Automated assessment of balance: A neural network approach based on large-scale balance function data.

Balance impairment (BI) is an important cause of falls in the elderly. However, the existing balance estimation system needs to measure a large number of items to obtain the balance score and balance level, which is less efficient and redundant. In this context, we aim at building a model to automatically predict the balance ability, so that the early screening of large-scale physical examination data can be carried out quickly and accurately. We collected and sorted out 17,541 samples, each with 61-dimensional features and two labels. Moreover, using this data a lightweight artificial neural network model was trained to accurately predict the balance score and balance level. On the premise of ensuring high prediction accuracy, we reduced the input feature dimension of the model from 61 to 13 dimensions through the recursive feature elimination (RFE) algorithm, which makes the evaluation process more streamlined with fewer measurement items. The proposed balance prediction method was evaluated on the test set, in which the determination coefficient (R2) of balance score reaches 92.2%. In the classification task of balance level, the metrics of accuracy, area under the curve (AUC), and F1 score reached 90.5, 97.0, and 90.6%, respectively. Compared with other competitive machine learning models, our method performed best in predicting balance capabilities, which is especially suitable for large-scale physical examination.

The effectiveness of low intensity exercise and blood flow restriction without exercise on exercise induced muscle damage: A systematic review.

OBJECTIVE: To investigate the evidence and provide clinical recommendations for low intensity exercises(LIE) and blood flow restriction(BFR) without exercise on reducing the effects of exercise induced muscle damage(EIMD). METHOD: PubMed, Embase, Web of science, and PEDro(Physiotherapy Evidence Database) were searched up to December 2019 for studies that included LIE or BFR without exercise and their effect on EIMD. RESULTS: Out of 3192 studies, 23 were included with 17 on LIE and 6 on BFR without exercise. 11 studies demonstrated positive effects for LIE on EIMD, with two level 2 and nine level 3 studies. Two level 2 and two level 3 studies found benefits for BFR without exercise on reducing the negative effects of EIMD, while two level 2 studies found did not find benefits for BFR without exercise. CONCLUSION: Moderate to low levels of evidence supported LIE, particularly in the form of protective low load eccentric exercise, in reducing the negative effects of EIMD. Conflicting moderate to low levels of evidence was found regarding BFR without exercise. There does seem to be potential benefit for BFR without exercise in untrained individuals. Clinicians can provide clinical recommendations as LIE and BFR without exercise reducing EIMD.