Using AI technology to improve esophageal cancer detection
Official title: Effectiveness and Performance of a Mobile, Automated, Optical Biopsy Technology for Esophageal Cancer Screening: A Clinical Study in Brazil and the United States
Run by Baylor College of Medicine · NCT06435286 · Data updated 2026-11-12
This study is testing if a new AI tool can help doctors find esophageal cancer more accurately in high-risk patients during routine screenings.
Quick facts
| Phase | Phase 2 |
|---|---|
| Study type | Interventional |
| Ages | 18 Years and up |
| Sex | All |
| Enrollment | 200 (estimated) |
| Sponsor | Baylor College of Medicine Academic / other |
| Locations | 4 sites (Houston, Texas and 3 other locations) |
| Status | Recruiting |
| Started | February 17, 2025 |
| Main results expected | March 1, 2027 |
| Study ends | March 1, 2027 |
| Registry record updated | March 2, 2026 |
| Trial ID | NCT06435286 on ClinicalTrials.gov |
Is this trial a fit for you?
✓Likely a good fit
Ideal candidates include outpatients over 18 years old with a history of squamous cell neoplasia or related risk factors undergoing routine screening.
✕Probably not a fit
Patients with advanced squamous cell carcinoma or those unable to undergo routine endoscopy will not benefit from this study.
A plain-English reading of the study's rules. Only the study team can confirm whether you qualify.
What this trial studies
This clinical trial evaluates the effectiveness of an artificial intelligence mobile high-resolution microendoscope (AI-mHRME) combined with Lugol's chromoendoscopy (LCE) for detecting esophageal squamous cell neoplasia in patients at high risk. The study will involve 200 outpatients undergoing routine LCE screening, assessing the diagnostic performance and efficiency of the AI-mHRME compared to traditional methods. The trial aims to enhance the accuracy of cancer detection, particularly among novice clinicians, and reduce unnecessary biopsies. It will also measure clinician confidence and the clinical impact of AI-assisted diagnoses.
Why it matters
Potential benefit: If successful, this technology could lead to earlier and more accurate detection of esophageal cancer, potentially improving patient outcomes.
How similar studies have gone: Previous studies have shown promising results with similar AI-assisted diagnostic approaches, indicating potential for success in this trial.
Who can join: the full rules
Show full inclusion / exclusion criteria
Inclusion Criteria: * Outpatients undergoing routine (standard of care) Lugol's chromoendoscopic screening for squamous cell neoplasia will be eligible for enrollment, including patients with a known history of head/neck squamous cell cancer; heavy smoking and alcohol, other dietary or geographic risk factors or prior dysplasia * Patients \>18 years old. * Patients of any sex or gender. * Patients who are willing and able to give informed consent. Exclusion Criteria: * Allergy or prior reaction to the fluorescent contrast agent proflavine hemisulfate. * Patients who are unable to give informed consent. * Known advanced squamous cell carcinoma of the distal esophagus or dysplastic/suspected malignant esophageal lesion greater than or equal to 2 cm in size not amenable to endoscopic therapy. * Patient unable to undergo routine endoscopy with biopsy: * Women who are pregnant or breast feeding, * Prothrombin time greater than 50% of control; PTT greater than 50 sec, or INR greater than 2.0, * Inability to tolerate sedated upper endoscopy due to cardio-pulmonary instability or other significant medical issues.
Where it's running
-
Baylor St. Luke's Medical Center
Houston, Texas, United States Recruiting -
Ben Taub Hospital (Harris Health Systems)
Houston, Texas, United States Recruiting -
Hospital de Cancer de Barretos - Fundacao Pio XII
Barretos, São Paulo, Brazil Recruiting -
Instituto do Câncer do Estado de São Paulo
São Paulo, São Paulo, Brazil Recruiting
Study contacts
- Principal investigator: Mimi C Tan, MD, MPH — Baylor College of Medicine
- Study coordinator: Mimi C Tan, MD, MPH
- Email: mc2@bcm.edu
- Phone: 7137980950
Similar studies
Other studies for the same condition or treatment. Recruiting studies are listed first.
-
GelPOINT Path-assisted endoscopic removal of colorectal polyps
This study tests whether using the GelPOINT Path access platform during endoscopic submucosal dissection can safely help remove colorectal polyps in adults.
-
Acceptance Based Coping Skills for Hispanic/Latino Military Patients With Type 2 Diabetes
A bilingual health coach will lead a 10-week telehealth program to help Hispanic/Latino military patients with type 2 diabetes manage their condition better.
-
Postoperative Pain After Pediatric Adenotonsillectomy: Ibuprofen Plus Tylenol vs Ketorolac Plus Tylenol
This observational study will see if teens (13-18) who have adenotonsillectomy and take acetaminophen with ibuprofen or acetaminophen with ketorolac after discharge experience different levels of pain and recovery.
-
Non-invasive brain stimulation to try to improve memory in early Alzheimer's
Scientists test whether repetitive transcranial magnetic stimulation to the cerebellum can help short-term memory in people with early Alzheimer's disease compared with a sham procedure.
-
Using a steroid cream to prevent repeat urinary tract infections in uncircumcised baby boys
This pilot will test whether applying a steroid cream twice weekly for four weeks can help prevent repeat urinary tract infections in uncircumcised male infants under 6 months who have had a first UTI.
-
Speedboat UltraSlim™ for POEM in adults with achalasia and other esophageal motility disorders.
This registry will see if using the Speedboat UltraSlim™ device for POEM is safe and effective for adults with achalasia or other esophageal motility disorders.
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.