Objective: Several features of the surface electromyography (sEMG) signal are related to muscle activity and fatigue. However, the time-evolution of these features are non-stationary and vary between subjects. The aim of this study is to investigate the use of adaptive algorithms to forecast sMEG feature of the trunk muscles. Methods: Shallow models and a deep convolutional neural network (CNN) were used to simultaneously learn and forecast 5 common sEMG features in real-time to provide tailored predictions. This was investigated for: up to a 25 second horizon; for 14 different muscles in the trunk; across 13 healthy subjects; while they were performing various exercises. Results: The CNN was able to forecast 25 seconds ahead of time, with 6.88% mean absolute percentage error and 3.72% standard deviation of absolute percentage error, across all the features. Moreover, the CNN outperforms the best shallow model in terms of a figure of merit combining accuracy and precision by at least 30% for all the 5 features. Conclusion: Even though the sEMG features are non-stationary and vary between subjects, adaptive learning and forecasting, especially using CNNs, can provide accurate and precise forecasts across a range of physical activities. Significance: The proposed models provide the groundwork for a wearable device which can forecast muscle fatigue in the trunk, so as to potentially * Ahmad Moniri and Dan Terracina contributed equally to this work.

Low Back Pain (LBP) affects the vast majority of the population at some point in their lives. People with LBP show altered trunk muscle activity and increased fatigue of trunk muscles. A system that can forecast trunk muscle activity and detect fatigue may help subjects, practitioners and physiotherapists in the diagnosis, monitoring and recovery of LBP. In this paper, we directly model the time evolution of muscle fatigue-related features of the surface electromyography (sEMG) from a number of trunk muscles. We show that it is possible to accurately and precisely forecast 5 common sEMG features 25 seconds ahead of time for 14 different muscles in the trunk for 13 healthy subjects. We investigate both shallow and deep models using adaptive algorithms, which adapt to each individual subject over time. The deep model, namely a convolutional neural network (CNN), consists of a stack of dilated causal convolutional layers, similar to the celebrated WaveNet. We show that, in terms of a figure of merit combining accuracy and precision across all subjects, the CNN improves the overall performance by at least 30% compared with the shallow models. The proposed approach provides the groundwork for a wearable device which can forecast muscle fatigue in the trunk, so as to potentially prevent muscle injury. Additionally, the explicit forecasting of the well-known sEMG features in real-time provides a general model which can be applied to many fields and applications of muscle activity monitoring such as human-computer interaction and prosthetics.

This paper presents a 4 channel ASIC for sEMG sensing with in-built muscle fatigue and activity feature extraction. Each channel filters and conditions the electrode signal in parallel, while extracting key features for Low Back Pain (LBP) fatigue monitoring and forecasting -Zero Crossing rate and Root Mean Square through sEMG Envelope. The channels are integrated with a Transimpedance Amplifier, an 10-Bit ADC and a Digital Control Unit to digitise and enable transmission of extracted features. Fabricated in TSMC 180nm, these channels present a compact form factor (90µm× 630µm) and a low power consumption (42.61 µW ), ideal characteristic for wearable devices utilised for long-term monitoring of activities.

Aim Abdominal cavity access accounts for 50% of complications during laparoscopic surgery. Different safety maneuvers have been used to try to diminish these. Our study aims to establish the usefulness of Palmer's test in the correct positioning of the Veress needle and the reduction of complications during laparoscopic access maneuvers, when used in addition to the determination of intraabdominal pressure. Methods Prospective observational analytic multi‐centered cohort study with 370 patients undergoing gynecologic laparoscopy between July 2014 and November 2019, comparing the additional use of Palmer's test in 185 patients (Palmer‐Test‐Yes, PTY), with intraabdominal pressure determination alone in 185 patients (Palmer‐Test‐No, PTN). Results Intergroup homogeneity was described for the basic characteristics of both population samples, except for mean age and percentage of previous laparotomy. A total of 19 complications were recorded, 10 in PTY and 9 in PTN, with no significant differences (P = 0.814). No differences were found in the analysis of these complications, except for the rate of conversion to laparotomy, which occurred four times in the PTY group and none in PTN (P = 0.044). Furthermore, no differences were found once fixed for the history of previous laparotomy (P = 514.), nor for the percentage of successful access after the first attempt between both groups (P = 0.753). Conclusion Palmer's test, when used in addition to intraabdominal pressure determination, has not shown to be effective in preventing failed access to abdominal cavity or reducing complications associated with access maneuvers with the Veress needle. Hence, its systematic use is not justified, since it could generate a sense of false security.