A Circulating miRNA Signature for Stratification of Breast Lesions among Women with Abnormal Screening Mammograms

Abstract

Although mammography is the gold standard for breast cancer screening, the high rates of false-positive mammograms remain a concern. Thus, there is an unmet clinical need for a non-invasive and reliable test to differentiate between malignant and benign breast lesions in order to avoid subjecting patients with abnormal mammograms to unnecessary follow-up diagnostic procedures. Serum samples from 116 malignant breast lesions and 64 benign breast lesions were comprehensively profiled for 2,083 microRNAs (miRNAs) using next-generation sequencing. Of the 180 samples profiled, three outliers were removed based on the principal component analysis (PCA), and the remaining samples were divided into training (n = 125) and test (n = 52) sets at a 70:30 ratio for further analysis. In the training set, significantly differentially expressed miRNAs (adjusted p < 0.01) were identified after correcting for multiple testing using a false discovery rate. Subsequently, a predictive classification model using an eight-miRNA signature and a Bayesian logistic regression algorithm was developed. Based on the receiver operating characteristic (ROC) curve analysis in the test set, the model could achieve an area under the curve (AUC) of 0.9542. Together, this study demonstrates the potential use of circulating miRNAs as an adjunct test to stratify breast lesions in patients with abnormal screening mammograms.

Functional coding haplotypes and machine-learning feature elimination identifies predictors of Methotrexate Response in Rheumatoid Arthritis patients

“…58 When coupled with RFECV, Random Forest is able to identify a small subset of features that produces the highest accuracy in the specific classifier model. 58,59 To ensure that the selected features are stable and robust to differences in sample size, 51,60 RFECV feature selection was performed on eight random subsets of training data with variable sample sizes. Only features that are common across all eight random, variable sized training subsets were selected for further evaluation of their predictive performance.…”

Prediction of Overall Survival Among Female Patients With Breast Cancer Using a Prognostic Signature Based on 8 DNA Repair–Related Genes

“…However, for reasons such as insufficient sample size and lack of verification in other external cohorts, the prognosis and prediction capabilities of the current BC prognostic models are not satisfactory. 8,9,27 Studies on DNA repair pathways and DRGs have found some new results. Inactivation of DRGs can disrupt genome integrity, which can increase the risk of the accumulation of gene mutations associated with cancer development.…”

Review—Systematic Review on Electrochemical Biosensing of Breast Cancer miRNAs to Develop Alternative DCIS Diagnostic Tool

“…[12][13][14][15][16][17][18][19][20] Tumor Markers (EGTM) and the American Society of Clinical Oncology (ASCO) guidelines for BC screening even though approved by FDA due sensitivity issues and the lacking confirmation for their significance in early-stage BC control. 22 Other significant DCIS biomarkers include microribonucleic acids (miRNAs), lipids, and the proteins p16, COX-2, Ki67, in addition to HER-2, estrogen and progesterone. [22][23][24] Among the above-mentioned DCIS biomarkers, the miRNAs are considered as minimally invasive liquid biomarkers identified in blood (plasma/serum) that acts as a diagnostic tool/desirable biomarker to detect cancer at very early stage accurately.…”

“…22 Other significant DCIS biomarkers include microribonucleic acids (miRNAs), lipids, and the proteins p16, COX-2, Ki67, in addition to HER-2, estrogen and progesterone. [22][23][24] Among the above-mentioned DCIS biomarkers, the miRNAs are considered as minimally invasive liquid biomarkers identified in blood (plasma/serum) that acts as a diagnostic tool/desirable biomarker to detect cancer at very early stage accurately. [22][23][24] The blood biopsy is a simple procedure where it can be done plasma exosome extraction can be avoided within 2 h of total analysis duration using very low sample volumes needed, which indicates its high possibility to be extended to clinical application.…”