A machine learning-based electronic nose for detecting neonatal sepsis: Analysis of volatile organic compound biomarkers in fecal samples.

BACKGROUND: Neonatal sepsis is a global health threat, contributing to high morbidity and mortality rates among newborns. Recognizing the profound impact of neonatal sepsis on long-term health outcomes emphasizes the critical need for timely detection to mitigate its consequences and ensure optimal health for the affected newborns. Currently, various diagnostic approaches have been implemented, but they are limited by their invasiveness, high costs, centralized testing, frequent delays, inaccuracies in results, and the need for sophisticated laboratory equipment. METHODS: We introduced a novel, non-invasive, cost-efficient, and easy-to-use technology that can provide rapid results at a point-of-care. The technology utilized a lab-built metal oxide semiconductor-based electronic nose (cNose) combined with volatile organic compound (VOC) biomarkers identified through gas chromatography-mass spectrometry (GC-MS) analysis. The system was evaluated using fecal profiling tests involving a total of 32 samples, including 17 positive and 15 negative sepsis, confirmed by blood culture. To assess the performance in discriminating patients from healthy controls, four machine learning algorithms were implemented. RESULTS: Based on the cross-validation results, the MLPNN model provided the best results in distinguishing between neonates with positive and negative sepsis, achieving high-performance results of 90.63 % accuracy, 88.24 % sensitivity, and 93.33 % specificity at a 95 % confidence interval. Specific VOCs associated with neonatal sepsis, such as alcohols, acids, and esters, were successfully identified through GC-MS analysis, further validating the diagnostic capability of the cNose device. CONCLUSION: The overall observations show the feasibility of using cNose system as a promising tool for real-time and bedside sepsis detection, potentially improving patient outcomes.

Rapid analysis of meat floss origin using a supervised machine learning-based electronic nose towards food authentication.

Authentication of meat floss origin has been highly critical for its consumers due to existing potential risks of having allergic diseases or religion perspective related to pork-containing foods. Herein, we developed and assessed a compact portable electronic nose (e-nose) comprising gas sensor array and supervised machine learning with a window time slicing method to sniff and to classify different meat floss products. We evaluated four different supervised learning methods for data classification (i.e., linear discriminant analysis (LDA), quadratic discriminant analysis (QDA), k-nearest neighbors (k-NN), and random forest (RF)). Among them, an LDA model equipped with five-window-extracted feature yielded the highest accuracy values of >99% for both validation and testing data in discriminating beef, chicken, and pork flosses. The obtained e-nose results were correlated and confirmed with the spectral data from Fourier-transform infrared (FTIR) spectroscopy and gas chromatography-mass spectrometry (GC-MS) measurements. We found that beef and chicken had similar compound groups (i.e., hydrocarbons and alcohol). Meanwhile, aldehyde compounds (e.g., dodecanal and 9-octadecanal) were found to be dominant in pork products. Based on its performance evaluation, the developed e-nose system shows promising results in food authenticity testing, which paves the way for ubiquitously detecting deception and food fraud attempts.

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.