Addressing data limitations in seizure prediction through transfer learning.

According to the literature, seizure prediction models should be developed following a patient-specific approach. However, seizures are usually very rare events, meaning the number of events that may be used to optimise seizure prediction approaches is limited. To overcome such constraint, we analysed the possibility of using data from patients from an external database to improve patient-specific seizure prediction models. We present seizure prediction models trained using a transfer learning procedure. We trained a deep convolutional autoencoder using electroencephalogram data from 41 patients collected from the EPILEPSIAE database. Then, a bidirectional long short-term memory and a classifier layers were added on the top of the encoder part and were optimised for 24 patients from the Universitätsklinikum Freiburg individually. The encoder was used as a feature extraction module. Therefore, its weights were not changed during the patient-specific training. Experimental results showed that seizure prediction models optimised using pretrained weights present about four times fewer false alarms while maintaining the same ability to predict seizures and achieved more 13% validated patients. Therefore, results evidenced that the optimisation using transfer learning was more stable and faster, saving computational resources. In summary, adopting transfer learning for seizure prediction models represents a significant advancement. It addresses the data limitation seen in the seizure prediction field and offers more efficient and stable training, conserving computational resources. Additionally, despite the compact size, transfer learning allows to easily share data knowledge due to fewer ethical restrictions and lower storage requirements. The convolutional autoencoder developed in this study will be shared with the scientific community, promoting further research.

Relationship between Bioelectrical Impedance Phase Angle and Upper and Lower Limb Muscle Strength in Athletes from Several Sports: A Systematic Review with Meta-Analysis.

The phase angle (PhA) of bioelectrical impedance is determined by primary factors such as age, body mass index and sex. The researchers' interest in applying PhA to better understand the skeletal muscle property and ability has grown, but the results are still heterogeneous. This systematic review with a meta-analysis aimed to examine the existence of the relationship between PhA and muscle strength in athletes. The data sources used were PubMed, Scielo, Scopus, SPORTDiscus, and Web of Science and the study eligibility criteria were based on the PECOS. The searches identified 846 titles. From those, thirteen articles were eligible. Results showed a positive correlation between PhA and lower limb strength (r = 0.691 [95% CI 0.249 to 0.895]; p = 0.005), while no meta-analysis was possible for the relationships between PhA and lower limb strength. Furthermore, GRADE shows very low certainty of evidence. In conclusion, it was found that most studies showed a positive correlation between PhA and vertical jump or handgrip strength. The meta-analysis showed the relationship between PhA and vertical jump, however, little is known for the upper limbs as was not possible to perform a meta-analysis, and for the lower limbs we performed it with four studies and only with vertical jump.

Removing artefacts and periodically retraining improve performance of neural network-based seizure prediction models.

The development of seizure prediction models is often based on long-term scalp electroencephalograms (EEGs) since they capture brain electrical activity, are non-invasive, and come at a relatively low-cost. However, they suffer from major shortcomings. First, long-term EEG is usually highly contaminated with artefacts. Second, changes in the EEG signal over long intervals, known as concept drift, are often neglected. We evaluate the influence of these problems on deep neural networks using EEG time series and on shallow neural networks using widely-used EEG features. Our patient-specific prediction models were tested in 1577 hours of continuous EEG, containing 91 seizures from 41 patients with temporal lobe epilepsy who were undergoing pre-surgical monitoring. Our results showed that cleaning EEG data, using a previously developed artefact removal method based on deep convolutional neural networks, improved prediction performance. We also found that retraining the models over time reduced false predictions. Furthermore, the results show that although deep neural networks processing EEG time series are less susceptible to false alarms, they may need more data to surpass feature-based methods. These findings highlight the importance of robust data denoising and periodic adaptation of seizure prediction models.

The goal of explaining black boxes in EEG seizure prediction is not to explain models' decisions.

Many state-of-the-art methods for seizure prediction, using the electroencephalogram, are based on machine learning models that are black boxes, weakening the trust of clinicians in them for high-risk decisions. Seizure prediction concerns a multidimensional time-series problem that performs continuous sliding window analysis and classification. In this work, we make a critical review of which explanations increase trust in models' decisions for predicting seizures. We developed three machine learning methodologies to explore their explainability potential. These contain different levels of model transparency: a logistic regression, an ensemble of 15 support vector machines, and an ensemble of three convolutional neural networks. For each methodology, we evaluated quasi-prospectively the performance in 40 patients (testing data comprised 2055 hours and 104 seizures). We selected patients with good and poor performance to explain the models' decisions. Then, with grounded theory, we evaluated how these explanations helped specialists (data scientists and clinicians working in epilepsy) to understand the obtained model dynamics. We obtained four lessons for better communication between data scientists and clinicians. We found that the goal of explainability is not to explain the system's decisions but to improve the system itself. Model transparency is not the most significant factor in explaining a model decision for seizure prediction. Even when using intuitive and state-of-the-art features, it is hard to understand brain dynamics and their relationship with the developed models. We achieve an increase in understanding by developing, in parallel, several systems that explicitly deal with signal dynamics changes that help develop a complete problem formulation.

Unsupervised EEG preictal interval identification in patients with drug-resistant epilepsy.

Typical seizure prediction models aim at discriminating interictal brain activity from pre-seizure electrographic patterns. Given the lack of a preictal clinical definition, a fixed interval is widely used to develop these models. Recent studies reporting preictal interval selection among a range of fixed intervals show inter- and intra-patient preictal interval variability, possibly reflecting the heterogeneity of the seizure generation process. Obtaining accurate labels of the preictal interval can be used to train supervised prediction models and, hence, avoid setting a fixed preictal interval for all seizures within the same patient. Unsupervised learning methods hold great promise for exploring preictal alterations on a seizure-specific scale. Multivariate and univariate linear and nonlinear features were extracted from scalp electroencephalography (EEG) signals collected from 41 patients with drug-resistant epilepsy undergoing presurgical monitoring. Nonlinear dimensionality reduction was performed for each group of features and each of the 226 seizures. We applied different clustering methods in searching for preictal clusters located until 2 h before the seizure onset. We identified preictal patterns in 90% of patients and 51% of the visually inspected seizures. The preictal clusters manifested a seizure-specific profile with varying duration (22.9 ± 21.0 min) and starting time before seizure onset (47.6 ± 27.3 min). Searching for preictal patterns on the EEG trace using unsupervised methods showed that it is possible to identify seizure-specific preictal signatures for some patients and some seizures within the same patient.

EPIC: Annotated epileptic EEG independent components for artifact reduction.

Scalp electroencephalogram is a non-invasive multi-channel biosignal that records the brain's electrical activity. It is highly susceptible to noise that might overshadow important data. Independent component analysis is one of the most used artifact removal methods. Independent component analysis separates data into different components, although it can not automatically reject the noisy ones. Therefore, experts are needed to decide which components must be removed before reconstructing the data. To automate this method, researchers have developed classifiers to identify noisy components. However, to build these classifiers, they need annotated data. Manually classifying independent components is a time-consuming task. Furthermore, few labelled data are publicly available. This paper presents a source of annotated electroencephalogram independent components acquired from patients with epilepsy (EPIC Dataset). This dataset contains 77,426 independent components obtained from approximately 613 hours of electroencephalogram, visually inspected by two experts, which was already successfully utilised to develop independent component classifiers.

Epileptic seizure prediction based on features extracted from lagged Poincaré plots.

OBJECTIVE: The present work proposes a new epileptic seizure prediction method based on lagged Poincaré plot analysis of heart rate (HR). METHODS: In this article, the Poincaré plots with six different lags (1-6) were constructed for four episodes of heart rate variability (HRV) before the seizures. Moreover, two features were extracted based on lagged Poincare plots, which include the angle between the time series and the ellipse density fitted to the RR points. RESULTS: The proposed method was applied to 16 epileptic patients with 170 seizures. The results included sensitivity of 80.42% for the angle feature and 75.19% for the density feature. The false-positive rate was 0.15/Hr, which indicates that the system has superiority over the random predictor. CONCLUSION: The proposed HRV-based epileptic seizure prediction method has the potential to be used in daily life because HR can be measured easily by using a wearable sensor.

On the clinical acceptance of black-box systems for EEG seizure prediction.

Seizure prediction may be the solution for epileptic patients whose drugs and surgery do not control seizures. Despite 46 years of research, few devices/systems underwent clinical trials and/or are commercialized, where the most recent state-of-the-art approaches, as neural networks models, are not used to their full potential. The latter demonstrates the existence of social barriers to new methodologies due to data bias, patient safety, and legislation compliance. In the form of literature review, we performed a qualitative study to analyze the seizure prediction ecosystem to find these social barriers. With the Grounded Theory, we draw hypotheses from data, while with the Actor-Network Theory we considered that technology shapes social configurations and interests, being fundamental in healthcare. We obtained a social network that describes the ecosystem and propose research guidelines aiming at clinical acceptance. Our most relevant conclusion is the need for model explainability, but not necessarily intrinsically interpretable models, for the case of seizure prediction. Accordingly, we argue that it is possible to develop robust prediction models, including black-box systems to some extent, while avoiding data bias, ensuring patient safety, and still complying with legislation, if they can deliver human- comprehensible explanations. Due to skepticism and patient safety reasons, many authors advocate the use of transparent models which may limit their performance and potential. Our study highlights a possible path, by using model explainability, on how to overcome these barriers while allowing the use of more computationally robust models.

Interpretable EEG seizure prediction using a multiobjective evolutionary algorithm.

Seizure prediction might be the solution to tackle the apparent unpredictability of seizures in patients with drug-resistant epilepsy, which comprise about a third of all patients with epilepsy. Designing seizure prediction models involves defining the pre-ictal period, a transition stage between inter-ictal brain activity and the seizure discharge. This period is typically a fixed interval, with some recent studies reporting the evaluation of different patient-specific pre-ictal intervals. Recently, researchers have aimed to determine the pre-ictal period, a transition stage between regular brain activity and a seizure. Authors have been using deep learning models given the ability of such models to automatically perform pre-processing, feature extraction, classification, and handling temporal and spatial dependencies. As these approaches create black-box models, clinicians may not have sufficient trust to use them in high-stake decisions. By considering these problems, we developed an evolutionary seizure prediction model that identifies the best set of features while automatically searching for the pre-ictal period and accounting for patient comfort. This methodology provides patient-specific interpretable insights, which might contribute to a better understanding of seizure generation processes and explain the algorithm's decisions. We tested our methodology on 238 seizures and 3687 h of continuous data, recorded on scalp recordings from 93 patients with several types of focal and generalised epilepsies. We compared the results with a seizure surrogate predictor and obtained a performance above chance for 32% patients. We also compared our results with a control method based on the standard machine learning pipeline (pre-processing, feature extraction, classifier training, and post-processing), where the control marginally outperformed our approach by validating 35% of the patients. In total, 54 patients performed above chance for at least one method: our methodology or the control one. Of these 54 patients, 21 ([Formula: see text]38%) were solely validated by our methodology, while 24 ([Formula: see text]44%) were only validated by the control method. These findings may evidence the need for different methodologies concerning different patients.

Ensemble Deep Neural Network for Automatic Classification of EEG Independent Components.

OBJECTIVE: Independent component analysis (ICA) is commonly used to remove noisy artifacts from multi-channel scalp electroencephalogram (EEG) signals. ICA decomposes EEG into different independent components (ICs) and then, experts remove the noisy ones. This process is highly time-consuming and experts are not always available. To surpass this drawback, research is going on to develop models to automatically conduct IC classification. Current state-of-the-art models use power spectrum densities (PSDs) and topoplots to classify ICs. The performance of these methods may be limited by disregarding the IC time-series that would contribute to fully simulate the visual inspection performed by experts. METHODS: We present a novel ensemble deep neural network that combines time-series, PSDs, and topoplots to classify ICs. Moreover, we study the ability to use our model in transfer learning approaches. RESULTS: Experimental results showed that using time-series improves IC classification. Results also indicated that transfer learning obtained higher performance than simply training a new model from scratch. CONCLUSION: Researchers should develop IC classifiers using the three sources of information. Moreover, transfer learning approaches should be considered when producing new deep learning models. SIGNIFICANCE: This work improves IC classification, enhancing the automatic removal of EEG artifacts. Additionally, since labelled ICs are generally not publicly available, the possibility of using our model in transfer learning studies may motivate other researchers to develop their own classifiers.

Can a genetic profile be related to performance in young talent track and field athletes? A pilot study

Abstract Aim: This study analyzed the influences of ACE and ACTN3 gene variants in sprinters, jumpers, and endurance young athletes of track and field. Methods: 36 school-level competitors of both sex (15 girls and 21 boys; aged 16.4 ± 1.2 years; training experience 4 ± 1.2 years) practitioners of different sport disciplines (i.e., sprint, jump, and endurance athletes) participated in the study. The deoxyribonucleic acid (DNA) was extracted from peripheral blood using a standard protocol. Anthropometric measurements, 30 m sprint, squat jump (SJ), and maximal oxygen uptake (VO2max) tests were measured. Results: Genotype distribution of the ACE and ACTN3 genes did not differ between groups. In ACE DD and ACTN3 RX genotypes, the SJ test was bigger in sprinters and jumpers than in the endurance runners. In contrast, when analyzing the ACE ID genotype, sprinters had higher SJ than endurance athletes. Moreover, in the ACE DD genotype, the sprinters and jumpers' athletes had lower time in 30 m tests compared to endurance runners. However, the ACE ID and ACTN3 RX genotypes was greater aerobic fitness in endurance runners than in jumpers' athletes. Conclusion: Although the genetic profile is not a unique factor for determining athletic performance, the ACE DD and ACTN3 RX genotypes seem to favor athletic performance in power and sprint versus endurance sports. Thus, this study evidenced that assessing genetic variants could be used as an auxiliary way to predict a favorable profile for the identification of young talents of track and field.

Heart rate variability analysis for the identification of the preictal interval in patients with drug-resistant epilepsy.

Electrocardiogram (ECG) recordings, lasting hours before epileptic seizures, have been studied in the search for evidence of the existence of a preictal interval that follows a normal ECG trace and precedes the seizure's clinical manifestation. The preictal interval has not yet been clinically parametrized. Furthermore, the duration of this interval varies for seizures both among patients and from the same patient. In this study, we performed a heart rate variability (HRV) analysis to investigate the discriminative power of the features of HRV in the identification of the preictal interval. HRV information extracted from the linear time and frequency domains as well as from nonlinear dynamics were analysed. We inspected data from 238 temporal lobe seizures recorded from 41 patients with drug-resistant epilepsy from the EPILEPSIAE database. Unsupervised methods were applied to the HRV feature dataset, thus leading to a new perspective in preictal interval characterization. Distinguishable preictal behaviour was exhibited by 41% of the seizures and 90% of the patients. Half of the preictal intervals were identified in the 40 min before seizure onset. The results demonstrate the potential of applying clustering methods to HRV features to deepen the current understanding of the preictal state.

A personalized and evolutionary algorithm for interpretable EEG epilepsy seizure prediction.

Seizure prediction may improve the quality of life of patients suffering from drug-resistant epilepsy, which accounts for about 30% of the total epileptic patients. The pre-ictal period determination, characterized by a transitional stage between normal brain activity and seizure, is a critical step. Past approaches failed to attain real-world applicability due to lack of generalization capacity. More recently, deep learning techniques may outperform traditional classifiers and handle time dependencies. However, despite the existing efforts for providing interpretable insights, clinicians may not be willing to make high-stake decisions based on them. Furthermore, a disadvantageous aspect of the more usual seizure prediction pipeline is its modularity and significant independence between stages. An alternative could be the construction of a search algorithm that, while considering pipeline stages' synergy, fine-tunes the selection of a reduced set of features that are widely used in the literature and computationally efficient. With extracranial recordings from 19 patients suffering from temporal-lobe seizures, we developed a patient-specific evolutionary optimization strategy, aiming to generate the optimal set of features for seizure prediction with a logistic regression classifier, which was tested prospectively in a total of 49 seizures and 710 h of continuous recording and performed above chance for 32% of patients, using a surrogate predictor. These results demonstrate the hypothesis of pre-ictal period identification without the loss of interpretability, which may help understanding brain dynamics leading to seizures and improve prediction algorithms.

Dose-Response Relationship Between Internal Training Load and Changes in Performance During the Preseason in Youth Soccer Players.

ABSTRACT: Figueiredo, DH, Figueiredo, DH, Moreira, A, Gonçalves, HR, and Dourado, AC. Dose-response relationship between internal training load and changes in performance during the preseason in youth soccer players. J Strength Cond Res 35(8): 2294-2301, 2021-The aim of this study was to describe training intensity distribution based on the session rating of perceived exertion (sRPE) and heart rate (HR) methods and examine the dose-response relation between internal training load (ITL) and change in performance of 16 youth soccer players (mean ± SD age: 18.75 ± 0.68 years, height: 175.3 ± 5.5 cm, body mass: 68.7 ± 6.5 kg, and body fat: 10.7 ± 1.2%) belonging to a Brazilian first division team during a 3-week preseason. The sRPE and HR data were registered daily to calculate the ITL and the training intensity distribution, in 3 intensity zones (low, moderate, and high). The Yo-yo Intermittent Recovery Level 1 (Yo-yo IR1) was evaluated before and after experimental period. The total time spent in the low-intensity zone (HR method) was greater (p < 0.01) compared with the moderate- and high-intensity zones. No difference was observed between training intensity zones determined by the sRPE method (p > 0.05). Negative correlations were observed between weekly mean sRPE-TL (r = -0.69), Edward's-TL (r = -0.50), and change in Yo-yo IR1. Linear regression indicated that weekly mean sRPE-TL (F1;14 = 13.3; p < 0.01) and Edward's-TL (F1;14 = 4.8; p < 0.05) predicted 48.7 and 25.5% of the variance in performance change, respectively. Stepwise linear regression revealed that these 2-predictor variables (F2;13 = 18.9; p < 0.001) explained 74.5% of the variance in performance change. The results suggest that the sRPE and HR methods cannot be used interchangeably to determine training intensity distribution. Moreover, sRPE-TL seems to be more effective than the HR-based TL method to predict changes in performance in youth soccer players.

Motives of participation in Paraná School Games of students-athlets in Brazil / Motivos de participación en los Juegos Escolares de Paraná de estudiantes-atletas en Brasil / Motivos de participação nos Jogos Escolares do Paraná de estudantes-atletas no Brasil

A sports practice for young people has been shown as an important tool in searching for physical, psychological and social benefits. However, some international surveys pointed out that only one part of the children and youths practice sports with some regularity, and that those who start a sports practice, there is a high rate of abandonment. In this sense, experts point out that understanding the reasons that lead to a sport practice can be an important way to understand this phenomenon, especially for the school athlete. Thua, the objective of this study was to identify the reasons for sports practice of school athletes in different sports modalities participating in the School Games of Paraná - 2016 and the variables, gender, age, and training time. In total, 2014 school athletes (1050 girls and 964 boys), aged 10 to 17, participated in the study. The results demonstrate that school athletes gave greatest importance to aspects related to improvement in technical skills, tackling challenges and exposure to risks, learning new skills, and moving to a higher level

Algunos levantamientos han señalado que sólo una parte de la población juvenil practica deporte con cierta regularidad, y entre aquellos que inician la práctica deportiva, existe un elevado índice de casos de abandono. En ese sentido, los expertos apuntan que entender los motivos que llevan a la práctica del deporte puede ser un importante camino para el entendimiento de este fenómeno, principalmente para el atleta escolar. Así, el objetivo de este estudio fue identificar los motivos para la práctica del deporte de atletas escolares participantes en los Juegos Escolares de Paraná -2016 y las variables, sexo, edad y tiempo de entrenamiento. Participaron del estudio 2014 atletas. Los resultados demuestran que los atletas escolares asignaron mayor importancia a aspectos equivalentes a las razones relacionadas con el perfeccionamiento de las habilidades técnicas, el enfrentamiento de desafíos y exposición de riesgos, aprender nuevas habilidades y seguir hacia un alto nivel

Alguns levantamentos têm apontado que apenas uma parcela da população infantil e juvenil pratica esporte com alguma regularidade, e dentre aqueles que iniciam a prática esportiva, existe um elevado índice de casos de abandono. Nesse sentindo, especialistas apontam que entender os motivos que levam a prática de esporte pode ser um importante caminho para o entendimento deste fenômeno, principalmente para o atleta escolar. Assim, o objetivo desse estudo foi identificar os motivos para a prática de esporte de atletas escolares participantes dos Jogos Escolares do Paraná -2016 e as variáveis, sexo, idade e tempo de treino. Participaram do estudo 2014 atletas escolares. Os resultados demonstram que os atletas escolares atribuíram maior importância para aspectos equivalentes às razões relacionadas ao aprimoramento das habilidades técnicas, ao enfrentamento de desafios e exposição de riscos, aprender novas habilidades e seguir para um alto nível

Coaches' and young soccer players' training load perceptions during different training phases / Percepciones de la carga de entrenamiento de entrenadores y jóvenes jugadores de fútbol durante diferentes fases de entrenamiento / Percepção da carga de treinamento de técnicos e jovens jogadores de futebol durante diferentes fases de treinamento

OBJECTIVE: To our Knowledge, information about the agreement between coaches and the young soccer players' session rating of perceived exertion is not consistent during specific periods of training (intensification and taper) and has not been established. The purpose of this study was to examine and compare the internal training load and session rating of perceived exertion between coaches' and young soccer players' during three weeks in different training phases. METHOD: Participants were 16 male elite Under19 soccer players and their coaches. Before each training session, the coaches reported a session rating of perceived exertion using the Borg CR-10 scale as well as the planned duration (min) of the training based on prior planning, while the athletes responded the scale after each training session. RESULTS: No differences in intensity session rating of perceived exertion (t = 0.49; p = 0.62) and training load (t = 0.18; p = 0.86) were observed between coaches and players during the training period analyzed. During different training phases, no significant differences were found during intensification (t = 0.18; p = 0.85) and taper (t = -0.19; p = 0.85) in training loads and in the session rating of perceived exertion prescribed by coaches and perceived by players. A very large correlation was observed between coaches training load (r= 0.84) and players training load. However, a trivial correlation was found between players training load and changes in the Yo-yo IR1 performance (r= -0.09), age (r= -0.06) and years of competitive experience (r= -0.08). Stepwise linear regression revealed that coaches training load (F1; 238= 582.7; R2= 0.710; p < 0.001) explained 71% of the variance in players training load. CONCLUSION: The results suggest that the session rating of perceived exertion and training load prescribed during three weeks in different training phases (by coaches) was not different from perceived by young soccer players. Moreover, coaches training load seem to be effective to predict the training load in soccer players

OBJETIVO: En nuestro conocimiento, la información sobre la concordáncia entre la percepción subjetiva del esfuerzo durante el entrenamiento de entrenadores y de jóvenes julgadores de fútbol, durante los períodos específicos de entrenamiento (intensificación y reducción de cargas), no se ha establecido. El propósito de este estudio fue examinar y comparar la carga interna de entrenamiento y la percepción subjetiva del esfuerzo durante el entrenamiento entre los entrenadores y jóvenes jugadores de fútbol durante tres semanas en diferentes fases de formación. MÉTODO: Participaron 16 jugadores de fútbol sub19 y sus entrenadores. Antes de cada sesión de entrenamiento, los entrenadores informaron una clasificación del esfuerzo de sesión percibido usando la escala Borg CR-10 así como la duración planificada (min) de la capacitación basada en la planificación previa, mientras que los atletas respondieron la escala después de cada sesión de entrenamiento. RESULTADOS: No se observaron diferencias en la percepción subjetiva del esfuerzo durante el entrenamiento (t = 0.49; p = 0.62) y la carga de entrenamiento (t = 0.18; p = 0.86) entre el entrenador y los jugadores durante el período de entrenamiento analizado. Durante las diferentes fases de entrenamiento no se encontraron diferencias significativas durante la intensificación (t = 0.18; p = 0.85) ni la reducción de cargas (t = -0.19; p = 0.85), en las cargas de entrenamiento y en la percepción subjetiva del esfuerzo, durante el entrenamiento prescrito por el entrenador y percibido por los julgadores. Se observaron correlaciones muy grandes entre la carga de entrenamiento de los entrenadores (r = 0.84) y la carga de entrenamiento de los jugadores. Sin embargo, se encontró una correlación trivial entre la carga de entrenamiento de los jugadores y los cambios en el rendimiento del Yo-yo IR1 (r = -0.09), edad (r = -0.06) y años de experiencia competitiva (r = -0.08). La regresión lineal múltiple reveló que la carga de entrenamiento de los entrenadores (F1; 238 = 582.7, R2 = 0.710, p <0.001) explicó el 71% de la varianza en la carga de entrenamiento de los jugadores. CONCLUSIONES: Los resultados sugieren que la percepción subjetiva del esfuerzo durante el entrenamiento prescrito durante tres semanas, en diferentes fases de entrenamiento, no fue diferente de lo percibido por los jugadores jóvenes de fútbol. Además, la carga de entrenamiento de los entrenadores parece ser eficaz para predecir la carga de entrenamiento en estos jugadores

OBJETIVO: Nenhum estudo examinou se a concordância entre a percepção subjetiva de esforço do treinador e de jovens jogadores de futebol é consistente durante períodos específicos de treinamento (intensificação e taper). O objetivo deste estudo foi examinar e comparar a carga interna de treinamento e a percepção subjetiva de esforço da sessão entre treinadores e jovens futebolistas durante três semanas em diferentes fases de treinamento. MÉTODOS: Participaram 16 jogadores de futebol sub-19 e seus treinadores. Antes de cada sessão de treinamento, os treinadores informaram uma classificação de esforço da sessão percebido usando a escala de BORG CR-10 assim como a duração planejada (min) do treinamento, enquanto os atletas responderam à escala após cada sessão de treinamento. RESULTADOS: Não foram observadas diferenças para a percepção subjetiva de esforço da sessão (t = 0.49; p = 0.62) e para a carga de treinamento (t = 0.18; p = 0.86) entre os técnicos e jogadores durante o período de treinamento analizado. Durante as diferentes fases de treinamento, não foram encontradas diferenças significantes durante a intensificação (t = 0.18; p = 0.85) e taper (t = -0.19; p = 0.85) na carga de treinamento e a percepção subjetiva de esforço da sessão prescrita pelos técnicos e a percebida pelos jogadores. Correlações muito grandes foram observadas entre a carga de treinamento dos treinadores (r= 0.84) e a carga de treinamento dos jogadores. No entanto, foi encontrada uma correlação trivial entre a carga de treinamento dos jogadores e as mudanças no desempenho do Yo-yo IR1 (r = -0.09), idade (r = -0.06) e anos de experiência competitiva (r = -0.08). A regressão linear múltipla revelou que a carga de treinamento dos treinadores (F1; 238 = 582.7; R2 = 0.710; p <0.001) explicou 71% da variância na carga de treinamento dos jogadores. CONCLUSÃO: Os resultados sugerem que, a percepção subjetiva de esforço da sessão e a carga de treinamento prescritos durante três semanas em diferentes fases de treinamento (pelos treinadores), não foi diferente do percebido pelos jovens jogadores de futebol. Além disso, a carga de treinamento dos treinadores parece ser eficaz para prever a carga de treinamento em jovens jogadores de futebol

Características antropométricas e motoras em jogadores de futebol: diferenças entre categorias sub17. sub19 e profissional / Antrophometric and motor caratheristics in soccer players: differences between under 17. under 19 and professional categories

O objetivo do presente estudo foi analisar e comparar as características antropométricas e motoras de atletas pertencentes as categorias Sub17, Sub19 e Profissional. Todos os dados foram coletados anteriormente ao início da temporada competitiva. A amostra deste estudo foi composta por 48 futebolistas masculinos divididos em três grupos: Sub17 (n=16), Sub19 (n=16) e Profissional (n=16). Para avaliar as características antropométricas foram realizadas avaliações de estatura e de composição corporal por meio de Pletismografia por deslocamento de ar. Já para determinação das características motoras foram realizados os testes de resistência aeróbia (Yo-Yo IR1); Counter movement jump (CMJ); Squat jump (SJ); performance de sprint 5m e 30m e potência anaeróbia (RAST teste) para determinação das potências máxima, média e mínima. Para determinar as diferenças entre as categorias no que se refere as características antropométricas e motoras uma ANOVA one way complementando-se com o teste posthoc de Bonferroni foi utilizado, levando-se em consideração um nível de significância de p>0,016. Atletas profissionais apresentaram maiores valores de peso corporal e massa magra absoluta se comparadas as categorias Sub17 e Sub19, não sendo identificadas diferenças para massa gorda absoluta e relativa e massa magra relativa. Não foram identificadas diferenças antropométricas entre os atletas das categorias Sub17 e Sub19. Atletas profissionais apresentaram valores de CMJ, SJ, sprint de 30m e potência máxima, média e mínima maiores do que atletas Sub17 e Sub19, não apresentando diferença em relação ao Yo-Yo IR1 e sprint de 5m. Atletas Sub19 apresentaram maiores valores de Yo-Yo IR1 se comparados ao Sub17 e Profissionais e maiores valores de CMJ, sprint de 30m e potência média e mínima se comparado aos atletas Sub17. Atletas de diferentes categorias apresentam características antropométricas e motoras distintas, enfatizando a importância em acompanhar o desenvolvimento destas características de acordo com a idade....(AU)

The aim of the present study was to analyze and compare the anthropometric and motor characteristics of under 17, under 19 and Professional athletes. All data were collected prior to the beginning of the competitive season. The sample of this study was composed of 48 male soccer players divided into three groups: Under 17 (n=16), Under 19 (n=16) and Professional (n=16). To evaluate anthropometric characteristics, height and body composition were performed by means of air displacement pletismography. For determination of the motor characteristics the aerobic resistance test (Yo-Yo IR1), Counter movement jump (CMJ), Squat jump (SJ), performance of 5m and 30 m sprint and anaerobic power (RAST test) to determine the maximum, mean and minimum power were performed. To determine the differences between the categories regarding anthropometric and motor characteristics, a one-way ANOVA complemented with Bonferroni post-hoc test was used, with a level of significance of p>0,016. Professional athletes shown higher values of body weight and absolute lean mass compared to Under 17 and Under 19 categories, with no difference for absolute and relative fat mass and relative lean mass. No anthropometric differences were identified among athletes in the Under 17 and Under 19 categories. Professional athletes presented values of CMJ, SJ, sprint of 30m and maximal, mean, and minimum power higher than Under 17 and Under 19 athletes, with no difference in relation to Yo-Yo IR1 and sprint of 5m. Under 19 athletes presented higher values of Yo-Yo IR1 compared to Under 17 and Professionals, and higher values of CMJ, sprint of 30 m, mean and, minimum power compared to Under 17 athletes. Athletes of different categories present distinct anthropometric and motor characteristics, emphasizing the importance of accompanying the development of these characteristics according to playing age....(AU)

Análise de componentes principais na identificação de características físicas primordiais em esportes coletivos / Analysis of principal components in the identification of primordial physical characteristics in collective sports

Os objetivos do presente estudo foram: demonstrar por meio da análise de componentes principais (ACP), quais as variáveis físicas que poderiam estar mais relacionadas com o desempenho de atletas de modalidades coletivas, podendo assim colaborar com uma maior caracterização das mesmas e testar se a utilização da técnica multivariada de análise por meio da ACP seria capaz de sintetizar essas variáveis. Fizeram parte do estudo 108 atletas (38 do sexo masculino e 70 do feminino) representantes da cidade de Londrina nos Jogos da Juventude do Paraná de 2008 e 2011 nas modalidades de futsal, handebol, basquetebol e voleibol. Foram realizadas medidas de composição corporal por meio de plestimografia por deslocamento de ar, estatura e massa corporal, saltos verticais em placa de contato, testes de agilidade e velocidade, flexões abdominais e o teste de corrida de Leger. A ACP foi utilizada na tentativa de sumarizar em fatores as variáveis investigadas para todas as modalidades investigadas. Foram identificados 4 componentes principais para as modalidades de Futsal e Voleibol, representando 79,7% e 77% da variância total e de 3 componentes para as modalidades Basquetebol e Handebol, respondendo por 77% e 81,6% da variância total. A ACP foi capaz de identificar e discriminar as variáveis que mais respondem pela variância total em modalidades coletivas. As variáveis que mais contribuíram para a formação dos componentes vão ao encontro com os principais atributos específicos das modalidades estudadas, identificando assim as principais variáveis que em tese poderiam contribuir para o sucesso esportivo nas modalidades em questão....(AU)

The objectives of the present study were: to demonstrate through the principal components analysis (PCA), which physical variables could be more related to the performance of athletes of collective modalities and, thus collaborate with a greater characterization of then and to test if the use of the multivariate analysis technique by the PCA would be able to synthesize these variables. Participated in the study 108 athletes that represents the city of Londrina at the Youth Games of Paraná in 2008 and 2011 in the modalities of futsal, handball, basketball and volleyball. Body composition, height, body mass, vertical jumps, agility, speed tests, abdominal flexions and the Leger running test were conducted. PCA was used to summarize the variables investigated. Four principal components were identified for futsal and volleyball, representing 79,7% and 77% of the total variance and 3 principal components for basketball and handball, accounting for 77% and 81,6% of the total variance. The PCA was able to identify and discriminate the variables that most respond by the total variance in collective modalities. The variables that contributed the most to the formation of the components are in agreement with the main specific attributes of the modalities studied, thus identifying the main variables that in theory contribute to the sporting success in the modalities in question....(AU)

A knowledge discovery methodology from EEG data for cyclic alternating pattern detection.

BACKGROUND: Detection and quantification of cyclic alternating patterns (CAP) components has the potential to serve as a disease bio-marker. Few methods exist to discriminate all the different CAP components, they do not present appropriate sensitivities, and often they are evaluated based on accuracy (AC) that is not an appropriate measure for imbalanced datasets. METHODS: We describe a knowledge discovery methodology in data (KDD) aiming the development of automatic CAP scoring approaches. Automatic CAP scoring was faced from two perspectives: the binary distinction between A-phases and B-phases, and also for multi-class classification of the different CAP components. The most important KDD stages are: extraction of 55 features, feature ranking/transformation, and classification. Classification is performed by (i) support vector machine (SVM), (ii) k-nearest neighbors (k-NN), and (iii) discriminant analysis. We report the weighted accuracy (WAC) that accounts for class imbalance. RESULTS: The study includes 30 subjects from the CAP Sleep Database of Physionet. The best alternative for the discrimination of the different A-phase subtypes involved feature ranking by the minimum redundancy maximum relevance algorithm (mRMR) and classification by SVM, with a WAC of 51%. Concerning the binary discrimination between A-phases and B-phases, k-NN with mRMR ranking achieved the best WAC of 80%. CONCLUSIONS: We describe a KDD that, to the best of our knowledge, was for the first time applied to CAP scoring. In particular, the fully discrimination of the three different A-phases subtypes is a new perspective, since past works tried multi-class approaches but based on grouping of different sub-types. We also considered the weighted accuracy, in addition to simple accuracy, resulting in a more trustworthy performance assessment. Globally, better subtype sensitivities than other published approaches were achieved.

Gender-Related Differences in Heart Rate Variability of Epileptic Patients.

Recently, heart rate variability (HRV) analysis has been used as an indicator of epileptic seizures. As women have a lower sudden, unexpected death in epilepsy risk and greater longevity than men, the authors postulated that there are significant gender-related differences in heart rate dynamics of epileptic patients. The authors analyzed HRV during 5-minute segments of continuous electrocardiogram recording of age-matched populations. The middle-aged epileptic patients included males ( n = 12) and females ( n = 12), ranging from 41 to 65 years of age. Relatively high- (0.15 Hz-0.40 Hz) and low-frequency (0.01 Hz-0.15 Hz) components of HRV were computed using spectral analysis. Poincaré parameters of each heart rate time series were considered as nonlinear features. The mean heart rate markedly differed between gender groups including both right- and left-sided seizures. High-frequency heart rate power and the low-frequency/high-frequency ratio increased in the pre-ictal phase of both male and female groups ( p < .01), but men showed more increase especially in right-sided seizures. The standard deviation ratio, SD2/ SD1, of pre-ictal phase was greater in males than females ( p < .01). High-frequency spectral power and parasympathetic activity were higher in the female group with both right- and left-sided seizures. Men showed a sudden increase in sympathetic activity in the pre-ictal phase, which might increase the risk of cardiovascular disease in comparison to women. These complementary findings indicate the need to account for gender, as well as localization in HRV analysis.