Long- and short-run asymmetric impacts of climate variation on tuberculosis based on a time series study.

Distinguishing between long-term and short-term effects allows for the identification of different response mechanisms. This study investigated the long- and short-run asymmetric impacts of climate variation on tuberculosis (TB) and constructed forecasting models using the autoregressive distributed lag (ARDL) and nonlinear ARDL (NARDL). TB showed a downward trend, peaking in March-May per year. A 1 h increment or decrement in aggregate sunshine hours resulted in an increase of 32 TB cases. A 1 m/s increment and decrement in average wind velocity contributed to a decrement of 3600 and 5021 TB cases, respectively (Wald long-run asymmetry test [WLR] = 13.275, P < 0.001). A 1% increment and decrement in average relative humidity contributed to an increase of 115 and 153 TB cases, respectively. A 1 hPa increment and decrement in average air pressure contributed to a decrease of 318 and 91 TB cases, respectively (WLR = 7.966, P = 0.005). ∆temperature(-), ∆(sunshine hours)( -), ∆(wind velocity)(+) and ∆(wind velocity)(-) at different lags had a meaningful short-run effect on TB. The NARDL outperformed the ARDL in forecasting. Climate variation has significant long- and short-run asymmetric impacts on TB. By incorporating both dimensions of effects into the NARDL, the accuracy of the forecasts and policy recommendations for TB can be enhanced.

Spatiotemporal multilevel joint modeling of longitudinal and survival outcomes in end-stage kidney disease.

Individuals with end-stage kidney disease (ESKD) on dialysis experience high mortality and excessive burden of hospitalizations over time relative to comparable Medicare patient cohorts without kidney failure. A key interest in this population is to understand the time-dynamic effects of multilevel risk factors that contribute to the correlated outcomes of longitudinal hospitalization and mortality. For this we utilize multilevel data from the United States Renal Data System (USRDS), a national database that includes nearly all patients with ESKD, where repeated measurements/hospitalizations over time are nested in patients and patients are nested within (health service) regions across the contiguous U.S. We develop a novel spatiotemporal multilevel joint model (STM-JM) that accounts for the aforementioned hierarchical structure of the data while considering the spatiotemporal variations in both outcomes across regions. The proposed STM-JM includes time-varying effects of multilevel (patient- and region-level) risk factors on hospitalization trajectories and mortality and incorporates spatial correlations across the spatial regions via a multivariate conditional autoregressive correlation structure. Efficient estimation and inference are performed via a Bayesian framework, where multilevel varying coefficient functions are targeted via thin-plate splines. The finite sample performance of the proposed method is assessed through simulation studies. An application of the proposed method to the USRDS data highlights significant time-varying effects of patient- and region-level risk factors on hospitalization and mortality and identifies specific time periods on dialysis and spatial locations across the U.S. with elevated hospitalization and mortality risks.

Trends and multi-model prediction of hepatitis B incidence in Xiamen.

Background: This study aims to analyze the trend of Hepatitis B incidence in Xiamen City from 2004 to 2022, and to select the best-performing model for predicting the number of Hepatitis B cases from 2023 to 2027. Methods: Data were obtained from the China Information System for Disease Control and Prevention (CISDCP). The Joinpoint Regression Model analyzed temporal trends, while the Age-Period-Cohort (APC) model assessed the effects of age, period, and cohort on hepatitis B incidence rates. We also compared the predictive performance of the Neural Network Autoregressive (NNAR) Model, Bayesian Structural Time Series (BSTS) Model, Prophet, Exponential Smoothing (ETS) Model, Seasonal Autoregressive Integrated Moving Average (SARIMA) Model, and Hybrid Model, selecting the model with the highest performance to forecast the number of hepatitis B cases for the next five years. Results: Hepatitis B incidence rates in Xiamen from 2004 to 2022 showed an overall declining trend, with rates higher in men than in women. Higher incidence rates were observed in adults, particularly in the 30-39 age group. Moreover, the period and cohort effects on incidence showed a declining trend. Furthermore, in the best-performing NNAR(10, 1, 6)[12] model, the number of new cases is predicted to be 4271 in 2023, increasing to 5314 by 2027. Conclusions: Hepatitis B remains a significant issue in Xiamen, necessitating further optimization of hepatitis B prevention and control measures. Moreover, targeted interventions are essential for adults with higher incidence rates.

Adaptive and self-learning Bayesian filtering algorithm to statistically characterize and improve signal-to-noise ratio of heart-rate data in wearable devices.

The use of wearable sensors to monitor vital signs is increasingly important in assessing individual health. However, their accuracy often falls short of that of dedicated medical devices, limiting their usefulness in a clinical setting. This study introduces a new Bayesian filtering (BF) algorithm that is designed to learn the statistical characteristics of signal and noise, allowing for optimal smoothing. The algorithm is able to adapt to changes in the signal-to-noise ratio (SNR) over time, improving performance through windowed analysis and Bayesian criterion-based smoothing. By evaluating the algorithm on heart-rate (HR) data collected from Garmin Vivoactive 4 smartwatches worn by individuals with amyotrophic lateral sclerosis and multiple sclerosis, it is demonstrated that BF provides superior SNR tracking and smoothing compared with non-adaptive methods. The results show that BF accurately captures SNR variability, reducing the root mean square error from 2.84 bpm to 1.21 bpm and the mean absolute relative error from 3.46% to 1.36%. These findings highlight the potential of BF as a preprocessing tool to enhance signal quality from wearable sensors, particularly in HR data, thereby expanding their applications in clinical and research settings.

Assessing the impact of COVID-19 non-pharmaceutical interventions and relaxation policies on Class B respiratory infectious diseases transmission in China.

This study investigates the incidence of Class B respiratory infectious diseases (RIDs) in China under the Coronavirus disease 2019 (COVID-19) epidemic and examines variations post-epidemic, following the relaxation of non-pharmaceutical interventions (NPIs). Two-stage evaluation was used in our study. In the first stage evaluation, we established counterfactual models for the pre-COVID-19 period to estimate expected incidences of Class B RIDs without the onset of the epidemic. In the second stage evaluation, we constructed seasonal autoregressive integrated moving average intervention (SARIMA-Intervention) models to evaluate the impact on the Class B RIDs after NPIs aimed at COVID-19 pandemic were relaxed. The counterfactual model in the first stage evaluation suggested average annual increases of 10.015%, 78.019%, 70.439%, and 67.799% for tuberculosis, scarlet fever, measles, and pertussis respectively, had the epidemic not occurred. In the second stage evaluation, the total relative reduction in 2023 of tuberculosis, scarlet fever, measles and pertussis were - 35.209%, - 59.184%, - 4.481%, and - 9.943% respectively. The actual incidence declined significantly in the first stage evaluation. However, the results of the second stage evaluation indicated that a rebound occurred in four Class B RIDs after the relaxation of NPIs; all of these showed a negative total relative reduction rate.

Unanticipated evolution of cardio-respiratory interactions with cognitive load during a Go-NoGo shooting task in virtual reality.

The cardiovascular system interacts continuously with the respiratory system to maintain the vital balance of oxygen and carbon dioxide in our body. The interplay between the sympathetic and parasympathetic branches of the autonomic nervous system regulates the aforesaid involuntary functions. This study analyzes the dynamics of the cardio-respiratory (CR) interactions using RR Intervals (RRI), Systolic Blood Pressure (SBP), and Respiration signals after first-order differencing to make them stationary. It investigates their variation with cognitive load induced by a virtual reality (VR) based Go-NoGo shooting task with low and high levels of task difficulty. We use Pearson's correlation-based linear and mutual information-based nonlinear measures of association to indicate the reduction in RRI-SBP and RRI-Respiration interactions with cognitive load. However, no linear correlation difference was observed in SBP-Respiration interactions with cognitive load, but their mutual information increased. A couple of open-loop autoregressive models with exogenous input (ARX) are estimated using RRI and SBP, and one closed-loop ARX model is estimated using RRI, SBP, and Respiration. The impulse responses (IRs) are derived for each input-output pair, and a reduction in the positive and negative peak amplitude of all the IRs is observed with cognitive load. Some novel parameters are derived by representing the IR as a double exponential curve with cosine modulation and show significant differences with cognitive load compared to other measures, especially for the IR between SBP and Respiration.

Predictive analytics for traffic flow optimization in urban logistics: A transformer-based time series approach.

In this study, we focus on the analysis and prediction of urban logistics traffic flow, a field that is gaining increasing attention due to the acceleration of global urbanization and heightened environmental awareness. Existing forecasting methods face challenges in processing large and complex datasets, particularly when extracting and analyzing valid information from these data, often hindered by noise and outliers. In this context, time series analysis, as a key technique for predicting future trends, becomes crucial for supporting real-time traffic management and long-term traffic planning. To this end, we propose a composite network model that integrates gated recurrent unit (GRU), autoregressive integrated moving average (ARIMA), and temporal fusion transformer (TFT), namely the GRU-ARIMA-TFT network model, to enhance prediction accuracy and efficiency. Through the analysis of experimental results on different datasets, we demonstrate the significant advantages of this model in improving prediction accuracy and understanding complex traffic patterns. This research not only theoretically expands the boundaries of urban logistics traffic flow prediction but also holds substantial practical significance in real-world applications, especially in optimizing urban traffic planning and logistics distribution strategies during peak periods and under complex traffic conditions. Our study provides a robust tool for addressing real-world issues in the urban logistics domain and offers new perspectives and methodologies for future urban traffic management and logistics system planning.

Development and Comparison of Time Series Models in Predicting Severe Fever with Thrombocytopenia Syndrome Cases - Hubei Province, China, 2013-2020.

Introduction: Severe fever with thrombocytopenia syndrome (SFTS) is an emerging infectious disease caused by the SFTS virus, which has a high mortality rate. Predicting the number of SFTS cases is essential for early outbreak warning and can offer valuable insights for establishing prevention and control measures. Methods: In this study, data on monthly SFTS cases in Hubei Province, China, from 2013 to 2020 were collected. Various time series models based on seasonal auto-regressive integrated moving average (SARIMA), Prophet, eXtreme Gradient Boosting (XGBoost), and long short-term memory (LSTM) were developed using these historical data to predict SFTS cases. The established models were evaluated and compared using mean absolute error (MAE) and root mean squared error (RMSE). Results: Four models were developed and performed well in predicting the trend of SFTS cases. The XGBoost model outperformed the others, yielding the closest fit to the actual case numbers and exhibiting the smallest MAE (2.54) and RMSE (2.89) in capturing the seasonal trend and predicting the monthly number of SFTS cases in Hubei Province. Conclusion: The developed XGBoost model represents a promising and valuable tool for SFTS prediction and early warning in Hubei Province, China.

Workplace learning: the bidirectional relationship between stress and self-regulated learning in undergraduates.

The present study focused on the relationships between various aspects of self-regulated learning (SRL) and stress among undergraduate health science students in workplace settings. Although both constructs are associated with academic achievement (Ahmady Set al., in J Educ Health Promotion 10:32, 2021, Cho KK et al., in BMC Med Educ 17:112, 2017), it is still unclear how they influence each other. Employing a longitudinal diary design, the aim of the present study was to examine whether perceived stress in the previous week impacts SRL-aspects in the current week and, conversely, whether SRL-aspects in the previous week impacts stress in the current week. Subjects were 192 undergraduate health sciences students in their workplace placements. SRL-aspects and stress were assessed using scales and previously tested single-item measures. The 21 SRL-aspects used in this study included cognition (learning strategies), motivation, emotion, perception of the learning environment, and regulation of these areas on a metalevel (monitoring and control). Data collected over 15 weeks were analyzed using multilevel vector autoregressive models, with the data nested within weeks and one model dedicated to each SRL-aspect and its relationship with stress. Among the 21 path estimates assessing the impact of prior stress on individual SRL-aspects, 10 were statistically significant. For individual SRL-aspects impacting stress, 7 out of 21 paths were statistically significant (p < .05). Notably, no model showed statistical significance of effects in both directions. Except for two results, cross-lagged relationships were negative, indicating that better SRL-aspects from the previous week resulted in reduced stress in the current week and vice versa. The effects for the cross-lagged paths from SRL-aspects to stress were predominantly of medium size, whereas the influence of stress on individual SRL-aspects was predominantly small. The present study highlights a potentially causal and mostly negative relationship between stress and various aspects of SRL, but also that the individual relationships require differentiated consideration. The results can be used to develop targeted interventions in the practical part of the training of health science students to reduce stress and improve specific aspects of SRL. Furthermore, these findings underscore assumptions regarding connections between anxiety and increased stress, negative relationships between stress and motivation, and the importance of effective time management strategies for stress reduction.

The Impact of Social Expenditure on Sustainable Human Development: Empirical Evidence on the Suicide Deaths in a Developing Country.

Suicide has been a serious international public mental health problem and is one of the top twenty leading causes of death worldwide. This study aims to investigate the impact of social expenditure on suicide deaths in Turkiye as a developing country from 1982 to 2019. The Bounds Testing Approach to Cointegration and Autoregressive Distributed Lag (ARDL) methods were used. The results indicated that social expenditure has a statistically significant and negative effect on total suicide and female suicide deaths, but it has a statistically insignificant and negative impact on male suicide death. The contribution of this study is to examine for the first time whether social expenditure has an impact on total, female, and male suicide mortality in Turkiye. Policymakers should regard increasing social spending in the government budget to prevent suicide deaths in Turkiye.

Asymmetric association between meteorological factors and human infections with hemorrhagic fever with renal syndrome: A 16-year ecological trend study in Shaanxi, China.

Objective: Hemorrhagic fever with renal syndrome (HFRS) continues to pose a significant threat to global health. This study aimed to investigate both the long- and short-term asymmetric impacts of variations in meteorological variables on HFRS. Methods: The reported monthly HFRS incidence data from Shaanxi between 2004 and 2019, along with corresponding meteorological data, were collected to conduct an ecological trend analysis. Subsequently, the autoregressive distributed lag (ARDL) and nonlinear ARDL (NARDL) models were used to examine the long- and short-term asymmetric effects of climate variables on HFRS incidence. Results: Overall, a reduction in HFRS incidence was observed in Shaanxi from 2004 to 2019, with an average annual percentage change of -0.498 % (95 %CI -13.247 % to 12.602 %). HFRS incidence peaked in December and reached its lowest point in March each year. A 1 mm increase in aggregate precipitation (AP) was associated with a 4.3 % rise in HFRS incidence, while a 1 mm decrease contributed to a 3.7 % increase, indicating a long-term asymmetric impact (Wald long-term asymmetry test [WLT] = 9.072, P = 0.003). In the short term, a 1 % decrease in mean relative humidity (MRH) led to a 5.7 % decline in HFRS incidence (Wald short-term asymmetry test [WSR] = 5.978, P = 0.015). Additionally, changes in meteorological variables showed varied effects: ΔMWV(+) at a 1-month lag had a significant positive short-term effect on HFRS; ΔMRH(+) at a 3-month lag, ΔAP(+) at a 2-month lag, ΔAP(-) at a 1-month lag, ΔASH(+) at a 1-month lag, and ΔASH(-) at a 3-month lag all exhibited strong negative short-term impacts on HFRS incidence. Conclusions: Weather variability plays a significant role in influencing HFRS incidence, with both long- and short-term asymmetric and/or symmetric effects. Utilizing the NARDL model through a One Health lens offers promising opportunities for enhancing HFRS control measures.

Seasonality of common respiratory viruses: Analysis of nationwide time-series data.

BACKGROUND AND OBJECTIVE: Understanding the seasonal behaviours of respiratory viruses is crucial for preventing infections. We evaluated the seasonality of respiratory viruses using time-series analyses. METHODS: This study analysed prospectively collected nationwide surveillance data on eight respiratory viruses, gathered from the Korean Influenza and Respiratory Surveillance System. The data were collected on a weekly basis by 52 nationwide primary healthcare institutions between 2015 and 2019. We performed Spearman correlation analyses, similarity analyses via dynamic time warping (DTW) and seasonality analyses using seasonal autoregressive integrated moving average (SARIMA). RESULTS: The prevalence of rhinovirus (RV, 23.6%-31.4%), adenovirus (AdV, 9.2%-16.6%), human coronavirus (HCoV, 3.0%-6.6%), respiratory syncytial virus (RSV, 11.7%-20.1%), influenza virus (IFV, 11.7%-21.5%), parainfluenza virus (PIV, 9.2%-12.6%), human metapneumovirus (HMPV, 5.6%-6.9%) and human bocavirus (HBoV, 5.0%-6.4%) were derived. Most of them exhibited a high positive correlation in Spearman analyses. In DTW analyses, all virus data from 2015 to 2019, except AdV, exhibited good alignments. In SARIMA, AdV and RV did not show seasonality. Other viruses showed 12-month seasonality. We describe the viruses as winter viruses (HCoV, RSV and IFV), spring/summer viruses (PIV, HBoV), a spring virus (HMPV) and all-year viruses with peak incidences during school periods (RV and AdV). CONCLUSION: This is the first study to comprehensively analyse the seasonal behaviours of the eight most common respiratory viruses using nationwide, prospectively collected, sentinel surveillance data.

Exchange rate and inflation dynamics in Kenya: Does the threshold level matter?

This study empirically examined the threshold effect of exchange rate pass-through (ERPT) on inflation in Kenya, while augmenting the exchange rate depreciation in the monetary policy rate using the Taylor rule. The monthly time series data spanning January 2005 to November 2023 was collected for analysis, in which the non-linear threshold autoregressive (TAR) model was employed as the main econometric model. This study's ERPT results reveal that, exchange rate depreciation has positive and significant effect on inflation only when it raises above the monthly threshold level of 0.51 %. In contrast, the Taylor rule analysis results reveal that the exchange rate depreciation has a positive and significant effect the monetary policy rate regardless of the threshold level of 0.67 %. Therefore, keeping domestic currency depreciation below a monthly growth rate of 0.51 % will control the pass-through effect on inflation, and the exchange rate depreciation at any level should always act as a reaction function for the monetary policy rate setting. This study also found that the relationship between exchange rate depreciation and inflation, as well as monetary policy rate is non-linear, which implies a greater pass-through effect when exchange rate depreciation is high. Therefore, we recommend the monetary authority in Kenya to pay attention to the depreciation of the exchange rate depreciation at any level when adjusting the policy rate to tame inflation.

Climate-driven context-dependent structure of population cycles.

Multiannual population cycles of small mammals are of interest within population biology. We propose an approach for multidimensional autoregressive (AR) time series and analyse monitoring data on grey-sided voles (Myodes rufocanus) in Japan to investigate one or possibly multiple multiannual cycles that drive population dynamics. Temperature, through modifying rodent communities, is found to be a key factor shaping population dynamics. Warmer areas are the main habitat for other rodent species resulting in low vole abundance/dominance, as opposed to higher vole dominance in colder areas-a pattern associated with the AR structure and population cycle. Vole populations in simple rodent communities exhibit an AR(2) cycle of 2-3 years. In areas with complex rodent communities, vole dynamics follows an AR(4) process and a combination of two cycles with different lengths. The AR structure varies in relatively small spatial scales, thus widening the scope of AR analyses needed. Historically, vole abundance increased in the late 1970s and decreased from the 1980s, with warm winters shown to be associated with the decline of vole abundance in the AR(4) populations. This significant association between the AR order, population dynamics, temperature and rodent community provides insights into the declining trends observed in rodent populations of the Northern Hemisphere.

Temporal assessment of Gross alpha emissions from the petroleum industry in Tenerife, Canary Islands (2001-2022).

A ca. 76% decrease in gross alpha activity levels, measured in surface aerosols collected in the city of Santa Cruz de Tenerife (Spain), has been explained in the present study in connection with the reduction of activities, and eventual closure, of an oil refinery in the city. Gross Alpha in surface aerosols, collected at weekly intervals over a period of 22 years (2001-2022), was used for the analysis. The dynamic behaviour of the gross alpha time series was studied using statistical wavelet, multifractal analysis, empirical decomposition method, multivariate analysis, principal component, and cluster analyses approaches. This was performed to separate the impact of other sources of alpha emitting radionuclides influencing the gross alpha levels at this site. These in-depth analyses revealed a noteworthy shift in the dynamic behaviour of the gross alpha levels following the refinery's closure in 2013. This analysis also attributed fluctuations and trends in the gross alpha levels to factors such as the 2008 global economic crisis and the refinery's gradual reduction of activity leading up to its closure. The mixed-model approach, incorporating multivariate regression and autoregressive integrated moving average methods, explained approximately 84% of the variance of the gross alpha levels. Finally, this work underscored the marked reduction in alpha activity levels following the refinery's closure, alongside the decline of other pollutants (CO, SO2, NO, NO2, Benzene, Toluene and Xylene) linked to the primary industrial activity in the municipality of Santa Cruz de Tenerife.

Machine learning investigation of tuberculosis with medicine immunity impact.

Tuberculosis (T.B.) remains a prominent global cause of health challenges and death, exacerbated by drug-resistant strains such as multidrug-resistant tuberculosis MDR-TB and extensively drug-resistant tuberculosis XDR-TB. For an effective disease management strategy, it is crucial to understand the dynamics of T.B. infection and the impacts of treatment. In the present article, we employ AI-based machine learning techniques to investigate the immunity impact of medications. SEIPR epidemiological model is incorporated with MDR-TB for compartments susceptible to disease, exposed to risk, infected ones, preventive or resistant to initial treatment, and recovered or healed population. These masses' natural trends, effects, and interactions are formulated and described in the present study. Computations and stability analysis are conducted upon endemic and disease-free equilibria in the present model for their global scenario. Both numerical and AI-based nonlinear autoregressive exogenous NARX analyses are presented with incorporating immediate treatment and delay in treatment. This study shows that the active patients and MDR-TB, both strains, exist because of the absence of permanent immunity to T.B. Furthermore, patients who have recovered from tuberculosis may become susceptible again by losing their immunity and contributing to transmission again. This article aims to identify patterns and predictors of treatment success. The findings from this research can contribute to developing more effective tuberculosis interventions.

Iterative Data-adaptive Autoregressive (IDAR) whitening procedure for long and short TR fMRI.

Introduction: Functional magnetic resonance imaging (fMRI) has become a fundamental tool for studying brain function. However, the presence of serial correlations in fMRI data complicates data analysis, violates the statistical assumptions of analyses methods, and can lead to incorrect conclusions in fMRI studies. Methods: In this paper, we show that conventional whitening procedures designed for data with longer repetition times (TRs) (>2 s) are inadequate for the increasing use of short-TR fMRI data. Furthermore, we comprehensively investigate the shortcomings of existing whitening methods and introduce an iterative whitening approach named "IDAR" (Iterative Data-adaptive Autoregressive model) to address these shortcomings. IDAR employs high-order autoregressive (AR) models with flexible and data-driven orders, offering the capability to model complex serial correlation structures in both short-TR and long-TR fMRI datasets. Results: Conventional whitening methods, such as AR(1), ARMA(1,1), and higher-order AR, were effective in reducing serial correlation in long-TR data but were largely ineffective in even reducing serial correlation in short-TR data. In contrast, IDAR significantly outperformed conventional methods in addressing serial correlation, power, and Type-I error for both long-TR and especially short-TR data. However, IDAR could not simultaneously address residual correlations and inflated Type-I error effectively. Discussion: This study highlights the urgent need to address the problem of serial correlation in short-TR (< 1 s) fMRI data, which are increasingly used in the field. Although IDAR can address this issue for a wide range of applications and datasets, the complexity of short-TR data necessitates continued exploration and innovative approaches. These efforts are essential to simultaneously reduce serial correlations and control Type-I error rates without compromising analytical power.

A Multidimensional Health Indicator Based on Autoregressive Power Spectral Density for Machine Condition Monitoring.

Condition monitoring (CM) is the basis of prognostics and health management (PHM), which is gaining more and more importance in the industrial world. CM, which refers to the tracking of industrial equipment's state of health during operations, plays, in fact, a significant role in the reliability, safety, and efficiency of industrial operations. This paper proposes a data-driven CM approach based on the autoregressive (AR) modeling of the acquired sensor data and their analysis within frequency subbands. The number and size of the bands are determined with negligible human intervention, analyzing only the time-frequency representation of the signal of interest under normal system operating conditions. In particular, the approach exploits the synchrosqueezing transform to improve the signal energy distribution in the time-frequency plane, defining a multidimensional health indicator built on the basis of the AR power spectral density and the symmetric Itakura-Saito spectral distance. The described health indicator proved capable of detecting changes in the signal spectrum due to the occurrence of faults. After the initial definition of the bands and the calculation of the characteristics of the nominal AR spectrum, the procedure requires no further intervention and can be used for online condition monitoring and fault diagnosis. Since it is based on the comparison of spectra under different operating conditions, its applicability depends neither on the nature of the acquired signal nor on a specific system to be monitored. As an example, the effectiveness of the proposed method was favorably tested using real data available in the Case Western Reserve University (CWRU) Bearing Data Center, a widely known and used benchmark.

Forecasting the consumptions of coagulation tests using a deep learning model.

Background: Laboratory professionals aim to provide a reliable laboratory service using public resources efficiently while planning a test's procurement. This intuitive approach is ineffective, as seen in the COVID-19 pandemic, where the dramatic changes in admissions (e.g. decreased patient admissions) and the purpose of testing (e.g. D-dimer) were experienced. A model based on objective data was developed that predicts the future test consumption of coagulation tests whose consumptions were highly variable during the pandemic. Methods: Between December 2018 and July 2021, monthly consumptions of coagulation tests (PTT, aPTT, D-dimer, fibrinogen), total-, inpatient-, outpatient-, emergency-, non-emergency -admission numbers were collected. The relationship between input and output is modeled with an external input nonlinear autoregressive artificial neural network (NARX) using the MATLAB program. Monthly test consumption between January and July 2021 was used to test the power of the forecasting model.

Independent Vector Analysis for Feature Extraction in Motor Imagery Classification.

Independent vector analysis (IVA) can be viewed as an extension of independent component analysis (ICA) to multiple datasets. It exploits the statistical dependency between different datasets through mutual information. In the context of motor imagery classification based on electroencephalogram (EEG) signals for the brain-computer interface (BCI), several methods have been proposed to extract features efficiently, mainly based on common spatial patterns, filter banks, and deep learning. However, most methods use only one dataset at a time, which may not be sufficient for dealing with a multi-source retrieving problem in certain scenarios. From this perspective, this paper proposes an original approach for feature extraction through multiple datasets based on IVA to improve the classification of EEG-based motor imagery movements. The IVA components were used as features to classify imagined movements using consolidated classifiers (support vector machines and K-nearest neighbors) and deep classifiers (EEGNet and EEGInception). The results show an interesting performance concerning the clustering of MI-based BCI patients, and the proposed method reached an average accuracy of 86.7%.