Digitalisation and modern imaging technologies in dermatology

Teledermatology is one of the most important developments of digitalisation in dermatology. It has helped to ensure continuity of care during the COVID-19 pandemic. The combination of teledermatology with artificial intelligence can significantly improve medical decision-making. Among imaging modalities, dermoscopy is the most widely used, and its effectiveness can be significantly enhanced when combined with artificial intelligence. Novel techniques that have emerged in recent years include high-frequency ultrasound, optical coherence tomography or multispectral imaging. These are currently used in dermatological research but are expected to gradually become part of daily patient care. The knowledge of digital technologies and new imaging techniques is essential for the modern dermatologist. In the future, it is expected to be an essential part of modern and optimised patient care.

Preface

The title of the ConferenceXXII Conference of PhD Students and Young Scientists "Interdisciplinary topics in mining and geology”The location and the date of the conferencevirtual event – online conference, June 29th to July 1st, 2022 in Wrocław, PolandXXIInd Conference of PhD Students and Young Scientists "Interdisciplinary topics in mining and geology” continues a series of events that started in 2000 at Wrocław University of Science and Technology. Scientific programme of the Conference focuses on four thematic panels:1. Mining Engineering: sustainable development, digitalisation in mining, problems of securing, protecting and using remnants of old mining works, underground mining, opencast mining, mineral processing, waste management, mining machinery, mine transport, economics in mining, mining aeronautics, ventilation and air conditioning in mines,2. Earth and Space Sciences: geology, hydrogeology, environmental protection, extraterrestrial resources, groundwater and medicinal waters, engineering and environmental protection, geotourism,3. Geoengineering: environmental protection, applied geotechnics, rock and soil mechanics, geohazards,4. Geoinformation: mining geodesy, GIS, photogrammetry and remote sensing, geodata modeling and analysis.The XXII Conference of PhD Students and Young Scientists was held as a virtual event, that is as a virtual, online conference in real-time. The reason why the Organizing Committee decided to change the traditional formula of the event to online formula was related to the concern for the health of the participants due to the COVID-19 epidemic.The XXII Conference of PhD Students and Young Scientists took place from June 29th to July 1st, 2022 in Wroclaw, Poland. That is the organizers worked and managed the event from the Wrocław University of Science and Technology Geocentre building. Because the conference focused on four thematic panels, four different special opening lectures were delivered by wellknown scientists- Professor Jan Zalasiewicz (University of Leicester, England)- Associate Professor Artur Krawczyk (AGH University of Science and Technology, Poland)- Professor Biljana Kovacević-Zelić (University of Zagreb, Croatia)- Assistant Professor Eduard Kan (Tashkent Institute of Irrigation and Agricultural Mechanizations Engineers, Uzbekistan).The Conference was divided into 8 oral sessions (with 33 presentations) and 1 poster session (with 33 posters). The amount of time provided to one presentation was 15 minutes, after presentation there was 5 minutes available for discussion. The poster session was available throughout the event, and the posters were available for online viewing on the Conference's website with the possibility of make discussion and ask questions in real time via zoom meeting application as well. Every day of the Conference one "virtual coffee break” was devoted for discussion between participants and question and answer session for the Organizers.There were 96 registered participants from 13 countries. The online XXII Conference of PhD Students and Young Scientists was conducted using the Zoom meeting platform with commemorative screen shots taken. By tradition two competitions, for the best oral presentation and for the best poster were held. The award for the best oral presentation was given ex aequo to Julia Tiganj (TH Georg Agricola University of Applied Sciences, Germany) for the presentation entitled Post-mining goes international: hurdles to climate neutrality using the example of China and Oksana Khomiak, Jörg Benndorf (TU Bergakademie Freiberg, Germany) for the presentation entitled Spectral analysis of ore hyperspectral images at different stages of the mining value chain, whereas the best poster was awarded to Adam Wróblewski, Jacek Wodecki, Paweł Trybała, Radosław Zimroz (Wrocław University of Science and technology, Poland) for the poster entitled Large underground structures geometry evaluation based on point cloud data analysis.List of Scientific Committee, Organizing Committee, Editorial Team are available i this pdf.

Method for Determining the Dominant Type of Human Breathing Using Motion Capture and Machine Learning

Since the COVID-19 pandemic, the demand for respiratory rehabilitation has significantly increased. This makes developing home (remote) rehabilitation methods using modern technology essential. New techniques and tools, including wireless sensors and motion capture systems, have been developed to implement remote respiratory rehabilitation. Significant attention during respiratory rehabilitation is paid to the type of human breathing. Remote rehabilitation requires the development of automated methods of breath analysis. Most currently developed methods for analyzing breathing do not work with different types of breathing. These methods are either designed for one type (for example, diaphragmatic) or simply analyze the lungs' condition. Developing methods of determining the types of human breathing is necessary for conducting remote respiratory rehabilitation efficiently. We propose a method of determining the type of breathing using wireless sensors with the motion capture system. To develop that method, spectral analysis and machine learning methods were used to detect the prevailing spectrum, the marker coordinates, and the prevailing frequency for different types of breathing. An algorithm for determining the type of human breathing is described. It is based on approximating the shape of graphs of distances between markers using sinusoidal waves. Based on the features of the resulting waves, we trained machine learning models to determine the types of breathing. After the first stage of training, we found that the maximum accuracy of machine learning models was below 0.63, which was too low to be reliably used in respiratory rehabilitation. Based on the analysis of the obtained accuracy, the training and running time of the models, and the error function, we choose the strategy of achieving higher accuracy by increasing the training and running time of the model and using a two-stage method, composed of two machine learning models, trained separately. The first model determines whether the breath is of the mixed type;if it does not predict the mixed type of breathing, the second model determines whether breathing is thoracic or abdominal. The highest accuracy achieved by the composite model was 0.81, which surpasses single models and is high enough for use in respiratory rehabilitation. Therefore, using three wireless sensors placed on the patient's body and a two-stage algorithm using machine learning models, it was possible to determine the type of human breathing with high enough precision to conduct remote respiratory rehabilitation. The developed algorithm can be used in building rehabilitation applications.

Synthesis, DFT and In Silico Anti-COVID Evaluation of Novel Tetrazole Analogues

A new series of 3-aryl/heteroaryl-2-(1H-tetrazol-5-yl) acrylamides have been synthesized through catalyst-free, one-pot cascade reactions, utilizing click chemistry approach and evaluated for their anti-COVID activities against two proteins in silico. The structural properties of the synthesized molecules were evaluated based on DFT calculations. Total energy of the synthesized tetrazole compounds were obtained through computational analysis which indicate the high stability of the synthesized compounds. The Frontier Molecular Orbitals (FMO) and associated energies and molecular electrostatic potential (MEP) surfaces were generated for the compounds. Spectral analysis by DFT gave additional evidence to the structural properties of the synthesized molecules. All tetrazole analogues come under good ADMET data as they followed the standard value for ADMET parameters. Docking studies offered evidence of the molecules displaying excellent biological properties as an anti-Covid drug. Compound 4 g exhibited excellent anti-COVID-19 properties with four hydrogen binding interactions with amino acids GLN 2.486 Å, GLN 2.436 Å, THR 2.186 Å and HSD 2.468 Å with good full-fitness score (–1189.12) and DeltaG (–7.19). Similarly, compound 4d shown potent activity against anti-COVID-19 mutant protein (PDB: 3K7H) with three hydrogen binding interactions, i.e., SER 2.274 Å, GLU 1.758 Å and GLU 1.853 Å with full-fitness score of –786.60) and DeltaG (–6.85). The result of these studies revealed that the compounds have the potential to become lead molecules in the drug discovery process.

Spectral analysis of cough sounds of patients with COVID-19.

Cough is a frequent manifestation of COVID-19 (COronaVIrus Disease 2019), therefore, it has an important diagnostic value. There is little information about the characteristics of cough of COVID-19 patients in the literature. To perform a spectral analysis of cough sounds in COVID-19 patients in comparison with induced cough of healthy individuals. Methods. The main group consisted of 218 COVID-19 patients (48.56% - men, 51.44% - women, average age 40.2 (32.4;50.1) years). The comparison group consisted of 60 healthy individuals (50.0% men, 50.0% women, average age 41.7 (31.2;53.0) years) who were induced to cough. Each subject had a cough sound recorded, followed by digital processing using a fast Fourier transform algorithm. The temporal-frequency parameters of cough sounds were evaluated: duration (ms), the ratio of the energy of low and medium frequencies (60 - 600 Hz) to the energy of high frequencies (600 - 6 000 Hz), the frequency of the maximum sound energy (Hz). These parameters were determined in relation to both the entire cough and individual phases of the cough sound. Results. Significant differences were found between some cough parameters in the main group and in the comparison group. The total duration of the coughing act was significantly shorter in patients with COVID-19, in contrast to the induced cough of healthy individuals (T = 342.5 (277.0;394.0) - in the main group;T (c) = 400.5 (359.0;457.0) - in the comparison group;p = 0.0000). In addition, it was found that the cough sounds of COVID-19 patients are dominated by the energy of higher frequencies as compared to the healthy controls (Q = 0.3095 (0.223;0.454) - in the main group;Q (c) = 0.4535 (0.3725;0.619) - in the comparison group;p = 0.0000). The maximum frequency of cough sound energy in the main group was significantly higher than in the comparison group (Fmax = 463.0 (274.0;761.0) - in the main group;Fmax = 347 (253.0;488.0) - in the comparison group;p = 0.0013). At the same time, there were no differences between the frequencies of the maximum energy of cough sound of the individual phases of cough act and the duration of the first phase. Conclusion. The cough of patients with COVID-19 is characterized by a shorter duration and a predominance of high-frequency energy compared to the induced cough of healthy individuals.Copyright © 2022 Budnevsky A.V. et al.

Without a mask: Judgments of Corona virus exposure as a function of inter personal distance

In order to minimize the risk of infection during the Covid-19 pandemic, people are recommended to keep interpersonal distance (e.g., 1 m, 2 m, 6 feet), wash their hands frequently, limit social contacts and sometimes to wear a face mask. We investigated how people judge the protective effect of interpersonal distance against the Corona virus. The REM model, based on earlier empirical studies, describes how a person's virus exposure decreases with the square of the distance to another person emitting a virus in a face to face situation. In a comparison with model predictions, most participants underestimated the protective effect of moving further away from another person. Correspondingly, most participants were not aware of how much their exposure would increase if they moved closer to the other person. Spectral analysis of judgments showed that a linear ratio model with the independent variable = (initial distance)/(distance to which a person moves) was the most frequently used judgment rule. It leads to insensitivity to change in exposure compared with the REM model. The present study indicated a need for information about the effects of keeping interpersonal distance and about the importance of virus carrying aerosols in environments with insufficient air ventilation. Longer conversations emitting aerosols in a closed environment may lead to ambient concentrations of aerosols in the air that no distance can compensate for. The results of the study are important for risk communications in countries where people do not wear a mask and when authorities consider removal of a recommendation or a requirement to wear a face mask. (PsycInfo Database Record (c) 2023 APA, all rights reserved)

Crisis Periods Detection on NASDAQ Index Via EEMD-AE

It is proposed to identify the beginning and end of the SARS-CoV-2 and subprime crises on the NASDAQ. The EEMD was used to decompose the index into consecutive series with the same number of components and their correlation coefficients were calculated, the power spectrum of the original series was also analyzed. Signals of instability associated with changes in both the components' correlations and the NASDAQ spectrum were identified. It is recommended to apply the procedure on other series and other crises;likewise, the method is based on the detection of discrepancies, thus being a monitoring tool, but not one of quantitative forecasts. The originality of the work lies in the use of the modified EEMD for the decomposition of consecutive series in the same number of components, and the use of the correlation coefficient between components and the spectrum of the original series as measures of system stability. The approach proved to be useful for identifying and anticipating large changes in the behavior of a time series. © 2022 The authors.

Left Ventricular Diastolic Dysfunction Screening by a Smartphone-Case Based on Single Lead ECG.

Aims: To investigate the potential of a signal processed by smartphone-case based on single lead electrocardiogram (ECG) for left ventricular diastolic dysfunction (LVDD) determination as a screening method. Methods and Results: We included 446 subjects for sample learning and 259 patients for sample test aged 39 to 74 years for testing with 2D-echocardiography, tissue Doppler imaging and ECG using a smartphone-case based single lead ECG monitor for the assessment of LVDD. Spectral analysis of ECG signals (spECG) has been used in combination with advanced signal processing and artificial intelligence methods. Wavelengths slope, time intervals between waves, amplitudes at different points of the ECG complexes, energy of the ECG signal and asymmetry indices were analyzed. The QTc interval indicated significant diastolic dysfunction with a sensitivity of 78% and a specificity of 65%, a Tpeak parameter >590 ms with 63% and 58%, a T value off >695 ms with 63% and 74%, and QRSfi > 674 ms with 74% and 57%, respectively. A combination of the threshold values from all 4 parameters increased sensitivity to 86% and specificity to 70%, respectively (OR 11.7 [2.7-50.9], P < .001). Algorithm approbation have shown: Sensitivity-95.6%, Specificity-97.7%, Diagnostic accuracy-96.5% and Repeatability-98.8%. Conclusion: Our results indicate a great potential of a smartphone-case based on single lead ECG as novel screening tool for LVDD if spECG is used in combination with advanced signal processing and machine learning technologies.

Machine Learning Analyses Revealed Distinct Arterial Pulse Variability According to Side Effects of Pfizer-BioNTech COVID-19 Vaccine (BNT162b2).

Various adverse events and complications have been attributed to COVID-19 (coronavirus disease 2019) vaccinations, which can affect the cardiovascular system, with conditions such as myocarditis, thrombosis, and ischemia. The aim of this study was to combine noninvasive pulse measurements and frequency domain analysis to determine if the Pfizer-BioNTech COVID-19 vaccine (BNT162b2) vaccination and its accompanying cardiovascular side effects will induce changes in arterial pulse transmission and waveform. Radial blood pressure waveform and photoplethysmography signals were measured noninvasively for 1 min in 112 subjects who visited Shuang-Ho Hospital for a BNT162b2 vaccination. Based on side effects, each subject was assigned to Group N (no side effects), Group CV (cardiac or vascular side effects), Group C (cardiac side effects only), or Group V (vascular side effects only). Two classification methods were used: (1) machine-learning (ML) analysis using 40 harmonic pulse indices (amplitude proportions, phase angles, and their variability indices) as features, and (2) a pulse-variability score analysis developed in the present study. Significant effects on the pulse harmonic indices were noted in Group V following vaccination. ML and pulse-variability score analyses provided acceptable AUCs (0.67 and 0.80, respectively) and hence can aid discriminations among subjects with cardiovascular side effects. When excluding ambiguous data points, the AUC of the score analysis further improved to 0.94 (with an adopted proportion of around 64.1%) for vascular side effects. The present findings may help to facilitate a time-saving and easy-to-use method for detecting changes in the vascular properties associated with the cardiovascular side effects following BNT162b2 vaccination.

Advances in spectral techniques for detection of pathogenic microorganisms

The highly contagious viral illness Coronavirus disease 2019, caused by severe acute respiratory syndrome coronavirus-2, has led to nearly 5 million deaths worldwide. The detection of highly infectious pathogens or novel pathogens causing emerging infectious diseases is highly challenging. Encouragingly, spectral detection-including laser-induced fluorescence spectroscopy, infrared absorption spectroscopy, Raman spectroscopy and their combinations-has been broadly used to detect pathogenic microorganisms on the basis of their physical and chemical characteristics. Surface-enhanced Raman spectroscopy with labels can detect organisms at a minimum concentration of 3 cells/mL. The changes in cells' biochemical reactions before and after polioviral infection can be detected by Fourier transform infrared spectroscopy. However, the sensitivity and specificity of different spectral detection categories differs, owing to their different detection principles. Flexible detection methods require interdisciplinary researchers familiar with both pathogen biology and instruments. This review summarizes the advances in spectral techniques used in detecting pathogenic microorganism.

Analysis of Respiratory Signals in Spectral Domain for Detecting Respiratory Disorders with Emphasis on COVID-19

Sound signals from different processes of respiratory system are vital indicators of human health. With the onset of Coronavirus pandemic, the importance of early diagnosis of respiratory disorders has further been highlighted. In this paper, research works related to analysis of respiratory system functioning in spectral domain using acoustic signal processing methods has been reviewed with special focus on work related to COVID-19 diagnosis using non-invasive techniques. Various deep learning and machine learning models for identifying acoustic biomarkers of COVID-19 have been studied and summarised. Three modalities that have been considered are breathing, cough and voice recordings. Feature extraction techniques on these modalities have been reviewed for classification, prediction and similarity metrics analysis. Another vital health parameter is the rate of respiration that can be estimated by performing spectral analysis of sound signal envelope of breathe signal recording. Various datasets and pre-processing techniques related to sounds associated with symptoms of respiratory disorders including COVID-19 sounds have also been listed. © 2022 IEEE.

2050 Projections of the Persian Gulf Economies

Projections of Persian Gulf Economies are obtained by forecasting their GDPs (constant 2010 US$) with spectral analysis until 2050. Persian Gulf Economies being oil-driven, the special relationship between oil price and Persian Gulf Economies is unfolded with Multiscale Principal Component Analysis and integrated into the forecasts. The GDPs are decomposed into clearer signals called approximations and details in the one-dimensional discrete wavelet analysis framework. The simplified signals are recomposed after the Burg extension. Spectral analysis forecasts are all bullish for the eight economies of the Persian Gulf. Two thousand fifty spectral analysis projections rank Iraq first with an annual growth rate of +2.37% and Iran second with +2.19%. The two laggers among the 2050 spectral analysis projections are Saudi Arabia (+1.37%) and Kuwait (-0.04%). Two thousand twenty-four spectral analysis projections rank Iran first with an annual growth rate compounded of +4.12% and Iraq second with +3.79%. In comparison, IMF projections rank Iraq first (+3.17%) and United Arab Emirates (+2.92%). The two laggers among the 2024 spectral analysis projections are Qatar (0.22%) and Kuwait (-3.74%), while the two laggers among the 2024 IMF projections are Saudi Arabia (+2.15%) and Iran (-0.30%). In 2020, the COVID-19 pandemic brutally hurt Persian Gulf Economies following a collapse in the global demand for oil and an oversupplied industry. The individual effect on these economies will depend on the response brought by their respective governments. © University of Tehran.

Analysis of Worldwide Time-Series Data Reveals Some Universal Patterns of Evolution of the SARS-CoV-2 Pandemic

Predicting the evolution of the current epidemic depends significantly on understanding the nature of the underlying stochastic processes. To unravel the global features of these processes, we analyse the world data of SARS-CoV-2 infection events, scrutinising two 8-month periods associated with the epidemic’s outbreak and initial immunisation phase. Based on the correlation-network mapping, K-means clustering, and multifractal time series analysis, our results reveal several universal patterns of infection dynamics, suggesting potential predominant drivers of the pandemic. More precisely, the Laplacian eigenvectors localisation has revealed robust communities of different countries and regions that break into clusters according to similar profiles of infection fluctuations. Apart from quantitative measures, the immunisation phase differs significantly from the epidemic outbreak by the countries and regions constituting each cluster. While the similarity grouping possesses some regional components, the appearance of large clusters spanning different geographic locations is persevering. Furthermore, characteristic cyclic trends are related to these clusters;they dominate large temporal fluctuations of infection evolution, which are prominent in the immunisation phase. Meanwhile, persistent fluctuations around the local trend occur in intervals smaller than 14 days. These results provide a basis for further research into the interplay between biological and social factors as the primary cause of infection cycles and a better understanding of the impact of socio-economical and environmental factors at different phases of the pandemic. Copyright © 2022 Mitrović Dankulov, Tadić and Melnik.

Comparative Analysis of Major Stock Markets in Relation to Global Financial Crises: Evidence from 2000 to the COVID-19 Pandemic

We analyze the impact of financial crises on major stock markets from 2000 to the COVID-19 pandemic using Fourier series. Analyzing the behaviors of the spectra obtained from monthly returns of their indices, we identify three global financial crises from 2000 to 2015, with different characteristics. In addition, applying Z-test and the color-contour plotting method to monthly propagations of the spectra of major frequencies from the monthly returns of each index, we analyze the developments in each market around the crises by comparing patterns in the color-contour plots. Using recent status analysis, we identify an instability around 2016 close to a real crisis;starting in 2020, the markets, which had already recovered from this instability have generated abnormal signals of an approaching crisis. Applying Z-test and color-contour plotting to monthly propagations from the recent status, we show that recent developments in major markets might be more serious than those occurring around previous financial crises. © 2022, Kauno Technologijos Universitetas. All rights reserved.

Arsenic in Groundwater Sources from Selected Communities Surrounding Taal Volcano, Philippines: An Exploratory Study

Arsenic (As) is a highly toxic, carcinogenic trace metal that can potentially contaminate groundwater sources in volcanic regions. This study provides the first comparative documentation of As concentrations in groundwater in a volcano-sedimentary region in the Philippines. Matched, repeated As measurements and physico-chemical analyses were performed in 26 individual wells from 11 municipalities and city in Batangas province from July 2020 to November 2021. Using the electrothermal atomic absorption spectrometric method, analysis of the wells revealed that in 2020, 23 out of 26 (88.46%) had As levels above the WHO limit of >10 ppb while 20 out of 26 wells (76.92%) had persistently high As levels a year later. Using a Wilcoxon signed-rank test, levels of As were found to be statistically elevated compared to the national safe limit of 10 pbb in the 26 matched sampling sites in both 2020 (p-value < 0.001) and 2021 (p-value = 0.013). Additionally, a two-paired Wilcoxon signed-rank test revealed that As levels were statistically higher in 2020 than in 2021 (p-value = 0.003), suggesting that As levels may be higher in years when there is more volcanic activity;however, this remains to be further elucidated with suitable longitudinal data, as this study is still in its preliminary stages. The data was also analyzed using a bivariable regression, which showed no evidence of a significant relationship between As levels and distance from the danger zone (Taal volcano crater);however, results showed an inverse but statistically insignificant relationship between As levels and elevation. Due to the toxic profile and persistence of As in groundwater in Batangas Province, continuous groundwater As monitoring, timely public health risk communication, and the provision of alternative water sources to affected populations are recommended.

Dynamics of COVID-19 in the Gulf Cooperation Council (GCC) countries.

Objectives: The cumulative numbers of confirmed cases, despite providing few details regarding the dynamics, are widely used to model the COVID-19 pandemic. The purpose of this study was to determine the dynamics of COVID-19 in the Gulf Cooperation Council (GCC) countries by using the number of daily new cases rather than the cumulative number of new cases. Methods: Data on daily new cases of COVID-19 in the GCC countries from February 2020 to September 2021 were obtained from the Worldometer website. In MATLAB, the Savitzky-Golay filter was used to obtain smoothed curves of the daily profiles of the pandemic, and power spectrum analysis was performed to identify the dominant frequencies. Results: The smoothed curves indicated that the GCC countries have experienced two major waves of the pandemic with different peaks and durations. During the first wave, the exponential growth rates ranged from 9 cases/day in Bahrain to 53 cases/day in KSA, whereas the decline rates varied from 6 cases/day in Kuwait to 72 cases/day in KSA. Conclusions: Despite the similarities in socio-economic and environmental conditions among GCC countries, the results indicated that the dynamics of COVID-19 are unique for each GCC country.

Identification and Characterization of Peruvian Native Bacterial Strains as Bioremediation of Hg-Polluted Water and Soils Due to Artisanal and Small-Scale Gold Mining in the Secocha Annex, Arequipa

The water and soils pollution due to mercury emissions from mining industries represents a serious environmental problem and continuous risk to human health. Although many strategies have been designed for the recovery or elimination of this metal from environmental sources, microbial bioremediation has proven to be the most effective and environmentally friendly strategy and thus control heavy metal contamination. The main objective of this work, using native bacterial strains obtained from contaminated soils of the Peruvian region of Secocha, was to identify which of these strains would have growth capacity on mercury substrates to evaluate their adsorption behavior and mercury removal capacity. Through a DNA analysis (99.78% similarity) and atomic absorption spectrometry, the Gram-positive bacterium Zhihengliuella alba sp. T2.2 was identified as the strain with the highest mercury removal capacity from culture solutions with an initial mercury concentration of 162 mg·L−1. The removal capacity reached values close to 39.5% in a period of incubation time of 45 days, with maximum elimination efficiency in the first 48 h. These results are encouraging and show that this native strain may be the key to the bioremediation of water and soils contaminated with mercury.

Detection of SARS-CoV-2 infection by exhaled breath spectral analysis: Introducing a ready-to-use point-of-care mass screening method.

BACKGROUND: The current SARS-CoV-2 pandemic created an urgent need for rapid, infection screening applied to large numbers of asymptomatic individuals. To date, nasal/throat swab polymerase chain reaction (PCR) is considered the "gold standard". However, this is inconducive to mass, point-of-care (POC) testing due to person discomfort during sampling and a prolonged result turnaround. Breath testing for disease specific organic compounds potentially offers a practical, rapid, non-invasive, POC solution. The study compares the Breath of Health, Ltd. (BOH) breath analysis system to PCR's ability to screen asymptomatic individuals for SARS-CoV-2 infection. The BOH system is mobile and combines Fourier-transform infrared (FTIR) spectroscopy with artificial intelligence (AI) to generate results within 2 min and 15 s. In contrast to prior SARS-CoV-2 breath analysis research, this study focuses on diagnosing SARS-CoV-2 via disease specific spectrometric profiles rather than through identifying the disease specific molecules. METHODS: Asymptomatic emergency room patients with suspected SARS-CoV-2 exposure in two leading Israeli hospitals were selected between February through April 2021. All were tested via nasal/throat-swab PCR and BOH breath analysis. In total, 297 patients were sampled (mean age 57·08 ± SD 18·86, 156 males, 139 females, 2 unknowns). Of these, 96 were PCR-positive (44 males, 50 females, 2 unknowns), 201 were PCR-negative (112 males, 89 females). One hundred samples were used for AI identification of SARS-CoV-2 distinguishing spectroscopic wave-number patterns and diagnostic algorithm creation. Algorithm validation was tested in 100 proof-of-concept samples (34 PCR-positive, 66 PCR-negative) by comparing PCR with AI algorithm-based breath-test results determined by a blinded medical expert. One hundred additional samples (12 true PCR-positive, 85 true PCR-negative, 3 confounder false PCR-positive [not included in the 297 total samples]) were evaluated by two blinded medical experts for further algorithm validation and inter-expert correlation. FINDINGS: The BOH system identified three distinguishing wave numbers for SARS-CoV-2 infection. In the first phase, the single expert identified the first 100 samples correctly, yielding a 1:1 FTIR/AI:PCR correlation. The two-expert second-phase also yielded 1:1 FTIR/AI:PCR correlation for 97 non-confounders and null correlation for the 3 confounders. Inter-expert correlation was 1:1 for all results. In total, the FTIR/AI algorithm demonstrated 100% sensitivity and specificity for SARS-CoV-2 detection when compared with PCR. INTERPRETATION: The SARS-CoV-2 method of breath analysis via FTIR with AI-based algorithm demonstrated high PCR correlation in screening for asymptomatic individuals. This is the first practical, rapid, POC breath analysis solution with such high PCR correlation in asymptomatic individuals. Further validation is required with a larger sample size. FUNDING: Breath of Health Ltd, Rehovot, Israel provided study funding.

Complex network-based pertussis and croup cough analysis: A machine learning approach

The paper proposes a novel approach to bring out the potential of complex networks based on graph theory to unwrap the hidden characteristics of cough signals, croup (BC), and pertussis (PS). The spectral and complex network analyses of 48 cough sounds are utilized for understanding the airflow through the infected respiratory tract. Among the different phases of the cough sound time-domain signals of BC and PS – expulsive (X), intermediate (I), and voiced (V) - the phase ‘I’ is noisy in BC due to improper glottal functioning. The spectral analyses reveal high-frequency components in both cough signals with an additional high-intense low-frequency spread in BC. The complex network features created by the correlation mapping approach, like number of edges (E), graph density (G), transitivity (Tr), degree centrality (D), average path length (L), and number of components (Nc) distinguishes BC and PS. The higher values of E, G, and Tr for BC indicate its musical nature through the strong correlation between the signal segments and the presence of high-intense low-frequency components in BC, unlike that in PS. The values of D, L, and Nc discriminate BC and PS in terms of the strength of the correlation between the nodes within them. The linear discriminant analysis (LDA) and quadratic support vector machine (QSVM) classifies BC and PS, with greater accuracy of 94.11% for LDA. The proposed work opens up the potentiality of employing complex networks for cough sound analysis, which is vital in the current scenario of COVID-19.

Approach to COVID-19 time series data using deep learning and spectral analysis methods

This article focuses on the application of deep learning and spectral analysis to epidemiology time series data, which has recently piqued the interest of some researchers. The COVID-19 virus is still mutating, particularly the delta and omicron variants, which are known for their high level of contagiousness, but policymakers and governments are resolute in combating the pandemic's spread through a recent massive vaccination campaign of their population. We used extreme machine learning (ELM), multilayer perceptron (MLP), long short-term neural network (LSTM), gated recurrent unit (GRU), convolution neural network (CNN) and deep neural network (DNN) methods on time series data from the start of the pandemic in France, Russia, Turkey, India, United states of America (USA), Brazil and United Kingdom (UK) until September 3, 2021 to predict the daily new cases and daily deaths at different waves of the pandemic in countries considered while using root mean square error (RMSE) and relative root mean square error (rRMSE) to measure the performance of these methods. We used the spectral analysis method to convert time (days) to frequency in order to analyze the peaks of frequency and periodicity of the time series data. We also forecasted the future pandemic evolution by using ELM, MLP, and spectral analysis. Moreover, MLP achieved best performance for both daily new cases and deaths based on the evaluation metrics used. Furthermore, we discovered that errors for daily deaths are much lower than those for daily new cases. While the performance of models varies, prediction and forecasting during the period of vaccination and recent cases confirm the pandemic's prevalence level in the countries under consideration. Finally, some of the peaks observed in the time series data correspond with the proven pattern of weekly peaks that is unique to the COVID-19 time series data.