Accurate Discrimination Research Articles

Thermally Triggered Double Emulsion-Integrated Hydrogel Microparticles for Multiplexed Molecular Diagnostics.

During the COVID-19 pandemic, reverse transcription-quantitative polymerase chain reaction (RT-qPCR) has been recognized as the most reliable diagnostic tool. However, there is a need to develop multiplexed assays capable of analyzing multiple genes simultaneously to expand its application. To address this, a multiplexed RT-qPCR using a double emulsion (DE)-based carrier and a polymer microparticle reactor, termed primer-incorporated network tailored with Taqman probe (TaqPIN) is developed. The DE securely stores nucleic acid reagents like primers and probes within the polymer network until heating releases them for the reaction. The TaqPIN RT-qPCR demonstrates an amplification efficiency of 93.8% and can detect as few as 20 copies/µL. By loading the multiple microparticles into a single reaction, a multiplexed assay with only one optical channel is enabled. In practice, a nine-plex assay is designed to distinguish between variants of the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Even subtle variations of a single nucleotide can be simultaneously detected. Testing on 75 nasopharyngeal swab samples yields 100% sensitivity and specificity for SARS-CoV-2 detection and 94% accuracy in variant discrimination.

Identifying risk factors and constructing a predictive model for heart failure combined with intracardiac thrombus in non-compaction cardiomyopathy patients

This study aims to develop a nomogram prediction model for assessing the cardiogenic composite endpoint, which includes intracardiac thrombosis (ICT) combined with heart failure (HF) in patients with non-compaction cardiomyopathy (NCM) patients. We retrospectively analyzed clinical data from NCM patients (January 2018 to May 2024), who were randomly assigned to training and validation cohorts. Independent predictors were identified using logistic regression, and a nomogram model was developed. The model’s discriminative ability, accuracy, and clinical applicability were subsequently validated. A total of 976 patients were included, of whom 54 had ICT and 191 had HF. Diabetes mellitus (DM), left ventricular end-systolic diameter (LVESD), and ejection fraction (EF) were identified as independent predictors for the composite endpoint. The nomogram demonstrated good performance, with an area under the curve (AUC) of 0.747 (95% CI: 0.707–0.787) in the training group and 0.803 (95% CI: 0.752–0.854) in the validation group. The calibration curve for the training group showed an average absolute error of 0.028, with a Hosmer-Lemeshow test P-value of 0.076. Decision curve analysis and clinical impact curves further indicated that the clinical net benefit was maximized at a threshold probability of 0.05–0.61. This study establishes and validates a nomogram for predicting cardiogenic composite endpoint in NVM patients, demonstrating robust clinical predictive value.

Risk factors for plastic bronchitis in children with macrolide-unresponsive Mycoplasma pneumoniae pneumonia and establishment of a nomogram model

To investigate the risk factors for plastic bronchitis (PB) in children with macrolide-unresponsive Mycoplasma pneumoniae pneumonia (MUMPP) and to establish a nomogram prediction model. A retrospective analysis was conducted on 178 children with MUMPP who underwent bronchoscopy from January to December 2023. According to the presence or absence of PB, the children were divided into a PB group (49 children) and a non-PB group (129 children). The predictive factors for the development of PB in children with MUMPP were analyzed, and a nomogram prediction model was established. The model was assessed in terms of discriminatory ability, accuracy, and clinical effectiveness. The multivariate logistic regression analysis showed that older age and higher levels of lactate dehydrogenase and fibrinogen were closely associated with the development of PB in children with MUMPP (P<0.05). A nomogram model established based on these factors had an area under the receiver operating characteristic curve of 0.733 (95%CI: 0.651-0.816, P<0.001) and showed a good discriminatory ability. The Hosmer-Lemeshow goodness-of-fit test indicated that the predictive model had a good degree of fit (P>0.05), and the decision curve analysis showed that the model had a good clinical application value. The risk nomogram model established based on age and lactate dehydrogenase and fibrinogen levels has good discriminatory ability, accuracy, and predictive efficacy for predicting the development of PB in children with MUMPP.

Mental Health and the Intersection of Perceived Discrimination and Social Inequalities Among Students in Germany – a Quantitative Intersectional Study

ObjectivesDiscrimination poses a threat to the mental health of university students, especially those affected by social inequality, yet understanding its intersectional impact remains limited. This study examines the intersection of social inequalities with perceived discrimination to explore differences in mental health among students in Germany.MethodsData from the cross-sectional project “Survey on study conditions and mental health of university students” (n = 14,592) were analysed using Multilevel Analysis of Individual Heterogeneity and Discriminatory Accuracy (MAIHDA). Depressive symptoms, cognitive stress symptoms, and exhaustion were examined across 48 intersectional strata based on gender, first academic generation, family care tasks, and perceived discrimination.ResultsThe MAIHDA analysis revealed substantial between strata variance, with most of it explained by additive rather than intersectional interaction effects. Perceived discrimination, diverse or female gender, first academic generation, and family care tasks (for exhaustion only) were associated with worse mental health outcomes.ConclusionThe profound associations between perceived discrimination and the mental health among university students call for urgent attention and intervention within university settings. Adopting an intersectional lens is key to identifying and addressing inequalities.

A sensitized dual-response ratiometric fluorescent sensor integrated smartphone platform for accurate discrimination and detection of tetracycline homologues based on N-CDs‒Eu3+ complex.

Asensitized dual-response ratiometric fluorescent sensor integrated smartphone platform for accurate discrimination and detection of tetracycline(TC) homologues was fabricated based on N-CDs-Eu3+ complex. In the sensing system, N-CDs act as a sensitizer of Eu3+ and significantly enhance the fluorescence of TC-Eu3+ complex approximate 40-fold owing to the synergistic effect of antenna effect (AE) and fluorescence resonance energy transfer (FRET). A paper sensor integrated with a smartphone platform is further fabricated for on-site measurement of TC. The proposed sensing platform exhibits an obvious color change from blue to red with limit of detection (LOD) of 1.5 and 63.2 nM for spectrofluorimetry and paper sensor, respectively. In addition, to eliminate the interference from TC homologues, a simple and effective sensor array was constructed by regulating thepH of the system. The different fluorescence responses to four tetracycline homologues used widely (TC, OTC, CTC, and DOX) were examined and dealt with principal component analysis, and accurate differentiation of TC homologues was therefore achieved. This work provides an integrated method for identification and synchronous quantitative detection of TCs, and a potential application for visual and on-site detection of TCs in environmental monitoring and food safety.

"The M-APNE score: an objective screening tool for OSA highlighting the area under the inspiratory flow-volume curve".

Polysomnography (PSG) is resource-intensive but remains the gold standard for diagnosing Obstructive Sleep Apnea (OSA). We aimed to develop a screening tool to better allocate resources by identifying individuals at higher risk for OSA, overcoming limitations of current tools that may under-diagnose based on self-reported symptoms. A total of 884 patients (490 diagnosed with OSA) were included, which was divided into the training, validation, and test sets. Using multivariate logistic regression analyses, we developed a scoring system incorporating male sex, age, sawtooth pattern, area under the inspiratory flow-volume curve (AreaFI), and neck circumference to objectively identify patients at higher risk of OSA. Sensitivity and specificity were evaluated using area under the curve (AUC) metrics. The M-APNE Score was compared to other non-symptom-based tools, the No-Apnea Score and the Symptomless Multivariable Apnea Prediction (sMVAP) model, using the Delong test. The M-APNE Score showed sensitivity rates of 79.3% in the training set, 70.8% in the test, and 80% in the validation set. ROC analysis for M-APNE score yielded AUCs of 0.82 in the training, 0.76 in the test, 0.82 in the validation set. The discriminative accuracy of M-APNE Score were found to be better than the No-Apnea Score (AUC = 0.82 vs. 0.76, p < 0.001) and the sMVAP (AUC = 0.82 vs. 0.75, p = 0.001) in the training set. Hosmer Lemeshow test indicated good calibration for M-Apne Score (p = 0.46). The M-APNE Score is a robust and objective tool for OSA screening, potentially reducing classification errors and improving accuracy.

Diagnostic value of glypican-1; a new marker differentiating pulmonary squamous cell carcinoma from adenocarcinoma: immunohistochemical study on Egyptian series

Lung cancer is one of the major causes of cancer morbidity and mortality. Subtyping of non-small cell lung cancer is necessary owing to different treatment options. This study is to evaluate the value of immunohistochemical expression of glypican-1 in the diagnosis of lung squamous cell carcinoma (SCC). This retrospective study included a total of 68 cases, of which 36 were diagnosed as SCC and 32 as adenocarcinoma (ADC). Furthermore, glypican-1 expression was compared with the expressions of p63, thyroid transcription factor-1 (TTF-1), and napsin A. All cases of SCC except one showed positive immunostaining to glypican-1; 35/36 (97.2%) cases, and predominantly scored 3 + . While only 5 cases of ADC showed positive immunostaining to glypican-1, having a score of 1 + or 2 + . The difference between glypican-1 expression of the two tumor types was highly significant (p value < 0.001). The sensitivity, specificity, and overall accuracy of glypican-1 expression for differentiating lung SCC from ADC were 97.2%, 84.4%, and 91.2%, respectively. The sensitivity of glypican-1 is more than p63 in the diagnosis of lung SCC. Glypican-1 can be added as a new diagnostic marker to help in the accurate discrimination between poorly differentiated lung SCC and solid predominant adenocarcinoma cases.

Molecular Dynamics of Peptide Sequencing through MoS2 Solid-State Nanopores for Binary Encoding Applications.

Biological peptides have emerged as promising candidates for data storage applications due to their versatility and programmability. Recent advances in peptide synthesis and sequencing technologies have enabled the development of peptide-based data storage systems for realizing novel information storage technologies with enhanced capacity, durability, and data access speeds. In this study, we performed coarse-grained peptide sequencing of 12 distinct sequences through single-layer MoS2 solid-state nanopores (SSNs) using molecular dynamics (MD). Peptide sequences were composed of 1 positively charged, 1 negatively charged, and 4 neutral amino acids, with the position of amino acids in the sequence being shuffled to generate all possible configurations. From MD, the goal was to evaluate the efficiency of these peptide sequences to encode binary information based on ionic current traces monitored during their passage through the SSNs. Classification approaches using LightGBM were trained and tested to analyze different sequence factors such as the position of amino acids or the spacing between charged amino acids in the sequences. Our findings reveal the presence of two distinct groups of sequences determined by the relative position of the positively charged amino acid compared to the negatively charged amino acid. Furthermore, we observe a strong correlation between discrimination accuracy and the separation in the sequence between charged amino acids, depending on the number of adjacent neutral amino acids between them. Finally, MD allowed us to establish the nonlinear relationship between amino acid positions inside the pore (called sequence motifs) and fluctuations in ionic current traces to discriminate false positives and to enable effective training of machine learning classification algorithms. These very promising results emphasized the best approaches to design peptide sequences as building blocks for molecular data storage. Finally, this study highlights the potential of the proposed approach for designing peptide sequence combinations that could help the development of efficient, scalable, and reliable molecular data storage solutions, with future research focused on encoding longer binary chains to enhance storage capacity and support the goal of stable, energy-free biological systems.

Discrimination of Benign and Malignant Thyroid Nodules through Comparative Analyses of Human Saliva Samples via Metabolomics and Deep-Learning-Guided Label-free SERS.

Thyroid nodules are a very common entity. The overall prevalence in the populace is estimated to be around 65-68%, among which a small portion (less than 5%) is malignant (cancerous). Therefore, it is important to discriminate benign thyroid nodules from malignant thyroid nodules. In this study, an equal number of participants with benign and malignant thyroid nodules (N = 10/group) were recruited. Saliva samples were collected from each participant, and SERS spectra were acquired, followed by validation using a metabolomics approach. An additional equal number of patients (N = 40/group) were recruited to construct diagnostic models. The performance of various machine learning (ML) algorithms was assessed using multiple evaluation metrics. Finally, the reliability of the optimal model was tested using blind test data (N = 10/group for benign and malignant thyroid nodules). The results showed a consistent trend between the SERS metabolic profile and the metabolites identified through MS analysis. The Multi-ResNet algorithm was optimal, achieving a 95% accuracy in sample discrimination. Additionally, blind test data sets yielded an overall accuracy of 83%. In summary, the deep-learning-guided SERS technique holds great potential in the accurate discrimination of benign and malignant thyroid nodules via human saliva samples, which facilitates the noninvasive diagnosis of malignant thyroid nodules in clinical settings.

Molecular Ferroelectrics for Highly Sensitive Detection Toward Low-Frequency Sound Recognition.

Human hearing cannot sensitively detect sounds below 100Hz, which can affect the physical well-being and lead to dizziness, headaches, and nausea. Piezoelectric acoustic sensors still lack sensitivity to low-frequency sounds owing to the low piezoelectric coefficient or high elastic modulus of materials. The low elastic modulus and substantial piezoelectric coefficient of molecular ferroelectric materials make them excellent candidates for acoustic sensors. In this study, the molecular ferroelectric, [(CH3)3NCH2Cl]CdCl3, is used as a piezoelectric active layer in the construction of a piezoelectric acoustic sensor for low-frequency sound detection. The sensor exhibits high sensitivity (47.43mV Pa-1 cm-2) at 87Hz, with an excellent level of frequency resolution (up to 0.1Hz). This facilitates the accurate discrimination and detection of low-frequency sounds, which is suitable for noise detection applications. The sensor differentiates between various musical instruments and heartbeats, and recognizes audio signals. This study highlights the potential of molecular ferroelectric materials in piezoelectric acoustic device applications, including noise detection, health monitoring, and human-computer interactions.

Predicting High-Grade Acute Urinary Toxicity and Lower Gastrointestinal Toxicity After Postoperative Volumetric Modulated Arc Therapy for Cervical and Endometrial Cancer Using a Normal Tissue Complication Probability Model

(1) Background: Volumetric modulated arc therapy (VMAT) can deliver more accurate dose distribution and reduce radiotherapy-induced toxicities for postoperative cervical and endometrial cancer. This study aims to retrospectively analyze the relationship between dosimetric parameters of organs at risk (OARs) and acute toxicities and provide suggestions for the dose constraints. (2) Methods: A total of 164 postoperative cervical and endometrial cancer patients were retrospectively analyzed, and the endpoints were grade ≥ 2 acute urinary toxicity (AUT) and acute lower gastrointestinal toxicity (ALGIT). The normal tissue complication probability (NTCP) model was established using the logistic regression model. Restricted cubic spline (RCS) curves were used to explore the association between dosimetric parameters and toxicities. The receiver operating characteristic (ROC) curve, calibration curve, Akaike’s corrected information criterion (AICc), decision curve analysis (DCA), and clinical impact curve (CIC) were analyzed to evaluate the performance of NTCP models. (3) Results: Bladder V40Gy was identified to develop the NTCP model of AUT, and the mean AUC was 0.69 (CI: 0.58–0.80). Three candidate predictors, namely the small intestine V30Gy, colon D45%, and rectum D55%, were identified to develop the NTCP model of ALGIT, and the mean AUC was 0.71 (CI: 0.61–0.80). Both models were considered to have relatively good discriminative accuracy and could provide a high net benefit in clinical applications. (4) Conclusions: We developed NTCP models to predict the probability for grade ≥ 2 AUT and ALGIT. We recommend that bladder V40Gy, the small intestine V30Gy, colon D45%, and rectum D55% be controlled below 42%, 20.4%, 16.9 Gy, and 32.0 Gy, respectively.

Positive signs from the history as an aid for early diagnosis in functional movement disorders: The prospective TASMAN study.

There has been a concerted move in recent times to shift from an exclusionary to a positive diagnosis of functional movement disorders (FMDs). To date, most of the focus has been on defining positive physical signs. Here the focus was on the diagnostic specificity of specific symptoms and patient characteristics. For this prospective cohort study, newly referred patients in the Netherlands and Australia were recruited before their first neurology appointment. Participants completed questionnaires within 2 months prior to their visit at one of the six different clinics. Directly following the first consultation, physicians received a questionnaire about their diagnostic process. Patients were excluded if the diagnosis was not a movement disorder. Univariate and multivariate regression analyses were conducted to identify predictors of FMDs. Subsequently, a predictive model was constructed and assessed using the area under the receiver operating curve. Between 1 March 2021 and 1 March 2023, 465 patients were eligible for inclusion, of whom 171 (37%) had an FMD and 294 (63%) a non-FMD. Distinguishing factors amongst these groups included age at onset, gender, history or family history of a functional and psychiatric disorder, sudden onset, specific triggers, fluctuation patterns throughout the day and over an extended period, pain, fatigue, depression, anxiety and dissociation. Using these, a predictive model was developed, yielding a discriminative accuracy of 88%. Specific symptoms and patient characteristics have high diagnostic discriminative value between FMDs and non-FMDs, providing an additional tool in positive diagnosis.

A novel method of species-specific molecular target mining and accurate discrimination of Bacillus cereus sensu lato

A novel method of species-specific molecular target mining and accurate discrimination of Bacillus cereus sensu lato

Development and validation of a mortality predictive model for ICU patients with primary pulmonary hypertension

There is a lack of an effective prognostic model for predicting outcomes in patients with primary pulmonary hypertension (PPH). A retrospective analysis was conducted on PPH patients from MIMIC and eICU databases. A predictive model was developed to assess mortality risk. The Consistency Index (C-index) and Receiver Operating Characteristic (ROC) curve were utilized to assess the overall performance of the model and its discriminatory capacity. The model’s calibration and clinical applicability were assessed through calibration curve and decision curve analysis (DCA). The nomogram was employed for visual representation of the model. The study included 420 patients, 260 in the development group, 104 in the internal validation group and 56 in the external validation group. The predictive model’s risk factors included age, respiratory rate, red blood cell distribution width, glucose, and SAPS II. The model demonstrated C-indexes of 0.736 and 0.696 in the development and internal validation groups, respectively. The ROC curves for the development, internal validation and external validation groups demonstrated robust discriminatory capabilities. The calibration curves indicated a slope close to 1, suggesting good calibration of the model. Additionally, DCA analysis revealed the model offered significant clinical benefits across a wide range of thresholds. The model showed good discrimination ability, accuracy and clinical application value in predicting the prognosis of patients with PPH.

Kinetic Modelling and Machine Learning Approaches on the Conductance Transients of Zn0.5Ni0.5Fe2O4 Sensors for Addressing Cross-sensitivity towards Ethanol and Acetone Vapors.

The accurate discrimination among various volatile organic compounds, especially ethanol and acetone possess a serious concern for metal oxide based chemiresistive sensors. The work presents a systematic approach to address the issue by utilizing superior sensing potentiality of Zn0.5Ni0.5Fe2O4 coupled with efficient machine learning (ML) techniques. The work provides a thorough understanding on the synthesis, characterization of Zn0.5Ni0.5Fe2O4 nanoparticles and evaluating their sensing performance towards ethanol and acetone vapors. The optimized sensor performance recorded under varying concentrations (100-1000 ppm) of analytes across the range of temperature (225-300 °C) provides lesser selectivity between acetone and ethanol. TheLangmuir-Hinshelwoodreaction mechanism was invoked further to address the selectivity issue by modeling the response transients of the sensor to get an insight into sensing interaction at microscopic level. The estimated activation energy values of ethanol (0.26 eV) have been found to be smaller compared to that of acetone (0.34 eV), explaining little higher response of the sensor towards ethanol. Moreover, some efficient ML algorithms were employed to predictively analyze the acquired sensing data for achieving more precise discriminations between these two analytes.

Machine Learning for Predicting Zearalenone Contamination Levels in Pet Food.

Zearalenone (ZEN) has been detected in both pet food ingredients and final products, causing acute toxicity and chronic health problems in pets. Therefore, the early detection of mycotoxin contamination in pet food is crucial for ensuring the safety and well-being of animals. This study aims to develop a rapid and cost-effective method using an electronic nose (E-nose) and machine learning algorithms to predict whether ZEN levels in pet food exceed the regulatory limits (250 µg/kg), as set by Chinese pet food legislation. A total of 142 pet food samples from various brands, collected between 2021 and 2023, were analyzed for ZEN contamination via liquid chromatography-tandem mass spectrometry. Additionally, the "AIR PEN 3" E-nose, equipped with 10 metal oxide sensors, was employed to identify volatile compounds in the pet food samples, categorized into 10 different groups. Machine learning algorithms, including liner regression, k-nearest neighbors, support vector machines, random forests, XGBoost, and multi-layer perceptron (MLP), were used to classify the samples based on their volatile profiles. The MLP algorithm showed the highest discrimination accuracy at 86.6% in differentiating between pet food samples above and below the ZEN threshold. Other algorithms showed moderate accuracy, ranging from 77.1% to 84.8%. The ensemble model, which combined the predictions from all classifiers, further improved the classification performance, achieving the highest accuracy at 90.1%. These results suggest that the combination of E-nose technology and machine learning provides a rapid, cost-effective approach for screening ZEN contamination in pet food at the market entry stage.

Inequities in Unmet Oral Care Needs after a Swedish Subsidization Reform: An Intersectional Analysis.

The main strategy to achieve equal provision of oral care in Sweden has been to offer partial subsidies for the adult population. However, their effects on unmet oral care needs (UOCNs) have not been extensively assessed. This study used an intersectionality framework to examine 1) the overall frequency of UOCNs, 2) single-indicator inequities, and 3) intersectional inequities in total UOCNs and financial-related UOCNs (FUOCNs) in Sweden before and after implementation of a partial subsidization reform in 2008. Data from 12 national surveys conducted over 2004 to 2018 were divided into 3 periods: prereform (2004 to 2007), early postreform (2008 to 2011), and late postreform (2012 to 2018). The analytic sample consisted of 98,177 respondents aged 24 to 84 y. Changes in the prevalence of UOCNs were estimated by inferential statistics. Single-indicator and intersectional inequities were examined by intersectional analysis of individual heterogeneity and discriminatory accuracy, across 48 strata defined by gender, age, educational level, income, and immigrant status. The prevalence of total UOCNs and FUOCNs decreased significantly early after the reform, followed by a slight rebound. Relative inequities increased by education, income, and immigrant status after the reform and decreased for age. The discriminatory accuracy for both types of UOCNs was moderate and improved marginally but significantly with the inclusion of the intersectional strata. Most intersectional strata showed greater FUOCN inequities after the reform. Contrary to expected, larger inequities in FUOCNs were identified in most intersectional strata after the reform. The moderate discriminatory accuracy suggested that Sweden could benefit from future strategies to foster equity that are universal but proportionately more intense among the intersectional strata with greater inequities (proportionate universalism). This analysis highlighted the benefit of adopting the principle of proportionate universalism as a strategy to reduce unmet oral care needs in Sweden. This would mean implementing universal strategies and specific support measures for the most vulnerable social groups as a future oral care policy change in Sweden.

Finger contact keyboard for typing with tiny movement recognition

Hemiplegic patients often struggle with typing rapidly and accurately using a standard keyboard. This study developed a keyboard in continuous contact with the fingers, allowing for easier and more effective typing. With the proposed keyboard, the user types with their healthy hand and paralyzed hand. The hardware and software of the finger contact keyboard were investigated. In deciding the hardware, we measured the hand shape, finger speed, and muscle fatigue using electromyography, magnetic positioning sensors, and force sensors for eight participants. Using the Pareto solution, we optimized the keyboard’s structure to maximize finger movement speed and minimize muscle fatigue. As the software of the proposed keyboard, we developed an algorithm implementing a neural network to identify intentional typing and tested the algorithm on five participants. The highest average discrimination accuracy was 99.3% when the force threshold was approximately 1.32 N. The mean accuracy achieved using the neural network was 90.8%, which is higher than that achieved using the threshold algorithm (80.4%). In 40 trials, the proposed keyboard achieved the same accuracy and speed as the standard keyboard, and the input time for a patient with hemiplegia was reduced by 16.2%.

Machine Learning‐Driven Ultrasensitive WSe2/MWCNT Hybrid‐Based E‐Nose Sensor Array for Volatiles Amines Mixture

AbstractVolatile amines in breath act as biomarkers for kidney and liver diseases. Monitoring these amines, especially when present as a mixture, provides insights into the metabolic state of the body. This study focuses on differentiating volatile amines by systematically modulating the conductivity and sensitivity of WSe2/Multiwalled Carbon Nanotubes composite‐based sensors. The fabricated chemiresistive sensor array demonstrates high selectivity, sensitivity (7.67% ppm−1), fast response and recovery kinetics (32 s/137 s), and accurate discrimination among target amines, even in the presence of other VOCs (volatile organic compounds). The sensor array operates at room temperature and achieves a theoretical limit of detection (LOD) of 387 ppt, 206, 157, and 202 ppb for triethylamine (TEA), dimethylamine (DMA), methylamine (MA), and ammonia (NH3), respectively, demonstrating its suitability for breath sensing and diagnostics. Machine learning (ML) analysis is employed to differentiate between the volatile amines and mixtures with 94% accuracy. The ability to detect these amines at such low ppt and ppb levels underscores the potential of this e‐nose technology for high‐performance applications in early‐stage disease diagnostics.

Effectiveness of Differentiating Mold Levels in Soybeans with Electronic Nose Detection Technology.

This study employed electronic nose technology to assess the mold levels in soybeans, conducting analyses on artificially inoculated soybeans with five strains of fungi and distinguishing them from naturally moldy soybeans. Principal component analysis (PCA) and linear discriminant analysis (LDA) were used to evaluate inoculated and naturally moldy samples. The results revealed that the most influential sensor was W2W, which is sensitive to organic sulfur compounds, followed by W1W (primarily responsive to inorganic sulfur compounds), W5S (sensitive to small molecular nitrogen oxides), W1S (responsive to short-chain alkanes such as methane), and W2S (sensitive to alcohols, ethers, aldehydes, and ketones). These findings highlight that variations in volatile substances among the moldy soybean samples were predominantly attributed to organic sulfur compounds, with significant distinctions noted in inorganic sulfur, nitrogen compounds, short-chain alkanes, and alcohols/ethers/aldehydes/ketones. The results of the PCA and LDA analyses indicated that while both methods demonstrated moderate effectiveness in distinguishing between different dominant fungal inoculations and naturally moldy soybeans, they were more successful in differentiating various levels of moldiness, achieving a discriminative accuracy rate of 82.72% in LDA. Overall, the findings suggest that electronic nose detection technology can effectively identify mold levels in soybeans.