A Systematic Approach to Obtain Validated Partial Least Square Models for Predicting Lipoprotein Subclasses from Serum NMR Spectra

详细信息    查看全文

• 作者：Velitchka V. Mihaleva ; Dani毛l B. van Schalkwijk ; Albert A. de Graaf ; John van Duynhoven ; Ferdinand A. van Dorsten ; Jacques Vervoort ; Age Smilde ; Johan A. Westerhuis ; Doris M. Jacobs
• 刊名：Analytical Chemistry
• 出版年：2014
• 出版时间：January 7, 2014
• 年：2014
• 卷：86
• 期：1
• 页码：543-550
• 全文大小：394K
• ISSN：1520-6882

文摘

A systematic approach is described for building validated PLS models that predict cholesterol and triglyceride concentrations in lipoprotein subclasses in fasting serum from a normolipidemic, healthy population. The PLS models were built on diffusion-edited ¹H NMR spectra and calibrated on HPLC-derived lipoprotein subclasses. The PLS models were validated using an independent test set. In addition to total VLDL, LDL, and HDL lipoproteins, statistically significant PLS models were obtained for 13 subclasses, including 5 VLDLs (particle size 64鈥?1.3 nm), 4 LDLs (particle size 28.6鈥?0.7 nm) and 4 HDLs (particle size 13.5鈥?.8 nm). The best models were obtained for triglycerides in VLDL (0.82 < Q² <0.92) and HDL (0.69 < Q² <0.79) subclasses and for cholesterol in HDL subclasses (0.68 < Q² <0.96). Larger variations in the model performance were observed for triglycerides in LDL subclasses and cholesterol in VLDL and LDL subclasses. The potential of the NMR-PLS model was assessed by comparing the LPD of 52 subjects before and after a 4-week treatment with dietary supplements that were hypothesized to change blood lipids. The supplements induced significant (p < 0.001) changes on multiple subclasses, all of which clearly exceeded the prediction errors.