Sepsis Clinical Scoring Systems

SUMMARY:

  • Sepsis scoring systems to identify patients with potential sepsis have been in use for decades.

  • Very few have been incorporated into clinical practice due to a number of limitations.

  • The evolution of machine learning algorithms will be a major disruptor in this area.

REVIEW:

  • The original sepsis scoring tool was published in 1992 with the first Sepsis Consensus Conference, entitled the Systemic Inflammatory Response Syndrome (SIRS).
  • A number of clinical scoring systems have been developed since then with the goal of an easy approach to assessing a patient’s outcome based on a small number of predefined clinical variables.

  • Originally focused on a single organ system, these scoring tools have evolved for general use.

  • Many scoring systems used to potentially identify early sepsis patients were actually designed to indicate patient severity by organ system.

  • These scoring systems have similar design considerations:

    • Use threshold values for specific organ systems
    • Some are used to assess length of stay and/or mortality
  • These scoring systems ARE NOT:
    • Intended as an individual prognostic indicator, but are typically used in that manner.
    • Differentiate between Severity, Acuity, or Stability
    • Generally not designed specifically for sepsis
    • Of value outside the ICU setting
  • Biochemical markers may play a major role in the assessment of blood stream infections and sepsis.
    • However, since up to 40% of sepsis patients may have negative blood cultures, these markers are not typically included in the scoring systems.
  • Inclusion of factors contributing to patient clinical context (i.e. comorbidities, genomics, etc) are also typically missing from these scoring systems.
  • For these reasons, only a few scoring systems have been integrated into clinical practice.

CONCLUSIONS:

  • Clinical scoring systems have been used for early sepsis identification for decades.

  • Unfortunately, these scoring systems have not gained widespread integration into clinical practice due to the heterogeneous nature of sepsis and lack of sensitivity and specificity of any score.

  • New scoring systems are needed which include biochemical, clinical parameters and machine learning techniques.

To receive articles like these in your Inbox, you can subscribe to Sepsis Program Optimization Insights.

Subscribe to sepsis program optimization insights

Erkan Hassan is the Co-Founder & Chief Clinical Officer of Sepsis Program Optimization where he designs & oversees the implementation of solutions to optimize sepsis programs.

To discuss your organization’s Barriers of Effective Sepsis Care, contact Erkan by phone (844) 4SEPSIS (844-473-7747), email (erkan@spo.icu), or video chat.