Dose Regulation Model of Norepinephrine Based on LSTM Network and Clustering Analysis in Sepsis

Abstract

Sepsis is a life-threatening condition that arises when the body's response to infection causes injury to its own tissues and organs. Despite the advancement of medical diagnosis and treatment technologies, the morbidity and mortality of sepsis are still relatively high. In this paper, a two-layer long short-term memory (LSTM) model is proposed to predict the dose of norepinephrine, in order to control the blood pressure of patients. The proposed modeling approach is evaluated using the MIMIC-III dataset, achieving higher performance.

Keywords

• Time series data
• LSTM
• Clustering
• Sepsis
• Blood pressure regulation