (1.47% vs 1.83%) in most cases. By increasing the effect of confounders, our proposed model always shows superiority against the state-of-the-art model. In addition, we adopted T-SNE to visualize the disentangled representations and present the effectiveness of disentanglement explicitly and intuitively.The experimental results indicate the powerful capacity of our model in learning disentangled representations from longitudinal observational data and dealing with the time-varying confounders, and demonstrate the surpassing performance achieved by our proposed model on dynamic treatment effect estimation." @default.
• W4302024654 created "2022-10-06" @default.
• W4302024654 creator A5024071911 @default.
• W4302024654 creator A5046872618 @default.
• W4302024654 creator A5047856952 @default.
• W4302024654 creator A5051501904 @default.
• W4302024654 creator A5056505424 @default.
• W4302024654 creator A5091899643 @default.
• W4302024654 date "2022-11-01" @default.
• W4302024654 modified "2023-09-28" @default.
• W4302024654 title "Disentangled representation for sequential treatment effect estimation" @default.
• W4302024654 cites W2008029919 @default.
• W4302024654 cites W2009187570 @default.
• W4302024654 cites W2034806082 @default.
• W4302024654 cites W2039811614 @default.
• W4302024654 cites W2064675550 @default.
• W4302024654 cites W2064903582 @default.
• W4302024654 cites W2082299845 @default.
• W4302024654 cites W2085227190 @default.
• W4302024654 cites W2088188021 @default.
• W4302024654 cites W2101794973 @default.
• W4302024654 cites W2107602010 @default.
• W4302024654 cites W2111201888 @default.
• W4302024654 cites W2150291618 @default.
• W4302024654 cites W2760826895 @default.
• W4302024654 cites W2799605298 @default.
• W4302024654 cites W2912533302 @default.
• W4302024654 cites W2928673187 @default.
• W4302024654 cites W3080718665 @default.
• W4302024654 cites W3125459412 @default.
• W4302024654 cites W3138387740 @default.
• W4302024654 cites W3160537436 @default.
• W4302024654 cites W4281777295 @default.
• W4302024654 doi "https://doi.org/10.1016/j.cmpb.2022.107175" @default.
• W4302024654 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36242866" @default.
• W4302024654 hasPublicationYear "2022" @default.
• W4302024654 type Work @default.
• W4302024654 citedByCount "0" @default.
• W4302024654 crossrefType "journal-article" @default.
• W4302024654 hasAuthorship W4302024654A5024071911 @default.
• W4302024654 hasAuthorship W4302024654A5046872618 @default.
• W4302024654 hasAuthorship W4302024654A5047856952 @default.
• W4302024654 hasAuthorship W4302024654A5051501904 @default.
• W4302024654 hasAuthorship W4302024654A5056505424 @default.
• W4302024654 hasAuthorship W4302024654A5091899643 @default.
• W4302024654 hasConcept C105795698 @default.
• W4302024654 hasConcept C119043178 @default.
• W4302024654 hasConcept C119857082 @default.
• W4302024654 hasConcept C144237770 @default.
• W4302024654 hasConcept C148220186 @default.
• W4302024654 hasConcept C149782125 @default.
• W4302024654 hasConcept C154945302 @default.
• W4302024654 hasConcept C158600405 @default.
• W4302024654 hasConcept C23131810 @default.
• W4302024654 hasConcept C2776135515 @default.
• W4302024654 hasConcept C2776214188 @default.
• W4302024654 hasConcept C33923547 @default.
• W4302024654 hasConcept C41008148 @default.
• W4302024654 hasConcept C77350462 @default.
• W4302024654 hasConceptScore W4302024654C105795698 @default.
• W4302024654 hasConceptScore W4302024654C119043178 @default.
• W4302024654 hasConceptScore W4302024654C119857082 @default.
• W4302024654 hasConceptScore W4302024654C144237770 @default.
• W4302024654 hasConceptScore W4302024654C148220186 @default.
• W4302024654 hasConceptScore W4302024654C149782125 @default.
• W4302024654 hasConceptScore W4302024654C154945302 @default.
• W4302024654 hasConceptScore W4302024654C158600405 @default.
• W4302024654 hasConceptScore W4302024654C23131810 @default.
• W4302024654 hasConceptScore W4302024654C2776135515 @default.
• W4302024654 hasConceptScore W4302024654C2776214188 @default.
• W4302024654 hasConceptScore W4302024654C33923547 @default.
• W4302024654 hasConceptScore W4302024654C41008148 @default.
• W4302024654 hasConceptScore W4302024654C77350462 @default.
• W4302024654 hasFunder F4320321001 @default.
• W4302024654 hasLocation W43020246541 @default.
• W4302024654 hasLocation W43020246542 @default.
• W4302024654 hasOpenAccess W4302024654 @default.
• W4302024654 hasPrimaryLocation W43020246541 @default.
• W4302024654 hasRelatedWork W2301199057 @default.
• W4302024654 hasRelatedWork W2540939911 @default.
• W4302024654 hasRelatedWork W2982818049 @default.
• W4302024654 hasRelatedWork W3105378735 @default.
• W4302024654 hasRelatedWork W3138340382 @default.
• W4302024654 hasRelatedWork W3208489104 @default.
• W4302024654 hasRelatedWork W4221146606 @default.
• W4302024654 hasRelatedWork W4286896224 @default.
• W4302024654 hasRelatedWork W4287119207 @default.
• W4302024654 hasRelatedWork W4296012301 @default.
• W4302024654 hasVolume "226" @default.
• W4302024654 isParatext "false" @default.
• W4302024654 isRetracted "false" @default.
• W4302024654 workType "article" @default.