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

The timeliness of detection of a sepsis event in progress is a crucial factorin the outcome for the patient. Machine learning models built from data inelectronic health records can be used as an effective tool for improving thistimeliness, but so far the potential for clinical implementations has beenlargely limited to studies in intensive care units. This study will employ aricher data set that will expand the applicability of these models beyondintensive care units. Furthermore, we will circumvent several importantlimitations that have been found in the literature: 1) Models are evaluatedshortly before sepsis onset without considering interventions alreadyinitiated. 2) Machine learning models are built on a restricted set of clinicalparameters, which are not necessarily measured in all departments. 3) Modelperformance is limited by current knowledge of sepsis, as feature interactionsand time dependencies are hardcoded into the model. In this study, we present amodel to overcome these shortcomings using a deep learning approach on adiverse multicenter data set. We used retrospective data from multiple Danishhospitals over a seven-year period. Our sepsis detection system is constructedas a combination of a convolutional neural network and a long short-term memorynetwork. We suggest a retrospective assessment of interventions by looking atintravenous antibiotics and blood cultures preceding the prediction time.Results show performance ranging from AUROC 0.856 (3 hours before sepsis onset)to AUROC 0.756 (24 hours before sepsis onset). We present a deep learningsystem for early detection of sepsis that is able to learn characteristics ofthe key factors and interactions from the raw event sequence data itself,without relying on a labor-intensive feature extraction work.

Early detection of sepsis utilizing deep learning on electronic health record event sequences