Using laparoscopy camera images to predict whether surgery can remove advanced ovarian cancer
Predicting Outcome of Cytoreduction in Advanced Ovarian Cancer, Using a Machine Learning Algorithm and Patterns of Disease Distribution at Laparoscopy (PREDAtOOR)
NA · Fondazione Policlinico Universitario Agostino Gemelli IRCCS · NCT06017557
This project will try to use videos taken during diagnostic laparoscopy to predict whether surgeons can remove all visible tumors at primary surgery for people with stage III–IV ovarian cancer.
Quick facts
| Phase | NA |
|---|---|
| Study type | Interventional |
| Enrollment | 151 (estimated) |
| Ages | 18 Years and up |
| Sex | Female |
| Sponsor | Fondazione Policlinico Universitario Agostino Gemelli IRCCS (other) |
| Drugs / interventions | chemotherapy |
| Locations | 1 site (Roma) |
| Trial ID | NCT06017557 on ClinicalTrials.gov |
What this trial studies
PREDAtOOR is a pilot interventional effort that collects images from diagnostic laparoscopy to train machine-learning models linking intra‑abdominal appearance to surgical outcomes. Patients are enrolled at the time of their planned surgery or interval cytoreduction, with no extra visits beyond standard care. Collected laparoscopic images and clinical data will be used to develop and test algorithms that predict the likelihood of complete cytoreduction. Outcomes from the subsequent primary or interval surgery will be compared with model predictions to estimate accuracy and refine the approach.
Who should consider this trial
Good fit: People with suspected stage III–IV ovarian cancer who are fit for cytoreductive surgery and undergoing diagnostic laparoscopy at a participating center are ideal candidates.
Not a fit: Patients with early-stage (I–II) disease, those unfit for surgery, or those with certain histologic subtypes (low‑grade serous, clear cell, mucinous, or non‑epithelial) are unlikely to benefit from the model's predictions.
Why it matters
Potential benefit: If successful, this approach could help doctors choose the best first treatment—surgery or chemotherapy—so patients avoid unnecessary operations and receive the therapy most likely to remove their tumors.
How similar studies have performed: CT/MRI and laparoscopy scoring systems have been used to predict resectability and early AI work in surgical imaging is promising, but applying machine learning to laparoscopy video specifically for ovarian cytoreduction prediction remains experimental.
Eligibility criteria
Show full inclusion / exclusion criteria
Inclusion Criteria: * Patients treated at Fondazione Policlinico Gemelli Hospital, Rome Italy, Trillium -Credit Valley Hospital, Mississauga, Ontario and Princess Margaret Cancer Centre, Toronto, Canada * Patients fit for cytoreductive surgery * Patients with a primary diagnosis of suspect Stage III-IV ovarian cancer * Patients selected for interval cytoreductive surgery after NACT Exclusion Criteria: * Patients with pre-operative Stage I-II disease confined to the pelvis * Patients unfit for surgery * Lack of information about patients' surgical outcomes and clinicopathological characteristics * LGSOC, Clear cell and mucinous, non-epithelial histologic subtypes (if available)
Where this trial is running
Roma
- Fondazione Policlinico Universitario A. Gemelli IRCCS, UOC Ginecologia Oncologica — Roma, Italy (RECRUITING)
Study contacts
- Principal investigator: Anna Fagotti, Prof — Fondazione Policlinico Universitario Agostino Gemelli IRCCS
- Study coordinator: Liat Hogen, MD
- Email: liat.hogen@uhn.ca
- Phone: 416-946-4501
How to participate
- Review the eligibility criteria above with your treating physician.
- Visit the official trial page on ClinicalTrials.gov for the most current contact information and recruitment status.
- Contact the listed study coordinator or principal investigator to request pre-screening. Pre-screening is free and never obligates you to enroll.
Conditions: Ovarian Cancer Stage III, Ovarian Cancer Stage IV