Unpacking prevalence and dichotomy in qsofa parameters: A step towards multi-parameter intelligent sepsis prediction in ICU

Nazmus Sakib, Devansh Saxena, Lin He, Paul M. Griffin, Sheikh Iqbal Ahamed, Munirul Haque

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Scopus citations

Abstract

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.

Original languageEnglish (US)
Title of host publication2019 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2019 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728108483
DOIs
StatePublished - May 2019
Event2019 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2019 - Chicago, United States
Duration: May 19 2019May 22 2019

Publication series

Name2019 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2019 - Proceedings

Conference

Conference2019 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2019
Country/TerritoryUnited States
CityChicago
Period5/19/195/22/19

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Signal Processing
  • Information Systems and Management
  • Biomedical Engineering
  • Health Informatics
  • Radiology Nuclear Medicine and imaging

Fingerprint

Dive into the research topics of 'Unpacking prevalence and dichotomy in qsofa parameters: A step towards multi-parameter intelligent sepsis prediction in ICU'. Together they form a unique fingerprint.

Cite this