Search for: All records

BackgroundWhile many factors are associated with stepping activity after stroke, there is significant variability across studies. One potential reason to explain this variability is that there are certain characteristics that arenecessaryto achieve greater stepping activity that differ from others thatmayneed to be targeted to improve stepping activity. ObjectiveUsing two step thresholds (2500 steps/day, corresponding to home vs. community ambulation and 5500 steps/day, corresponding to achieving physical activity guidelines through walking), we applied 3 different algorithms to determine which predictors are most important to achieve these thresholds. MethodsWe analyzed data from 268 participants with stroke that included 25 demographic, performance-based and self-report variables. Step 1 of our analysis involved dimensionality reduction using lasso regularization. Step 2 applied drop column feature importance to compute the mean importance of each variable. We then assessed which predictors were important to all 3 mathematically unique algorithms. ResultsThe number of relevant predictors was reduced from 25 to 7 for home vs. community and from 25 to 16 for aerobic thresholds. Drop column feature importance revealed that 6 Minute Walk Test and speed modulation were the only variables found to be important to all 3 algorithms (primary characteristics)for each respective threshold. Other variables related to readiness to change activity behavior and physical health, among others, were found to be important to one or two algorithms (ancillary characteristics). ConclusionsAddressing physical capacity isnecessary but not sufficientto achieve important step thresholds, asancillary characteristics, such as readiness to change activity behavior and physical health may also need to be targeted. This delineation may explain heterogeneity across studies examining predictors of stepping activity in stroke. 

We consider transferability estimation, the prob- lem of estimating how well deep learning models transfer from a source to a target task. We focus on regression tasks, which received little previous attention, and propose two simple and computa- tionally efficient approaches that estimate trans- ferability based on the negative regularized mean squared error of a linear regression model. We prove novel theoretical results connecting our ap- proaches to the actual transferability of the optimal target models obtained from the transfer learning process. Despite their simplicity, our approaches significantly outperform existing state-of-the-art regression transferability estimators in both accu- racy and efficiency. On two large-scale keypoint re- gression benchmarks, our approaches yield 12% to 36% better results on average while being at least 27% faster than previous state-of-the-art methods.