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

Background Korian® group is specialized in care and support for fragile people. Its professional data warehouse (DWH) is operational today in 300 French nursing homes (NH). The transmissions' table, daily-fed by caregivers, contains key data about residents' care and health. Thanks to long-term stays and substantial available data, we can build residents' life trajectories. In the past, we designed syndromes such as falls, flu, acute gastro enteritis and emergency calls by using the standard query language (SQL) but now we want to go further, analyzing the caregiver's feelings about residents' health. We will show here that our method involving syndromes' approach and then, sentiment analysis can improve residents' life prediction and achieve transparency and interpretability of the whole data flow process. Methods First, we selected all residents with at least one transmission over the last six weeks of 2014. Second, we extracted among them those having at least one transmission over the last six weeks of 2018, the 'survivors', and those found dead before, the 'deceased'. Third, we extracted both groups' transmissions over a 60 days period, removed the 'syndromic' ones and gave small subsets of the remaining ones, after anonymization and random sampling, to the Korian® physicians' network to classify into four features. Then, we completed this qualitative data with scores such as the autonomy level (AL = 1-6 higher the better), to build sentiment analysis but also new 'opinion' syndromes with SQL. Results We found, among 12,278 residents living in 155 NH in 2014: 3,075 survivors with 82% women (mean age = 85.3, AL = 3), 18% men (mean age=79.7, AL = 3.2) with 9,687 syndromes among 84,416 transmissions.2,900 deceased with 72% women (mean age = 88.7, AL = 2.3), 28% men (mean age=86.5, AL = 2.3) with 11,305 syndromes among 109,073transmissions. Conclusions We are confident that our interdisciplinary sentiment analysis will deepen the quantitative aging process understanding. Key messages After SQL procedures to extract syndromes, we moved health-transmissions data out of the silos and gave it to our physicians’ network for further analysis designing a truly interdisciplinary approach. The transmissions’ table with its nursing care narratives textual content can help us track every resident through time and space, define health features and deepen residents’ aging process knowledge.

Moving out of the silos: from nursing homes clinical narratives to salient features of care