FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4220688658> ?p ?o ?g. }

• W4220688658 abstract "Analysing distributed medical data is challenging because of data sensitivity and various regulations to access and combine data. Some privacy-preserving methods are known for analyzing horizontally-partitioned data, where different organisations have similar data on disjoint sets of people. Technically more challenging is the case of vertically-partitioned data, dealing with data on overlapping sets of people. We use an emerging technology based on cryptographic techniques called secure multi-party computation (MPC), and apply it to perform privacy-preserving survival analysis on vertically-distributed data by means of the Cox proportional hazards (CPH) model. Both MPC and CPH are explained.We use a Newton-Raphson solver to securely train the CPH model with MPC, jointly with all data holders, without revealing any sensitive data. In order to securely compute the log-partial likelihood in each iteration, we run into several technical challenges to preserve the efficiency and security of our solution. To tackle these technical challenges, we generalize a cryptographic protocol for securely computing the inverse of the Hessian matrix and develop a new method for securely computing exponentiations. A theoretical complexity estimate is given to get insight into the computational and communication effort that is needed.Our secure solution is implemented in a setting with three different machines, each presenting a different data holder, which can communicate through the internet. The MPyC platform is used for implementing this privacy-preserving solution to obtain the CPH model. We test the accuracy and computation time of our methods on three standard benchmark survival datasets. We identify future work to make our solution more efficient.Our secure solution is comparable with the standard, non-secure solver in terms of accuracy and convergence speed. The computation time is considerably larger, although the theoretical complexity is still cubic in the number of covariates and quadratic in the number of subjects. We conclude that this is a promising way of performing parametric survival analysis on vertically-distributed medical data, while realising high level of security and privacy." @default.
• W4220688658 created "2022-04-03" @default.
• W4220688658 creator A5011847040 @default.
• W4220688658 creator A5032557386 @default.
• W4220688658 creator A5059641753 @default.
• W4220688658 creator A5063680118 @default.
• W4220688658 creator A5082927171 @default.
• W4220688658 date "2022-02-24" @default.
• W4220688658 modified "2023-10-18" @default.
• W4220688658 title "Accurate training of the Cox proportional hazards model on vertically-partitioned data while preserving privacy" @default.
• W4220688658 cites W1914060921 @default.
• W4220688658 cites W1946622722 @default.
• W4220688658 cites W1990464273 @default.
• W4220688658 cites W1991724805 @default.
• W4220688658 cites W1992190287 @default.
• W4220688658 cites W2032880981 @default.
• W4220688658 cites W2066203299 @default.
• W4220688658 cites W2077373711 @default.
• W4220688658 cites W2103512230 @default.
• W4220688658 cites W2141420453 @default.
• W4220688658 cites W2293886080 @default.
• W4220688658 cites W2322285943 @default.
• W4220688658 cites W2324805613 @default.
• W4220688658 cites W2402235285 @default.
• W4220688658 cites W2499359132 @default.
• W4220688658 cites W2539273492 @default.
• W4220688658 cites W2615825791 @default.
• W4220688658 cites W2625373021 @default.
• W4220688658 cites W2918009042 @default.
• W4220688658 cites W2956118517 @default.
• W4220688658 cites W2963620978 @default.
• W4220688658 cites W2975921124 @default.
• W4220688658 cites W2995099704 @default.
• W4220688658 cites W3015150750 @default.
• W4220688658 cites W3017915781 @default.
• W4220688658 cites W3021150134 @default.
• W4220688658 cites W3108533068 @default.
• W4220688658 cites W3141585064 @default.
• W4220688658 cites W3147894994 @default.
• W4220688658 cites W3208465125 @default.
• W4220688658 cites W4205228770 @default.
• W4220688658 cites W4292363360 @default.
• W4220688658 cites W6162803 @default.
• W4220688658 cites W102674675 @default.
• W4220688658 doi "https://doi.org/10.1186/s12911-022-01771-3" @default.
• W4220688658 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35209883" @default.
• W4220688658 hasPublicationYear "2022" @default.
• W4220688658 type Work @default.
• W4220688658 citedByCount "4" @default.
• W4220688658 countsByYear W42206886582023 @default.
• W4220688658 crossrefType "journal-article" @default.
• W4220688658 hasAuthorship W4220688658A5011847040 @default.
• W4220688658 hasAuthorship W4220688658A5032557386 @default.
• W4220688658 hasAuthorship W4220688658A5059641753 @default.
• W4220688658 hasAuthorship W4220688658A5063680118 @default.
• W4220688658 hasAuthorship W4220688658A5082927171 @default.
• W4220688658 hasBestOaLocation W42206886581 @default.
• W4220688658 hasConcept C11413529 @default.
• W4220688658 hasConcept C123201435 @default.
• W4220688658 hasConcept C124101348 @default.
• W4220688658 hasConcept C13280743 @default.
• W4220688658 hasConcept C178489894 @default.
• W4220688658 hasConcept C18396474 @default.
• W4220688658 hasConcept C185798385 @default.
• W4220688658 hasConcept C203616005 @default.
• W4220688658 hasConcept C205649164 @default.
• W4220688658 hasConcept C28826006 @default.
• W4220688658 hasConcept C33923547 @default.
• W4220688658 hasConcept C38652104 @default.
• W4220688658 hasConcept C41008148 @default.
• W4220688658 hasConcept C45374587 @default.
• W4220688658 hasConcept C80444323 @default.
• W4220688658 hasConceptScore W4220688658C11413529 @default.
• W4220688658 hasConceptScore W4220688658C123201435 @default.
• W4220688658 hasConceptScore W4220688658C124101348 @default.
• W4220688658 hasConceptScore W4220688658C13280743 @default.
• W4220688658 hasConceptScore W4220688658C178489894 @default.
• W4220688658 hasConceptScore W4220688658C18396474 @default.
• W4220688658 hasConceptScore W4220688658C185798385 @default.
• W4220688658 hasConceptScore W4220688658C203616005 @default.
• W4220688658 hasConceptScore W4220688658C205649164 @default.
• W4220688658 hasConceptScore W4220688658C28826006 @default.
• W4220688658 hasConceptScore W4220688658C33923547 @default.
• W4220688658 hasConceptScore W4220688658C38652104 @default.
• W4220688658 hasConceptScore W4220688658C41008148 @default.
• W4220688658 hasConceptScore W4220688658C45374587 @default.
• W4220688658 hasConceptScore W4220688658C80444323 @default.
• W4220688658 hasIssue "1" @default.
• W4220688658 hasLocation W42206886581 @default.
• W4220688658 hasLocation W42206886582 @default.
• W4220688658 hasLocation W42206886583 @default.
• W4220688658 hasLocation W42206886584 @default.
• W4220688658 hasLocation W42206886585 @default.
• W4220688658 hasLocation W42206886586 @default.
• W4220688658 hasOpenAccess W4220688658 @default.
• W4220688658 hasPrimaryLocation W42206886581 @default.
• W4220688658 hasRelatedWork W1451223395 @default.
• W4220688658 hasRelatedWork W2082804893 @default.
• W4220688658 hasRelatedWork W2130457818 @default.
• W4220688658 hasRelatedWork W2206791037 @default.

• next