English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Multi-source data fusion, in which multiple data sources are jointly analyzedto obtain improved information, has considerable research attention. For thedatasets of multiple medical institutions, data confidentiality andcross-institutional communication are critical. In such cases, datacollaboration (DC) analysis by sharing dimensionality-reduced intermediaterepresentations without iterative cross-institutional communications may beappropriate. Identifiability of the shared data is essential when analyzingdata including personal information. In this study, the identifiability of theDC analysis is investigated. The results reveals that the shared intermediaterepresentations are readily identifiable to the original data for supervisedlearning. This study then proposes a non-readily identifiable DC analysis onlysharing non-readily identifiable data for multiple medical datasets includingpersonal information. The proposed method solves identifiability concerns basedon a random sample permutation, the concept of interpretable DC analysis, andusage of functions that cannot be reconstructed. In numerical experiments onmedical datasets, the proposed method exhibits a non-readily identifiabilitywhile maintaining a high recognition performance of the conventional DCanalysis. For a hospital dataset, the proposed method exhibits a ninepercentage point improvement regarding the recognition performance over thelocal analysis that uses only local dataset.

Non-readily identifiable data collaboration analysis for multiple datasets including personal information