Binrui Xie , Yanbing Li , Nan Zhang , Chuangui Zhou , Jiexun Bu , Lun Wu , Jun Zhu , Wenzhuo Wang , Lei Liu , Ming Li
{"title":"An adaptive EEMD-machine learning algorithm for multi-matrix drug concentration prediction using miniature mass spectrometry","authors":"Binrui Xie , Yanbing Li , Nan Zhang , Chuangui Zhou , Jiexun Bu , Lun Wu , Jun Zhu , Wenzhuo Wang , Lei Liu , Ming Li","doi":"10.1016/j.ijms.2025.117485","DOIUrl":null,"url":null,"abstract":"<div><div>In this study, an innovative approach combining Machine Learning (ML) with Ensemble Empirical Mode Decomposition (EEMD) was proposed to predict lamotrigine concentrations in actual samples, improving detection performance in complex matrices. EEMD decomposed the mass spectrometry data to extract Intrinsic Mode Functions (IMFs), enabling separation of noise from key signal features. Ridge Regression (RR) addressed multicollinearity among high-dimensional IMF features and enhanced model generalization via L2 regularization. ML was further applied to optimize the key EEMD parameter (ensemble number K),thereby improving both decomposition quality and prediction accuracy. Experimental validation showed that the method achieved over 90 % prediction accuracy in three types of blind samples (PBS, rabbit blood, and human matrix), with improved Relative Standard Deviation (RSD). These results confirm the method’s precision and robustness in diverse biological matrices. Compared to traditional techniques, the proposed approach delivers marked improvements in both accuracy and stability, can supporting more reliable drug concentration monitoring for clinical applications.</div></div>","PeriodicalId":338,"journal":{"name":"International Journal of Mass Spectrometry","volume":"516 ","pages":"Article 117485"},"PeriodicalIF":1.6000,"publicationDate":"2025-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Mass Spectrometry","FirstCategoryId":"92","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1387380625000892","RegionNum":3,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"PHYSICS, ATOMIC, MOLECULAR & CHEMICAL","Score":null,"Total":0}
引用次数: 0
Abstract
In this study, an innovative approach combining Machine Learning (ML) with Ensemble Empirical Mode Decomposition (EEMD) was proposed to predict lamotrigine concentrations in actual samples, improving detection performance in complex matrices. EEMD decomposed the mass spectrometry data to extract Intrinsic Mode Functions (IMFs), enabling separation of noise from key signal features. Ridge Regression (RR) addressed multicollinearity among high-dimensional IMF features and enhanced model generalization via L2 regularization. ML was further applied to optimize the key EEMD parameter (ensemble number K),thereby improving both decomposition quality and prediction accuracy. Experimental validation showed that the method achieved over 90 % prediction accuracy in three types of blind samples (PBS, rabbit blood, and human matrix), with improved Relative Standard Deviation (RSD). These results confirm the method’s precision and robustness in diverse biological matrices. Compared to traditional techniques, the proposed approach delivers marked improvements in both accuracy and stability, can supporting more reliable drug concentration monitoring for clinical applications.
期刊介绍:
The journal invites papers that advance the field of mass spectrometry by exploring fundamental aspects of ion processes using both the experimental and theoretical approaches, developing new instrumentation and experimental strategies for chemical analysis using mass spectrometry, developing new computational strategies for data interpretation and integration, reporting new applications of mass spectrometry and hyphenated techniques in biology, chemistry, geology, and physics.
Papers, in which standard mass spectrometry techniques are used for analysis will not be considered.
IJMS publishes full-length articles, short communications, reviews, and feature articles including young scientist features.