Decoding Electroencephalography Signal Response by Stacking Ensemble Learning and Adaptive Differential Evolution.

Electroencephalography (EEG) is an exam widely adopted to monitor cerebral activities regarding external stimuli, and its signals compose a nonlinear dynamical system. There are many difficulties associated with EEG analysis. For example, noise can originate from different disorders, such as muscle or physiological activity. There are also artifacts that are related to undesirable signals during EEG recordings, and finally, nonlinearities can occur due to brain activity and its relationship with different brain regions. All these characteristics make data modeling a difficult task. Therefore, using a combined approach can be the best solution to obtain an efficient model for identifying neural data and developing reliable predictions. This paper proposes a new hybrid framework combining stacked generalization (STACK) ensemble learning and a differential-evolution-based algorithm called Adaptive Differential Evolution with an Optional External Archive (JADE) to perform nonlinear system identification. In the proposed framework, five base learners, namely, eXtreme Gradient Boosting, a Gaussian Process, Least Absolute Shrinkage and Selection Operator, a Multilayer Perceptron Neural Network, and Support Vector Regression with a radial basis function kernel, are trained. The predictions from all these base learners compose STACK's layer-0 and are adopted as inputs of the Cubist model, whose hyperparameters were obtained by JADE. The model was evaluated for decoding the electroencephalography signal response to wrist joint perturbations. The variance accounted for (VAF), root-mean-squared error (RMSE), and Friedman statistical test were used to validate the performance of the proposed model and compare its results with other methods in the literature, including the base learners. The JADE-STACK model outperforms the other models in terms of accuracy, being able to explain around, as an average of all participants, 94.50% and 67.50% (standard deviations of 1.53 and 7.44, respectively) of the data variability for one step ahead and three steps ahead, which makes it a suitable approach to dealing with nonlinear system identification. Also, the improvement over state-of-the-art methods ranges from 0.6% to 161% and 43.34% for one step ahead and three steps ahead, respectively. Therefore, the developed model can be viewed as an alternative and additional approach to well-established techniques for nonlinear system identification once it can achieve satisfactory results regarding the data variability explanation.

Multi-step ahead meningitis case forecasting based on decomposition and multi-objective optimization methods.

Epidemiological time series forecasting plays an important role in health public systems, due to its ability to allow managers to develop strategic planning to avoid possible epidemics. In this paper, a hybrid learning framework is developed to forecast multi-step-ahead (one, two, and three-month-ahead) meningitis cases in four states of Brazil. First, the proposed approach applies an ensemble empirical mode decomposition (EEMD) to decompose the data into intrinsic mode functions and residual components. Then, each component is used as the input of five different forecasting models, and, from there, forecasted results are obtained. Finally, all combinations of models and components are developed, and for each case, the forecasted results are weighted integrated (WI) to formulate a heterogeneous ensemble forecaster for the monthly meningitis cases. In the final stage, a multi-objective optimization (MOO) using the Non-Dominated Sorting Genetic Algorithm - version II is employed to find a set of candidates' weights, and then the Technique for Order of Preference by similarity to Ideal Solution (TOPSIS) is applied to choose the adequate set of weights. Next, the most adequate model is the one with the best generalization capacity out-of-sample in terms of performance criteria including mean absolute error (MAE), relative root mean squared error (RRMSE), and symmetric mean absolute percentage error (sMAPE). By using MOO, the intention is to enhance the performance of the forecasting models by improving simultaneously their accuracy and stability measures. To access the model's performance, comparisons based on metrics are conducted with: (i) EEMD, heterogeneous ensemble integrated by direct strategy, or simple sum; (ii) EEMD, homogeneous ensemble of components WI; (iii) models without signal decomposition. At this stage, MAE, RRMSE, and sMAPE criteria as well as Diebold-Mariano statistical test are adopted. In all twelve scenarios, the proposed framework was able to perform more accurate and stable forecasts, which showed, on 89.17% of the cases, that the errors of the proposed approach are statistically lower than other approaches. These results showed that combining EEMD, heterogeneous ensemble and WI with weights obtained by optimization can develop precise and stable forecasts. The modeling developed in this paper is promising and can be used by managers to support decision making.

Forecasting Brazilian and American COVID-19 cases based on artificial intelligence coupled with climatic exogenous variables.

The novel coronavirus disease (COVID-19) is a public health problem once according to the World Health Organization up to June 24th, 2020, more than 9.1 million people were infected, and more than 470 thousand have died worldwide. In the current scenario, the Brazil and the United States of America present a high daily incidence of new cases and deaths. Therefore, it is important to forecast the number of new cases in a time window of one week, once this can help the public health system developing strategic planning to deals with the COVID-19. The application of the forecasting artificial intelligence (AI) models has the potential of deal with dynamical behavior of time-series like of COVID-19. In this paper, Bayesian regression neural network, cubist regression, k-nearest neighbors, quantile random forest, and support vector regression, are used stand-alone, and coupled with the recent pre-processing variational mode decomposition (VMD) employed to decompose the time series into several intrinsic mode functions. All AI techniques are evaluated in the task of time-series forecasting with one, three, and six-days-ahead the cumulative COVID-19 cases in five Brazilian and American states, with a high number of cases up to April 28th, 2020. Previous cumulative COVID-19 cases and exogenous variables as daily temperature and precipitation were employed as inputs for all forecasting models. The models' effectiveness are evaluated based on the performance criteria. In general, the hybridization of VMD outperformed single forecasting models regarding the accuracy, specifically when the horizon is six-days-ahead, the hybrid VMD-single models achieved better accuracy in 70% of the cases. Regarding the exogenous variables, the importance ranking as predictor variables is, from the upper to the lower, past cases, temperature, and precipitation. Therefore, due to the efficiency of evaluated models to forecasting cumulative COVID-19 cases up to six-days-ahead, the adopted models can be recommended as a promising models for forecasting and be used to assist in the development of public policies to mitigate the effects of COVID-19 outbreak.

Short-term forecasting COVID-19 cumulative confirmed cases: Perspectives for Brazil.

The new Coronavirus (COVID-19) is an emerging disease responsible for infecting millions of people since the first notification until nowadays. Developing efficient short-term forecasting models allow forecasting the number of future cases. In this context, it is possible to develop strategic planning in the public health system to avoid deaths. In this paper, autoregressive integrated moving average (ARIMA), cubist regression (CUBIST), random forest (RF), ridge regression (RIDGE), support vector regression (SVR), and stacking-ensemble learning are evaluated in the task of time series forecasting with one, three, and six-days ahead the COVID-19 cumulative confirmed cases in ten Brazilian states with a high daily incidence. In the stacking-ensemble learning approach, the CUBIST regression, RF, RIDGE, and SVR models are adopted as base-learners and Gaussian process (GP) as meta-learner. The models' effectiveness is evaluated based on the improvement index, mean absolute error, and symmetric mean absolute percentage error criteria. In most of the cases, the SVR and stacking-ensemble learning reach a better performance regarding adopted criteria than compared models. In general, the developed models can generate accurate forecasting, achieving errors in a range of 0.87%-3.51%, 1.02%-5.63%, and 0.95%-6.90% in one, three, and six-days-ahead, respectively. The ranking of models, from the best to the worst regarding accuracy, in all scenarios is SVR, stacking-ensemble learning, ARIMA, CUBIST, RIDGE, and RF models. The use of evaluated models is recommended to forecasting and monitor the ongoing growth of COVID-19 cases, once these models can assist the managers in the decision-making support systems.

Ethyl-acetate fraction of Trichilia catigua protects against oxidative stress and neuroinflammation after cerebral ischemia/reperfusion.

ETHNOPHARMACOLOGICAL RELEVANCE: Trichilia catigua A. Juss (Meliaceae) preparations have been used in folk medicine to alleviate fatigue, stress, and improve memory. Antinociceptive, antiinflammatory, and in vitro neuroprotective effects have been observed in animals. Cerebral ischemia/reperfusion (I/R) leads to severe neuropsychological deficits that are largely associated with oxidative stress, inflammation and neurodegeneration. We reported previously that an ethyl-acetate fraction (EAF) of T. catigua reduced brain ischemia-induced learning and memory impairments in the absence of histological protection. AIM OF THE STUDY: Continuing those studies, here we aimed to investigate the antioxidant and antiinflammatory properties of T. catigua in an in vivo model of I/R. MATERIAL AND METHODS: Rats were subjected to 15 min of brain ischemia (4-VO model) followed by up to 15 days of reperfusion. Vehicle was given by gavage 30 min before ischemia and at 1 h of reperfusion. In a first experiment, brain ischemia-induced changes in oxidative stress markers, i.e., reduced glutathione (GSH), oxidized glutathione (GSSG), superoxide dismutase (SOD), catalase (CAT), malondialdehyde (MDA), and protein carbonyl groups (PCGs) were measured on days 1, 3, and 5 post-ischemia. Similar time course analysis was done for neuroinflammation markers, i.e., microglia (OX42 immunorreactivity) and astrocytes (GFAP immunorreactivity), in the hippocampus. In a second experiment, the time points at which these markers of oxidative stress and neuroinflammation peaked were used to test the effects of T. catigua (400 mg/kg, p.o.). RESULTS: Oxidative stress markers peaked on day 1 post-ischemia. GSH decreased (-23.2%) while GSSG increased (+ 71.1%), which yielded a significant reduction in the GSH/GSSG ratio (-39.1%). The activity of CAT was largely reduced by ischemia (-54.6% to -65.1%), while the concentration of PCG almost doubled in the brain of ischemic rats (+99.10%) in comparison to sham. Treatment with the EAF of T. catigua normalized these changes in oxidative markers to the control levels (GSH: +27.5%; GSSG: -23.8%; GSH/GSSG: +44.6%; PCG: -80.3%). In the hippocampus, neuroinflammation markers peaked on day 5 post-ischemia, with microglial and astrocytic responses increasing to 54.8% and 37.1%, respectively. The elevation in glial cells response was completely prevented by EAF. CONCLUSION: These results demonstrate that T. catigua has both antioxidant and antiinflammatory activities after transient global cerebral ischemia in rats, which may contribute to the previously reported memory protective effect of T. catigua.

Three-dimensional analysis of the pharyngeal airway space and hyoid bone position after orthognathic surgery.

PURPOSE: The aim of this study was to evaluate changes in the pharyngeal airway space (PAS) and hyoid bone position after orthognathic surgery with cone-beam computed tomography (CBCT). MATERIAL AND METHODS: This study was conducted with the tomographic records of 30 patients with skeletal class II or III deformities submitted to two different types of orthognathic surgery: Group 1 (n = 15), maxillary advancement, and mandibular setback; and Group 2 (n = 15), maxillomandibular advancement. CBCT scans were acquired preoperatively (T0); and at around 1.5 months (T1) and 6.7 months (T2) postoperatively. PAS volume, minimum cross-sectional area (min CSA), and hyoid bone position changes were assessed with Dolphin Imaging 3D software, and results analyzed with ANOVA and a Tukey-Kramer test (p < 0.05). RESULTS: The hyoid bone was significantly displaced in the horizontal dimension, moving posteriorly in Group 1, and anteriorly in Group 2. Although PAS volume and min CSA increased after both surgeries, these measurements were significantly larger only in Group 2. The significant differences that existed between groups preoperatively no longer existed after the surgeries. CONCLUSIONS: Both orthognathic surgeries assessed resulted in changes in hyoid bone position and increased PAS volume and min CSA, particularly after maxillomandibular advancement surgery.

Postischemic fish oil treatment restores long-term retrograde memory and dendritic density: An analysis of the time window of efficacy.

We reported that fish oil (FO) prevented the loss of spatial memory caused by transient, global cerebral ischemia (TGCI), provided the treatment covered the first days prior to and after ischemia. Continuing these studies, trained rats were subjected to TGCI, and FO was administered for 10days, with a time window of efficacy (TWE) of 4, 8 or 12h post-ischemia. Retrograde memory was assessed up to 43days after TGCI. In another experiment, ischemic rats received FO with a 4- or 12-h TWE, and dendritic density was assessed in the hippocampus and cerebral cortex. The brain lipid profile was evaluated in sham-operated and ischemic rats that were treated with FO or vehicle with a 4-h TWE. Ischemia-induced retrograde amnesia was prevented by FO administration that was initiated with either a 4- or 8-h TWE. Fish oil was ineffective after a 12-h TWE. Independent of the TWE, FO did not prevent ischemic neuronal death. In the hippocampus, but not cerebral cortex, TGCI-induced dendritic loss was prevented by FO with a 4-h TWE but not 12-h TWE. The level of docosahexaenoic acid almost doubled in the hippocampus in ischemic, FO-treated rats (4-h TWE). The data indicate that (i) the anti-amnesic effect of FO can be observed with a TWE of up to 8h, (ii) the stimulation of dendritic neuroplasticity may have contributed to this effect, and (iii) DHA in FO may be the main active constituent in FO that mediates the cognitive and neuroplasticity effects on TGCI.

Robust and enduring atorvastatin-mediated memory recovery following the 4-vessel occlusion/internal carotid artery model of chronic cerebral hypoperfusion in middle-aged rats.

Chronic cerebral hypoperfusion (CCH) is a common condition associated with the development and/or worsening of age-related dementia.We previously reported persistent memory loss and neurodegeneration after CCH in middle-aged rats. Statin-mediated neuroprotection has been reported after acute cerebral ischemia. Unknown, however, is whether statins can alleviate the outcome of CCH. The present study investigated whether atorvastatin attenuates the cognitive and neurohistological outcome of CCH. Rats (12­15 months old) were trained in a non-food-rewarded radial maze, and then subjected to CCH. Atorvastatin (10 mg/kg, p.o.) was administered for 42 days or 15 days, beginning 5 h after the first occlusion stage. Retrograde memory performance was assessed at 7, 14, 21, 28, and 35 days of CCH, and expressed by "latency," "number of reference memory errors" and "number of working memory errors." Neurodegeneration was then examined at the hippocampus and cerebral cortex. Compared to sham, CCH caused profound and persistent memory loss in the vehicle-treated groups, as indicated by increased latency (91.2% to 107.3%) and number of errors (123.5% to 2508.2%), effects from which the animals did not spontaneously recover across time. This CCH-induced retrograde amnesia was completely prevented by atorvastatin (latency: −4.3% to 3.3%; reference/working errors: −2.5% to 45.7%), regardless of the treatment duration. This effect was sustained during the entire behavioral testing period (5 weeks), even after discontinuing treatment. This robust and sustained memory-protective effect of atorvastatin occurred in the absence of neuronal rescue (39.58% to 56.45% cell loss). We suggest that atorvastatin may be promising for the treatment of cognitive sequelae associated with CCH.