AIM The purpose of this study was to evaluate the diagnostic value of trefoil factor family 3(TFF3) for the early detection of colorectal cancer(CC). METHODS Serum TFF3 and carcino-embryonic antigen(CEA) were detected in 527 individuals, including 115 healthy control(HC), 198 colorectal adenoma(CA), and 214 CC individuals in the training group. RESULTS Serum TFF3 showed no significant correlation with age, gender, or tumor location but showed significant correlation with the tumor stage. Serum TFF3 in the CC group was significantly higher than in the HC or CA group. The AUC values of TFF3 for discriminating between HC and CC and between CA and CC were 0.930(0.903, 0.958) and 0.834(0.796, 0.873). A multivariate model combining TFF3 and CEA was built. Compared to TFF3 or CEA alone, the multivariate model showed significant improvement(P < 0.001). For discriminating between HC and CC, HC and early stage CC, HC and advanced stage CC, CA and CC, CA and early stage CC, and CA and advanced stage CC in the training group, the sensitivities were 92.99%, 91.46%, 93.18%, 73.83%, 76.83%, and 81.82%, and the specificities were 91.30%, 91.30%, 93.91%, 88.38%, 77.27%, and 88.38%, respectively. After validation, the sensitivities were 89.39%, 85.71%, 90.79%, 72.73%, 71.43%, and 78.95%, and the specificities were 87.85%, 87.85%, 2.52%, 87.85%, 80.77%, and 87.50%, respectively. CONCLUSION The multivariate diagnostic model that included TFF3 and CEA showed significant improvement over the conventional biomarker CEA and might provide a potential method for the early detection of CC. AIM The purpose of this study was to evaluate the diagnostic value of trefoil factor family 3 (TFF3) for the early detection of colorectal cancer (CC). METHODS Serum TFF3 and carcino-embryonic antigen (CEA) were detected in 527 individuals, including 115 Healthy control (HC), 198 colorectal adenoma (CA), and 214 CC individuals in the training group. RESULTS Serum TFF3 showed no significant correlation with age, gender, or tumor location but showed significant correlation with the tumor stage. The AUC values ​​of TFF3 for discriminating between HC and CC and between CA and CC were 0.930 (0.903, 0.958) and 0.834 (0.796, 0.873). A multivariate model combining TFF3 and CEA was built. Compared to TFF3 or CEA alone, the multivariate model showed significant improvement (P <0.001). For discriminating between HC and CC, HC and early stage CC, HC and advanced stage CC, CA and CC, CA and early stage CC, and CA and advanced st age CC in the training group, the sensitivities were 92.99%, 91.46%, 93.18%, 73.83%, 76.83%, and 81.82%, and the specificities were 91.30%, 91.30%, 93.91%, 88.38%, 77.27%, and 88.38 After validation, the sensitivities were 89.39%, 85.71%, 90.79%, 72.73%, 71.43%, and 78.95%, and the specificities were 87.85%, 87.85%, 2.52%, 87.85%, 80.77%, and 87.50 %, respectively. CONCLUSION The multivariate diagnostic model that included TFF3 and CEA showed significant improvement over the conventional biomarker CEA and might provide provide a potential method for the early detection of CC.