Early Machine-Human Interface around Sepsis Severity Identification: From Diagnosis to Improved Management?

Vikas Bansal, Emir Festic, Muhammad A. Mangi, Nicholl A. Decicco, Ashley N. Reid, Elizabeth L. Gatch, James M Naessens, Pablo Moreno-Franco

Research output: Contribution to journalArticle

Abstract

OBJECTIVE: To investigate the statistical measures of the performance of 2 interventions: a) early sepsis identification by a computerized sepsis "sniffer" algorithm (CSSA) in the emergency department (ED) and b) human decision to activate a multidisciplinary early resuscitation sepsis and shock response team (SSRT). METHODS: This study used a prospective and historical cohort study design to evaluate the performance of two interventions. INTERVENTION: A computerized sepsis sniffer algorithm (CSSA) to aid in early diagnosis and a multidisciplinary sepsis and shock response team (SSRT) to improve patient care by increasing compliance with Surviving Sepsis Campaign (SSC) bundles. RESULTS: The CSSA yielded a sensitivity of 100% (95% CI, 99.13-100%) and a specificity of 96.2% (95% CI, 95.55-96.45%) to identifying sepsis in the ED (Table 1). The SSRT resource was activated appropriately in 34.1% (86/252) of patients meeting severe sepsis or septic shock criteria; the SSRT was inappropriately activated only three times in sepsis-only patients. In 53% (134/252) of cases meeting criteria for SSRT activation, the critical care team was consulted as opposed to activating the SSRT resource. CONCLUSION: Our two-step machine-human interface approach to patients with sepsis utilized an outstandingly sensitive and specific electronic tool followed by more specific human decision-making.

Original languageEnglish (US)
Pages (from-to)27-38
Number of pages12
JournalActa medica academica
Volume47
Issue number1
DOIs
StatePublished - May 1 2018

Fingerprint

Sepsis
Shock
Hospital Emergency Service
Critical Care
Septic Shock
Resuscitation
Early Diagnosis
Decision Making
Patient Care
Cohort Studies

Keywords

  • Algorithm
  • Computerized decision support
  • Sepsis

ASJC Scopus subject areas

  • Medicine(all)

Cite this

Early Machine-Human Interface around Sepsis Severity Identification : From Diagnosis to Improved Management? / Bansal, Vikas; Festic, Emir; Mangi, Muhammad A.; Decicco, Nicholl A.; Reid, Ashley N.; Gatch, Elizabeth L.; Naessens, James M; Moreno-Franco, Pablo.

In: Acta medica academica, Vol. 47, No. 1, 01.05.2018, p. 27-38.

Research output: Contribution to journalArticle

Bansal, Vikas ; Festic, Emir ; Mangi, Muhammad A. ; Decicco, Nicholl A. ; Reid, Ashley N. ; Gatch, Elizabeth L. ; Naessens, James M ; Moreno-Franco, Pablo. / Early Machine-Human Interface around Sepsis Severity Identification : From Diagnosis to Improved Management?. In: Acta medica academica. 2018 ; Vol. 47, No. 1. pp. 27-38.
@article{0687e72dc4094eab8aefd22f71f6c4d5,
title = "Early Machine-Human Interface around Sepsis Severity Identification: From Diagnosis to Improved Management?",
abstract = "OBJECTIVE: To investigate the statistical measures of the performance of 2 interventions: a) early sepsis identification by a computerized sepsis {"}sniffer{"} algorithm (CSSA) in the emergency department (ED) and b) human decision to activate a multidisciplinary early resuscitation sepsis and shock response team (SSRT). METHODS: This study used a prospective and historical cohort study design to evaluate the performance of two interventions. INTERVENTION: A computerized sepsis sniffer algorithm (CSSA) to aid in early diagnosis and a multidisciplinary sepsis and shock response team (SSRT) to improve patient care by increasing compliance with Surviving Sepsis Campaign (SSC) bundles. RESULTS: The CSSA yielded a sensitivity of 100{\%} (95{\%} CI, 99.13-100{\%}) and a specificity of 96.2{\%} (95{\%} CI, 95.55-96.45{\%}) to identifying sepsis in the ED (Table 1). The SSRT resource was activated appropriately in 34.1{\%} (86/252) of patients meeting severe sepsis or septic shock criteria; the SSRT was inappropriately activated only three times in sepsis-only patients. In 53{\%} (134/252) of cases meeting criteria for SSRT activation, the critical care team was consulted as opposed to activating the SSRT resource. CONCLUSION: Our two-step machine-human interface approach to patients with sepsis utilized an outstandingly sensitive and specific electronic tool followed by more specific human decision-making.",
keywords = "Algorithm, Computerized decision support, Sepsis",
author = "Vikas Bansal and Emir Festic and Mangi, {Muhammad A.} and Decicco, {Nicholl A.} and Reid, {Ashley N.} and Gatch, {Elizabeth L.} and Naessens, {James M} and Pablo Moreno-Franco",
year = "2018",
month = "5",
day = "1",
doi = "10.5644/ama2006-124.212",
language = "English (US)",
volume = "47",
pages = "27--38",
journal = "Acta medica academica",
issn = "1840-1848",
publisher = "Academy of Sciences and Arts of Bosnia and Herzegovina",
number = "1",

}

TY - JOUR

T1 - Early Machine-Human Interface around Sepsis Severity Identification

T2 - From Diagnosis to Improved Management?

AU - Bansal, Vikas

AU - Festic, Emir

AU - Mangi, Muhammad A.

AU - Decicco, Nicholl A.

AU - Reid, Ashley N.

AU - Gatch, Elizabeth L.

AU - Naessens, James M

AU - Moreno-Franco, Pablo

PY - 2018/5/1

Y1 - 2018/5/1

N2 - OBJECTIVE: To investigate the statistical measures of the performance of 2 interventions: a) early sepsis identification by a computerized sepsis "sniffer" algorithm (CSSA) in the emergency department (ED) and b) human decision to activate a multidisciplinary early resuscitation sepsis and shock response team (SSRT). METHODS: This study used a prospective and historical cohort study design to evaluate the performance of two interventions. INTERVENTION: A computerized sepsis sniffer algorithm (CSSA) to aid in early diagnosis and a multidisciplinary sepsis and shock response team (SSRT) to improve patient care by increasing compliance with Surviving Sepsis Campaign (SSC) bundles. RESULTS: The CSSA yielded a sensitivity of 100% (95% CI, 99.13-100%) and a specificity of 96.2% (95% CI, 95.55-96.45%) to identifying sepsis in the ED (Table 1). The SSRT resource was activated appropriately in 34.1% (86/252) of patients meeting severe sepsis or septic shock criteria; the SSRT was inappropriately activated only three times in sepsis-only patients. In 53% (134/252) of cases meeting criteria for SSRT activation, the critical care team was consulted as opposed to activating the SSRT resource. CONCLUSION: Our two-step machine-human interface approach to patients with sepsis utilized an outstandingly sensitive and specific electronic tool followed by more specific human decision-making.

AB - OBJECTIVE: To investigate the statistical measures of the performance of 2 interventions: a) early sepsis identification by a computerized sepsis "sniffer" algorithm (CSSA) in the emergency department (ED) and b) human decision to activate a multidisciplinary early resuscitation sepsis and shock response team (SSRT). METHODS: This study used a prospective and historical cohort study design to evaluate the performance of two interventions. INTERVENTION: A computerized sepsis sniffer algorithm (CSSA) to aid in early diagnosis and a multidisciplinary sepsis and shock response team (SSRT) to improve patient care by increasing compliance with Surviving Sepsis Campaign (SSC) bundles. RESULTS: The CSSA yielded a sensitivity of 100% (95% CI, 99.13-100%) and a specificity of 96.2% (95% CI, 95.55-96.45%) to identifying sepsis in the ED (Table 1). The SSRT resource was activated appropriately in 34.1% (86/252) of patients meeting severe sepsis or septic shock criteria; the SSRT was inappropriately activated only three times in sepsis-only patients. In 53% (134/252) of cases meeting criteria for SSRT activation, the critical care team was consulted as opposed to activating the SSRT resource. CONCLUSION: Our two-step machine-human interface approach to patients with sepsis utilized an outstandingly sensitive and specific electronic tool followed by more specific human decision-making.

KW - Algorithm

KW - Computerized decision support

KW - Sepsis

UR - http://www.scopus.com/inward/record.url?scp=85056267898&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85056267898&partnerID=8YFLogxK

U2 - 10.5644/ama2006-124.212

DO - 10.5644/ama2006-124.212

M3 - Article

C2 - 29957969

AN - SCOPUS:85056267898

VL - 47

SP - 27

EP - 38

JO - Acta medica academica

JF - Acta medica academica

SN - 1840-1848

IS - 1

ER -