Evaluating Artificial Intelligence-Based Clinical Decision Support for Sepsis and ARDS

NCT07025096 | Enrolling By Invitation

• 2 other identifiers: 858201R35GM155262
• Study Type: interventional
• Target: 350
• Locations: 1 country
• Sites: 1

Brief Summary

Sepsis and acute respiratory distress syndrome (ARDS) are common in intensive care units. Managing sepsis and ARDS is inherently complex and requires making numerous decisions under uncertainty. Artificial intelligence (AI) clinical decision support systems (CDSSs) offer a promising approach to support care management for sepsis and ARDS. The goal of this randomized, survey-based study is to compare treatment recommendations enacted by clinicians to those generated by an AI CDSS. The study will investigate whether an AI CDSS can generate treatment recommendations that are safe, appropriate, and indistinguishable to those provided by real clinicians. In this study, participants (i.e., critical care clinicians) will review a series of critical care cases (vignettes) in an electronic survey. Each vignette will contain a de-identified case of a patient with sepsis and ARDS as well as treatment recommendations for the case. Participants will assess the safety and appropriateness of each treatment recommendations and answer whether they think the treatment recommendations came from the clinician or an AI CDSS.

Conditions

Sepsis; Acute Respiratory Distress Syndrome (ARDS)

Keywords

Sepsis; Acute Respiratory Distress Syndrome; Clinical Decision Support; Clinical Decision Support System; Invasive Mechanical Ventilation; Artificial Intelligence

Outcome Measures

Primary Outcomes (1)

• Accuracy of Predicting the Source of Treatment Recommendation

  Participants will answer if they think the treatment recommendations came from artificial intelligence (AI) or a clinician for each clinical vignette. Accuracy will be measured by participants correctly identifying the source of treatment recommendation.

  From enrollment to the end of the survey, an average of 45 minutes

Secondary Outcomes (3)

• Confidence of Predicting the Source of Treatment Recommendation

  From enrollment to the end of the survey, an average of 45 minutes

• Appropriateness of Treatment Recommendations

  From enrollment to the end of the survey, an average of 45 minutes

• Safety of Treatment Recommendations

  From enrollment to the end of the survey, an average of 45 minutes

Study Arms (2)

Artificial Intelligence

EXPERIMENTAL

Critical care cases / vignettes in this arm will contain treatment recommendations generated by an artificial intelligence-based clinical decision support system. Each participant will review four vignettes from this arm.

Other: Artifical Intelligence-Generated Treatment Recommendations

Human Clinician

NO INTERVENTION

Critical care cases / vignettes in this arm will contain treatment recommendations that were enacted by the clinician in the actual case. Each participant will review four vignettes from this arm.

Interventions

Artifical Intelligence-Generated Treatment Recommendations OTHER

The clinical vignette will contain treatment recommendations which were generated by an artificial intelligence-based clinical decision support system.

Artificial Intelligence

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)

You may qualify if:

• Working as a physician (i.e., MD, DO) or an advanced practice provider (i.e., nurse practitioner, physician assistant)
• Working at a hospital or medical center in medical critical care, anesthesia critical care, surgical critical care, or emergency medicine

You may not qualify if:

• Has not completed a residency training program (i.e., medical intern or resident)

Sponsors & Collaborators

• University of Pennsylvania: lead
• National Institute of General Medical Sciences (NIGMS): collaborator

Study Sites (1)

University of Pennsylvania

Philadelphia, Pennsylvania, 19104, United States

Location

Related Publications (1)

• Angeli Gazola A, Bishop NS, Schmid BE, Pirracchio R, Valley TS, Bhavani SV, Krutsinger DC, Giannini HM, Lu Y, Ungar LH, Meyer NJ, Kerlin MP, Weissman GE. Evaluating AI-based comprehensive clinical decision support for sepsis and ARDS: protocol for a Clinician Turing Test. BMJ Open. 2025 Dec 24;15(12):e106757. doi: 10.1136/bmjopen-2025-106757.

  PMID: 41448698 DERIVED

MeSH Terms

Conditions

Sepsis; Respiratory Distress Syndrome

Condition Hierarchy (Ancestors)

Infections; Systemic Inflammatory Response Syndrome; Inflammation; Pathologic Processes; Pathological Conditions, Signs and Symptoms; Lung Diseases; Respiratory Tract Diseases; Respiration Disorders

Study Officials

• Gary Weissman, MD, MSHP

  University of Pennsylvania

  PRINCIPAL INVESTIGATOR

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: RANDOMIZED
• Masking: SINGLE
• Who Masked: PARTICIPANT
• Purpose: HEALTH SERVICES RESEARCH
• Intervention Model: PARALLEL
• Sponsor Type: OTHER
• Responsible Party: SPONSOR

Model Details: Participants will review a series of clinical vignettes. Each vignette will be randomized to show a treatment recommendation either from an artificial intelligence-based clinical decision support system (AI CDSS) or from the clinician in the case, reflecting actual clinical practice. Vignettes will be randomized equally, and participants will see an equal number of vignettes from each arm.

Study Record Dates

• First Submitted: May 30, 2025
• First Posted: June 17, 2025
• Study Start: December 5, 2025
• Primary Completion: May 1, 2026
• Study Completion: May 1, 2026
• Last Updated: February 17, 2026

Record last verified: 2026-02

Locations

US (1)