Recent Progress in Smart Electronic Nose Technologies Enabled with Machine Learning Methods

Progress in machine learning-supported electronic nose and hyperspectral imaging technologies for food safety assessment: A review

The growing concern over food safety, driven by threats such as food contaminations and adulterations has prompted the adoption of advanced technologies like electronic nose (e-nose) and hyperspectral imaging (HSI), which are increasingly enhanced by machine learning innovations. This paper aims to provide a comprehensive review on food safety, by combining insights from both e-nose and HSI technologies alongside machine learning algorithms. First, the basic principles of e-nose, HSI, and machine learning, with particular emphasis on artificial neural network (ANN) and deep learning (DL) are briefly discussed. The review then examines how machine learning enhances the performance of e-nose and HSI, followed by an exploration of recent applications in detecting food hazards, including drug residues, microbial contaminants, pesticide residues, toxins, and adulterants. Subsequently, key limitations encountered in the applications of machine learning, e-nose and HSI, along with future perspectives on the potential advancements of these technologies are highlighted. E-nose and HSI technologies have shown their great potential for applications in food safety assessment through machine learning assistance. Despite this, their use is primarily limited to laboratory environments, restricting their real-world applications. Additionally, the lack of standardized protocols hampers their acceptance and the reproducibility of tests in food safety assessments. Thus, further research is essential to address these limitations and enhance the effectiveness of e-nose and HSI technologies in practical applications. Ultimately, this paper offers a detailed understanding of both technologies, highlighting the pivotal role of machine learning and presenting insights into their innovative applications within food safety evaluation.

Stomach cancer identification based on exhaled breath analysis: a review

Early prediction of cancer is crucial for effective treatment decisions. Stomach cancer is one of the worst malignancies in the world because it does not reveal the growth in symptoms. In recent years, non-invasive diagnostic methods, particularly exhaled breath analysis, have attracted interest in detecting stomach cancer. This review discusses invasive and non-invasive diagnostic methods for stomach cancer, with a special emphasis on breath analysis and electronic nose (e-nose) technology. Various analytical methods have been used to analyze volatile organic compounds (VOCs) associated with stomach cancer. Gas chromatography-mass Spectrometry is one of the most widely used techniques. These techniques enable the detection and analysis of VOCs, offering a promising route for early stomach cancer diagnosis. The e-nose system has been introduced as a cost-effective and portable alternative for VOC detection in stomach cancer to overcome the challenges associated with conventional methods. This review discusses the advantages and disadvantages of the e-nose system. This review recommends that e-nose sensors, combined with advanced pattern recognition techniques, be utilized to enable rapid and reliable diagnosis of stomach cancer.

Breathomics: A Non-Invasive Approach for the Diagnosis of Breast Cancer

Breast cancer is the most commonly diagnosed cancer worldwide, underscoring the critical need for effective early detection methods to reduce mortality. Traditional detection techniques, such as mammography, present significant limitations, particularly in women with dense breast tissue, highlighting the need for alternative screening approaches. Breathomics, based on the analysis of Volatile Organic Compounds (VOCs) present in exhaled breath, offers a non-invasive, potentially transformative diagnostic tool. These VOCs are metabolic byproducts from various organs of the human body whose presence and varying concentrations in breath are reflective of different health conditions. This review explores the potential of breathomics, highlighting its promise as a rapid, cost-effective screening approach for breast cancer, facilitated through the integration of portable solutions like electronic noses (e-noses). Key considerations for clinical translation-including patient selection, environmental confounders, and different breath collection methods-will be examined in terms of how each of them affects the breath profile. However, there are also challenges such as patient variability in VOC signatures, and the need for standardization in breath sampling protocols. Future research should prioritize standardizing sampling and analytical procedures and validating their clinical utility through large-scale clinical trials.

Artificial Intelligence in Gas Sensing: A Review

The role of artificial intelligence (AI), machine learning (ML), and deep learning (DL) in enhancing and automating gas sensing methods and the implications of these technologies for emergent gas sensor systems is reviewed. Applications of AI-based intelligent gas sensors include environmental monitoring, industrial safety, remote sensing, and medical diagnostics. AI, ML, and DL methods can process and interpret complex sensor data, allowing for improved accuracy, sensitivity, and selectivity, enabling rapid gas detection and quantitative concentration measurements based on sophisticated multiband, multispecies sensor systems. These methods can discern subtle patterns in sensor signals, allowing sensors to readily distinguish between gases with similar sensor signatures, enabling adaptable, cross-sensitive sensor systems for multigas detection under various environmental conditions. Integrating AI in gas sensor technology represents a paradigm shift, enabling sensors to achieve unprecedented performance, selectivity, and adaptability. This review describes gas sensor technologies and AI while highlighting approaches to AI-sensor integration.

Nanomaterial Innovations and Machine Learning in Gas Sensing Technologies for Real-Time Health Diagnostics

Breath sensors represent a frontier in noninvasive diagnostics, leveraging the detection of volatile organic compounds (VOCs) in exhaled breath for real-time health monitoring. This review highlights recent advancements in breath-sensing technologies, with a focus on the innovative materials driving their enhanced sensitivity and selectivity. Polymers, carbon-based materials like graphene and carbon nanotubes, and metal oxides such as ZnO and SnO2 have demonstrated significant potential in detecting biomarkers related to diseases including diabetes, liver/kidney dysfunction, asthma, and gut health. The structural and operational principles of these materials are examined, revealing how their unique properties contribute to the detection of key respiratory gases like acetone, ammonia (NH3), hydrogen sulfide, and nitric oxide. The complexity of breath samples is addressed through the integration of machine learning (ML) algorithms, including convolutional neural networks (CNNs) and support vector machines (SVMs), which optimize data interpretation and diagnostic accuracy. In addition to sensing VOCs, these devices are capable of monitoring parameters such as airflow, temperature, and humidity, essential for comprehensive breath analysis. This review also explores the expanding role of artificial intelligence (AI) in transforming wearable breath sensors into sophisticated tools for personalized health diagnostics, enabling real-time disease detection and monitoring. Together, advances in sensor materials and ML-based analytics present a promising platform for the future of individualized, noninvasive healthcare.

Design Principles From Natural Olfaction for Electronic Noses

Natural olfactory systems possess remarkable sensitivity and precision beyond what is currently achievable by engineered gas sensors. Unlike their artificial counterparts, noses are capable of distinguishing scents associated with mixtures of volatile molecules in complex, typically fluctuating environments and can adapt to changes. This perspective examines the multifaceted biological principles that provide olfactory systems their discriminatory prowess, and how these ideas can be ported to the design of electronic noses for substantial improvements in performance across metrics such as sensitivity and ability to speciate chemical mixtures. The topics examined herein include the fluid dynamics of odorants in natural channels; specificity and kinetics of odorant interactions with olfactory receptors and mucus linings; complex signal processing that spatiotemporally encodes physicochemical properties of odorants; active sampling techniques, like biological sniffing and nose repositioning; biological priming; and molecular chaperoning. Each of these components of natural olfactory systems are systmatically investigated, as to how they have been or can be applied to electronic noses. While not all artificial sensors can employ these strategies simultaneously, integrating a subset of bioinspired principles can address issues like sensitivity, drift, and poor selectivity, offering advancements in many sectors such as environmental monitoring, industrial safety, and disease diagnostics.

Recent advances in signal processing algorithms for electronic noses

Electronic nose (e-nose) technology has emerged as a pivotal tool in various domains, which has been widely utilized for odor identification, concentration evaluation, and prediction tasks. This review provides a comprehensive survey on the most recent advances in the development of e-nose systems and their algorithmic applications, emphasizing the roles of various methodologies and deep learning technologies in odor classification and concentration forecasting. Additionally, we delve into model evaluation methods, including multidimensional performance assessment and cross-validation. Future trends encompass broader application domains, advanced drift correction techniques, comprehensive multifactorial analysis, and enhanced capabilities for dealing with unknown interferents. These trends are set to propel significant breakthroughs in e-nose technology within scientific research and practical applications, solidifying the e-nose system as a crucial tool in many areas such as environmental monitoring, biomedicine, and public safety.

Development of Electronic Nose as a Complementary Screening Tool for Breath Testing in Colorectal Cancer

(1) Background: Colorectal cancer is one of the leading causes of cancer-related death, while early detection decreases incidence and mortality. Current screening programs involving fecal immunological testing and colonoscopy commonly bring about unnecessary colonoscopies, which adds burden to healthcare systems. The objective of this study was to provide an assessment of the diagnostic performance of an electronic nose serving as a complementary screening tool to improve current screening programs in clinical settings. (2) Methods: We conducted a case-control study that included patients from a medical center with colorectal cancer and non-colorectal cancer controls. We analyzed the composition of volatile organic compounds in their exhaled breath using the electronic nose. We then used machine learning algorithms to develop predictive models and provided the estimated accuracy and reliability of the breath testing. (3) Results: We enrolled 77 patients, with 40 cases and 37 controls. The area under the curve, Kappa coefficient, sensitivity, and specificity of the selected model were 0.87 (95% CI 0.76-0.95), 0.66 (95% CI 0.49-0.83), 0.81, and 0.85. For subjects at an early stage of disease, the sensitivity and specificity were 0.90 and 0.85. Excluding smokers, the sensitivity and specificity were 0.88 and 0.92. (4) Conclusions: This study highlights the promising potential of breath testing using an electronic nose for enabling early detection and reducing unnecessary treatments. However, more independent data for external validation are required to ensure applicability and generalizability.

Cr-Doped Nanocrystalline TiO2-Cr2O3 Nanocomposites with p-p Heterojunction as a Stable Gas-Sensitive Material

Nanocrystalline TiO2 is a perspective semiconductor gas-sensing material due to its long-term stability of performance, but it is limited in application because of high electrical resistance. In this paper, a gas-sensing nanocomposite material with p-p heterojunction is introduced based on p-conducting Cr-doped TiO2 in combination with p-conducting Cr2O3. Materials were synthesized via a single-step flame spray pyrolysis (FSP) technique and comprehensively studied by X-ray diffraction (XRD), Brunauer-Emmett-Teller (BET) specific surface area analysis, transition electron microscopy (TEM), energy dispersive X-ray (EDX) spectroscopy, X-ray photoelectron spectroscopy (XPS), electron paramagnetic resonance (EPR), and Raman spectroscopy. Gas sensor performance in direct current (DC) mode was studied toward a number of gasses (H2, CO, CH4, NO2, H2S, NH3) as well as volatile organic compounds (VOCs) (acetone, methanol, and formaldehyde) in dry and humid conditions. The long-term stability of the obtained materials' gas sensor performance was evaluated alongside with an ex situ study of structural evolution. High sensitivity toward oxygenated VOCs and a lower detection limit below ppm level with a limited influence of humidity were shown. The long-term gas sensor performance stability of the obtained materials and its connection to the defect structure of doped TiO2 is demonstrated.

AACVD synthesized tungsten oxide-NWs loaded with osmium oxide as a gas sensor array: enhancing detection with PCA and ANNs

This paper presents the fabrication of sensors based on tungsten trioxide nanowires decorated with osmium oxide nanoparticles using the aerosol-assisted chemical vapor deposition (AACVD) technique. This methodology allows the obtention of different osmium oxide decoration loadings on the tungsten oxide nanowires. The morphological and chemical characteristics; and the structural properties of the sensing layers of the sensors were studied using different techniques such as FESEM, HR-TEM, and ToF-SIMS. The gas sensing properties were analyzed for pure tungsten trioxide sensors and tungsten trioxide loaded with osmium exposed to nitrogen dioxide, hydrogen, and ethanol, thus assessing the impact of the loading on the sensor response. A sensor array comprising pure and osmium-loaded tungsten oxide devices coupled to multivariate pattern recognition techniques is shown to perform well in gas identification and quantification tasks, offering promising implications in the field of gas sensing technology.

A paradigm shift in the detection of bloodborne pathogens: conventional approaches to recent detection techniques

Bloodborne pathogens (BBPs) pose formidable challenges in the realm of infectious diseases, representing significant risks to both human and animal health worldwide. The review paper provides a thorough examination of bloodborne pathogens, highlighting the serious worldwide threat they pose and the effects they have on animal and human health. It addresses the potential dangers of exposure that healthcare workers confront, which have affected 3 million people annually, and investigates the many pathways by which these viruses can spread. The limitations of traditional detection techniques like PCR and ELISA have been criticized, which has led to the investigation of new detection methods driven by advances in sensor technology. The objective is to increase the amount of knowledge that is available regarding bloodborne infections as well as effective strategies for their management and detection. This review provides a thorough overview of common bloodborne infections, including their patterns of transmission, and detection techniques.

Intelligent Evaluation and Dynamic Prediction of Oysters Freshness with Electronic Nose Non-Destructive Monitoring and Machine Learning

Physiological and environmental fluctuations in the oyster cold chain can lead to quality deterioration, highlighting the importance of monitoring and evaluating oyster freshness. In this study, an electronic nose was developed using ten partially selective metal oxide-based gas sensors for rapid freshness assessment. Simultaneous analyses, including GC-MS, TVBN, microorganism, texture, and sensory evaluations, were conducted to assess the quality status of oysters. Real-time electronic nose measurements were taken at various storage temperatures (4 °C, 12 °C, 20 °C, 28 °C) to thoroughly investigate quality changes under different storage conditions. Principal component analysis was utilized to reduce the 10-dimensional vectors to 3-dimensional vectors, enabling the clustering of samples into fresh, sub-fresh, and decayed categories. A GA-BP neural network model based on these three classes achieved a test data accuracy rate exceeding 93%. Expert input was solicited for performance analysis and optimization suggestions enhanced the efficiency and applicability of the established prediction system. The results demonstrate that combining an electronic nose with quality indices is an effective approach for diagnosing oyster spoilage and mitigating quality and safety risks in the oyster industry.

Role of Machine Learning Assisted Biosensors in Point-of-Care-Testing For Clinical Decisions

Point-of-Care-Testing (PoCT) has emerged as an essential component of modern healthcare, providing rapid, low-cost, and simple diagnostic options. The integration of Machine Learning (ML) into biosensors has ushered in a new era of innovation in the field of PoCT. This article investigates the numerous uses and transformational possibilities of ML in improving biosensors for PoCT. ML algorithms, which are capable of processing and interpreting complicated biological data, have transformed the accuracy, sensitivity, and speed of diagnostic procedures in a variety of healthcare contexts. This review explores the multifaceted applications of ML models, including classification and regression, displaying how they contribute to improving the diagnostic capabilities of biosensors. The roles of ML-assisted electrochemical sensors, lab-on-a-chip sensors, electrochemiluminescence/chemiluminescence sensors, colorimetric sensors, and wearable sensors in diagnosis are explained in detail. Given the increasingly important role of ML in biosensors for PoCT, this study serves as a valuable reference for researchers, clinicians, and policymakers interested in understanding the emerging landscape of ML in point-of-care diagnostics.

A 10-Channel, 120 nW/Channel, Reconfigurable Capacitance-to-Digital Converter for Sub- μW Robust Wearable Sensing

This paper presents a 10-channel, 120 nW/channel, reconfigurable capacitance-to-digital converter (CDC) enabling sub- μW wearable sensing applications. The proposed multi-channel architecture supports 10 channels with a shared reconfigurable 6-bit differential analog-to-digital converter (ADC). The reconfigurable nature of the CDC enables adaptive sensing range and sensing speed based on the target application. Furthermore, the architecture performs both on/off-chip parasitic correction and baseline calibration to measure the change in capacitance ( ∆C), excluding baseline and parasitic capacitances. The experimental results show the measurement range of ∆C are 5.34 pF for 1x sensitivity and 1.8 pF for 3x sensitivity respectively. The capacitive divider-based architecture excludes power-hungry operational trans-impedance amplifiers for capacitance to voltage conversion, and the architecture supports programmable channel access to activate or deactivate each channel independently. The random interrupt protection logic avoids any broken sample or data error in a sampling window. Additionally, the channel monitoring logic helps keep track of specific channel information. The measured silicon result shows a total power consumption of 1.2 μW for 1.6 kHz sampling frequency when driven by a 32 kHz clock, which is 8.6x less than prior works. The CDC is also tested with DMMP (dimethyl-methylphosphonate) gas sensor in gas chromatography (GC). Implemented in 65 nm CMOS process, the 10-channel CDC occupies 0.251 mm2 of active area (0.0251 mm2/Ch).

Neonatal Exhaled Breath Sampling for Infrared Spectroscopy: Biomarker Analysis

Monitoring health conditions in neonates for early therapeutic intervention in case deviations from physiological conditions is crucial for their long-term development. Due to their immaturity preterm born neonates are dependent on particularly careful physical and neurological diagnostic methods. Ideally, these should be noninvasive, noncontact, and radiation free. Infrared spectroscopy was used to analyze exhaled breath from 71 neonates with a special emphasis on preterm infants, as a noninvasive, noncontact, and radiation-free diagnostic tool. Passive sample collection was performed by skilled clinicians. Depending on the mode of respiratory support of infants, four different sampling procedures were adapted to collect exhaled breath. With the aid of appropriate reference samples, infrared spectroscopy has successfully demonstrated its effectiveness in the analysis of breath samples of neonates. The discernible increase in concentrations of carbon dioxide, carbon monoxide, and methane in collected samples compared to reference samples served as compelling evidence of the presence of exhaled breath. With regard to technical hurdles and sample analysis, samples collected from neonates without respiratory support proved to be more advantageous compared to those obtained from intubated infants and those with CPAP (continuous positive airway pressure). The main obstacle lies in the significant dilution of exhaled breath in the case of neonates receiving respiratory support. Metabolic analysis of breath samples holds promise for the development of noninvasive biomarker-based diagnostics for both preterm and sick neonates provided an adequate amount of breath is collected.

AI-Enabled Portable E-Nose Regression Predicting Harmful Molecules in a Gas Mixture

The biomimetic electronic nose (e-nose) technology is a novel technology used for the identification and monitoring of complex gas molecules, and it is gaining significance in this field. However, due to the complexity and multiplicity of gas mixtures, the accuracy of electronic noses in predicting gas concentrations using traditional regression algorithms is not ideal. This paper presents a solution to the difficulty by introducing a fusion network model that utilizes a transformer-based multikernel feature fusion (TMKFF) module combined with a 1DCNN_LSTM network to enhance the accuracy of regression prediction for gas mixture concentrations using a portable electronic nose. The experimental findings demonstrate that the regression prediction performance of the fusion network is significantly superior to that of single models such as convolutional neural network (CNN) and long short-term memory (LSTM). The present study demonstrates the efficacy of our fusion network model in accurately predicting the concentrations of multiple target gases, such as SO2, NO2, and CO, in a gas mixture. Specifically, our algorithm exhibits substantial benefits in enhancing the prediction performance of low-concentration SO2 gas, which is a noteworthy achievement. The determination coefficient (R2) values of 93, 98, and 99% correspondingly demonstrate that the model is very capable of explaining the variation in the concentration of the target gases. The root-mean-square errors (RMSE) are 0.0760, 0.0711, and 3.3825, respectively, while the mean absolute errors (MAE) are 0.0507, 0.0549, and 2.5874, respectively. These results indicate that the model has relatively small prediction errors. The method we have developed holds significant potential for practical applications in detecting atmospheric pollution detection and other molecular detection areas in complex environments.

Rapid and Online Microvolume Flow-Through Dialysis Probe for Sample Preparation in Veterinary Drug Residue Analysis

A rapid and online microvolume flow-through dialysis probe designed for sample preparation in the analysis of veterinary drug residues is introduced. This study addresses the need for efficient and green sample preparation methods that reduce chemical waste and reagent use. The dialysis probe integrates with liquid chromatography and mass spectrometry (LC-MS) systems, facilitating automated, high-throughput analysis. The dialysis method utilizes minimal reagent volumes per sample, significantly reducing the generation of solvent waste compared to traditional sample preparation techniques. Several veterinary drugs were spiked into tissue homogenates and analyzed to validate the probe's efficacy. A diagnostic sensitivity of >97% and specificity of >95% were obtained for this performance evaluation. The results demonstrated the effective removal of cellular debris and particulates, ensuring sample integrity and preventing instrument clogging. The automated dialysis probe yielded recovery rates between 27 and 77% for multiple analytes, confirming its potential to streamline veterinary drug residue analysis, while adhering to green chemistry principles. The approach highlights substantial improvements in both environmental impact and operational efficiency, presenting a viable alternative to conventional sample preparation methods in regulatory and research applications.

Electronic nose for odor monitoring at a landfill fenceline: Training and validation of a model for real-time odor concentration measurement

In recent years, electronic noses, or more generally Instrumental Odor Monitoring Systems (IOMS), have aroused increasing interest in the field of environmental monitoring. One of the most interesting applications of these instruments is the real-time estimation of the odor concentration at plant fencelines to continuously monitor odor emissions and identify anomalous conditions. In this type of application, it is possible to setting a "warning" threshold, enabling the continuous check of proper functioning of the plant and sudden intervention in case of malfunctions, preventing, at the same time, the risk of odor events at the receptors. For this purpose, it is necessary to provide a continuous, fast and reliable measurement of the odor concentration, which is nowadays one of the main challenges of this technology. In this context, this work proposes the development of a quantification model for quantifying odors detected at the fenceline of a landfill characterized by very different odor fingerprints. A double-step quantification model, firstly identifying the different odor classes to which the ambient air monitored at the fenceline by the IOMS belong to, and then developing different specific PLS regression models for each of the odor classes identified, was developed. The results of the proposed quantification model were compared to the ones obtained developing a "global" quantification model, which implements the regression on the globality of the training set, without differentiating between the odor classes. Then, they were further evaluated by comparison with the odor events detected at the sensitive receptor by another electronic nose. Moreover, the combined evaluation of the odor events at the plant fenceline and the receptor, respectively, together with the meteorological data highlighted the need of identifying variable warning thresholds for the odor concentrations at the fenceline according to effectively account for meteorological conditions and produce an output that is more correlated with the probability that an odor is perceived outside of the plant.

Electronic Tongues and Noses: A General Overview

As technology advances, electronic tongues and noses are becoming increasingly important in various industries. These devices can accurately detect and identify different substances and gases based on their chemical composition. This can be incredibly useful in fields such as environmental monitoring and industrial food applications, where the quality and safety of products or ecosystems should be ensured through a precise analysis. Traditionally, this task is performed by an expert panel or by using laboratory tests but sometimes becomes a bottleneck because of time and other human factors that can be solved with technologies such as the provided by electronic tongue and nose devices. Additionally, these devices can be used in medical diagnosis, quality monitoring, and even in the automotive industry to detect gas leaks. The possibilities are endless, and as these technologies continue to improve, they will undoubtedly play an increasingly important role in improving our lives and ensuring our safety. Because of the multiple applications and developments in this field in the last years, this work will present an overview of the electronic tongues and noses from the point of view of the approaches developed and the methodologies used in the data analysis and steps to this aim. In the same manner, this work shows some of the applications that can be found in the use of these devices and ends with some conclusions about the current state of these technologies.

Intelligent Detection and Odor Recognition of Cigarette Packaging Paper Boxes Based on a Homemade Electronic Nose

The printing process of box packaging paper can generate volatile organic compounds, resulting in odors that impact product quality and health. An efficient, objective, and cost-effective detection method is urgently needed. We utilized a self-developed electronic nose system to test four different cigarette packaging paper samples. Employing multivariate statistical methods like Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA), Statistical Quality Control (SQC), and Similarity-based Independent Modeling of Class Analogy (SIMCA), we analyzed and processed the collected data. Comprehensive evaluation and quality control models were constructed to assess sample stability and distinguish odors. Results indicate that our electronic nose system rapidly detects odors and effectively performs quality control. By establishing models for quality stability control, we successfully identified samples with acceptable quality and those with odors. To further validate the system's performance and extend its applications, we collected two types of cigarette packaging paper samples with odor data. Using data augmentation techniques, we expanded the dataset and achieved an accuracy rate of 0.9938 through classification and discrimination. This highlights the significant potential of our self-developed electronic nose system in recognizing cigarette packaging paper odors and odorous samples.

Data science opportunities of large language models for neuroscience and biomedicine

Large language models (LLMs) are a new asset class in the machine-learning landscape. Here we offer a primer on defining properties of these modeling techniques. We then reflect on new modes of investigation in which LLMs can be used to reframe classic neuroscience questions to deliver fresh answers. We reason that LLMs have the potential to (1) enrich neuroscience datasets by adding valuable meta-information, such as advanced text sentiment, (2) summarize vast information sources to overcome divides between siloed neuroscience communities, (3) enable previously unthinkable fusion of disparate information sources relevant to the brain, (4) help deconvolve which cognitive concepts most usefully grasp phenomena in the brain, and much more.

Breaking barriers in Candida spp. detection with Electronic Noses and artificial intelligence

The timely and accurate diagnosis of candidemia, a severe bloodstream infection caused by Candida spp., remains challenging in clinical practice. Blood culture, the current gold standard technique, suffers from lengthy turnaround times and limited sensitivity. To address these limitations, we propose a novel approach utilizing an Electronic Nose (E-nose) combined with Time Series-based classification techniques to analyze and identify Candida spp. rapidly, using culture species of C. albicans, C.kodamaea ohmeri, C. glabrara, C. haemulonii, C. parapsilosis and C. krusei as control samples. This innovative method not only enhances diagnostic accuracy and reduces decision time for healthcare professionals in selecting appropriate treatments but also offers the potential for expanded usage and cost reduction due to the E-nose's low production costs. Our proof-of-concept experimental results, carried out with culture samples, demonstrate promising outcomes, with the Inception Time classifier achieving an impressive average accuracy of 97.46% during the test phase. This paper presents a groundbreaking advancement in the field, empowering medical practitioners with an efficient and reliable tool for early and precise identification of candidemia, ultimately leading to improved patient outcomes.

Advancing Colorectal Cancer Diagnosis with AI-Powered Breathomics: Navigating Challenges and Future Directions

Early detection of colorectal cancer is crucial for improving outcomes and reducing mortality. While there is strong evidence of effectiveness, currently adopted screening methods present several shortcomings which negatively impact the detection of early stage carcinogenesis, including low uptake due to patient discomfort. As a result, developing novel, non-invasive alternatives is an important research priority. Recent advancements in the field of breathomics, the study of breath composition and analysis, have paved the way for new avenues for non-invasive cancer detection and effective monitoring. Harnessing the utility of Volatile Organic Compounds in exhaled breath, breathomics has the potential to disrupt colorectal cancer screening practices. Our goal is to outline key research efforts in this area focusing on machine learning methods used for the analysis of breathomics data, highlight challenges involved in artificial intelligence application in this context, and suggest possible future directions which are currently considered within the framework of the European project ONCOSCREEN.

Olfactory system-inspired electronic nose system using numerous low-cost homogenous and hetrogenous sensors

This paper presents an electronic nose system inspired by the biological olfactory system. When comparing the human olfactory system to that of a dog, it's worth noting that dogs have 30 times more olfactory receptors and three times as many types of olfactory receptors. This implies that the number of olfactory receptors could be a more important parameter for classifying chemical compounds than the number of receptor types. Instead of using expensive precision sensors, the proposed electronic nose system relies on numerous low-cost homogeneous and heterogeneous sensors with poor cross-interference characteristics due to their low gas selectivity. Even if the same type of sensor shows a slightly different output for the same chemical compound, this variation becomes a unique signal for the target gas being measured. The electronic nose system comprises 30 sensors, the e-nose had 6 differing sensors with 5 replicates of each type. The characteristics of the electronic nose system are evaluated using three different volatile alcoholic compounds, more than 99% of which are the same. Liquid samples are supplied to the sensor chamber for 60 seconds using an air bubbler, followed by a 60-second cleaning of the chamber. Sensor signals are acquired at a sampling rate of 100 Hz. In this experimental study, the effects of data preprocessing methods and the number of sensors of the same type are investigated. By increasing the number of sensors of the same type, classification accuracy exceeds 99%, regardless of the deep learning model. The proposed electronic nose system, based on low-cost sensors, demonstrates similar results to commercial expensive electronic nose systems.

Volatile Organic Compound Assessment as a Screening Tool for Early Detection of Gastrointestinal Diseases

Gastrointestinal (GI) diseases have a high prevalence throughout the United States. Screening and diagnostic modalities are often expensive and invasive, and therefore, people do not utilize them effectively. Lack of proper screening and diagnostic assessment may lead to delays in diagnosis, more advanced disease at the time of diagnosis, and higher morbidity and mortality rates. Research on the intestinal microbiome has demonstrated that dysbiosis, or unfavorable alteration of organismal composition, precedes the onset of clinical symptoms for various GI diseases. GI disease diagnostic research has led to a shift towards non-invasive methods for GI screening, including chemical-detection tests that measure changes in volatile organic compounds (VOCs), which are the byproducts of bacterial metabolism that result in the distinct smell of stool. Many of these tools are expensive, immobile benchtop instruments that require highly trained individuals to interpret the results. These attributes make them difficult to implement in clinical settings. Alternatively, electronic noses (E-noses) are relatively cheaper, handheld devices that utilize multi-sensor arrays and pattern recognition technology to analyze VOCs. The purpose of this review is to (1) highlight how dysbiosis impacts intestinal diseases and how VOC metabolites can be utilized to detect alterations in the microbiome, (2) summarize the available VOC analytical platforms that can be used to detect aberrancies in intestinal health, (3) define the current technological advancements and limitations of E-nose technology, and finally, (4) review the literature surrounding several intestinal diseases in which headspace VOCs can be used to detect or predict disease.

Quantifying the dynamic characteristics of indoor air pollution using real-time sensors: Current status and future implication

People generally spend most of their time indoors, making indoor air quality be of great significance to human health. Large spatiotemporal heterogeneity of indoor air pollution can be hardly captured by conventional filter-based monitoring but real-time monitoring. Real-time monitoring is conducive to change air assessment mode from static and sparse analysis to dynamic and massive analysis, and has made remarkable strides in indoor air evaluation. In this review, the state of art, strengths, challenges, and further development of real-time sensors used in indoor air evaluation are focused on. Researches using real-time sensors for indoor air evaluation have increased rapidly since 2018, and are mainly conducted in China and the USA, with the most frequently investigated air pollutants of PM_2.5. In addition to high spatiotemporal resolution, real-time sensors for indoor air evaluation have prominent advantages in 3-dimensional monitoring, pollution peak and source identification, and short-term health effect evaluation. Huge amounts of data from real-time sensors also facilitate the modeling and prediction of indoor air pollution. However, challenges still remain in extensive deployment of real-time sensors indoors, including the selection, performance, stability, as well as calibration of sensors. In future, sensors with high performance, long-term stability, low price, and low energy consumption are welcomed. Furthermore, more target air pollutants are also expected to be detected simultaneously by real-time sensors in indoor air monitoring.

Repetitive Direct Comparison Method for Odor Sensing

Olfactory sensors are one of the most anticipated applications of gas sensors. To distinguish odors-complex mixtures of gas species, it is necessary to extract sensor responses originating from the target odors. However, the responses of gas sensors tend to be affected by interfering gases with much higher concentrations than target odor molecules. To realize practical applications of olfactory sensors, extracting minute sensor responses of odors from major interfering gases is required. In this study, we propose a repetitive direct comparison (rDC) method, which can highlight the difference in odors by alternately injecting the two target odors into a gas sensor. We verified the feasibility of the rDC method on chocolates with two different flavors by using a sensor system based on membrane-type surface stress sensors (MSS). The odors of the chocolates were measured by the rDC method, and the signal-to-noise ratios (S/N) of the measurements were evaluated. The results showed that the rDC method achieved improved S/N compared to a typical measurement. The result also indicates that sensing signals could be enhanced for a specific combination of receptor materials of MSS and target odors.

Non-Invasive Disease Specific Biomarker Detection Using Infrared Spectroscopy: A Review

Many life-threatening diseases remain obscure in their early disease stages. Symptoms appear only at the advanced stage when the survival rate is poor. A non-invasive diagnostic tool may be able to identify disease even at the asymptotic stage and save lives. Volatile metabolites-based diagnostics hold a lot of promise to fulfil this demand. Many experimental techniques are being developed to establish a reliable non-invasive diagnostic tool; however, none of them are yet able to fulfil clinicians' demands. Infrared spectroscopy-based gaseous biofluid analysis demonstrated promising results to fulfil clinicians' expectations. The recent development of the standard operating procedure (SOP), sample measurement, and data analysis techniques for infrared spectroscopy are summarized in this review article. It has also outlined the applicability of infrared spectroscopy to identify the specific biomarkers for diseases such as diabetes, acute gastritis caused by bacterial infection, cerebral palsy, and prostate cancer.

Exhaled Biomarkers for Point-of-Care Diagnosis: Recent Advances and New Challenges in Breathomics

Cancers, chronic diseases and respiratory infections are major causes of mortality and present diagnostic and therapeutic challenges for health care. There is an unmet medical need for non-invasive, easy-to-use biomarkers for the early diagnosis, phenotyping, predicting and monitoring of the therapeutic responses of these disorders. Exhaled breath sampling is an attractive choice that has gained attention in recent years. Exhaled nitric oxide measurement used as a predictive biomarker of the response to anti-eosinophil therapy in severe asthma has paved the way for other exhaled breath biomarkers. Advances in laser and nanosensor technologies and spectrometry together with widespread use of algorithms and artificial intelligence have facilitated research on volatile organic compounds and artificial olfaction systems to develop new exhaled biomarkers. We aim to provide an overview of the recent advances in and challenges of exhaled biomarker measurements with an emphasis on the applicability of their measurement as a non-invasive, point-of-care diagnostic and monitoring tool.

Breath VOC analysis and machine learning approaches for disease screening: a review

Early disease detection is often correlated with a reduction in mortality rate and improved prognosis. Currently, techniques like biopsy and imaging that are used to screen chronic diseases are invasive, costly or inaccessible to a large population. Thus, a non-invasive disease screening technology is the need of the hour. Existing non-invasive methods like gas chromatography-mass spectrometry, selected-ion flow-tube mass spectrometry, and proton transfer reaction-mass-spectrometry are expensive. These techniques necessitate experienced operators, making them unsuitable for a large population. Various non-invasive sources are available for disease detection, of which exhaled breath is preferred as it contains different volatile organic compounds (VOCs) that reflect the biochemical reactions in the human body. Disease screening by exhaled breath VOC analysis can revolutionize the healthcare industry. This review focuses on exhaled breath VOC biomarkers for screening various diseases with a particular emphasis on liver diseases and head and neck cancer as examples of diseases related to metabolic disorders and diseases unrelated to metabolic disorders, respectively. Single sensor and sensor array-based (Electronic Nose) approaches for exhaled breath VOC detection are briefly described, along with the machine learning techniques used for pattern recognition.

Machine Learning-Assisted Volatile Organic Compound Gas Classification Based on Polarized Mixed-Potential Gas Sensors

The performance of electrochemical gas sensors depends on the reactions at the three-phase boundary. In this work, a mixed-potential gas sensor containing a counter electrode, a reference electrode, and a sensitive electrode was constructed. By applying a bias voltage to the counter electrode, the three-phase boundary can be polarized. The polarization state of the three-phase boundary determined the gas-sensitive performance. Taking 100 ppm ethanol vapor as an example, by regulating the polarization state of the three-phase boundary, the response value of the sensor can be adjusted from -170 to 40 mV, and the sensitivity can be controlled from -126.4 to 42.6 mV/decade. The working temperature of the sensor can be reduced after polarizing the three-phase boundary, lowering the power consumption from 1.14 to 0.625 W. The sensor also showed good stability and short response-recovery time (3 s). Based on this sensor, the Random Forest algorithm reached 99% accuracy in identifying the kind of VOC vapors. This accuracy was made possible by the ability to generate several signals concurrently. The above gas-sensitive performance improvements were due to the polarized three-phase boundary.

Early Detection of Fusarium oxysporum Infection in Processing Tomatoes (Solanum lycopersicum) and Pathogen-Soil Interactions Using a Low-Cost Portable Electronic Nose and Machine Learning Modeling

The early detection of pathogen infections in plants has become an important aspect of integrated disease management. Although previous research demonstrated the idea of applying digital technologies to monitor and predict plant health status, there is no effective system for detecting pathogen infection before symptomatology appears. This paper presents the use of a low-cost and portable electronic nose coupled with machine learning (ML) models for early disease detection. Several artificial neural network models were developed to predict plant physiological data and classify processing tomato plants and soil samples according to different levels of pathogen inoculum by using e-nose outputs as inputs, plant physiological data, and the level of infection as targets. Results showed that the pattern recognition models based on different infection levels had an overall accuracy of 94.4-96.8% for tomato plants and between 94.81% and 96.22% for soil samples. For the prediction of plant physiological parameters (photosynthesis, stomatal conductance, and transpiration) using regression models or tomato plants, the overall correlation coefficient was 0.97-0.99, with very significant slope values in the range 0.97-1. The performance of all models shows no signs of under or overfitting. It is hence proven accurate and valid to use the electronic nose coupled with ML modeling for effective early disease detection of processing tomatoes and could also be further implemented to monitor other abiotic and biotic stressors.

A Virtual Electronic Nose for the Efficient Classification and Quantification of Volatile Organic Compounds

Although many chemical gas sensors report high sensitivity towards volatile organic compounds (VOCs), finding selective gas sensing technologies that can classify different VOCs is an ongoing and highly important challenge. By exploiting the synergy between virtual electronic noses and machine learning techniques, we demonstrate the possibility of efficiently discriminating, classifying, and quantifying short-chain oxygenated VOCs in the parts-per-billion concentration range. Several experimental results show a reproducible correlation between the predicted and measured values. A 10-fold cross-validated quadratic support vector machine classifier reports a validation accuracy of 91% for the different gases and concentrations studied. Additionally, a 10-fold cross-validated partial least square regression quantifier can predict their concentrations with coefficients of determination, R², up to 0.99. Our methodology and analysis provide an alternative approach to overcoming the issue of gas sensors' selectivity, and have the potential to be applied across various areas of science and engineering where it is important to measure gases with high accuracy.

Hybrid learning method based on feature clustering and scoring for enhanced COVID-19 breath analysis by an electronic nose

Breath pattern analysis based on an electronic nose (e-nose), which is a noninvasive, fast, and low-cost method, has been continuously used for detecting human diseases, including the coronavirus disease 2019 (COVID-19). Nevertheless, having big data with several available features is not always beneficial because only a few of them will be relevant and useful to distinguish different breath samples (i.e., positive and negative COVID-19 samples). In this study, we develop a hybrid machine learning-based algorithm combining hierarchical agglomerative clustering analysis and permutation feature importance method to improve the data analysis of a portable e-nose for COVID-19 detection (GeNose C19). Utilizing this learning approach, we can obtain an effective and optimum feature combination, enabling the reduction by half of the number of employed sensors without downgrading the classification model performance. Based on the cross-validation test results on the training data, the hybrid algorithm can result in accuracy, sensitivity, and specificity values of (86 ± 3)%, (88 ± 6)%, and (84 ± 6)%, respectively. Meanwhile, for the testing data, a value of 87% is obtained for all the three metrics. These results exhibit the feasibility of using this hybrid filter-wrapper feature-selection method to pave the way for optimizing the GeNose C19 performance.

Rapid Assessment of Rice Quality Traits Using Low-Cost Digital Technologies

Aroma and other physicochemical parameters are important attributes influencing consumer perception and acceptance of rice. However, current methods using multiple instruments and laboratory analysis make these assessments costly and time-consuming. Therefore, this study aimed to assess rice quality traits of 17 commercial rice types using a low-cost electronic nose and portable near-infrared spectrometer coupled with machine learning (ML). Specifically, artificial neural networks (ANN) were used to classify the type of rice and predict rice quality traits (aromas, color, texture, and pH of cooked rice) as targets. The ML models developed showed that the chemometrics obtained from both sensor technologies successfully classified the rice (Model 1: 98.7%; Model 2: 98.6%) and predicted the peak area of aromas obtained by gas chromatography-mass spectroscopy found in raw (Model 3: R = 0.95; Model 6: R = 0.95) and cooked rice (Model 4: R = 0.98; Model 7: R = 0.96). Furthermore, a high R = 0.98 was obtained for Model 5 to estimate the color, texture, and pH of cooked rice. The proposed method is rapid, low-cost, reliable, and may help the rice industry increase high-quality rice production and accelerate the adoption of digital technologies and artificial intelligence to support the rice value chain.

High Density Resistive Array Readout System for Wearable Electronics

This work presents a wearable sensing system for high-density resistive array readout. The system comprising readout electronics for a high-density resistive sensor array and a rechargeable battery, was realized in a wristband. The analyzed data with the proposed system can be visualized using a custom graphical user interface (GUI) developed in a personal computer (PC) through a universal serial bus (USB) and using an Android app in smartphones via Bluetooth Low Energy (BLE), respectively. The readout electronics were implemented on a printed circuit board (PCB) and had a compact dimension of 3 cm × 3 cm. It was designed to measure the resistive sensor with a dynamic range of 1 KΩ–1 MΩ and detect a 0.1% change of the base resistance. The system operated at a 5 V supply voltage, and the overall system power consumption was 95 mW. The readout circuit employed a resistance-to-voltage (R-V) conversion topology using a 16-bit analog-to-digital converter (ADC), integrated in the Cypress Programmable System-on-Chip (PSoC^®) 5LP microcontroller. The device behaves as a universal-type sensing system that can be interfaced with a wide variety of resistive sensors, including chemiresistors, piezoresistors, and thermoelectric sensors, whose resistance variations fall in the target measurement range of 1 KΩ–1 MΩ. The system performance was tested with a 60-resistor array and showed a satisfactory accuracy, with a worst-case error rate up to 2.5%. The developed sensing system shows promising results for applications in the field of the Internet of things (IoT), point-of-care testing (PoCT), and low-cost wearable devices.

Electronic Nose and Tongue for Assessing Human Microbiota

The technological developments of recent times have allowed the use of innovative approaches to support the diagnosis of various diseases. Many of such clinical conditions are often associated with metabolic unbalance, in turn producing an alteration of the gut microbiota even during asymptomatic stages. As such, studies regarding the microbiota composition in biological fluids obtained by humans are continuously growing, and the methodologies for their investigation are rapidly changing, making it less invasive and more affordable. To this extent, Electronic Nose and Electronic Tongue tools are gaining importance in the relevant field, making them a useful alternative—or support—to traditional analytical methods. In light of this, the present manuscript seeks to investigate the development and use of such tools in the gut microbiota assessment according to the current literature. Significant gaps are still present, particularly concerning the Electronic Tongue systems, however the current evidence highlights the strong potential such tools own to enter the daily clinical practice, with significant advancement concerning the patients’ acceptability and cost saving for healthcare providers.