FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3131883061> ?p ?o ?g. }

• W3131883061 endingPage "388" @default.
• W3131883061 startingPage "378" @default.
• W3131883061 abstract "Background: Due to the non-randomized nature of real-world data, prognostic factors need to be balanced, which is often done by propensity scores (PSs). This study aimed to investigate whether autoencoders, which are unsupervised deep learning architectures, might be leveraged to compute PS. Methods: We selected patient-level data of 128,368 first-line treated cancer patients from the Flatiron Health EHR-derived de-identified database. We trained an autoencoder architecture to learn a lower-dimensional patient representation, which we used to compute PS. To compare the performance of an autoencoder-based PS with established methods, we performed a simulation study. We assessed the balancing and adjustment performance using standardized mean differences, root mean square errors (RMSE), percent bias, and confidence interval coverage. To illustrate the application of the autoencoder-based PS, we emulated the PRONOUNCE trial by applying the trial’s protocol elements within an observational database setting, comparing two chemotherapy regimens. Results: All methods but the manual variable selection approach led to well-balanced cohorts with average standardized mean differences <0.1. LASSO yielded on average the lowest deviation of resulting estimates (RMSE 0.0205) followed by the autoencoder approach (RMSE 0.0248). Altering the hyperparameter setup in sensitivity analysis, the autoencoder approach led to similar results as LASSO (RMSE 0.0203 and 0.0205, respectively). In the case study, all methods provided a similar conclusion with point estimates clustered around the null (e.g., HR autoencoder 1.01 [95% confidence interval = 0.80, 1.27] vs. HR PRONOUNCE 1.07 [0.83, 1.36]). Conclusions: Autoencoder-based PS computation was a feasible approach to control for confounding but did not perform better than some established approaches like LASSO." @default.
• W3131883061 created "2021-03-01" @default.
• W3131883061 creator A5018835914 @default.
• W3131883061 creator A5028827406 @default.
• W3131883061 creator A5030710827 @default.
• W3131883061 creator A5044005254 @default.
• W3131883061 creator A5045020502 @default.
• W3131883061 creator A5083128670 @default.
• W3131883061 creator A5090973737 @default.
• W3131883061 date "2021-02-01" @default.
• W3131883061 modified "2023-09-27" @default.
• W3131883061 title "Deep Learning-based Propensity Scores for Confounding Control in Comparative Effectiveness Research" @default.
• W3131883061 cites W1849521086 @default.
• W3131883061 cites W1967862917 @default.
• W3131883061 cites W1976167126 @default.
• W3131883061 cites W1987723939 @default.
• W3131883061 cites W1996016456 @default.
• W3131883061 cites W2000991311 @default.
• W3131883061 cites W2012658469 @default.
• W3131883061 cites W2034309896 @default.
• W3131883061 cites W2036193982 @default.
• W3131883061 cites W2037135054 @default.
• W3131883061 cites W2037564432 @default.
• W3131883061 cites W2040253672 @default.
• W3131883061 cites W2073225472 @default.
• W3131883061 cites W2080682920 @default.
• W3131883061 cites W2095967516 @default.
• W3131883061 cites W2126049444 @default.
• W3131883061 cites W2128305533 @default.
• W3131883061 cites W2146607417 @default.
• W3131883061 cites W2150291618 @default.
• W3131883061 cites W2152849583 @default.
• W3131883061 cites W2159767831 @default.
• W3131883061 cites W2168458505 @default.
• W3131883061 cites W2169711166 @default.
• W3131883061 cites W2298338128 @default.
• W3131883061 cites W2404901863 @default.
• W3131883061 cites W2537384258 @default.
• W3131883061 cites W2621763716 @default.
• W3131883061 cites W2749889369 @default.
• W3131883061 cites W2751349726 @default.
• W3131883061 cites W2794084722 @default.
• W3131883061 cites W2831840344 @default.
• W3131883061 cites W2886144609 @default.
• W3131883061 cites W2921045850 @default.
• W3131883061 cites W2938070244 @default.
• W3131883061 cites W2940166270 @default.
• W3131883061 cites W2942234794 @default.
• W3131883061 cites W2951381561 @default.
• W3131883061 cites W2964696298 @default.
• W3131883061 cites W2966630186 @default.
• W3131883061 cites W3011104356 @default.
• W3131883061 cites W3012524460 @default.
• W3131883061 cites W3046163941 @default.
• W3131883061 cites W3098865414 @default.
• W3131883061 cites W3098949126 @default.
• W3131883061 cites W3102970921 @default.
• W3131883061 doi "https://doi.org/10.1097/ede.0000000000001338" @default.
• W3131883061 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/33591049" @default.
• W3131883061 hasPublicationYear "2021" @default.
• W3131883061 type Work @default.
• W3131883061 sameAs 3131883061 @default.
• W3131883061 citedByCount "9" @default.
• W3131883061 countsByYear W31318830612022 @default.
• W3131883061 countsByYear W31318830612023 @default.
• W3131883061 crossrefType "journal-article" @default.
• W3131883061 hasAuthorship W3131883061A5018835914 @default.
• W3131883061 hasAuthorship W3131883061A5028827406 @default.
• W3131883061 hasAuthorship W3131883061A5030710827 @default.
• W3131883061 hasAuthorship W3131883061A5044005254 @default.
• W3131883061 hasAuthorship W3131883061A5045020502 @default.
• W3131883061 hasAuthorship W3131883061A5083128670 @default.
• W3131883061 hasAuthorship W3131883061A5090973737 @default.
• W3131883061 hasConcept C101738243 @default.
• W3131883061 hasConcept C105795698 @default.
• W3131883061 hasConcept C119857082 @default.
• W3131883061 hasConcept C139945424 @default.
• W3131883061 hasConcept C154945302 @default.
• W3131883061 hasConcept C17923572 @default.
• W3131883061 hasConcept C22679943 @default.
• W3131883061 hasConcept C23131810 @default.
• W3131883061 hasConcept C33923547 @default.
• W3131883061 hasConcept C41008148 @default.
• W3131883061 hasConcept C44249647 @default.
• W3131883061 hasConcept C50644808 @default.
• W3131883061 hasConcept C77350462 @default.
• W3131883061 hasConceptScore W3131883061C101738243 @default.
• W3131883061 hasConceptScore W3131883061C105795698 @default.
• W3131883061 hasConceptScore W3131883061C119857082 @default.
• W3131883061 hasConceptScore W3131883061C139945424 @default.
• W3131883061 hasConceptScore W3131883061C154945302 @default.
• W3131883061 hasConceptScore W3131883061C17923572 @default.
• W3131883061 hasConceptScore W3131883061C22679943 @default.
• W3131883061 hasConceptScore W3131883061C23131810 @default.
• W3131883061 hasConceptScore W3131883061C33923547 @default.
• W3131883061 hasConceptScore W3131883061C41008148 @default.
• W3131883061 hasConceptScore W3131883061C44249647 @default.
• W3131883061 hasConceptScore W3131883061C50644808 @default.

• next