RESULT: We tested Naive Bayes, Logistic Regression, KNN, J48, Random Forest, SVM, and Deep Neural Network algorithms to ASD screening dataset and compared the classifiers' based on significant parameters; sensitivity, specificity, accuracy, receiver operating characteristic, area under the curve, and runtime, in predicting ASD occurrences. We also found that most of previous studies focused on classifying health-related dataset while ignoring the missing values which may contribute to significant impacts to the classification result which in turn may impact the life of the patients. Thus, we addressed the missing values by implementing imputation method where they are replaced with the mean of the available records found in the dataset.
CONCLUSION: We found that J48 produced promising results as compared to other classifiers when tested in both circumstances, with and without missing values. Our findings also suggested that SVM does not necessarily perform well for small and simple datasets. The outcome is hoped to assist health practitioners in making accurate diagnosis of ASD occurrences in patients.
METHODS: S100A4 protein expression was examined by immunohistochemistry (IHC) using commercially available tissue microarray containing malignant and normal breast tissue cores from 216 patients.
RESULTS: S100A4 was absent in normal breast tissues while positive in 45.1% of infiltrating ductal carcinoma (IDC) node negative and 48.8% of infiltrating lobular carcinoma node negative. In paired samples, S100A4 protein was expressed in 13.5% of IDC node positive cases and 35.1% of matched lymph node metastasis.
CONCLUSION: S100A4 protein expression appears widely expressed in early and advanced breast cancer stages compared with normal breast. Our study suggests S100A4 may play a role in breast cancer progression and may prove to be an independent marker of breast cancer which appears to be down regulated in more advanced stages of breast cancer.
MATERIALS AND METHODS: A systematic review was performed in accordance with the 3rd edition of the Centre for Reviews and Dissemination (CRD) and Preferred Reporting Items for Systematic Reviews and Meta-analyses (PRISMA) statement. Electronic searches for articles were carried out in the PubMed, Web of Science, and Scopus databases. The quality assessment of the included studies was evaluated using the Newcastle-Ottawa Quality Assessment Scale (NOS) and the new version of the QUADOMICS tool. Meta-analysis was conducted whenever possible. The effect size was presented using the Forest plot, whereas the presence of publication bias was examined through Begg's funnel plot.
RESULTS: A total of nine studies were included in the systematic review. The metabolite profiling was heterogeneous across all the studies. The expression of several salivary metabolites was found to be significantly altered in OPMDs and OCs as compared to healthy controls. Meta-analysis was able to be conducted only for N-acetylglucosamine. There was no significant difference (SMD = 0.15; 95% CI - 0.25-0.56) in the level of N-acetylglucosamine between OPMDs, OC, and the control group.
CONCLUSION: Evidence for N-acetylglucosamine as a salivary biomarker for oral cancer is lacking. Although several salivary metabolites show changes between healthy, OPMDs, and OC, their diagnostic potential cannot be assessed in this review due to a lack of data. Therefore, further high-quality studies with detailed analysis and reporting are required to establish the diagnostic potential of the salivary metabolites in OPMDs and OC.
CLINICAL RELEVANCE: While some salivary metabolites exhibit significant changes in oral potentially malignant disorders (OPMDs) and oral cancer (OC) compared to healthy controls, the current evidence, especially for N-acetylglucosamine, is inadequate to confirm their reliability as diagnostic biomarkers. Additional high-quality studies are needed for a more conclusive assessment of salivary metabolites in oral disease diagnosis.