Soft Actuator with Biomass Porous Electrode: A Strategy for Lowering Voltage and Enhancing Durability.

Electroactive artificial muscles with deformability have attracted widespread interest in the field of soft robotics. However, the design of artificial muscles with low-driven voltage and operational durability remains challenging. Herein, novel biomass porous carbon (BPC) electrodes are proposed. The nanoporous BPC enables the electrode to provide exposed active surfaces for charge transfer and unimpeded channels for ion migration, thus decreasing the driving voltage, enhancing time durability, and maintaining the actuation performances simultaneously. The proposed actuator exhibits a high displacement of 13.6 mm (bending strain of 0.54%) under 0.5 V and long-term durability of 99.3% retention after 550,000 cycles (∼13 days) without breaks. Further, the actuators are integrated to perform soft touch on a smartphone and demonstrated as bioinspired robots, including a bionic butterfly and a crawling robot (moving speed = 0.08 BL s-1). This strategy provides new insight into the design and fabrication of high-performance electroactive soft actuators with great application potential.

Empirical Study of Overfitting in Deep Learning for Predicting Breast Cancer Metastasis.

Overfitting may affect the accuracy of predicting future data because of weakened generalization. In this research, we used an electronic health records (EHR) dataset concerning breast cancer metastasis to study the overfitting of deep feedforward neural networks (FNNs) prediction models. We studied how each hyperparameter and some of the interesting pairs of hyperparameters were interacting to influence the model performance and overfitting. The 11 hyperparameters we studied were activate function, weight initializer, number of hidden layers, learning rate, momentum, decay, dropout rate, batch size, epochs, L1, and L2. Our results show that most of the single hyperparameters are either negatively or positively corrected with model prediction performance and overfitting. In particular, we found that overfitting overall tends to negatively correlate with learning rate, decay, batch size, and L2, but tends to positively correlate with momentum, epochs, and L1. According to our results, learning rate, decay, and batch size may have a more significant impact on both overfitting and prediction performance than most of the other hyperparameters, including L1, L2, and dropout rate, which were designed for minimizing overfitting. We also find some interesting interacting pairs of hyperparameters such as learning rate and momentum, learning rate and decay, and batch size and epochs.

Deep Learning and Machine Learning with Grid Search to Predict Later Occurrence of Breast Cancer Metastasis Using Clinical Data.

BACKGROUND: It is important to be able to predict, for each individual patient, the likelihood of later metastatic occurrence, because the prediction can guide treatment plans tailored to a specific patient to prevent metastasis and to help avoid under-treatment or over-treatment. Deep neural network (DNN) learning, commonly referred to as deep learning, has become popular due to its success in image detection and prediction, but questions such as whether deep learning outperforms other machine learning methods when using non-image clinical data remain unanswered. Grid search has been introduced to deep learning hyperparameter tuning for the purpose of improving its prediction performance, but the effect of grid search on other machine learning methods are under-studied. In this research, we take the empirical approach to study the performance of deep learning and other machine learning methods when using non-image clinical data to predict the occurrence of breast cancer metastasis (BCM) 5, 10, or 15 years after the initial treatment. We developed prediction models using the deep feedforward neural network (DFNN) methods, as well as models using nine other machine learning methods, including naïve Bayes (NB), logistic regression (LR), support vector machine (SVM), LASSO, decision tree (DT), k-nearest neighbor (KNN), random forest (RF), AdaBoost (ADB), and XGBoost (XGB). We used grid search to tune hyperparameters for all methods. We then compared our feedforward deep learning models to the models trained using the nine other machine learning methods. RESULTS: Based on the mean test AUC (Area under the ROC Curve) results, DFNN ranks 6th, 4th, and 3rd when predicting 5-year, 10-year, and 15-year BCM, respectively, out of 10 methods. The top performing methods in predicting 5-year BCM are XGB (1st), RF (2nd), and KNN (3rd). For predicting 10-year BCM, the top performers are XGB (1st), RF (2nd), and NB (3rd). Finally, for 15-year BCM, the top performers are SVM (1st), LR and LASSO (tied for 2nd), and DFNN (3rd). The ensemble methods RF and XGB outperform other methods when data are less balanced, while SVM, LR, LASSO, and DFNN outperform other methods when data are more balanced. Our statistical testing results show that at a significance level of 0.05, DFNN overall performs comparably to other machine learning methods when predicting 5-year, 10-year, and 15-year BCM. CONCLUSIONS: Our results show that deep learning with grid search overall performs at least as well as other machine learning methods when using non-image clinical data. It is interesting to note that some of the other machine learning methods, such as XGB, RF, and SVM, are very strong competitors of DFNN when incorporating grid search. It is also worth noting that the computation time required to do grid search with DFNN is much more than that required to do grid search with the other nine machine learning methods.

The Efficacy and Safety of Mesalamine and Probiotics in Mild-to-Moderate Ulcerative Colitis: A Systematic Review and Meta-Analysis.

OBJECTIVE: To evaluate the efficacy and safety of mesalamine in conjunction with probiotics for ulcerative colitis. METHODS: Random controlled trials (RCTs) were searched in PubMed, EMBASE, Cochrane Library, China National Knowledge Infrastructure, Wanfang, and VIP (VIP Database for Chinese Technical Periodicals) from inception to October 2019. Methodological quality was assessed by the Cochrane Collaboration tool. The quality of evidence was rated by the Grading of Recommendations, Assessment, Development, and Evaluation (GRADE). Data analysis was carried out in Review Manager 5.3. RESULTS: A total of fifteen studies met the criteria for inclusion. Thirteen studies reported the clinical efficacy, three studies provided data on the clinical symptom scores, two trials reported disease activity index, four studies evaluated endoscopic score, and twelve studies reported adverse events. For ulcerative colitis (UC), mesalamine and probiotics had better clinical efficacy than mesalamine alone (≤8 weeks: RR = 1.12, 95% CI: 1.07-1.18, P < 0.0001; >8 weeks: RR = 1.25, 95% CI: 1.11-1.41, P=0.0003). On the clinical symptom scores, disease activity index, and endoscopic score, UC patients receiving mesalamine and probiotics had significant difference than patients receiving mesalazine alone (MD = -2.02, 95% CI: -3.28 to -0.76, P=0.002; MD = -1.20, 95% CI: -1.76 to -0.65, P < 0.001; and MD = -0.42, 95% CI: -0.61 to -0.23, P < 0.0001, respectively). There was no statistically significant difference in adverse events between the two groups (RR = 0.88, 95% CI: 0.54 to 1.43, P=0.60). CONCLUSION: Our meta-analysis results supported that mesalamine and probiotics were effective and safe in treating ulcerative colitis.