Vision-language AI helps emergency CT readers spot thoraco-abdominal problems
Official title: Clinical Research Protocol for a Vision-Language-Based Large-Scale Model in Emergency Screening
Run by The First Hospital of Jilin University · NCT07899931 · Data updated 2026-11-12
This trial tests whether a self-developed AI model can help radiologists find acute thoraco-abdominal emergencies on CT scans more accurately than standard reading in adult emergency patients.
Quick facts
| Study type | Interventional |
|---|---|
| Ages | 18 Years and up |
| Sex | All |
| Enrollment | 640 (estimated) |
| Sponsor | The First Hospital of Jilin University Academic / other |
| Locations | 1 site (Changchun, Jilin) |
| Status | Recruiting |
| Started | September 1, 2026 |
| Main results expected | October 31, 2026 |
| Study ends | November 10, 2026 |
| Registry record updated | October 28, 2026 |
| Trial ID | NCT07899931 on ClinicalTrials.gov |
Is this trial a fit for you?
✓Likely a good fit
Adults 18 years or older presenting to the ED with suspected acute thoraco-abdominal emergencies requiring CT and able to provide consent.
✕Probably not a fit
Patients who do not benefit may include those whose condition is already unmistakable on CT or where AI misreads complex findings.
A plain-English reading of the study's rules. Only the study team can confirm whether you qualify.
What this trial studies
This single-center, prospective randomized study compares AI-assisted CT interpretation with conventional radiology interpretation in adults needing emergency thoraco-abdominal CT. Radiologists use the powER vision-language model to aid lesion ranking and detection, while the control group reads scans without AI assistance; both arms have access to the same interface but only the experimental group sees AI outputs. The primary outcome is diagnostic performance against a clinical gold standard, with all participants followed for 60 days. Randomization is centralized and allocation is 1:1, open-label to radiologists, with outcome adjudicators and biostatisticians blinded to group assignment. Eligible patients include adults with suspected acute emergencies requiring thoraco-abdominal CT, excluding those with contraindications or inability to consent or complete follow-up.
Why it matters
Potential benefit: If successful, AI-assisted reading could improve speed and accuracy of emergency diagnoses.
How similar studies have gone: Prior work in AI-assisted radiology shows potential gains in diagnostic performance, though emergency thoraco-abdominal AI interpretation remains under active study.
Who can join: the full rules
Show full inclusion / exclusion criteria
Inclusion Criteria: * Adult patients aged 18 years or older presenting to emergency department requiring thoraco-abdominal CT examination for suspected acute intra-thoracic or intra-abdominal emergency conditions. * Clinically indicated emergency thoraco-abdominal CT scan ordered by emergency physicians. * Patient or legal representative provides written informed consent for participation in this prospective study. * Availability for clinical follow-up to establish reference-standard diagnosis. Exclusion Criteria: * Age under 18 years old. * Contraindications for contrast-enhanced CT examination (severe contrast allergy, uncorrectable severe renal dysfunction). * Inability to complete CT acquisition according to protocol due to critical clinical instability. * Refusal to participate or inability to obtain valid informed consent. * Prisoners or vulnerable populations who are inappropriate for enrollment.
Where it's running
-
The First Hospital of Jilin University
Changchun, Jilin, China Recruiting
Study contacts
- Study coordinator: Jiaqi Gong Gong, MBBS
- Email: 1223841862@qq.com
- Phone: +8615104483768
Similar studies
Other studies for the same condition or treatment. Recruiting studies are listed first.
-
Retroperitoneal Tumor Registry
This observational registry collects real-world data from people with retroperitoneal tumors to help understand features, treatments, and long-term outcomes.
-
Polatuzumab Vedotin plus Rituximab with Reduced-dose chemo for frail seniors with DLBCL
This trial tests whether a gentler, first-line treatment (Polatuzumab Vedotin with Rituximab and reduced-dose chemo) helps older, frail patients with DLBCL stay disease-free longer.
-
Tegileridine for pain after bariatric surgery
This phase 3 trial tests tegileridine vs standard opioid medicine to see if it provides good pain relief after bariatric surgery while considering sleep apnea status.
-
Modular robotic surgery to remove GEJ cancers at Siewert II/III
This trial tests a modular robotic system to perform minimally invasive removal of Siewert type II/III gastroesophageal junction cancers in adults.
-
Removing enlarged cardiophrenic lymph nodes during surgery for advanced ovarian cancer
This will try removing enlarged cardiophrenic lymph nodes during surgery in women with advanced ovarian, fallopian tube, or primary peritoneal cancer to see if it delays cancer coming back and is safe.
-
Second-line combination treatment for MSS metastatic colorectal cancer
This trial will try folinic acid plus continuous 5-FU with liposomal irinotecan, sometimes combined with cetuximab or bevacizumab, as a second-line option for adults with MSS metastatic colorectal cancer who progressed on or cannot tolerate oxaliplatin-based therapy.
How to take part
- Review the eligibility criteria above with your treating physician.
- Check the official listing on ClinicalTrials.gov for the latest contact details and recruitment status.
- Contact the study coordinator or principal investigator to ask for pre-screening. Pre-screening is free and never obligates you to enroll.