CYLGNov 30, 2017

Predicting Severe Sepsis Using Text from the Electronic Health Record

arXiv:1711.11536v121 citations
Originality Incremental advance
AI Analysis

This work addresses the critical problem of early severe sepsis prediction for clinicians, potentially enabling earlier intervention.

This paper predicts severe sepsis up to 24 hours in advance using only text reports from Electronic Health Records (EHR). The models built using unstructured text alone slightly outperform those using structured numerical data alone, and combining both further improves performance.

Employing a machine learning approach we predict, up to 24 hours prior, a diagnosis of severe sepsis. Strongly predictive models are possible that use only text reports from the Electronic Health Record (EHR), and omit structured numerical data. Unstructured text alone gives slightly better performance than structured data alone, and the combination further improves performance. We also discuss advantages of using unstructured EHR text for modeling, as compared to structured EHR data.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes