Medical Record Abstraction for Quality Improvement in Sepsis Care Using Artificial Intelligence: A Cluster - Scorecard - MDSpire

Medical Record Abstraction for Quality Improvement in Sepsis Care Using Artificial Intelligence: A Cluster

  • By

  • Aaron Boussina

  • Claire Allison

  • Kimberly Quintero

  • Sonia Jain

  • Chad VanDenBerg

  • Michael Hogarth

  • Amy M. Sitapati

  • Karandeep Singh

  • Atul Malhotra

  • Michael T. McCurdy

  • Christopher A. Longhurst

  • James S. Ford

  • Theodore Chan

  • Paul Ishimine

  • Richard Childers

  • Shamim Nemati

  • Gabriel Wardi

  • June 25, 2026

  • 0 min

Share

Clinical Scorecard: Utilizing Artificial Intelligence for Quality Enhancement in Sepsis Management through Medical Record Abstraction: A Cluster Analysis

At a Glance

CategoryDetail
ConditionSepsis Management
Key MechanismsArtificial Intelligence for quality measurement and performance feedback
Target PopulationPatients with severe sepsis and septic shock
Care SettingEmergency Departments

Key Highlights

  • AI-enabled scaling of SEP-1 measurement can improve compliance
  • Study conducted in two academic medical centers
  • Timely feedback provided to intervention group using LLM
  • SEP-1 compliance baseline was 65%
  • Quality measurement challenges include high costs and poor interrater reliability

Guideline-Based Recommendations

Diagnosis

  • Use clinical encounter diagnosis for identifying sepsis cases

Management

  • Implement AI systems for real-time feedback on sepsis care

Monitoring & Follow-up

  • Evaluate SEP-1 compliance at the time of discharge

Risks

  • Potential for noncompliance cases in standard reporting

Patient & Prescribing Data

Patients with severe sepsis and septic shock in emergency departments

AI systems can enhance the quality of sepsis care through timely feedback

Clinical Best Practices

  • Utilize LLMs for abstraction of quality measures
  • Conduct regular training for physicians on sepsis management
  • Ensure timely reporting and feedback mechanisms are in place

Related Resources & Content

Original Source(s)

Related Content