AI-Based Support for Sepsis and ARDS

Overseen By Nicholas Bishop

Age: 18+

Sex: Any

Trial Phase: Academic

Sponsor: University of Pennsylvania

Disqualifiers: Medical intern, Resident

No Placebo Group All trial participants will receive the active study treatment (no placebo)

Compensation: Varies

Number of Visits: 1

What You Need to Know Before You Apply

What is the purpose of this trial?

This trial explores how artificial intelligence (AI) can assist doctors in treating sepsis and acute respiratory distress syndrome (ARDS). The study compares AI-generated treatment suggestions to those made by clinicians to determine if AI recommendations are equally safe and appropriate. Critical care clinicians will participate by reviewing case studies and assessing whether treatment suggestions originated from AI or a human doctor. The trial seeks doctors and advanced practice providers working in critical care or emergency medicine. As an unphased trial, this study offers a unique opportunity to contribute to groundbreaking research that could enhance clinical decision-making in critical care.

Will I have to stop taking my current medications?

The trial does not specify whether participants need to stop taking their current medications. However, since the study involves reviewing patient cases rather than direct patient care, it is unlikely that participants need to change their medication routine.

What prior data suggests that this AI-based clinical decision support system is safe for generating treatment recommendations?

Research has shown that AI-based systems can safely assist in treating sepsis and acute respiratory distress syndrome (ARDS). Studies have found that AI can suggest treatments based on data, which might be as safe and effective as those suggested by human doctors.

AI systems may outperform current methods in quickly and accurately detecting sepsis, helping doctors make better treatment decisions. So far, no reports have indicated that AI causes harm in these situations.

Overall, using AI in sepsis and ARDS care appears promising and could enhance treatment safety by providing doctors with data-driven advice. ^{1 2 3 4 5}

Why are researchers excited about this trial?

Researchers are excited about AI-based support for sepsis and ARDS because it offers a new approach to enhancing clinical decision-making. Unlike traditional treatments where human clinicians rely on their expertise and experience to make recommendations, this system uses artificial intelligence to generate treatment suggestions based on critical care cases. This AI-driven method could potentially improve accuracy and speed in treatment decisions, helping to save lives by quickly identifying the best treatment path. By integrating AI, there is hope for more personalized and precise care, reducing the burden on healthcare professionals and improving patient outcomes.

What evidence suggests that this AI-based support is effective for managing sepsis and ARDS?

Research has shown that artificial intelligence (AI) can significantly aid in managing sepsis and acute respiratory distress syndrome (ARDS). AI tools have shown promise in predicting sepsis progression, understanding patient outcomes, and improving treatment choices. In this trial, participants will review critical care cases with treatment recommendations generated by an AI-based clinical decision support system in one arm. Studies have found that AI can assist in early detection of these conditions and in creating personalized treatment plans. AI-based clinical decision support systems (CDSS) analyze data to make recommendations as safe and effective as those made by human doctors. These systems use advanced methods to provide care tailored to each patient's needs, potentially leading to better health outcomes. ^{2 6 7 8 9}

Who Is on the Research Team?

Gary Weissman, MD, MSHP

Principal Investigator

University of Pennsylvania

Are You a Good Fit for This Trial?

This trial is for critical care clinicians who will evaluate treatment recommendations for sepsis and ARDS. The study aims to see if AI-generated advice can match the quality of human clinician suggestions.

Inclusion Criteria

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

Exclusion Criteria

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

Timeline for a Trial Participant

Screening

Participants are screened for eligibility to participate in the trial

1 week

Survey-based Study

Participants review critical care cases in an electronic survey and assess treatment recommendations

45 minutes

1 visit (virtual)

Follow-up

Participants are monitored for their responses and assessments post-survey

1 week

What Are the Treatments Tested in This Trial?

Interventions

• Artificial Intelligence-Generated Treatment Recommendations

Trial Overview The trial tests an AI Clinical Decision Support System (CDSS) by having participants compare its treatment recommendations with those from real clinicians, using case vignettes in a survey-based study.

How Is the Trial Designed?

Group I: Artificial Intelligence Experimental Treatment 1 Intervention

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.

Group II: Human Clinician Active Control 1 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.

Who Is Running the Clinical Trial?

University of Pennsylvania

Lead Sponsor

Trials

2,118

Recruited

45,270,000+

National Institute of General Medical Sciences (NIGMS)

Collaborator

Trials

315

Recruited

251,000+

Citations

1. pmc.ncbi.nlm.nih.gov pmc.ncbi.nlm.nih.gov/articles/PMC8155362/

Artificial Intelligence for Clinical Decision Support in Sepsis AI-derived algorithms can be applied to multiple stages of sepsis, such as early prediction, prognosis assessment, mortality prediction, and optimal management.

2. pair.upenn.edu pair.upenn.edu/projects/improving-sepsis-care-with-ai-based-clinical-decision-support/

Improving Sepsis Care with AI-Based Clinical Decision ... This project aims to address these gaps by developing and evaluating an AI-based CDSS for IMV management of patients with sepsis and ARDS.

3. isrctn.com isrctn.com/ISRCTN83789437

Effectiveness of an artificial intelligence clinical decision ... This study introduces an artificial intelligence-clinical decision support system (AI-CDSS) that uses machine learning algorithms to analyze blood test data ( ...

4. ccforum.biomedcentral.com ccforum.biomedcentral.com/articles/10.1186/s13054-025-05588-0

AI-driven innovations in early detection and tailored therapies Artificial intelligence (AI) offers promising solutions to improve sepsis care through earlier detection, risk stratification, and personalized ...

5. sciencedirect.com sciencedirect.com/science/article/pii/S2772501425000090

Systems-based framework for clinical decision-support ... The need to investigate and support sepsis care and treatment. In this context, recent advancements in technology, deep-learning algorithms, and artificial ...

6. pmc.ncbi.nlm.nih.gov pmc.ncbi.nlm.nih.gov/articles/PMC12366378/

Transforming sepsis management: AI-driven innovations in ... To summarize, AI-supported clinical decision support holds the promise to provide individualized treatment recommendations supported by data.

7. sciencedirect.com sciencedirect.com/science/article/pii/S2667100X23000816

Optimizing artificial intelligence in sepsis management AI has the potential to deliver timely and accurate sepsis detection on the ward and in the ED, potentially outperforming current clinical warning scores, which ...

8. onlinelibrary.wiley.com onlinelibrary.wiley.com/doi/10.1155/ccrp/9031137

Exploring the Potentials of Artificial Intelligence in Sepsis ... In this study, we review recent studies that applied AI-based approaches to the management of sepsis in the ICU, focusing on improving early ...

9. frontiersin.org frontiersin.org/journals/medicine/articles/10.3389/fmed.2024.1510792/full

Harnessing artificial intelligence in sepsis care: advances ... This review explores the potential of Artificial Intelligence (AI) to transform sepsis management, from early detection to personalized treatment and real-time ...