Improved diagnosis of colorectal cancer using combined biomarkers including Fusobacterium nucleatum, fecal occult blood, transferrin, CEA, CA19‐9, gender, and age

Abstract

Abstract Background Conventional blood and stool tests are normally used for early screening of colorectal cancer (CRC) but the accuracy and efficiency remain to be improved. Recent findings suggest Fusobacterium nucleatum to be a biomarker for CRC. This study evaluated the role of F. nucleatum and developed CRC diagnostic models by combining F. nucleatum with fecal occult blood (FOB), transferrin (TRF), carcinoembryonic antigen (CEA), carbohydrate antigen 19‐9 (CA19‐9), gender, and age. Materials and Methods Candidates including 71 healthy individuals and 59 CRC patients were recruited. Abundance of F. nucleatum in stool or tissue samples was measured by quantitative real‐time PCR. CEA, CA19‐9, TRF, and FOB were measured in parallel. These biomarkers together with genders and ages were the seven parameters used to develop CRC diagnostic models. Ten different machine learning algorithms were tested to achieve the best performance. Results Fecal F. nucleatum abundance was found significantly higher in CRC group compared to healthy group (p = 0.0005). Among the CRC patients, F. nucleatum abundance in tumor tissue was significantly higher than that in paracancerous tissue (p = 0.0087). CRC diagnostic models using different parameters were generated based on Logistic Regression algorithm, which showed good performance. The area under the curve (AUC) score of fecal F. nucleatum as the single diagnostic biomarker was 0.68 while the accuracy was 0.56. The diagnostic performance was obviously improved with the highest AUC (0.93) and accuracy (0.87) achieved when using all the 7 clinical parameters. The combination F. nucleatum + FOB + gender + age had the second highest AUC (0.92) and accuracy (0.85). A more utilitarian model using F. nucleatum + FOB showed relatively high AUC at 0.86 and accuracy at 0.81. Conclusions F. nucleatum is valuable for CRC diagnosis. Combination of different clinical parameters could significantly improve CRC diagnostic performance. The combination F. nucleatum + FOB + gender + age may be an effective and noninvasive method for clinical application.

Keywords

• biomarker
• colorectal cancer
• Fusobacterium nucleatum
• machine learning
• risk model
• screening