Sepsis Detection in Sparse Clinical Data Using Long Short-Term Memory Network with Dice Loss

Tomáš Vičar, Jakub Hejč, Petra Novotná, Marina Ronzhina, Radovan Smíšek

Computing in cardiology · 2019 · 10 citations · 22 references

DOIFull text

Open access

Concepts

Abstract

This paper aims to present a methodology for sepsis prediction from clinical time-series data. Sepsis is one of the most threatening states which could occur while treating a patient at the intensive care unit. Therefore its prediction could significantly improve the quality of the patient treatment.

References

22