A comparison of different chemometrics approaches for the robust classification of electronic nose data

Geographical identification of Chinese wine based on chemometrics combined with mineral elements, volatile components and untargeted metabonomics

Identifying the geographic origin of a wine is of great importance, as origin fakery is commonplace in the wine industry. This study analyzed the mineral elements, volatile components, and metabolites in wine using inductively coupled plasma-mass spectrometry, headspace solid phase microextraction gas chromatography-mass spectrometry, and ultra-high-performance liquid chromatography-quadrupole-exactive orbitrap mass spectrometry. The most critical variables (5 mineral elements, 13 volatile components, and 51 metabolites) for wine origin classification were selected via principal component analysis and orthogonal partial least squares discriminant analysis. Subsequently, three algorithms-K-nearest neighbors, support vector machine, and random forest -were used to model single and fused datasets for origin identification. These results indicated that fused datasets, based on feature variables (mineral elements, volatile components, and metabolites), achieved the best performance, with predictive rates of 100% for all three algorithms. This study demonstrates the effectiveness of a multi-source data fusion strategy for authenticity identification of Chinese wine.

Effects of geographical origin, vintage, and soil on stable isotopes and mineral elements in Ecolly grape berries for traceability

Stable isotopes and multi-element profiles of grapes and corresponding soils from different origins and vintages were determined by IRMS and ICP-MS, respectively. Stable isotope ratios and multi-element contents show significant differences among distinct regions and vintages. Grapes and soils were separated using δ2H and δ18O according to regions and vintages. PCA and CA results further verified that multi-element profiles were influenced by origins and vintages. In particular, δ2H, δ18O, and 21 elements in grapes were correlated with those in soil. Redundancy and Spearman analyses revealed that the BCF values were related to the longitude, latitude, altitude, precipitation, and average temperature. RF shows better performance than PLS-DA for discriminating grape origins and vintages. K, Tb, Cs, δ2H, and Co were important variables in discriminating grape origins. These findings confirm that isotopic and elemental profiles depend on the origin, vintage, and soil, establishing a promising method to discriminate grape origins and vintages.

Advancing accuracy in breath testing for lung cancer: strategies for improving diagnostic precision in imbalanced data

BACKGROUND

Breath testing using an electronic nose has been recognized as a promising new technique for the early detection of lung cancer. Imbalanced data are commonly observed in electronic nose studies, but methods to address them are rarely reported.

OBJECTIVE

The objectives of this study were to assess the accuracy of electronic nose screening for lung cancer with imbalanced learning and to select the best mechanical learning algorithm.

METHODS

We conducted a case‒control study that included patients with lung cancer and healthy controls and analyzed metabolites in exhaled breath using a carbon nanotube sensor array. The study used five machine learning algorithms to build predictive models and a synthetic minority oversampling technique to address imbalanced data. The diagnostic accuracy of lung cancer was assessed using pathology reports as the gold standard.

RESULTS

We enrolled 190 subjects between 2020 and 2023. A total of 155 subjects were used in the final analysis, which included 111 lung cancer patients and 44 healthy controls. We randomly divided samples into one training set, one internal validation set, and one external validation set. In the external validation set, the summary sensitivity was 0.88 (95% CI 0.84-0.91), the summary specificity was 1.00 (95% CI 0.85-1.00), the AUC was 0.96 (95% CI 0.94-0.98), the pAUC was 0.92 (95% CI 0.89-0.96), and the DOR was 207.62 (95% CI 24.62-924.64).

CONCLUSION

Electronic nose screening for lung cancer is highly accurate. The support vector machine algorithm is more suitable for analyzing chemical sensor data from electronic noses.

Prospective Detection of Early Lung Cancer in Patients With COPD in Regular Care by Electronic Nose Analysis of Exhaled Breath

BACKGROUND

Patients with COPD are at high risk of lung cancer developing, but no validated predictive biomarkers have been reported to identify these patients. Molecular profiling of exhaled breath by electronic nose (eNose) technology may qualify for early detection of lung cancer in patients with COPD.

RESEARCH QUESTION

Can eNose technology be used for prospective detection of early lung cancer in patients with COPD?

STUDY DESIGN AND METHODS

BreathCloud is a real-world multicenter prospective follow-up study using diagnostic and monitoring visits in day-to-day clinical care of patients with a standardized diagnosis of asthma, COPD, or lung cancer. Breath profiles were collected at inclusion in duplicate by a metal-oxide semiconductor eNose positioned at the rear end of a pneumotachograph (SpiroNose; Breathomix). All patients with COPD were managed according to standard clinical care, and the incidence of clinically diagnosed lung cancer was prospectively monitored for 2 years. Data analysis involved advanced signal processing, ambient air correction, and statistics based on principal component (PC) analysis, linear discriminant analysis, and receiver operating characteristic analysis.

RESULTS

Exhaled breath data from 682 patients with COPD and 211 patients with lung cancer were available. Thirty-seven patients with COPD (5.4%) demonstrated clinically manifest lung cancer within 2 years after inclusion. Principal components 1, 2, and 3 were significantly different between patients with COPD and those with lung cancer in both training and validation sets with areas under the receiver operating characteristic curve of 0.89 (95% CI, 0.83-0.95) and 0.86 (95% CI, 0.81-0.89). The same three PCs showed significant differences (P < .01) at baseline between patients with COPD who did and did not subsequently demonstrate lung cancer within 2 years, with a cross-validation value of 87% and an area under the receiver operating characteristic curve of 0.90 (95% CI, 0.84-0.95).

INTERPRETATION

Exhaled breath analysis by eNose identified patients with COPD in whom lung cancer became clinically manifest within 2 years after inclusion. These results show that eNose assessment may detect early stages of lung cancer in patients with COPD.

Evaluation of different classification methods using electronic nose data to diagnose sarcoidosis

Electronic nose (eNose) technology is an emerging diagnostic application, using artificial intelligence to classify human breath patterns. These patterns can be used to diagnose medical conditions. Sarcoidosis is an often difficult to diagnose disease, as no standard procedure or conclusive test exists. An accurate diagnostic model based on eNose data could therefore be helpful in clinical decision-making. The aim of this paper is to evaluate the performance of various dimensionality reduction methods and classifiers in order to design an accurate diagnostic model for sarcoidosis. Various methods of dimensionality reduction and multiple hyperparameter optimised classifiers were tested and cross-validated on a dataset of patients with pulmonary sarcoidosis (n= 224) and other interstitial lung disease (n= 317). Best performing methods were selected to create a model to diagnose patients with sarcoidosis. Nested cross-validation was applied to calculate the overall diagnostic performance. A classification model with feature selection and random forest (RF) classifier showed the highest accuracy. The overall diagnostic performance resulted in an accuracy of 87.1% and area-under-the-curve of 91.2%. After comparing different dimensionality reduction methods and classifiers, a highly accurate model to diagnose a patient with sarcoidosis using eNose data was created. The RF classifier and feature selection showed the best performance. The presented systematic approach could also be applied to other eNose datasets to compare methods and select the optimal diagnostic model.

Detection of Counterfeit Perfumes by Using GC-MS Technique and Electronic Nose System Combined with Chemometric Tools

The Scientific Committee on Cosmetic and Non-Food Products has identified 26 compounds that may cause contact allergy in consumers when present in concentrations above certain legal thresholds in a product. Twenty-four of these compounds are volatiles and can be analyzed by gas chromatography-mass spectrometry (GC-MS) or electronic nose (e-nose) technologies. This manuscript first describes the use of the GC-MS approach to identify the main volatile compounds present in the original perfumes and their counterfeit samples. The second part of this work focusses on the ability of an e-nose system to discriminate between the original fragrances and their counterfeits. The analyses were carried out using the headspace of the aqueous solutions. GC-MS analysis revealed the identification of 10 allergens in the perfume samples, some of which were only found in the imitated fragrances. The e-nose system achieved a fair discrimination between most of the fragrances analyzed, with the counterfeit fragrances being clearly separated from the original perfumes. It is shown that associating the e-nose system to the appropriate classifier successfully solved the classification task. With Principal Component Analysis (PCA), the three first principal components represented 98.09% of the information in the database.

HPLC–(Q)-TOF-MS-Based Study of Plasma Metabolic Profile Differences Associated with Age in Pediatric Population Using an Animal Model

A deep knowledge about the biological development of children is essential for appropriate drug administration and dosage in pediatrics. In this sense, the best approximation to study organ maturation is the analysis of tissue samples, but it requires invasive methods. For this reason, surrogate matrices should be explored. Among them, plasma emerges as a potential alternative since it represents a snapshot of global organ metabolism. In this work, plasma metabolic profiles from piglets of different ages (newborns, infants, and children) obtained by HPLC–(Q)-TOF-MS at positive and negative ionization modes were studied. Improved clustering within groups was achieved using multiblock principal component analysis compared to classical principal component analysis. Furthermore, the separation observed among groups was better resolved by using partial least squares-discriminant analysis, which was validated by bootstrapping and permutation testing. Thanks to univariate analysis, 13 metabolites in positive and 21 in negative ionization modes were found to be significant to discriminate the three groups of piglets. From these features, an acylcarnitine and eight glycerophospholipids were annotated and identified as metabolites of interest. The findings indicate that there is a relevant change with age in lipid metabolism in which lysophosphatidylcholines and lysophoshatidylethanolamines play an important role.

Selectivity enhancement for metal oxide (MOX) based gas sensor using thermally modulated datasets coupled with golden section optimization and chemometric techniques

The ever-increasing demand for smart sensors for internet of things applications drove the change in outlook toward smart sensor system design. This paper focuses on using low-cost gas sensors [Metal Oxide (MOX)] for detection of more than one gas, which is otherwise complex due to poor selectivity of MOX sensors. In this work, detection of two gases, namely, ammonia (NH₃) and carbon monoxide (CO), using a single metal oxide (pristine tin oxide) sensor is demonstrated. Furthermore, chemometric based algorithms have been used to classify and quantify both gases. The present investigation uses the temperature modulated gas sensor response obtained at different concentrations for the mentioned gases. The golden section based optimization technique has been employed to obtain two different ranges of temperatures for both gases. After applying certain pre-processing techniques, the acquired data from the sensors were fed to various classification techniques, such as partial least squares (PLS) discriminant analysis, k-means, and soft independent modeling by class analogy, and 100% classification results were obtained. Furthermore, PLS regression (PLS-R) was used to perform quantitative analysis on the data using the optimized temperature ranges for both gases, and R² regression coefficients, 0.999 25 for NH₃ and 0.9399 for CO, were obtained. The results obtained from both the qualitative and quantitative analyses make our approach low-cost and smart to mitigate the cross-selectivity of metal oxide semiconductor based smart sensor design.

A Machine Learning Modeling Framework for Predictive Maintenance Based on Equipment Load Cycle: An Application in a Real World Case

From a practical point of view, a turbine load cycle (TLC) is defined as the time a turbine in a power plant remains in operation. TLC is used by many electric power plants as a stop indicator for turbine maintenance. In traditional operations, a maximum time for the operation of a turbine is usually estimated and, based on the TLC, the remaining operating time until the equipment is subjected to new maintenance is determined. Today, however, a better process is possible, as there are many turbines with sensors that carry out the telemetry of the operation, and machine learning (ML) models can use this data to support decision making, predicting the optimal time for equipment to stop, from the actual need for maintenance. This is predictive maintenance, and it is widely used in Industry 4.0 contexts. However, knowing which data must be collected by the sensors (the variables), and their impact on the training of an ML algorithm, is a challenge to be explored on a case-by-case basis. In this work, we propose a framework for mapping sensors related to a turbine in a hydroelectric power plant and the selection of variables involved in the load cycle to: (i) investigate whether the data allow identification of the future moment of maintenance, which is done by exploring and comparing four ML algorithms; (ii) discover which are the most important variables (MIV) for each algorithm in predicting the need for maintenance in a given time horizon; (iii) combine the MIV of each algorithm through weighting criteria, identifying the most relevant variables of the studied data set; (iv) develop a methodology to label the data in such a way that the problem of forecasting a future need for maintenance becomes a problem of binary classification (need for maintenance: yes or no) in a time horizon. The resulting framework was applied to a real problem, and the results obtained pointed to rates of maintenance identification with very high accuracies, in the order of 98%.

Comparison of Self-Report Questionnaire and Eye Tracking Method in the Visual Preference Study of a Youth–Beverage Model

This study compares the characteristics of a self-report questionnaire (SRQ) and eye tracking (ET) based on a simple human–beverage visual cognition model. The young participants were mainly defined by their gender and body mass index (BMI). The beverage samples consisted of milk, coffee, cup, and coaster. SRQs allow the participants to clearly express their overall cognition of the samples in the form of vocabulary, while ET captures their hidden thinking process. The analysis, using a random forest (RF) classifier, found that participant parameters (gender and BMI) played a more important role for SRQ, while ET was related to beverage parameters (color and shape). This work reiterates that these two methods have their advantages and complement each other in food sensory analysis.

Combing machine learning and elemental profiling for geographical authentication of Chinese Geographical Indication (GI) rice

Identification of geographical origin is of great importance for protecting the authenticity of valuable agri-food products with designated origins. In this study, a robust and accurate analytical method that could authenticate the geographical origin of Geographical Indication (GI) products was developed. The method was based on elemental profiling using inductively coupled plasma mass spectrometry (ICP-MS) in combination with machine learning techniques for model building and feature selection. The method successfully predicted and classified six varieties of Chinese GI rice. The elemental profiles of 131 rice samples were determined, and two machine learning algorithms were implemented, support vector machines (SVM) and random forest (RF), together with the feature selection algorithm Relief. Prediction accuracy of 100% was achieved by both Relief-SVM and Relief-RF models, using only four elements (Al, B, Rb, and Na). The methodology and knowledge from this study could be used to develop reliable methods for tracing geographical origins and controlling fraudulent labeling of diverse high-value agri-food products.

Trends in artificial aroma sensing by means of electronic nose technologies to advance dairy production - a review

Controversies surrounding the name and how the electronics nose (e-nose) works have been at the center stage since the advent of the technology. Notwithstanding the controversies, the technology has gained popularity in the sensory analysis of dairy foods, because of its rapid results delivery on product aroma profile or pattern, which can be used to assess quality. This review critically evaluated the advances made in the application of the e-nose or artificial sensory system in the dairy industry, focusing on the evaluation of milk, yoghurt and cheese properties, and the trends and prospects of the technology. Most of the e-nose devices applied in the available scientific publications used sensors such as metal oxide semiconductor sensors (MOS), metal-oxide-semiconductor field-effect transistor (MOSFET), conducting polymers composites and quartz microbalance (QMB), and flame ionization detector FID, in a recent study. Though known for aroma sensing, the technology has been applied to evaluate the shelf life or microbial spoilage and to discriminate dairy products based on the volatile profile composition, as determined by the sensors. In most cases, the limitation of the technology is the inability of it to provide information on the nature of constituting compounds, except in gas chromatography and mass spectrometry-based e-nose systems.

Monitoring microstructural changes and moisture distribution of dry-cured pork: a combined confocal laser scanning microscopy and hyperspectral imaging study

BACKGROUND

Various spectral profiles, including reflectance, absorbance, and Kubelka-Munk spectra, have been derived from hyperspectral images and used to develop multivariate models to evaluate changes in the quality of meat and meat products as a function of processing. However, none of these has the capacity to produce images of the structural changes often associated with processing. This study explored the feasibility of combining hyperspectral imaging (HSI) with confocal laser scanning microscopy (CLSM) to examine the impact of processing on microstructural changes and the evolution of moisture. Reflectance spectra features were obtained and transformed into absorbance and Kubelka-Munk spectra and their ability to predict moisture content using models established on partial least-squares regression were evaluated.

RESULTS

The partial least-squares regression model (full-band wavelength) dubbed Rs-MSC yielded the best result, with R c 2 = 0.967 , RMSEC = 0.127, R cv 2 = 0.949 , RMSECV = 0.418, R p 2 = 0.937 , RMSEP = 0.824. Next, a total of 16 optimum wavelengths were selected using the competitive adaptive reweighted sampling algorithm. These wavelengths also yielded good results for Rs-MSC, with R c 2 = 0.958 , RMSEC = 0.840, R cv 2 = 0.931 , RMSECV = 0.118, R p 2 = 0.926 , RMSEP = 0.121. Regarding moisture distribution and microstructure analysis, HSI and CLSM were able to reveal moisture content distribution and conformational differences in microstructure in the test samples.

CONCLUSION

Using HSI in synergy with CLSM may offer a reliable means for assessing both the chemical and structural changes that occur in other congener food products during processing. © 2020 Society of Chemical Industry.

Optimization of electronic nose drift correction applied to tomato volatile profiling

E-noses can be routinely used to evaluate the volatile profile of tomato samples once the sensor drift and standardization issues are adequately solved. Short-term drift can be corrected using a strategy based on a multiplicative drift correction procedure coupled with a PLS adaptation of the component correction. It must be performed specifically for each sequence, using all sequence signals data. With this procedure, a drastic reduction of sensor signal %RSD can be obtained, ranging between 91.5 and 99.7% for long sequences and between 75.7 and 98.8% for short sequences. On the other hand, long-term drift can be fixed up using a synthetic reference standard mix (with a representation of main aroma volatiles of the species) to be included in each sequence that would enable sequence standardization. With this integral strategy, a high number of samples can be analyzed in different sequences, with a 94.4% success in the aggrupation of the same materials in PLS-DA two-dimensional graphical representations. Using this graphical interface, e-noses can be used to developed expandable maps of volatile profile similitudes, which will be useful to select the materials that most resemble breeding objectives or to analyze which preharvest and postharvest procedures have a lower impact on the volatile profile, avoiding the costs and sample limitations of gas chromatography.

1H NMR-based metabolomics study of the dynamic effect of Xue-Fu-Zhu-Yu capsules on coronary heart disease rats induced by high-fat diet, coronary artery ligation

An ¹H NMR-based metabolomics approach was conducted to holisticly explore the effect of Xue Fu Zhu Yu (XFZY) capsule (a well-known Chinese herbal medicine) on high-fat diets combined with coronary artery ligation induced coronary heart disease (CHD) model rats. 1H NMR-based metabolomics approach combined with multivariate analysis was performed to explore potential biomarkers, a total of 20 metabolites were confirmed as contributors to the discrimination of model group and sham group. We investigated the dynamic metabolic characteristics of XFZY capsule on CHD rats, lactate, glutamine, pyruvate, citrate, choline and taurine were potential biomarkers of early effect. More potential biomarkers changed after 28 days of medication, XFZY capsules primarily influenced the taurine and hypotaurine metabolism, glycine, serine and threonine metabolism, glyoxylate and dicarboxylate metabolism, purine metabolism, glycolysis/gluconeogenesis, amino sugar and nucleotide sugar metabolism, primary bile acid biosynthesis.

Explicitly Identifying the Desertification Change in CMREC Area Based on Multisource Remote Data

Explicitly identifying the desertification changes and causes has been a hot issue of eco-environment sustainable development in the China–Mongolia–Russia Economic Corridor (CMREC) area. In this paper, the desertification change patterns between 2000 and 2015 were identified by operating the classification and regression tree (CART) method with multisource remote sensing datasets on Google Earth Engine (GEE), which has the higher overall accuracy (85%) than three other methods, namely support vector machine (SVM), random forest (RF) and Albedo-normalized difference vegetation index (NDVI) models. A contribution index of climate change and human activities on desertification was introduced to quantitatively explicate the driving mechanisms of desertification change based on the temporal datasets and net primary productivity (NPP). The results show that the area of slight desertification land had increased from 719,700 km2 to 948,000 km2 between 2000 and 2015. The area of severe desertification land decreased from 82,400 km2 to 71,200 km2. The area of desertification increased by 9.68%, in which 69.68% was mainly caused by human activities. Climate change and human activities accounted for 68.8% and 27.36%, respectively, in the area of desertification restoration. In general, the degree of desertification showed a decreasing trend, and climate change was the major driving factor in the CMREC area between 2000 and 2015.

Multi-sensor integration approach based on hyperspectral imaging and electronic nose for quantitation of fat and peroxide value of pork meat

The study assessed the feasibility of merging data acquired from hyperspectral imaging (HSI) and electronic nose (e-nose) to develop a robust method for the rapid prediction of intramuscular fat (IMF) and peroxide value (PV) of pork meat affected by temperature and NaCl treatments. Multivariate calibration models for prediction of IMF and PV using median spectra features (MSF) and image texture features (ITF) from HSI data and mean signal values (MSV) from e-nose signals were established based on support vector machine regression (SVMR). Optimum wavelengths highly related to IMF and PV were selected from the MSF and ITF. Next, recurring optimum wavelengths from the two feature groups were manually obtained and merged to constitute "combined attribute features" (CAF) which yielded acceptable results with (R_c² = 0.877, 0.891; RMSEC = 2.410, 1.109; R_p² = 0.790, 0.858; RMSEP = 3.611, 2.013) respectively for IMF and PV. MSV yielded relatively low results with (R_c² = 0.783, 0.877; RMSEC = 4.591, 0.653; R_p² = 0.704, 0.797; RMSEP = 3.991, 0.760) respectively for IMF and PV. Finally, data fusion of CAF and MSV was performed which yielded relatively improved prediction results with (R_c² = 0.936, 0.955; RMSEC = 1.209, 0.997; R_p² = 0.895, 0.901; RMSEP = 2.099, 1.008) respectively for IMF and PV. The results obtained demonstrate that it is feasible to mutually integrate spectral and image features with volatile information to quantitatively monitor IMF and PV in processed pork meat. Graphical abstract.

Bulk and Surface Acoustic Wave Sensor Arrays for Multi-Analyte Detection: A Review

Bulk acoustic wave (BAW) and surface acoustic wave (SAW) sensor devices have successfully been used in a wide variety of gas sensing, liquid sensing, and biosensing applications. Devices include BAW sensors using thickness shear modes and SAW sensors using Rayleigh waves or horizontally polarized shear waves (HPSWs). Analyte specificity and selectivity of the sensors are determined by the sensor coatings. If a group of analytes is to be detected or if only selective coatings (i.e., coatings responding to more than one analyte) are available, the use of multi-sensor arrays is advantageous, as the evaluation of the resulting signal patterns allows qualitative and quantitative characterization of the sample. Virtual sensor arrays utilize only one sensor but combine it with enhanced signal evaluation methods or preceding sample separation, which results in similar results as obtained with multi-sensor arrays. Both array types have shown to be promising with regard to system integration and low costs. This review discusses principles and design considerations for acoustic multi-sensor and virtual sensor arrays and outlines the use of these arrays in multi-analyte detection applications, focusing mainly on developments of the past decade.

Front-face fluorescence spectroscopy combined with chemometrics to detect high proteinaceous matter in milk and whey ultrafiltration permeate

Proteinaceous matter can leak into the permeate stream during ultrafiltration (UF) of milk and whey and lead to financial losses. Although manufacturers can measure protein content in the finished permeate powders, there is currently no rapid monitoring tool during UF to identify protein leak. This study applied front-face fluorescence spectroscopy (FFFS) and chemometrics to identify the fluorophore of interest associated with the protein leak, develop predictive models to quantify true protein content, and classify the types of protein leak in permeate streams. Crude protein (CP), nonprotein nitrogen (NPN), true protein (TP), tryptone-equivalent peptide (TEP), α-lactalbumin (α-LA), and β-lactoglobulin (β-LG) contents were measured for 37 lots of whey permeate and 29 lots of milk permeate from commercial manufacturers. Whey permeate contained more TEP than did milk permeate, whereas milk permeate contained more α-LA and β-LG than did whey permeate. The types of protein leak were thus identified for predictive model development. Based on excitation-emission matrix (EEM) of high- and low-TP permeates, tryptophan excitation spectra were collected for predictive model development, measuring TP content in permeate. With external validation, a useful model for quality control purposes was developed, with a root mean square error of prediction of 0.22% (dry basis) and a residual prediction deviation of 2.8. Moreover, classification models were developed using partial least square discriminant analysis. These classification methods can detect high TP level, high TEP level, and presence of α-LA or β-LG with 83.3%, 84.8%, and 98.5% cross-validated accuracy, respectively. This method showed that FFFS and chemometrics can rapidly detect protein leaks and identify the types of protein leak in UF permeate. Implementation of this method in UF processing plants can reduce financial loss from protein leaks and maintain high-quality permeate production.

Methodological considerations for large-scale breath analysis studies: lessons from the U-BIOPRED severe asthma project

Methods for breath sampling and analysis require robust quality assessment to minimise the risk of false discoveries. Planning large-scale multi-site breath metabolite profiling studies also requires careful consideration of systematic and random variation as a result of sampling and analysis techniques. In this study we use breath sample data from the recent U-BIOPRED cohort to evaluate and discuss some important methodological considerations such as batch variation and correction, variation between sites, storage and transportation, as well as inter-instrument analytical differences. Based on this we provide a summary of recommended best practices for new large scale multi-site studies.

Partial least squares-discriminant analysis (PLS-DA) for classification of high-dimensional (HD) data: a review of contemporary practice strategies and knowledge gaps

This review highlights and discusses critically various knowledge gaps in classification modelling using PLS-DA for high dimensional data.

Discriminative Analysis of Different Grades of Gaharu (Aquilaria malaccensis Lamk.) via ¹H-NMR-Based Metabolomics Using PLS-DA and Random Forests Classification Models

Gaharu (agarwood, Aquilaria malaccensis Lamk.) is a valuable tropical rainforest product traded internationally for its distinctive fragrance. It is not only popular as incense and in perfumery, but also favored in traditional medicine due to its sedative, carminative, cardioprotective and analgesic effects. The current study addresses the chemical differences and similarities between gaharu samples of different grades, obtained commercially, using ¹H-NMR-based metabolomics. Two classification models: partial least squares-discriminant analysis (PLS-DA) and Random Forests were developed to classify the gaharu samples on the basis of their chemical constituents. The gaharu samples could be reclassified into a ‘high grade’ group (samples A, B and D), characterized by high contents of kusunol, jinkohol, and 10-epi-γ-eudesmol; an ‘intermediate grade’ group (samples C, F and G), dominated by fatty acid and vanillic acid; and a ‘low grade’ group (sample E and H), which had higher contents of aquilarone derivatives and phenylethyl chromones. The results showed that ¹H- NMR-based metabolomics can be a potential method to grade the quality of gaharu samples on the basis of their chemical constituents.

Detection of lung cancer in exhaled breath with an electronic nose using support vector machine analysis

Lung cancer is one of the most common malignancies and has a low 5-year survival rate. There are no cheap, simple and widely available screening methods for the early diagnostics of lung cancer. The aim of this study was to determine whether analysis of exhaled breath with an artificial olfactory sensor using support vector analysis can differentiate patients with lung cancer from healthy individuals and patients with other lung diseases, regardless of the stage of lung cancer and the most common comorbidities. Patients with histologically or cytologically verified lung cancer, healthy volunteers and patients with other lung diseases (e.g. chronic obstructive pulmonary disease (COPD), asthma, pneumonia, pulmonary embolism, benign lung tumors) were enrolled in the study. Breath sample collection and analysis with a Cyranose 320 sensor device was performed and data were further analyzed using a support vector machine (SVM). The SVM correctly differentiated between cancer patients and healthy volunteers in 98.8% of cases. The cancer versus non-cancer group patients (healthy volunteers and patients with other lung diseases) were classified correctly by SVM in 87.3% of cases. In the mixed diagnosis groups (only cancer, only COPD, cancer + COPD and control) all 79 out of 79 patients were predicted correctly in the cancer + COPD group, with the rate of correct prognosis in other patient groups being lower. Exhaled breath analysis by electronic nose using a SVM is able to discriminate patients with lung cancer from healthy subjects and mixed groups of patients with different lung diseases. It can also provide a certain level of discrimination between lung cancer patients, lung cancer patients with concomitant COPD, COPD alone and a healthy control group.

Probing the action of a novel anti-leukaemic drug therapy at the single cell level using modern vibrational spectroscopy techniques

Acute myeloid leukaemia (AML) is a life threatening cancer for which there is an urgent clinical need for novel therapeutic approaches. A redeployed drug combination of bezafibrate and medroxyprogesterone acetate (BaP) has shown anti-leukaemic activity in vitro and in vivo. Elucidation of the BaP mechanism of action is required in order to understand how to maximise the clinical benefit. Attenuated total reflectance Fourier transform infrared (ATR-FTIR) spectroscopy, Synchrotron radiation FTIR (S-FTIR) and Raman microspectroscopy are powerful complementary techniques which were employed to probe the biochemical composition of two AML cell lines in the presence and absence of BaP. Analysis was performed on single living cells along with dehydrated and fixed cells to provide a large and detailed data set. A consideration of the main spectral differences in conjunction with multivariate statistical analysis reveals a significant change to the cellular lipid composition with drug treatment; furthermore, this response is not caused by cell apoptosis. No change to the DNA of either cell line was observed suggesting this combination therapy primarily targets lipid biosynthesis or effects bioactive lipids that activate specific signalling pathways.

A European Respiratory Society technical standard: exhaled biomarkers in lung disease

Breath tests cover the fraction of nitric oxide in expired gas (F_eNO), volatile organic compounds (VOCs), variables in exhaled breath condensate (EBC) and other measurements. For EBC and for F_eNO, official recommendations for standardised procedures are more than 10 years old and there is none for exhaled VOCs and particles. The aim of this document is to provide technical standards and recommendations for sample collection and analytic approaches and to highlight future research priorities in the field. For EBC and F_eNO, new developments and advances in technology have been evaluated in the current document. This report is not intended to provide clinical guidance on disease diagnosis and management.Clinicians and researchers with expertise in exhaled biomarkers were invited to participate. Published studies regarding methodology of breath tests were selected, discussed and evaluated in a consensus-based manner by the Task Force members.Recommendations for standardisation of sampling, analysing and reporting of data and suggestions for research to cover gaps in the evidence have been created and summarised.Application of breath biomarker measurement in a standardised manner will provide comparable results, thereby facilitating the potential use of these biomarkers in clinical practice.

Geographical traceability of wild Boletus edulis based on data fusion of FT-MIR and ICP-AES coupled with data mining methods (SVM)

In this work, the data fusion strategy of Fourier transform mid infrared (FT-MIR) spectroscopy and inductively coupled plasma-atomic emission spectrometry (ICP-AES) was used in combination with Support Vector Machine (SVM) to determine the geographic origin of Boletus edulis collected from nine regions of Yunnan Province in China. Firstly, competitive adaptive reweighted sampling (CARS) was used for selecting an optimal combination of key wavenumbers of second derivative FT-MIR spectra, and thirteen elements were sorted with variable importance in projection (VIP) scores. Secondly, thirteen subsets of multi-elements with the best VIP score were generated and each subset was used to fuse with FT-MIR. Finally, the classification models were established by SVM, and the combination of parameter C and γ (gamma) of SVM models was calculated by the approaches of grid search (GS) and genetic algorithm (GA). The results showed that both GS-SVM and GA-SVM models achieved good performances based on the #9 subset and the prediction accuracy in calibration and validation sets of the two models were 81.40% and 90.91%, correspondingly. In conclusion, it indicated that the data fusion strategy of FT-MIR and ICP-AES coupled with the algorithm of SVM can be used as a reliable tool for accurate identification of B. edulis, and it can provide a useful way of thinking for the quality control of edible mushrooms.

Olfactory Recognition Based on EEG Gamma-Band Activity

There are various kinds of brain monitoring techniques, including local field potential, near-infrared spectroscopy, magnetic resonance imaging (MRI), positron emission tomography, functional MRI, electroencephalography (EEG), and magnetoencephalography. Among those techniques, EEG is the most widely used one due to its portability, low setup cost, and noninvasiveness. Apart from other advantages, EEG signals also help to evaluate the ability of the smelling organ. In such studies, EEG signals, which are recorded during smelling, are analyzed to determine the subject lacks any smelling ability or to measure the response of the brain. The main idea of this study is to show the emotional difference in EEG signals during perception of valerian, lotus flower, cheese, and rosewater odors by the EEG gamma wave. The proposed method was applied to the EEG signals, which were taken from five healthy subjects in the conditions of eyes open and eyes closed at the Swiss Federal Institute of Technology. In order to represent the signals, we extracted features from the gamma band of the EEG trials by continuous wavelet transform with the selection of Morlet as a wavelet function. Then the [Formula: see text]-nearest neighbor algorithm was implemented as the classifier for recognizing the EEG trials as valerian, lotus flower, cheese, and rosewater. We achieved an average classification accuracy rate of 87.50% with the 4.3 standard deviation value for the subjects in eyes-open condition and an average classification accuracy rate of 94.12% with the 2.9 standard deviation value for the subjects in eyes-closed condition. The results prove that the proposed continuous wavelet transform-based feature extraction method has great potential to classify the EEG signals recorded during smelling of the present odors. It has been also established that gamma-band activity of the brain is highly associated with olfaction.

Electronic Nose Testing Procedure for the Definition of Minimum Performance Requirements for Environmental Odor Monitoring

Despite initial enthusiasm towards electronic noses and their possible application in different fields, and quite a lot of promising results, several criticalities emerge from most published research studies, and, as a matter of fact, the diffusion of electronic noses in real-life applications is still very limited. In general, a first step towards large-scale-diffusion of an analysis method, is standardization. The aim of this paper is describing the experimental procedure adopted in order to evaluate electronic nose performances, with the final purpose of establishing minimum performance requirements, which is considered to be a first crucial step towards standardization of the specific case of electronic nose application for environmental odor monitoring at receptors. Based on the experimental results of the performance testing of a commercialized electronic nose type with respect to three criteria (i.e., response invariability to variable atmospheric conditions, instrumental detection limit, and odor classification accuracy), it was possible to hypothesize a logic that could be adopted for the definition of minimum performance requirements, according to the idea that these are technologically achievable.

Biomimetic Cross-Reactive Sensor Arrays: Prospects in Biodiagnostics

Biomimetic cross-reactive sensor arrays have been used to detect and analyze a wide variety of vapour and liquid components in applications such as food science, public health and safety, and diagnostics. As technology has advanced over the past three decades, these systems have become selective, sensitive, and affordable. Currently, the need for non-invasive and accurate devices for early disease diagnosis remains a challenge. This review provides an overview of the various types of Biomimetic cross-reactive sensor arrays (also referred to as electronic noses and tongues in the literature), their current use and future directions, and an outlook for future technological development.

Improved Discrimination for Brassica Vegetables Treated with Agricultural Fertilizers Using a Combined Chemometric Approach

Multielement and stable isotope (δ(13)C, δ(15)N, δ(2)H, δ(18)O, (207)Pb/(206)Pb, and (208)Pb/(206)Pb) analyses were combined to provide a new chemometric approach to improve the discrimination between organic and conventional Brassica vegetable production. Different combinations of organic and conventional fertilizer treatments were used to demonstrate this authentication approach using Brassica chinensis planted in experimental test pots. Stable isotope analyses (δ(15)N and δ(13)C) of B. chinensis using elemental analyzer-isotope ratio mass spectrometry easily distinguished organic and chemical fertilizer treatments. However, for low-level application fertilizer treatments, this dual isotope approach became indistinguishable over time. Using a chemometric approach (combined isotope and elemental approach), organic and chemical fertilizer mixes and low-level applications of synthetic and organic fertilizers were detectable in B. chinensis and their associated soils, improving the detection limit beyond the capacity of individual isotopes or elemental characterization. LDA shows strong promise as an improved method to discriminate genuine organic Brassica vegetables from produce treated with chemical fertilizers and could be used as a robust test for organic produce authentication.

Comparison of different classification methods for analyzing electronic nose data to characterize sesame oils and blends

An electronic nose (e-nose) was used to characterize sesame oils processed by three different methods (hot-pressed, cold-pressed, and refined), as well as blends of the sesame oils and soybean oil. Seven classification and prediction methods, namely PCA, LDA, PLS, KNN, SVM, LASSO and RF, were used to analyze the e-nose data. The classification accuracy and MAUC were employed to evaluate the performance of these methods. The results indicated that sesame oils processed with different methods resulted in different sensor responses, with cold-pressed sesame oil producing the strongest sensor signals, followed by the hot-pressed sesame oil. The blends of pressed sesame oils with refined sesame oil were more difficult to be distinguished than the blends of pressed sesame oils and refined soybean oil. LDA, KNN, and SVM outperformed the other classification methods in distinguishing sesame oil blends. KNN, LASSO, PLS, and SVM (with linear kernel), and RF models could adequately predict the adulteration level (% of added soybean oil) in the sesame oil blends. Among the prediction models, KNN with k = 1 and 2 yielded the best prediction results.

Multivariate data analysis and metabolic profiling of artemisinin and related compounds in high yielding varieties of Artemisia annua field-grown in Madagascar

An improved liquid chromatography-tandem mass spectrometry (LC-MS/MS) protocol for rapid analysis of co-metabolites of A. annua in raw extracts was developed and extensively characterized. The new method was used to analyse metabolic profiles of 13 varieties of A. annua from an in-field growth programme in Madagascar. Several multivariate data analysis techniques consistently show the association of artemisinin with dihydroartemisinic acid. These data support the hypothesis of dihydroartemisinic acid being the late stage precursor to artemisinin in its biosynthetic pathway.

Expiratory flow rate, breath hold and anatomic dead space influence electronic nose ability to detect lung cancer

Background

Electronic noses are composites of nanosensor arrays. Numerous studies showed their potential to detect lung cancer from breath samples by analysing exhaled volatile compound pattern (“breathprint”). Expiratory flow rate, breath hold and inclusion of anatomic dead space may influence the exhaled levels of some volatile compounds; however it has not been fully addressed how these factors affect electronic nose data. Therefore, the aim of the study was to investigate these effects.

Methods

37 healthy subjects (44 ± 14 years) and 27 patients with lung cancer (60 ± 10 years) participated in the study. After deep inhalation through a volatile organic compound filter, subjects exhaled at two different flow rates (50 ml/sec and 75 ml/sec) into Teflon-coated bags. The effect of breath hold was analysed after 10 seconds of deep inhalation. We also studied the effect of anatomic dead space by excluding this fraction and comparing alveolar air to mixed (alveolar + anatomic dead space) air samples. Exhaled air samples were processed with Cyranose 320 electronic nose.

Results

Expiratory flow rate, breath hold and the inclusion of anatomic dead space significantly altered “breathprints” in healthy individuals (p < 0.05), but not in lung cancer (p > 0.05). These factors also influenced the discrimination ability of the electronic nose to detect lung cancer significantly.

Conclusions

We have shown that expiratory flow, breath hold and dead space influence exhaled volatile compound pattern assessed with electronic nose. These findings suggest critical methodological recommendations to standardise sample collections for electronic nose measurements.