Unpacking Prevalence and Dichotomy in qSOFA Parameters: A Step towards Multi-parameter Intelligent Sepsis Prediction in ICU

Considering the severity and annual treatment costs, the rising incidents of sepsis and septic shock in the United States among ICU admissions is an increasing concern. The purpose of this research is to unpack the most prevalent criterion for sepsis based on the qSOFA predictors, the most prevalent sepsis scenario in the ICU; and investigate the dichotomy among qSOFA parameters. This study is conducted using critical care database of MIT: MIMIC-III; and takes the qSOFA parameters - altered mental status in Glasgow Coma Scale, respiratory rate, and systolic arterial blood pressure - for patients admitted to the critical care units from 2001 to 2012 into account to understand the prevalence and relation between these parameters among the patients underwent sepsis screening. This study reveals tachypnea (high respiratory rate) as the most prevalent sepsis criterion, and two-factored sepsis comprising of tachypnea and altered mental status as the most prevalent scenario experienced among the sepsis patients in ICU. Besides, Pearson correlation coefficients from our analysis affirm the dichotomy among the sepsis parameters. This data-driven insight offers design implication for multi-parameter intelligent sepsis prediction in ICU.