Evaluation of classification ability of logistic regression model on SERS data of miRNAs. Issue 12 (13th August 2022)

• Record Type: Journal Article
• Authors: Zeng, Xiaojun; Liu, Yu; Liu, Wei; Yuan, Changjing; Luo, Xizi; Xie, Fengxin; Chen, Xueping; de la Chapelle, Marc Lamy; Tian, Huiyan; Yang, Xiang; Fu, Weiling
• Is Part Of: Journal of biophotonics. Volume 15:Issue 12(2022)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2022-08-13
• Subjects: logistic regression -- loss function -- principal component analysis -- regularization -- surface enhanced Raman spectroscopy; Photonics -- Periodicals; Optical materials -- Periodicals; Optics -- Periodicals; Medical instruments and apparatus -- Periodicals; 621.3605
• DOI: 10.1002/jbio.202200108
• Languages: English
• ISSNs: 1864-063X

Abstract

Abstract: Logistic regression (LR) is a supervised multiple linear regression model, which uses linear weighted calculation for input to obtain weight coefficients of model. The surface enhanced Raman spectroscopy (SERS) technology greatly enhances the Raman signal of analyte. LR model was used to analyze the data of seven types of pancreatic cancer‐related miRNAs obtained from commercial SERS substrate. The classification ability of the model on such data was observed under the configurations of different key parameters (classification mode, regularization method and loss function optimization way), and the effect of the two types of data formats were also evaluated. The results showed that though LR model used to classify this data did not perform well as expected, miRNA‐191 and miRNA‐4306 still had high recalls (sensitivity), which laid a theoretical foundation for the purpose of using LR model to identify these two miRNAs to jointly diagnose of pancreatic cancer at miRNA level. Abstract : Raman spectra of miRNA are difficult to be distinguished by ordinary statistical approaches; therefore, it is necessary to use more complicated mathematical methods to solve this problem. When the SERS data of miRNAs are classified by logistic regression (LR) model, different LR configurations of key parameters will result in different outcomes. Just for this reason, it is also important to choose optimal parameters in practice, according to the requirements of issues.