ClinicalTrials.gg
RecruitingNCT07950943Updated Nov 20, 2026

AI Treatment Recommendations With Predicted Consequences for Sepsis Fluid and Vasopressor Decisions

An interventional study of Case review with on-duty plan (B0) and AI recommendation (B1) in Sepsis and Septic Shock, sponsored by Nanjing University. Recruiting at 2 sites in China. Open to participants aged 18 Years and older, including healthy volunteers. Per ClinicalTrials.gov, last updated 2026-11-20.

Primary conditionShock, SepticRegistry: SepsisReclassifiedWhy we changed it
Registry
Sepsis — the first condition term the registry derived for this study.
ClinicalTrials.gg
Shock, Septic
Why
  1. The study's listed conditions name Shock, Septic, a narrower term within Sepsis.
Confidence
High: the new condition is named in the study's own listed conditions. Of 351 hand-checked studies reclassified this way, 68% were exactly right and 84% in the right disease family; the registry's first term was right for 5% (measured 2026-10-21). How we classify →
Wrong?
Tell us the study's main condition →

Sponsored by Nanjing University · Not applicable, Interventional, and Health services research

How we know

Updated Nov 20, 2026Newly registeredGo to Updates ↓

Help build ClinicalTrials.gg — short surveys, remote interviews or testing, in your language. Take part →

Phase
Not applicable
Study type
Interventional
Enrollment
72
Allocation
Randomized
Ages
18 Years and older
Sex
All
01

Where this study stands

Counted across the records on this site · 2026-11-21

Among 89 studies in Shock, Septic with a site in China — 30 open to participants now, 32 under way, 1 of them phase 3. Shock, Septic · China.

Planned enrollment
31st of 62
72 · median 72
Started
2026
with 14 others
No phase
41 of 89
15 open now
Primary completion
2026-12
later than 12 of 31 live
Registered
89th of 89
by date

Among the 89 studies in Shock, Septic with a site in China, this one is the 31st largest by planned enrollment of the 62 interventional ones that give a count, is one of 15 that started in 2026, is one of 41 with no phase, reaches primary completion later than 12 of the 31 other live ones, and was the 89th registered.

Shock, Septic

1,084 studies on the registry are indexed under Shock, Septic; 236 are open to participants now.

Browse Shock, Septic studies →

Open to participants now

30 of the 89 studies in Shock, Septic with a site in China are open now. Recruiting first, the newest first:

24 more — sign in →

All 30 open studies →

A study can be open while its sites in China have not opened yet or have stopped. Only those recruiting at a site in China →

Who these studies take

Of the 137 Shock, Septic studies recruiting now, 103 (75%) set no upper age limit and 18 (13%) stop at 75 or younger; 11 take children under 18; 14 take healthy volunteers.

This study: 18 Years and older · all sexes · healthy volunteers too.

The full table on the hub →

This tab as a report to print or save as PDF → With an account.

Was this useful?
Get alerts for this landscapeDownload CSVNarrow it in search →With an account: a weekly mail of what changed among 89 studies in Shock, Septic with a site in China, or all of them as a file.
02

Study summary

When artificial intelligence (AI) recommends a treatment, clinicians must decide whether to follow it. This study tests whether showing the predicted consequences of a recommendation, in addition to the recommendation itself, helps clinicians accept appropriate advice and reject inappropriate advice.

We developed a clinician-anchored counterfactual model that compares the on-duty clinician's intravenous fluid and vasopressor plan with alternative plans for patients with sepsis. It predicts the patient's course under each plan and recommends a change only when the predicted benefit holds across several plausible assumptions about unrecorded factors; otherwise it states that the evidence is insufficient to recommend a change.

About 72 physicians from two hospitals, stratified by seniority, will review 30 retrospective, de-identified ICU decision points from patients with sepsis. In stage 1, each physician independently specifies fluid and vasopressor doses without any AI information. In stage 2, the same cases are reviewed under three conditions assigned by counterbalanced sequences: the case with the on-duty clinician's plan and no AI (B0); B0 plus the AI recommendation (B1); and B1 plus the predicted consequences of the on-duty and recommended plans (B2). The AI recommendation is identical in B1 and B2. Decision quality is assessed against plans made independently by expert intensivists. No patients are enrolled, and participants' decisions do not affect patient care.

Read the detailed description

Cases. Thirty decision points were selected from retrospective, de-identified ICU records before the experiment. Sampling was stratified so that the set includes AI recommendations to change treatment and to keep the current plan, both appropriate and inappropriate according to the expert reference. Each patient contributes one decision point, and none of the cases were used to develop the AI system.

Expert reference. A panel of intensivists who did not take part in AI development or in the experiment independently specify a fluid and vasopressor plan for every case, without AI output and without knowledge of study conditions. A participant's plan is scored by the number of dose levels by which it lies outside the range of expert plans (0 if within the range), summed over the two drugs. AI recommendations are classified as appropriate or inappropriate by the same rule before participant data are analyzed.

Analysis. Outcomes are analyzed with mixed-effects models with physician and case as crossed random effects. Secondary outcomes are tested in a prespecified order after the primary outcome to control the overall type I error.

Related non-interventional components. A retrospective comparison of clinicians' and the AI's plans and a prospective shadow deployment, in which the system ran on live ICU data without influencing treatment, are reported alongside this experiment but are not part of the randomized comparison.

03

Conditions studied

  • Sepsis
  • Septic Shock

Browse trials for

Keywords

  • human-AI collaboration
  • appropriate reliance
  • clinical decision support
  • artificial intelligence
  • counterfactual prediction
  • fluid therapy
  • vasopressor
  • randomized crossover
  • intensive care
04

In context

Shock, Septic Reclassified

1,084 studies on the registry are indexed under Shock, Septic; 236 are open to participants now.

This study's planned enrollment of 72 is close to the median of 78 across 639 interventional studies indexed under Shock, Septic.

Browse Shock, Septic studies →

Lead sponsor

Nanjing University is the lead sponsor of 21 studies on the registry; 9 are open to participants now.

Compared within Shock, Septic, this study's primary condition as ClinicalTrials.gg classifies it; the registry's first condition term is Sepsis. The counts are of registry records indexed under each term, refreshed daily. How we classify →

05

Who can participate

Ages eligible
18 Years and older
Sexes eligible
All
Accepts healthy volunteers
Yes

Go through the criteria one by one — yes, no or not sure — and take the list to your doctor or the study team. Kept in this browser only.

Inclusion criteria

  • Licensed physicians in critical care, emergency medicine, anaesthesiology, or respiratory medicine.
  • Currently treating ICU patients.
  • Able to complete the online questionnaire.

Exclusion criteria

Exclusion Criteria:

  • Involvement in developing or evaluating the AI system, or in case selection
  • Membership of the expert reference panel
  • Participation in the pilot survey
06

Study design

Phase
Not applicable
Primary purpose
Health services research
Allocation
Randomized
Intervention model
Crossover assignment
Masking
Single (Outcomes assessor)
Enrollment
72 participants (estimated)

Study arms

  • Experimental
    Sequence A

    Stage 1: all 30 cases answered without AI information. Stage 2 (questionnaire version A): cases 1-10 under B0, cases 11-20 under B1, cases 21-30 under B2.

    Other: Case review with on-duty plan (B0) · Other: AI recommendation (B1) · Other: AI recommendation with predicted consequences (B2)

  • Experimental
    Sequence B

    Stage 1: all 30 cases answered without AI information. Stage 2 (questionnaire version B): cases 1-10 under B1, cases 11-20 under B2, cases 21-30 under B0.

    Other: Case review with on-duty plan (B0) · Other: AI recommendation (B1) · Other: AI recommendation with predicted consequences (B2)

  • Experimental
    Sequence C

    Stage 1: all 30 cases answered without AI information. Stage 2 (questionnaire version C): cases 1-10 under B2, cases 11-20 under B0, cases 21-30 under B1.

    Other: Case review with on-duty plan (B0) · Other: AI recommendation (B1) · Other: AI recommendation with predicted consequences (B2)

Interventions

  • OtherCase review with on-duty plan (B0)

    Participants review the case together with the on-duty clinician's actual intravenous fluid rate and vasopressor dose and submit a final plan. No AI information is shown. This condition controls for the effect of a second review.

  • OtherAI recommendation (B1)

    As B0, plus the AI output: either a recommended dose level for intravenous fluid and for vasopressor, shown with the corresponding dose range, or a statement that the evidence is insufficient to recommend a change.

  • OtherAI recommendation with predicted consequences (B2)

    As B1, with identical AI output, plus the model's predicted mean arterial pressure, lactate and urine output over the next 4 hours under the on-duty plan and under the recommended plan, shown as point estimates.

07

What researchers measure

Primary outcomes

  1. Distance of final treatment decisions from the range of expert plans, B2 versus B1

    For each case, the number of dose levels by which the participant's final fluid and vasopressor plan lies outside the range of plans made independently by the expert panel (0 = within range), summed over the two drugs. Compared between B2 and B1 with a mixed-effects model with physician and case as crossed random effects, adjusted for stage-1 score, block position and sequence.

    Time frame: At completion of the participant's stage-2 review (single online session, approximately 2 hours)

Secondary outcomes

  1. Discrimination between appropriate and inappropriate AI recommendations, B2 versus B1

    Among cases in which the AI recommends changing treatment, acceptance is defined as a final plan equal to the AI-recommended dose level for the changed drug. The outcome is the interaction between condition (B2 vs B1) and recommendation appropriateness (classified by the expert-range rule before analysis) on acceptance, estimated with a mixed-effects probit model with physician and case as crossed random effects.

    Time frame: At completion of the participant's stage-2 review (single online session, approximately 2 hours)

08

Study locations

2 of 2 sites recruiting
09

References and documents

Individual participant data

Plan to share: Undecided — De-identified participant-level responses (treatment decisions, confidence, response times, condition assignments and participant characteristics without identifiers) will be shared. Patient case material derived from source databases will be shared only as permitted by their data use agreements.

No publications or documents are linked to this record.

10

Timeline

1 registry update since Sep 25, 2026
ElapsedEstimatedEstimated, not yet reachedSimilar studies: half by the dot; the band is the middle halfHalf of similar studies reached it by the dot; the band is the middle half, from a quarter to three quarters

Started Nov 2026 (actual). Primary completion is estimated for Dec 2026, 0 months after the start.

Of 165 non-industry interventional studies with no phase under Shock, Septic, half reached primary completion within 25 months of starting (the median), counting those still running; a quarter within 12 and three quarters within 41. This study's planned 0 months is below that.

Counting every sponsor, half of 173 studies reached it within 25 months; a quarter within 12 and three quarters within 42.

How these figures are worked out, and which studies are left out of them.

Registered
Nov 16, 2026
First posted
Nov 20, 2026
StartActual
Nov 5, 2026
Primary completionEst.
Dec 1, 2026
CompletionEst.
Dec 1, 2026
Last update
Nov 20, 2026
What these dates mean
Start.
When the first participant enrolled; while estimated, when the study expects to open to recruitment.
Primary completion.
When the last participant was examined or treated to collect data for the study's main question, its primary outcome. A study that stopped early gives the date its data collection stopped.
Completion.
When the last participant's last visit took place, for every outcome, secondary ones and side effects included: the end of the study. Often later than primary completion, sometimes the same day.
Actual and Est.
Actual means the registry says the date has happened. Est. (estimated) is a date the sponsor plans or expects. It can still move, and the sponsor is expected to change it to actual once it has passed.
Registered
First appeared on the registry. No changes since
Nov 20, 2026
Show all 1 update
  1. Nov 20, 2026
    First appeared on the registry

From the registry record's own update history. This site started tracking changes on Sep 25, 2026; for anything earlier, see the record history on ClinicalTrials.gov ↗

11

Registry details

Key details

Study ID
NCT07950943
Lead sponsor
Nanjing University
Collaborators
First Affiliated Hospital of Chongqing Medical University, The Affiliated Hospital Of Southwest Medical University
Responsible party
Yuqi Fang (Tenure-Track Associate Professor, Nanjing University) — Principal investigator
First posted
Nov 20, 2026
Start date
Nov 5, 2026
Primary completion
Dec 1, 2026 (estimated)
Completion
Dec 1, 2026 (estimated)
Last update
Nov 20, 2026

Oversight

Data monitoring committee
No
FDA-regulated drug
No
FDA-regulated device
No
View the source record on ClinicalTrials.gov ↗

Interested in this study?

Eligibility is decided by the study team. Share this record with your doctor or contact the team directly.

No contact was published for this record. The registry link below has the sponsor’s details.

Follow this study

Get an email when the registry record changes — status, dates, results — or when someone posts here.

Sign in to follow

Discussion

Questions and observations about this study, from anyone following it. Not medical advice, and not a channel to the study team — their contact details are on the registry record.

Sign in to join the discussion. Reading takes no account; posting does. You choose a display name, and a pseudonym is the default.

Nothing here yet. If you are running this trial, taking part in it, or weighing whether to, this is the place to say so.

Start the discussion