A machine learning breast cancer prediction model based on a panel from circulating exosomal miRNAs

In this study, we aim to reveal the value of plasma exo-miRNA in early diagnosis of breast cancer.In this study, after determining the success of plasma exocrine separation, we analyzed the expression of miRNA in plasma exocrine and selected 16 strong correlation features miRNA by Lasso logistic regression. Different machine learning algorithm models were constructed to evaluate the performance of 16 miRNA for early detection and diagnosis of breast cancer. The biological significance of 16 characteristic miRNAs was evaluated by bioinformatics analysis. Overall, these data highlight the value of exo-miRNA as a biomarker for breast cancer. They may be used for early detection and diagnosis of breast cancer in future clinical practice. Overall design: Exosomes isolated from plasma were identified by Nanoparticle Tracking Analysis (NTA), Transmission Electron Microscope (TEM) and Western Blot. MiRNA expression in plasma samples from 56 BC patients and 40 normal controls (NCS) was analyzed by high-throughput sequencing. MiRNAs with strong correlation characteristics were selected by Lasso logistic regression. Then, we build the training set and test set, evaluated the Lasso regression accuracy, and evaluated the performance of different models in the training set and test set. Finally, GO analysis, KEGG and Reactome pathway enrichment analysis were used to understand the biological significance of 16 characteristic miRNAs.