Can a preoperative photo predict root coverage success after gum surgery?
Official title: Development and Internal Validation of a Deep Learning Model Predicting the Outcome of Root Coverage Surgery From Preoperative Intraoral Photographs: A Prospective Observational Cohort Study
Run by Marmara University · NCT07775365 · Data updated 2026-11-12
Researchers test whether a preoperative intraoral photo can predict six-month root coverage after a specific gum recession surgery in adults with Cairo RT1-RT3 recessions.
Quick facts
| Study type | Observational |
|---|---|
| Ages | 18 Years to 65 Years |
| Sex | All |
| Enrollment | 36 (estimated) |
| Sponsor | Marmara University Academic / other |
| Locations | 1 site (Istanbul, Istanbul) |
| Status | Recruiting |
| Started | September 17, 2025 |
| Main results expected | September 17, 2026 |
| Study ends | September 17, 2027 |
| Registry record updated | August 20, 2026 |
| Trial ID | NCT07775365 on ClinicalTrials.gov |
Is this trial a fit for you?
✓Likely a good fit
Adults aged 18-65 who are systemically healthy (ASA I-II) with Cairo RT1-RT3 gingival recessions in the maxilla or mandible and good oral hygiene.
✕Probably not a fit
Patients with uncontrolled systemic conditions, pregnancy, or dental conditions that obscure the CEJ or photo angle may not benefit from the predictive model.
A plain-English reading of the study's rules. Only the study team can confirm whether you qualify.
What this trial studies
This observational study collects standardized intraoral photographs and clinical measurements from adults with Cairo RT1, RT2, or RT3 gingival recessions undergoing a coronally applied flap with a connective tissue graft. A deep learning model is trained to forecast the six-month surgical outcome using the preoperative photo and baseline clinical data, and its predictions are compared with actual six-month results. The model operates independently of clinical decision-making, and performance is evaluated for discrimination, calibration, and prediction error. An additional analysis checks agreement between automatic recession-type labeling from the image and the examiner’s classification. Internal validation is performed within a single cohort, with no external dataset validation planned. TRIPOD reporting guidelines are followed for prediction-model studies.
Why it matters
Potential benefit: If successful, this approach could enhance preoperative planning by providing a data-driven estimate of root coverage likelihood based on an image and baseline measurements.
How similar studies have gone: Prior work has explored image-based prognostic modeling in dental procedures, but this study’s internal validation without external data is exploratory and more evidence is needed for generalization.
Who can join: the full rules
Show full inclusion / exclusion criteria
Inclusion Criteria: * Systemically healthy patients (ASA I or II status) with no contraindications for periodontal surgery. * Adult patients aged 18 to 65 years. * Presence of isolated or multiple gingival recessions classified as Cairo RT1, RT2 or RT3 in the maxilla or mandible. * Patients with good oral hygiene standards, defined as a Full Mouth Plaque Score (FMPS) and Full Mouth Bleeding Score (FMBS) of \< 20% at baseline. * Presence of an identifiable Cemento-Enamel Junction (CEJ) (Crucial for AI segmentation). Exclusion Criteria: * Patients with uncontrolled diabetes, immune system disorders, or pregnant/lactating women. * Teeth with cervical restorations or abrasions that obscure the CEJ. * Malpositioned or rotated teeth that would distort the photographic angle for AI analysis.
Where it's running
-
Marmara University Faculty of Dentistry Department of Periodontology
Istanbul, Istanbul, Turkey (Türkiye) Recruiting
Study contacts
- Principal investigator: Leyla Kuru, Professor — Marmara University Faculty of Dentistry Department of Periodontology
- Study coordinator: Muhammed F Dogan, Resident
- Email: mfurkandogaan@gmail.com
- Phone: +905433890065
Similar studies
Other studies for the same condition or treatment. Recruiting studies are listed first.
-
Keratinized tissue and attached gingiva width in root coverage with a minimally invasive graft technique
This study tests whether the width of keratinized tissue and attached gingiva affect root coverage outcomes after a minimally invasive gum graft procedure for RT1 recession defects.
-
Managing pain after free gingival graft harvesting with Ora-Aid versus an acrylic palatal stent
This trial will test whether an Ora-Aid hydrogel dressing or an acrylic palatal stent better reduces pain for adults after free gingival graft donor-site harvesting.
-
CAF versus TCAF with connective tissue grafts for multiple maxillary gum recessions
This comparison will test whether coronally advanced flap (CAF) or tunneled coronally advanced flap (TCAF), each combined with a connective tissue graft, provides better root coverage for adults with multiple gum recessions in the upper jaw.
-
Comparing two gum‑repositioning surgeries with connective tissue grafts for multiple recessions in the lower front teeth
This trial will test whether the coronally advanced flap (CAF) or the tunneled coronally advanced flap (TCAF), both with connective tissue grafts, gives better root coverage for people with multiple gum recessions on their lower front teeth.
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.