Complement and its fractions (C3-C4) pattern in subjects with neoplasia

BH-index: A predictive system based on serum biomarkers and ensemble learning for early colorectal cancer diagnosis in mass screening

BACKGROUND AND OBJECTIVE

Colorectal cancer is one of the most common malignancies among the general population. Artificial Intelligence methodologies based on serum parameters are in continuous development to obtain less expensive tools for highly sensitive diagnoses. This study proposes a predictive system based on serum biomarkers and ensemble learning to predict colorectal cancer presence and the related TNM stage in patients.

METHODS

We have selected 17 significant plasmatic proteins, i.e., Carcinoembryonic Antigen, CA 19-9, CA 125, CA 50, CA 72-4, Tissue Polypeptide Antigen, C-Reactive Protein, Ceruloplasmin, Haptoglobin, Transferrin, Ferritin, α-1-Antitrypsin, α-2-Macroglobulin, α-1 Acid Glycoprotein, Complement C4, Complement C3, and Retinol Binding Protein, regarding 345 patients (248 affected by the neoplastic disease). The proposed system consists of two predictors, i.e., binary and staging; the former predicts the presence/absence of cancer, while the latter identifies the related TNM stage (I, II, III, or IV). The experiments were conducted by deploying and comparing Random Forest, XGBoost, Support Vector Machine, and Multilayer Perceptron with feature selection based on Gini Importance and with dimensionality reduction via PCA.

RESULTS

The results show that the system composed of XGBoost as binary and staging predictor reaches 91.30% accuracy, 90% sensitivity, and 93.33% specificity for the absence/presence outcome, while 66.66% accuracy for the staging response. With the expansion of the training set in favor of positive patients and majority voting, the system composed of the combination of Support Vector Machine, XGBoost, and Multilayer Perceptron as the binary predictor reaches 98.03% accuracy, 100% sensitivity, and 92.30% specificity, while the combination of Random Forest, XGBoost, and Multilayer Perceptron as staging predictor achieves 60% accuracy. The final system reaches, in terms of accuracy, 98.03%, and 66.66% for the binary and staging predictors, respectively. It was also found that the biomarkers which contribute most to the binary decision are Ceruloplasmin and α-2-Macroglobulin, while the least significant dimensions are CA 50 and α-1-Antitrypsin; instead, Carcinoembryonic Antigen and α-1 Acid Glycoprotein are the most significant to the staging decision.

CONCLUSIONS

The present study proves the effectiveness of deploying serum biomarkers as feature dimensions for early colorectal cancer diagnosis and of using majority voting for noise reduction in the prediction.

Independent validation of candidate breast cancer serum biomarkers identified by mass spectrometry

BACKGROUND

We previously selected a panel of 3 breast cancer biomarkers (BC1, BC2, and BC3) from serum samples collected at a single hospital based on their collective contribution to the optimal separation of breast cancer patients and noncancer controls by surface-enhanced laser desorption/ionization time-of-flight mass spectrometry (SELDI-TOF MS). The identities and general applicability of these markers, however, were unknown. In this study, we performed protein expression profiling on samples obtained from a second hospital, included a greater number of ductal carcinoma in situ (DCIS) cases, and performed purification and identification of the 2 confirmed markers.

METHODS

Using a case-control study design, we performed protein expression profiling on serum samples from the National Cancer Institute (Milan, Italy). The validation sample cohort consisted of 61 women with locally invasive breast cancer, 32 with DCIS, 37 with various benign breast diseases (including 13 atypical), and 46 age-matched apparently healthy women (age range, 44-68 years). Validated biomarkers were purified and identified with serial chromatography, 1-dimensional gel electrophoresis, in-gel ASP-N digestion, peptide mass fingerprinting, and tandem mass peptide sequencing.

RESULTS

The BC3 and BC2 expression patterns in this sample set were consistent with the first study sample set. BC3 and BC2 were identified to be complement component C3a(desArg) and a C-terminal-truncated form of C3a(desArg), respectively.

CONCLUSIONS

Evaluation of biomarkers in independent sample sets can help determine the broader utility of candidate markers, and protein identification permits understanding of their molecular basis. C3a(desArg) appears to lack specificity among patients with benign diseases, limiting its utility as a stand-alone tumor marker, but it may still be useful in a multimarker panel for early detection of breast cancer.

Total hemolytic complement (CH50) and its fractions (C3 and C4) in the sera of patients with carcinoma of the oral cavity, uterine cervix, and breast

The total hemolytic complement activity of CH50 and its fractions C3 and C4 was determined in the sera of 196 patients with carcinoma of the oral cavity, 172 patients with carcinoma of the uterine cervix, and 166 patients with breast cancer. The values were compared with those of 18 patients with mammary dysplasia, 32 patients with mild to moderate dysplasia of the cervix, and 100 healthy, normal age- and sex-matched controls. No alterations in CH50, C3, and C4 were observed in the sera of patients with benign lesions, whereas a significant rise in the three factors was observed in all the cancer patients studied. The complement activity increased significantly with the progression of the disease up to stage III and remained persistently elevated thereafter. Patients who had a clinical cure had normal levels of CH50, C3, and C4, whereas the values remained elevated in patients who were still undergoing treatment for residual lesions.