Please use this identifier to cite or link to this item:
Title: Artificial intelligence in sepsis early prediction and diagnosis using unstructured data in healthcare
Authors: Goh, Kim Huat
Wang, Le 
Yeow, Adrian Yong Kwang
Poh, Hermione
Li, Ke
Yeow, Joannas Jie Lin
Tan, Gamaliel Yu Heng
Issue Date: Dec-2021
Publisher: Springer Science and Business Media LLC
Citation: Goh, Kim Huat, Wang, Le, Yeow, Adrian Yong Kwang, Poh, Hermione, Li, Ke, Yeow, Joannas Jie Lin, Tan, Gamaliel Yu Heng (2021-12). Artificial intelligence in sepsis early prediction and diagnosis using unstructured data in healthcare. Nature Communications 12 (1). ScholarBank@NUS Repository.
Abstract: AbstractSepsis is a leading cause of death in hospitals. Early prediction and diagnosis of sepsis, which is critical in reducing mortality, is challenging as many of its signs and symptoms are similar to other less critical conditions. We develop an artificial intelligence algorithm, SERA algorithm, which uses both structured data and unstructured clinical notes to predict and diagnose sepsis. We test this algorithm with independent, clinical notes and achieve high predictive accuracy 12 hours before the onset of sepsis (AUC 0.94, sensitivity 0.87 and specificity 0.87). We compare the SERA algorithm against physician predictions and show the algorithm’s potential to increase the early detection of sepsis by up to 32% and reduce false positives by up to 17%. Mining unstructured clinical notes is shown to improve the algorithm’s accuracy compared to using only clinical measures for early warning 12 to 48 hours before the onset of sepsis.
Source Title: Nature Communications
ISSN: 20411723
DOI: 10.1038/s41467-021-20910-4
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
202101 Nature - AI in Sepsis Prediction.pdf1.02 MBAdobe PDF



Google ScholarTM



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.