PolyDeep Advance 3: Randomized Clinical Trial comparing PolyDeep-assisted and conventional colonoscopy for adenoma detection rate in a colorectal cancer screening program
Pedro Davila-Piñón, Astrid Irene Díez-Martín, Alba Nogueira-Rodríguez, Florentino Fdez-Riverola, Daniel Glez-Peña, Miguel Reboiro-Jato, Luisa De Castro, Daniel Fernández-De Castro, Pablo Vega, Miguel Telmo Galovart- Araguas, Santiago Soto, Sara Alonso-Lorenzo, Alfonso Martinez-Turnes, Noel Pin, Sara Zarraquiños, David Remedios, Cristina Sánchez-Gomez, Raquel Souto-Rodríguez, Franco Baiocchi, María José Iglesias-Varela, Alejandro Ledo, Coral Tejido-Sandoval, Laura Rivas, Natalia García-Morales, Antonio Rodríguez-De Jesus, Manuel Puga, María Belén Castiñeira-Domínguez, Nereida Fernández-Fernández, Arantza Germade-Martínez, Enrrique Gonzalez-De La Ballina, Indhira Pérez-Medrano, Hugo López-Fernández, Joaquin CubiellaBackground and study aim: The impact of computer-aided detection (CADe) systems remains uncertain. We evaluated whether PolyDeep, a CADe system, improves adenoma detection rate (ADR) in a colorectal cancer (CRC) screening program. Patients and methods: PolyDeep advance 3 (NCT05513261) was a multicenter randomized clinical trial. We included patients between 40 and 79 years, who underwent colonoscopy after a positive fecal immunochemical test (FIT) or surveillance. We randomized 854 patients to assess a 10% difference in ADR. The primary endpoint was ADR, while secondary endpoints were serrated lesion detection rate (SLDR), polyp detection rate (PDR), advanced adenoma detection rate (AADR) and advanced serrated lesion detection rate (ASLDR). We performed subgroup analysis according to indication, endoscopists ADR and bowel cleansing. Effect estimates were reported as adjusted risk ratios (aRR) and 95% confidence intervals (CI) Results: We randomized 857 patients to conventional or PolyDeep-assisted colonoscopy, and 827 were included in the analysis. Baseline characteristics were comparable between groups (male: 490; mean age: 61.7 ± 6.5; positive FIT: 552 and mean withdrawal time: 17:53 ± 09:49). We did not find statistically significant differences between assisted and conventional colonoscopy for ADR (60.8% vs 57.7%; aRR: 1.05, 95%CI 0.94-1.17). No significant differences were observed for SLDR (8.8% vs 7.2%; aRR: 1.04, 0.65-1.64), PDR (69.6% vs 68.8%; aRR: 1.00, 0.91-1.10), AADR (23.6% vs 24.4%; aRR: 0.90, 0.71-1.14) or ASLDR (4.9% vs 4.8%; aRR: 0.93, 0.51-1.68). Subgroup analysis showed no significant differences. Conclusion: In colonoscopies performed in a CRC screening program, PolyDeep-assisted colonoscopy did not increase ADR