Decoding lower-limb kinematic parameters during pedaling tasks using deep learning approaches and EEG.

Stroke is a neurological condition that usually results in the loss of voluntary control of body movements, making it difficult for individuals to perform activities of daily living (ADLs). Brain-computer interfaces (BCIs) integrated into robotic systems, such as motorized mini exercise bikes (MMEBs), have been demonstrated to be suitable for restoring gait-related functions. However, kinematic estimation of continuous motion in BCI systems based on electroencephalography (EEG) remains a challenge for the scientific community. This study proposes a comparative analysis to evaluate two artificial neural network (ANN)-based decoders to estimate three lower-limb kinematic parameters: x- and y-axis position of the ankle and knee joint angle during pedaling tasks. Long short-term memory (LSTM) was used as a recurrent neural network (RNN), which reached Pearson correlation coefficient (PCC) scores close to 0.58 by reconstructing kinematic parameters from the EEG features on the delta band using a time window of 250 ms. These estimates were evaluated through kinematic variance analysis, where our proposed algorithm showed promising results for identifying pedaling and rest periods, which could increase the usability of classification tasks. Additionally, negative linear correlations were found between pedaling speed and decoder performance, thereby indicating that kinematic parameters between slower speeds may be easier to estimate. The results allow concluding that the use of deep learning (DL)-based methods is feasible for the estimation of lower-limb kinematic parameters during pedaling tasks using EEG signals. This study opens new possibilities for implementing controllers most robust for MMEBs and BCIs based on continuous decoding, which may allow for maximizing the degrees of freedom and personalized rehabilitation.

Lower-limb kinematic reconstruction during pedaling tasks from EEG signals using Unscented Kalman filter.

Kinematic reconstruction of lower-limb movements using electroencephalography (EEG) has been used in several rehabilitation systems. However, the nonlinear relationship between neural activity and limb movement may challenge decoders in real-time Brain-Computer Interface (BCI) applications. This paper proposes a nonlinear neural decoder using an Unscented Kalman Filter (UKF) to infer lower-limb kinematics from EEG signals during pedaling. The results demonstrated maximum decoding accuracy using slow cortical potentials in the delta band (0.1-4 Hz) of 0.33 for Pearson's r-value and 8 for the signal-to-noise ratio (SNR). This leaves an open door to the development of closed-loop EEG-based BCI systems for kinematic monitoring during pedaling rehabilitation tasks.

Amputation after failure or complication of total knee arthroplasty: prevalence, etiology and functional outcomes.

OBJECTIVE: Identify the etiology and incidence, as well to assess functional outcomes of patients, undergoing lower limb amputation after failure or complication of total knee arthroplasty. These patients were treated at the Center for Knee Surgery at the National Institute of Traumatology and Orthopedics (INTO), during the period of January 2001 to December 2010. METHODS: The patients were interviewed and their charts were retrospectively analyzed to evaluate their functional outcome. RESULTS: The incidence of amputation due to failure or complication of total knee arthroplasty was 0.41% in 2409 cases. Recurrent deep infection was the cause of amputation in 81% of cases, being Staphylococcus aureus and Pseudomonas aeruginosa the most frequent germs. Vascular complications and periprosthetic fracture associated to metaphyseal bone loss were also causes of amputation. In our study, 44% of amputees patients were using orthesis and 62.5% have had the ability to walk. CONCLUSION: Incidence of 0.41%, being the main cause recurrent infection. The functional outcome is limited, and the fitting achieved in 44% of patients and only 62.5% are ambulatory.

OBJETIVO: Identificar a etiologia e a incidência da amputação do membro inferior após falha ou complicação da artroplastia total de joelho e avaliar os resultados funcionais dos pacientes tratados pelo Centro de Cirurgia de Joelho do Instituto Nacional de Traumatologia e Ortopedia (Into) entre janeiro de 2001 e dezembro de 2010. MÉTODOS: Os prontuários foram retrospectivamente analisados para coleta dos dados e entrevista para avaliação do resultado funcional. RESULTADOS: A incidência de amputação em decorrência de falha ou complicação após 2.409 artroplastias totais de joelho foi de 0.41%. Infecção profunda recorrente foi causa de amputação em 81% dos casos. Os germes mais frequentes foram Staphylococcus aureus e Pseudomonas aeruginosa. Complicações vasculares e fratura periprotética associada a perda óssea metafisária representaram indicação em menor número de casos. Em nosso estudo, 44% dos pacientes amputados apresentam­se protetizados e 62.5% apresentavam capacidade de deambulação. CONCLUSÕES: Incidência de 0.41% e principal causa infecção recorrente. O resultado funcional é limitado, a protetização foi alcançada em 44% dos pacientes e somente 62.5% são deambuladores.