Journal of Chemometrics最新文献

Measurements of blood glucose concentration use invasive methods such as venous blood sampling, and finger-prick blood testing using self-monitoring blood glucose meters with subcutaneous sensors. For daily use, the development of noninvasive blood glucose measurement methods is required. In this study, we constructed a model to estimate blood glucose concentrations noninvasively from mid-infrared absorption spectra measured using photothermal deflectometry enhanced by total internal reflection. We improved the estimation accuracy of the model using Savitzky–Golay preprocessing and the Boruta variable selection method. In addition, the model was corrected using subject data from the first day of measurements to improve estimation accuracy.

The COVID-19 pandemic has highlighted the urgent need for rapid, accurate, and cost-effective diagnostic alternatives to conventional methods such as RT-qPCR and immunoassays. In this study, we explored the potential of vibrational spectroscopy, specifically near-infrared (NIR) and mid-infrared (MID) spectroscopy, for detecting SARS-CoV-2 infection in dried plasma samples. Spectral data were obtained from 83 patients (45 COVID-19 positive and 38 negative) and analyzed using partial least squares discriminant analysis (PLS-DA), with and without variable selection by the ordered predictors selection for discriminant analysis (OPSDA) method. While initial models using full spectra showed moderate classification accuracy, the application of OPSDA significantly enhanced model performance. For the NIR dataset, OPSDA-based models achieved 100% sensitivity and specificity in both training and test sets (n = 25). For the MID dataset, the test set (n = 25) sensitivity reached 86%, with 100% specificity. These results demonstrate that NIR and MID spectroscopy, when combined with advanced chemometric approaches, can provide reliable, rapid, and low-cost screening for COVID-19. This platform holds promise for broader applications in clinical diagnostics beyond the current pandemic.

As advances in digital engineering continue to push the technological boundaries, digital twin (DT) visualizations for diagnostics and safeguards advancement become much more feasible and practical. DTs generate large and complex data streams that require effective user interfaces to provide monitoring and diagnostic capabilities. Unfortunately, while these frameworks exist, there is not much research on the systematic documentation of human–computer interaction (HCI) for DT visualization. This work presents a dual-mode visualization methodology (two dimensional [2D] graphical user interface dashboard and 3D mixed reality) designed to support diagnostic tasks in DT systems and building on a validated framework and applying established HCI principles. The methodology is demonstrated through a case study of aqueous processing at Idaho National Laboratory, using experimental data from the chemical solvent extraction runs. Our interfaces display real-time alerts and monitoring to inform users of safeguards anomalies. The interfaces use immersive 3D mixed-reality visualization for further system and experiment investigation. This work demonstrates how the systematic application of HCI principles can inform DT visualization design for diagnostic and safeguards applications. While formal user evaluation studies remain as future work, this paper documents the systematic design methodology and demonstrates a proof-of-concept implementation.

In the analysis of metabolomics data, selecting the appropriate statistical approach is crucial for maximizing model interpretation, predictivity and reliability. This study evaluates the effectiveness of Orthogonal Partial Least Squares (OPLS) models, specifically comparing OPLS-DA (assuming sample independence) and OPLS-EP (assuming sample dependency) in datasets of bacterial samples under different experimental conditions. OPLS-EP consistently demonstrates superior predictive performance, evidenced by higher predictive ability by means of cross-validation (Q2) compared to OPLS-DA, indicating greater model significance. Our findings prove the advantages of the paired statistical approach. This approach ensures that treatment effects are accurately measured by minimizing inter-sample variation and enhancing signal detection. Previous research in metabolomics has demonstrated the benefits of this method for biomarker sensitivity, particularly in matched case–control studies. The present study extends this understanding by applying paired statistical approaches to bacterial isolate treatments, offering novel insights into their utility. Overall, the findings emphasize the importance of OPLS-EP in enhancing biomarker sensitivity and model reliability in metabolomics research.

Reducing feature dimensionality in spectroscopic data is crucial for efficient analysis and classification. Using all available features for classification typically results in an unacceptably high runtime and poor accuracy. Popular feature extraction methods, such as principal component analysis (PCA), linear discriminant analysis (LDA), and autoencoders, reduce feature dimensionality by extracting latent features that can be challenging to interpret. To enable better human interpretation of the classification model, we avoid extraction methods and instead propose applying feature selection methods. In this work, we develop an innovative PCA-based feature selection method for spectroscopic data, providing an essential subset of the original features. As an important advantage, no prior knowledge about the characteristic signals of the respective target substance is required. In this proof-of-concept study, the proposed method is initially characterized using simulated Raman and infrared absorption datasets. From the top five PCA eigenvectors of spectroscopic data, we identify a set of three top peaks each at specific wavenumbers (features). The compact set of selected features is then used for classification tasks applying a decision tree. Based on two well-defined spectroscopic datasets, our study demonstrates that our new method of PCA-based peak finding outperforms selected other approaches with regard to interpretability and accuracy. For both investigated datasets, accuracies greater than 97% are achieved. Our approach shows large potential for accurate classification combined with interpretability in further scenarios involving spectroscopic datasets.

The first article in this column was published in 2014 [1], over 10 years ago. In this intermission, we look at the importance of chemometrics to analytical chemists and the central role of PLS (Partial Least Squares), which will be the subject of the next articles.

The name chemometrics (in Swedish) was first advocated in the literature in 1972 [2] but was far from the modern day emphasis on multivariate data and primarily involved univariate curve fitting. Although a few enthusiasts communicated together during the 1970s, it was not until the early 1980s that the subject we now recognise became organised.

Most of the major building blocks were developed in the 1980s, and we will look at how the subject fitted into analytical chemistry as from 1980. A good way to study the impact is via citations. We will use Web of Science (Clarivate) with a census date of 24 July 2025 to chart the progress of major publications in this area. We look at some of the more prominent relevant journals.

Analytica Chimica Acta is one of the first general analytical journals to publish a significant number of papers in chemometrics. The classic paper by Geladi and Kowalski on PLS (Partial Least Squares) [3] in 1986 is the most cited article ever in this journal since 1980 (5746 cites). The second most cited (2483 cites) is on a subject related to chemometrics (Box–Behnken designs), suggesting the dominant impact of chemometrics in this forum. What is remarkable is the longevity of this article. Most articles decline in importance after a few years. In Figure 1, we present the citations to this article as compared to all papers together in ACA since 1986. So not only is this, by a long way, the most highly cited article ever published in this journal, its importance is increasing with time over nearly a 40-year period, compared to general articles published in 1986. This is even clearer when we look at the percentage of citations to all papers in ACA published in 1986 over time, in Figure 2. By 2024, over 80% of all citations are to this one paper. This strongly suggests that PLS continues to remain a long-term advance in analytical chemistry over four decades.

In Elsevier's Chemometrics and Intelligent Laboratory Systems, which first published in 1986, the two most cited papers by a wide margin are about PCA (9016 cites) [4] and, again, PLS (7652 cites) [5]. However, as the former paper was published in 1987 and the latter in 2001, in fact, the interest in PLS has been greater than PCA.

The journal Analytical Chemistry, although it published some early reviews in chemometrics, does not prominently feature chemometrics articles. In the decade 1980–1989, the third most cited article was focused on chemometrics and involved PLS [6] suggesting the importance of PLS to chemometrics in its early days (2434 cites). The most cited article (7820 c

O.-C. G. Engstrøm, M. Albano-Gaglio, E. S. Dreier, et al., “ Transforming Hyperspectral Images Into Chemical Maps: A Novel End-to-End Deep Learning Approach,” Journal of Chemometrics 39, no. 8 (2025): e70041, https://doi.org/10.1002/cem.70041.

In the original work, there was an apparent discrepancy between two ways of making predictions with the same PLS model. One way was predicting directly on mean spectra. The other was predicting on pixel-wise spectra and subsequently averaging the result. The discrepancy between these two ways of evaluation was solely due to the order of application of preprocessing.

In the original work, the mean spectrum was computed by taking the negative logarithm of each pixel (to transform from reflectance to pseudo absorbance), averaging all pixels, applying SNV (Standard Normal Variate) transform, and finally convolution with an SG (Savitzky–Golay) filter. However, when applying pixel-wise PLS, SNV and SG were applied to each pixel individually. As SNV is nonlinear (the standard deviation is not linear), it matters whether it is applied before or after averaging. So, this update now applies preprocessing to each pixel individually before taking the average to compute a mean spectrum. This removes any discrepancy between the results obtained by pixel-wise PLS and PLS on mean spectra. Any reference to this discrepancy has been removed from the work and all results and figures have been updated accordingly. Appendix D describes the updates in detail.

We apologize for this error.