Use of a least absolute shrinkage and selection operator (LASSO) model to selected ion flow tube mass spectrometry (SIFT-MS) analysis of exhaled breath to predict the efficacy of dialysis: a pilot study
Publication in refereed journal


摘要Selected ion flow tube-mass spectrometry (SIFT-MS) provides rapid, non-invasive measurements of a full-mass scan of volatile compounds in exhaled breath. Although various studies have suggested that breath metabolites may be indicators of human disease status, many of these studies have included few breath samples and large numbers of compounds, limiting their power to detect significant metabolites. This study employed a least absolute shrinkage and selective operator (LASSO) approach to SIFT-MS data of breath samples to preliminarily evaluate the ability of exhaled breath findings to monitor the efficacy of dialysis in hemodialysis patients. A process of model building and validation showed that blood creatinine and urea concentrations could be accurately predicted by LASSO-selected masses. Using various precursors, the LASSO models were able to predict creatinine and urea concentrations with high adjusted R-square (>80%) values. The correlation between actual concentrations and concentrations predicted by the LASSO model (using precursor H3O+) was high (Pearson correlation coefficient = 0.96). Moreover, use of full mass scan data provided a better prediction than compounds from selected ion mode. These findings warrant further investigations in larger patient cohorts. By employing a more powerful statistical approach to predict disease outcomes, breath analysis using SIFT-MS technology could be applicable in future to daily medical diagnoses.
著者Wang MH, Chong KC, Storer M, Pickering JW, Endre ZH, Lau SYF, Kwok C, Lai M, Chung HY, Zee BCY
期刊名稱Journal of Breath Research
關鍵詞LASSO, mass spectrometry, selected ion flow tube, SIFT
Web of Science 學科類別Biochemical Research Methods; Biochemistry & Molecular Biology; Respiratory System

上次更新時間 2021-20-02 於 00:55