Search

Decades of research have shown machine learning superiority in discovering highly nonlinear patterns embedded in electroencephalography (EEG) records compared with conventional statistical techniques. However, even the most advanced machine learning techniques require relatively large, labeled EEG repositories. EEG data collection and labeling are costly. Moreover, combining available datasets to achieve a large data volume is usually infeasible due to inconsistent experimental paradigms across trials. Self-supervised learning (SSL) solves these challenges because it enables learning from EEG records across trials with variable experimental paradigms, even when the trials explore different phenomena. It aggregates multiple EEG repositories to increase accuracy, reduce bias, and mitigate overfitting in machine learning training. In addition, SSL could be employed in situations where there is limited labeled training data, and manual labeling is costly. This article: 1) provides a brief introduction to SSL; 2) describes some SSL techniques employed in recent studies, including EEG; 3) proposes current and potential SSL techniques for future investigations in EEG studies; 4) discusses the cons and pros of different SSL techniques; and 5) proposes holistic implementation tips and potential future directions for EEG SSL practices.

Introduction: University students have been extensively affected with psychological problems due to outbreak of COVID-19 pandemic given their special position and status. In this study, we intend to examine the prevalence of depression, anxiety and stress among a group of students., Methods: This cross-sectional study was performed in medical Sciences universities of Mazandaran Province. 352 students were recruited by simple available sampling method. Data collection tools were Standard Mental Health Questionnaire (DASS-21) and demographic information questionnaire. Data analysis was done using SPSS software through descriptive and analytical statistics., Results: The mean age of students was 22.44 ± 3.4 and 54.3% of them were females. 33.6, 28.4, and 27.3% of students had moderate to extremely severe levels of symptoms of depression, anxiety, and stress, respectively. There was a significant relationship between total mental health score with physical activity (p < 0.04) and with smoking (p < 0.02). There was also a significant relationship between smoking and depression (p < 0.01)., Conclusion: Considering the fact that anxiety, stress and depression are common among medical sciences students of Mazandaran Province, necessary measures must be taken to improve their mental health status., Competing Interests: SHMN and SMMMN are members of a family., (© 2022 The Authors.)

Objective: Handover without a structured format is prone to the omission of information and could be a potential risk to patient safety. We sought to determine the effect of a structured checklist on the quality of intraoperative change of shift handover between scrubs and circulars., Methods: We conducted a control intervention study on operating room wards of two teaching hospitals from 20 Feb to 21 Nov 2020. This research was conducted in three stages as follows: assessing the current situation (as a group before the intervention), performing the intervention and evaluating the effect of using a checklist on handover quality after the intervention in two groups: with and without checklist. We examined the quality of handover between scrub and circular personnel in terms of handover duration and quality, omission of information and improvement in OR staff satisfaction., Results: A total of 120 handovers were observed and evaluated. After intervention in the group using the checklist, the percentage of information omission in surgical report was decreased from 19.5 to 12.1% between scrubs (P < 0.00) and from 16.8 to 14.1% between circulars (P < 0.03). Also, in the role of scrub, the mean overall score of handover process quality was significantly higher after the intervention (x̄ = 7 ± 1.5) than before it (x̄ = 6.5 ± 0.9) (p < 0.02). In the role of circulating, despite the positive effect of overall score checklist, no significant difference was observed (p < 0.08). The use of checklist significantly increased the handover duration between scrubs (p < 0.03) and circulars (p < 0.00). The overall mean percentage of handover satisfaction increased from 67.5% before the intervention to 85.5% after the intervention (p < 0.00)., Conclusion: The implementation of a new structured handover checklist had a positive impact on improving the quality of communication between the surgical team, reducing the information omission rate and increasing the satisfaction., (© 2021. The Author(s).)

Background and Objective: Postoperative pressure ulcers are known as the most important quality indicators of intraoperative care that create critical and costly complications during hospital care. Accordingly, this study was performed to determine the risk factor for diabetes in postoperative pressure ulcers., Materials and Methods: The present study is a systematic review of PubMed, Scopus and the Web of Science databases with using standardized keywords of the performed English language articles between Jan 2010 to Jan 2020. The articles were searched independently by two related researchers to avoid possible biases. Then, all collected articles were reviewed, and articles with inclusion criteria were evaluated using a data collection table. It should be noted that the data were analyzed using STATA software version 11.1., Results: Overall, the results showed that 19724 patients were identified from 15 studies conducted in Asia (six), the America (four), Europe (four), and Australia (one) from 1989 to 2019. The results showed that patients with diabetes were more likely to experience surgery-related pressure ulcers than patients without diabetes (The odds ratio of 1.52; the 95% confidence interval: 1.25-1.85)., Conclusion: In general, patients with diabetes increased the risk of surgery-related pressure ulcers about 1.5 times more than others. Accordingly, the reduction of surgery-induced pressure ulcers should be more extensively considered in patients with diabetes., Competing Interests: All authors have no conflict of interest to report., (© 2021 The Authors.)

Background: Constraint-induced movement therapy (CI therapy) produces, on average, large and clinically meaningful improvements in the daily use of a more affected upper extremity in individuals with hemiparesis. However, individual responses vary widely., Objective: The study objective was to investigate the extent to which individual characteristics before treatment predict improved use of the more affected arm following CI therapy., Design: This study was a retrospective analysis of 47 people who had chronic (> 6 months) mild to moderate upper extremity hemiparesis and were consecutively enrolled in 2 CI therapy randomized controlled trials., Methods: An enhanced probabilistic neural network model predicted whether individuals showed a low, medium, or high response to CI therapy, as measured with the Motor Activity Log, on the basis of the following baseline assessments: Wolf Motor Function Test, Semmes-Weinstein Monofilament Test of touch threshold, Motor Activity Log, and Montreal Cognitive Assessment. Then, a neural dynamic classification algorithm was applied to improve prognostic accuracy using the most accurate combination obtained in the previous step., Results: Motor ability and tactile sense predicted improvement in arm use for daily activities following intensive upper extremity rehabilitation with an accuracy of nearly 100%. Complex patterns of interaction among these predictors were observed., Limitations: The fact that this study was a retrospective analysis with a moderate sample size was a limitation., Conclusions: Advanced machine learning/classification algorithms produce more accurate personalized predictions of rehabilitation outcomes than commonly used general linear models., (© 2019 American Physical Therapy Association.)

Virtual rehabilitation yields outcomes that are at least as good as traditional care for improving upper limb function and the capacity to carry out activities of daily living. Due to the advent of low-cost gaming systems and patient preference for game-based therapies, video game technology will likely be increasingly utilized in physical therapy practice in the coming years. Gaming systems that incorporate low-cost motion capture technology often generate large datasets of therapeutic movements performed over the course of rehabilitation. An infrastructure has yet to be established, however, to enable efficient processing of large quantities of movement data that are collected outside of a controlled laboratory setting. In this paper, a methodology is presented for extracting and evaluating therapeutic movements from game-based rehabilitation that occurs in uncontrolled and unmonitored settings. By overcoming these challenges, meaningful kinematic analysis of rehabilitation trajectory within an individual becomes feasible. Moreover, this methodological approach provides a vehicle for analyzing large datasets generated in uncontrolled clinical settings to enable better predictions of rehabilitation potential and dose-response relationships for personalized medicine.

The keys for the development of an effective classification algorithm are: 1) discovering feature spaces with large margins between clusters and close proximity of the classmates and 2) discovering the smallest number of the features to perform accurate classification. In this paper, a new supervised classification algorithm, called neural dynamic classification (NDC), is presented with the goal of: 1) discovering the most effective feature spaces and 2) finding the optimum number of features required for accurate classification using the patented robust neural dynamic optimization model of Adeli and Park. The new classification algorithm is compared with the probabilistic neural network (PNN), enhanced PNN (EPNN), and support vector machine using two sets of classification problems. The first set consists of five standard benchmark problems. The second set is a large benchmark problem called Mixed National Institute of Standards and Technology database of handwritten digits. In general, NDC yields the most accurate classification results followed by EPNN. A beauty of the new algorithm is the smoothness of convergence curves which is an indication of robustness and good performance of the algorithm. The main aim is to maximize the prediction accuracy.

The majority of rehabilitation research focuses on the comparative effectiveness of different interventions in groups of patients, while much less is currently known regarding individual factors that predict response to rehabilitation. In a recent article, the authors presented a prognostic model to identify the sensorimotor characteristics predictive of the extent of motor recovery after Constraint-Induced Movement (CI) therapy amongst individuals with chronic mild-to-moderate motor deficit using the enhanced probabilistic neural network (EPNN). This follow-up paper examines which participant characteristics are robust predictors of rehabilitation response irrespective of the training modality. To accomplish this, EPNN was first applied to predict treatment response amongst individuals who received a virtual-reality gaming intervention (utilizing the same enrollment criteria as the prior study). The combinations of predictors that yield high predictive validity for both therapies, using their respective datasets, were then identified. High predictive classification accuracy was achieved for both the gaming (94.7%) and combined datasets (94.5%). Though CI therapy employed primarily fine-motor training tasks and the gaming intervention emphasized gross-motor practice, larger improvements in gross motor function were observed within both datasets. Poorer gross motor ability at pre-treatment predicted better rehabilitation response in both the gaming and combined datasets. The conclusion of this research is that for individuals with chronic mild-to-moderate upper extremity hemiparesis, residual deficits in gross motor function are highly responsive to motor restorative interventions, irrespective of the modality of training., (Copyright © 2017 Elsevier B.V. All rights reserved.)

Constraint-induced movement therapy (CI therapy) is a well-researched intervention for treatment of upper limb function. Overall, CI therapy yields clinically meaningful improvements in speed of task completion and greatly increases use of the more affected upper extremity for daily activities. However, individual improvements vary widely. It has been suggested that intrinsic feedback from somatosensation may influence motor recovery from CI therapy. To test this hypothesis, an enhanced probabilistic neural network (EPNN) prognostic computational model was developed to identify which baseline characteristics predict extent of motor recovery, as measured by the Wolf Motor Function Test (WMFT). Individual characteristics examined were: proprioceptive function via the brief kinesthesia test, tactile sensation via the Semmes-Weinstein touch monofilaments, motor performance captured via the 15 timed items of the Wolf Motor Function Test, stroke affected side. A highly accurate predictive classification was achieved (100% accuracy of EPNN based on available data), but facets of motor functioning alone were sufficient to predict outcome. Somatosensation, as quantified here, did not play a large role in determining the effectiveness of CI therapy., (Copyright © 2017 Elsevier B.V. All rights reserved.)

Background: This study was performed to evaluate the learning curve and related complications of ultrasound (US) guided central venous catheter (CVC) insertion in infants., Materials and Methods: This study was performed in Imam Hosein Hospital of Isfahan from September 2014 to March 2015. Participants were infants consecutively candidate for CVC insertion. Three steps were designed to complement the learning. For each step of learning, 20 patients were considered and for every patient one CVC was inserted: (1) In the first step, venous puncture and guide wire passage was performed by an experienced radiologist and the surgeon was taught how to do it, then CVC was placed by the surgeon. (2) In the second step, venous puncture and guide-wire passage was performed by the surgeon under the supervision of the same radiologist, and then CVC was placed by the surgeon. (3) In the third step, US-guided CVC insertion was performed by the surgeon completely, and the radiologist came to the operating room only if it was necessary. In each of these steps, the time spent of the US probe on the skin until the guide wire passage into the vein was recorded for every patient. All perioperative complications were recorded., Results: The mean point for the time spent of the US probe on the skin until the guide wire passage into the vein was 84.9 ± 13.6, 119.1 ± 15.2, and 90.3 ± 11.2 s in the step 1, 2 and 3, respectively (P = 0.04). There was no significant difference between the frequencies of complications among tree steps., Conclusion: US-guided percutaneous CVC insertion is a safe and reliable method which can be easily and rapidly learned.

Background: Herniotomy is a common operation done by pediatric surgeons. Recent studies have shown that high ligation in herniation in adult is not necessary, but this method was not fully evaluated in children. We compared non-ligation with high-ligation sac in herniotomy in terms of surgical complications and duration., Materials and Methods: This randomized controlled trial study was done on 104 children with inguinal hernia at Al-Zahra Hospital, Isfahan, Iran, between 2011 and 2013. Patients were equally randomized to undergo herniotomy with ligation of sac at the internal ring level or to undergo herniotomy without sac ligation. Patients were followed up just after the operation, and in the 1(st), 6(th), and 12(th) weeks postoperation to discover early (scrotal hematoma, edema, wound infection, and postoperation fever) and late (adhesion and recurrence) complications. Also, duration of operation was recorded for each group., Results: The incidence of early complications (nine cases in high-ligation and eight cases in non-ligation group) was the same in both groups (P = 0.402). No late complication was observed in any group. The mean duration of operation in high-ligation group (18.84 ± 5.47 min) was significantly shorter than non-ligation group (21.46 ± 9.03 min) (P < 0.001)., Conclusion: Complications are the same in herniotomy with or without ligation of the sac, but the duration of the non-ligation procedure is shorter than that of high-ligation. We suggest that herniotomy without sac ligation in children be the procedure of choice to save time and also to prevent any other possible complications such as nerve damage, spermatic cord injury, or peritoneal tearing.

Background: Management of the severely injured lower limb in children remains a challenge despite advances in surgical techniques. Models that predict the risk of lower limb trauma patients are designed to provide an estimation of the probability of limb salvage. In this study, we validate Mangled Extremity Syndrome Index (Mangled Extremity Severity Score [MESS]) by measurement of its discrimination in children., Materials and Methods: From September 2009 to 2010, we collected the hospital records of all children who presented with lower extremity long bone open fractures. The inclusion criteria were I grade, II B, III C open fractures, severe injury to three of four organ systems, and severe injury to two of four organ systems with minor injury to two of four systems that require surgical interventions. Severity of limb injury was measured using MESS. Patients were followed up for 1 year. The discrimination of MESS model in differentiating of outcome in patients was assessed by calculating the area under the receiver operator characteristic plot., Results: We evaluated 200 children referred consecutively to our center. The mean MESS in the amputation group was 7.5 ± 1.59 versus 6.4 ± 2.02 in the limb salvage group (p = 0.04). Amputation rate was 7.5% (n = 15). Percentages of skeletal/soft-tissue injury was different between groups (p = 0.0001). Children in the amputation group showed more tissue injury compared with limb salvage group. The best clinical discriminator power was calculated as MESS ≥ 6.5 (sensitivity = 73%, specificity = 54%)., Conclusion: We assumed that patients with a high risk of amputation can be identified early, and specific measures can be implemented immediately by using MESS with threshold of 6.5., (Georg Thieme Verlag KG Stuttgart · New York.)