Supplementary Training Research Articles

PAs' perspective on leadership in medicine.

This study evaluated physician associate/assistant (PA) training and confidence in leadership and leadership skills, as well as where best to incorporate leadership training for the profession. A quantitative survey was administered to assess PAs' perceptions of leadership and degree of leadership training during their primary PA education. The study also solicited where in the career trajectory leadership training is perceived to be most effective. Of the 284 participants who responded to the survey, 207 had complete responses that were used in the analysis. Nearly 92% of PAs agreed that they aspire to be leaders, and 93.2% agreed or strongly agreed that leadership training would be beneficial during PA school. Additionally, more than 50% of PAs agreed that they had no training but desired more regarding personal mastery, teaching, administration, ideals of a healthy workforce, vision and goal setting, getting results, coalitions, and system transformation. This study demonstrated that PAs desired supplemental training in leadership to cultivate career goals and reported that formal leadership training would be useful to cope with and overcome adversity in clinical practice.

Use of an intelligent tutoring system for a curriculum on augmentative and alternative communication: Feasibility for implementation.

Over 8 million children with disabilities live in Africa and are candidates for augmentative and alternative communication (AAC), yet formal training for team members, such as speech-language therapists and special education teachers, is extremely limited. Only one university on the continent provides postgraduate degrees in AAC, and other institutions provide only short modules at an undergraduate level. The need for an introductory training course on AAC that is accessible by university students continent-wide was identified. An online programme, namely an intelligent tutoring system (ITS), was identified as a possible option to facilitate interactive learning without the need for synchronous teaching. The use of an ITS is shown to be effective in developing knowledge and clinical reasoning in the health and rehabilitation fields. However, it has not yet been applied to student teaching in the field of AAC. To determine both the feasibility of an ITS to implement an AAC curriculum for students in four African countries, and the usability and effectiveness of such a system as a mechanism for learning about AAC. The study included two components: the development of a valid AAC curriculum; and using the ITS to test the effectiveness of implementation in a pre- and post-test design with 98 speech-language therapy and special education students from five universities. Statistically significant differences were obtained between pre- and post-test assessments. Students perceived the learning experience as practical, with rich content. The findings suggest that the ITS-based AAC curriculum was positively perceived by the students and potentially offers an effective means of providing supplementary AAC training to students, although modifications to the system are still required. What is already known on the subject Professionals typically lack formal training in AAC. In Africa, this presents a serious challenge as there are over 8 million children who are candidates for AAC. A need for an introductory training course on AAC, which can be accessed by university students continent-wide, was identified. What this paper adds to existing knowledge An AAC curriculum was developed and integrated into an ITS, an online programme allowing interactive learning through asynchronous teaching. Students from four African countries completed the AAC ITS curriculum. The curriculum was positively received by the students and statistically significant changes in knowledge were identified. What are the practical and clinical implications of this work? This feasibility study shows that the use of an ITS is an effective means of providing AAC training to university students in these African countries. The results provide a valuable contribution toward ensuring the equitable distribution of AAC training opportunities in the African context. This will have a significant positive impact on those who are candidates for AAC.

Synthetically enhanced: unveiling synthetic data's potential in medical imaging research

BackgroundChest X-rays (CXR) are essential for diagnosing a variety of conditions, but when used on new populations, model generalizability issues limit their efficacy. Generative AI, particularly denoising diffusion probabilistic models (DDPMs), offers a promising approach to generating synthetic images, enhancing dataset diversity. This study investigates the impact of synthetic data supplementation on the performance and generalizability of medical imaging research. MethodsThe study employed DDPMs to create synthetic CXRs conditioned on demographic and pathological characteristics from the CheXpert dataset. These synthetic images were used to supplement training datasets for pathology classifiers, with the aim of improving their performance. The evaluation involved three datasets (CheXpert, MIMIC-CXR, and Emory Chest X-ray) and various experiments, including supplementing real data with synthetic data, training with purely synthetic data, and mixing synthetic data with external datasets. Performance was assessed using the area under the receiver operating curve (AUROC). FindingsAdding synthetic data to real datasets resulted in a notable increase in AUROC values (up to 0.02 in internal and external test sets with 1000% supplementation, p-value <0.01 in all instances). When classifiers were trained exclusively on synthetic data, they achieved performance levels comparable to those trained on real data with 200%–300% data supplementation. The combination of real and synthetic data from different sources demonstrated enhanced model generalizability, increasing model AUROC from 0.76 to 0.80 on the internal test set (p-value <0.01). InterpretationSynthetic data supplementation significantly improves the performance and generalizability of pathology classifiers in medical imaging. FundingDr. Gichoya is a 2022 Robert Wood Johnson Foundation Harold Amos Medical Faculty Development Program and declares support from RSNA Health Disparities grant (#EIHD2204), Lacuna Fund (#67), Gordon and Betty Moore Foundation, NIH (NIBIB) MIDRC grant under contracts 75N92020C00008 and 75N92020C00021, and NHLBI Award Number R01HL167811.

An enhanced non-iterative real-time solver via multilayer perceptron for on-board component-level models

The real-time on-board component-level model (CLM) of gas turbine engines (GTEs) is an important foundation for fault-tolerant control and health management. However, traditional iterative solving algorithms typically rely on the multiple computations of gas-path thermodynamic parameters, which seriously limits their practical application. In this paper, aiming to improve the real-time performance of CLM, an enhanced non-iterative real-time solver (ENRS) method is proposed. It has combined an input selection strategy, an under-sampling supplemental enhancement training (USET) technique, and a multilayer perceptron (MLP) network. Compared with the existing CLM solving methods, its innovations are as follows: (1) a novel framework for directly solving CLM is proposed, which helps get rid of the dilemma of increased time consumption due to multiple iterations. (2) an enhanced training process is designed for the MLP network, which helps improve the adaptivity to the full flight envelope and all engine states, especially to reduce the maximum error. Simulation tests eventually show that the ENRS effectively improves the real-time performance of CLM in practical applications, and maintains solution accuracy and robustness.

Improving license plate recognition via diverse stylistic plate generation

Deep learning-based license plate recognition heavily relies on the quantity and diversity of training images. However, manually collecting diverse license plate images is a highly time-consuming and labor-intensive task. Hence, generating license plate images to supplement training data emerges as a cost-effective solution for recognition enhancement. Previous generation methods treated the style of license plates as discrete features and extracted style features from a referenced image to generate multi-style license plate images. However, these methods are incapable of generating license plates with arbitrary new styles, as the style of the generated images is constrained by the existing images. To solve this problem, we propose to extract style features from randomly sampled vectors in continuous space for diverse stylistic license plate generation. This way, license plates with arbitrary styles can be generated by simply modifying the sampled style vectors. Besides, to provide controllable content information for the generator, we propose an orientation-aware content encoder to extract multi-oriented glyph content features from the input horizontal glyphs. Moreover, a dual-discriminator is proposed to conduct adversarial learning on both color images and image gradients, aiming to mitigate unnatural patterns and ensure realistic generated results. Finally, extensive experiments on multiple public license plate datasets demonstrate that our method can generate realistic and diverse license plates, and the generated images can significantly improve recognition performance by up to 11.5%.

A Systematic Review of Simulation in Burn Care: Education, Assessment, and Management.

Assessment and management of burns require nuanced, timely interventions in high-stake settings, creating challenges for trainees. Simulation-based education has become increasingly popular in surgical and nonsurgical subspecialties to supplement training without compromising patient safety. This study aimed to systematically review the literature on existing burn management-related simulations. A systematic review was conducted according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. Articles describing burn-specific surgical and nonsurgical simulation models were included. The model type, study description, simulated skills, assessment methods, fidelity, cost, and outcomes were collected. Of 3,472 articles, 31 met inclusion criteria. The majority of simulations were high-fidelity (n=17, 54.8%). Most were immersive (n=17, 54.8%) and used synthetic benchtop models (n=13, 41.9%), whereas none were augmented/virtual reality. Simulations of acute and early surgical intervention techniques (n=16, 51.6%) and burn wound assessments (n=15, 48.4%) were the most common, whereas burn reconstruction was the least common (n=3, 9.7%). Technical skills were taught more often (n=29, 93.5%) than non-technical skills (n=15, 48.4%). Subjective assessments (n=18, 58.1%) were used more often than objective assessments (n=23, 74.2%). Of the studies that reported costs, 91.7% (n=11) reported low costs. This review identified the need to expand burn simulator options, especially for burn reconstruction, and highlighted the paucity of animal, cadavers, and augmented/virtual reality models. Developing validated, accessible burn simulations to supplement training may improve education, patient safety, and outcomes.

Implementing supplementary breast cancer screening in women with dense breasts: Insights from European radiographers and radiologists

IntroductionIn response to the critical need for enhancing breast cancer screening for women with dense breasts, this study explored the understanding of challenges and requirements for implementing supplementary breast cancer screening for such women among clinical radiographers and radiologists in Europe. MethodFourteen (14) semi-structured online interviews were conducted with European clinical radiologists (n = 5) and radiographers (n = 9) specializing in breast cancer screening from 8 different countries: Denmark, Finland, Greece, Italy, Malta, the Netherlands, Switzerland, United Kingdom. The interview schedule comprised questions regarding professional background and demographics and 13 key questions divided into six subgroups, namely Supplementary Imaging, Training, Resources and Guidelines, Challenges, Implementing supplementary screening and Women's Perspective. Data analysis followed the six phases of reflexive thematic analysis. ResultsSix significant themes emerged from the data analysis: Understanding and experiences of supplementary imaging for women with dense breasts; Challenges and requirements related to training among clinical radiographers and radiologists; Awareness among radiographers and radiologists of guidelines on imaging women with dense breasts; Challenges to implement supplementary screening; Predictors of Implementing Supplementary screening; Views of radiologists and radiographers on women's perception towards supplementary screening. ConclusionThe interviews with radiographers and radiologists provided valuable insights into the challenges and potential strategies for implementing supplementary breast cancer screening. These challenges included patient and staff related challenges. Implementing multifaceted solutions such as Artificial Intelligence integration, specialized training and resource investment can address these challenges and promote the successful implementation of supplementary screening. Further research and collaboration are needed to refine and implement these strategies effectively. Implications for practiceThis study highlights the urgent need for specialized training programs and dedicated resources to enhance supplementary breast cancer screening for women with dense breasts in Europe. These resources include advanced imaging technologies, such as MRI or ultrasound, and specialized software for image analysis. Moreover, further research is imperative to refine screening protocols and evaluate their efficacy and cost-effectiveness, based on the findings of this study.

Expanding the pathfinder’s purpose: A pedagogical approach to redesigning LibGuides

Online research guides are an important service in academic libraries. Many argue for an instructional design approach that prioritizes course or assignment focused guides; however, this does not address how to design effective subject or topic guides that often follow outdated pathfinder structures. This case study outlines one subject library’s approach to redesigning their guides with pedagogy and accessibility at the forefront, demonstrating how to apply best practices articulated for course-based guides to a general setting. It addresses how to design effective subject guides to better facilitate patron browsing, promote the collection, and supplement training for staff at service points.

Polyp Generalization via Diversifying Style at Feature-Level Space

In polyp segmentation, the latest notable topic revolves around polyp generalization, which aims to develop deep learning-based models capable of learning from single or multiple source domains and applying this knowledge to unseen datasets. A significant challenge in real-world clinical settings is the suboptimal performance of generalized models due to domain shift. Convolutional neural networks (CNNs) are often biased towards low-level features, such as style features, impacting generalization. Despite attempts to mitigate this bias using data augmentation techniques, learning model-agnostic and class-specific feature representations remains complex. Previous methods have employed image-level transformations with styles to supplement training data diversity. However, these approaches face limitations in ensuring style diversity due to restricted style sources, limiting the utilization of the potential style space. To address this, we propose a straightforward yet effective style conversion and generation module integrated into the UNet model. This module transfers diverse yet plausible style features to the original training data at the feature-level space, ensuring that generated styles align closely with the original data. Our method demonstrates superior performance in single-domain generalization tasks across five datasets compared to prior methods.

A graduate student-staffed, low-cost mental health program: a community-based model to increase access to services

ABSTRACT Student-run and student-staffed behavioral health clinics increase service capacity and access to low-cost services and are usually created by medical schools and behavioral health graduate programs. There is little information about student-staffed programs developing independently of academic institutions. As the demand for mental health services continues to grow, it is essential that successful models of community-based service provision are shared so other agencies can replicate models and increase service capacity. This article outlines the elements of a student-staffed behavioral health program model run by a nonprofit. Details on staffing, student selection, supervision, evaluation methods, supplemental training, and funding are included.

MetaRLEC: Meta-Reinforcement Learning for Discovery of Brain Effective Connectivity

In recent years, the discovery of brain effective connectivity (EC) networks through computational analysis of functional magnetic resonance imaging (fMRI) data has gained prominence in neuroscience and neuroimaging. However, owing to the influence of diverse factors during data collection and processing, fMRI data typically exhibits high noise and limited sample characteristics, consequently leading to suboptimal performance of current methods. In this paper, we propose a novel brain effective connectivity discovery method based on meta-reinforcement learning, called MetaRLEC. The method mainly consists of three modules: actor, critic, and meta-critic. MetaRLEC first employs an encoder-decoder framework: the encoder utilizing a Transformer, converts noisy fMRI data into a state embedding; the decoder employing bidirectional LSTM, discovers brain region dependencies from the state and generates actions (EC networks). Then a critic network evaluates these actions, incentivizing the actor to learn higher-reward actions amidst the high-noise setting. Finally, a meta-critic framework facilitates online learning of historical state-action pairs, integrating an action-value neural network and supplementary training losses to enhance the model's adaptability to small-sample fMRI data. We conduct comprehensive experiments on both simulated and real-world data to demonstrate the efficacy of our proposed method.

Factors associated with the performance and achieving goals of specialized periodontal procedures in Brazilian dental specialties centers

BackgroundThe Brazilian Dental Specialty Centers (CEO, in Portuguese) represent the strategy of the National Oral Health Policy to provide secondary-level dental care. They offer more complex procedures, such as the treatment of periodontitis. This study aims to investigate the factors associated with the performance and the achievement goals of specialized procedures and the achievement gols of periodontics in CEO.MethodologyAnalytical and cross-sectional study using secondary data. The database of the second cycle of the External Evaluation of the National Program for Improving Access and Quality in CEO (PMAQ-CEO, in Portuguese), was utilized, which assessed 1,042 CEO on-site in 2018. The data were analyzed using multiple Poisson regression, estimating the prevalence ratio (PR) (p < 0.05).ResultsA third of the CEO (n = 305) performed all specialized procedures, with a higher prevalence observed in those with more than one bicarbonate jet prophylaxis unit (RP = 2.12; 95% CI: 1.160–3.881; p = 0.015) and when they had a higher percentage of specialist professionals (RP = 1.004; 95% CI: 1.002–1.006; p < 0.001). The periodontics goal was achieved by 617 (59.2%) CEO, with a higher prevalence among those who had a manager with supplementary training (PR = 1.21; 95% CI: 1.100-1.335; p < 0.001) and with a higher workload for the periodontist dentist (PR = 1.15; 95% CI: 1.103–1.201; p < 0,001).ConclusionAlthough most CEOs do not perform allspecialized periodontics procedures, more than half achieved the established goals. The provision of specialized periodontics services in CEO and the achievement of goals are influenced by the quantity and professional qualifications, as well as the availability of equipment.

Supplement data in federated learning with a generator transparent to clients

Federated learning is a decentralized learning approach that shows promise for preserving users' privacy by avoiding local data sharing. However, the heterogeneous data in federated learning limits its applications in wider scopes. The data heterogeneity from diverse clients leads to weight divergence between local models and degrades the global performance of federated learning. To mitigate data heterogeneity, supplementing training data in federated learning has been explored and proven effective. However, traditional methods of supplementing data raise privacy concerns and increase learning costs. In this paper, we propose a solution to supplement training data with a generative model that is transparent to local clients. We keep the learning of the generative model on the server side and store the supplementary data from the generative model on the server side as well. This approach avoids collecting auxiliary data directly from local clients, reducing privacy concerns for them and preventing rising costs for local clients. To avoid loose learning on the real and synthetic samples, we constrain the optimization of the global model with a distance between the training global model and the distribution of the aggregated global model. Extensive experiments have verified that the synthetic data from the generative model improve the performance of federated learning, especially in a heterogeneous environment.

Generative artificial intelligence and building design: early photorealistic render visualization of façades using local identity-trained models

Abstract This paper elucidates an approach that utilizes generative artificial intelligence (AI) to develop alternative architectural design options based on local identity. The advancement of AI technologies has increasingly piqued the interest of the architecture, engineering, construction, and facility management industry. Notably, the topic of “visualization” has gained prominence as a means for enhancing communication related to a project, especially in the early phases of design. This study aims to enhance the ease of obtaining design images during initial phases of design by drawing from multiple texts and images. It develops an additional training model to generate various design alternatives that resonate with the identity of the locale through the application of generative AI to the façade design of buildings. The identity of a locality in cities and regions is the capacity for the cities and regions to be identified and recognized as a specific area. Among the various visual elements of urban and regional landscapes, the front face of buildings may play a significant role in people’s aesthetic perception and overall impression of the local environment. The research proposes an approach that transcends the conventional employment of three-dimensional modeling and rendering tools by readily deriving design alternatives that consider this local identity in commercial building remodeling. This approach allows for financial and temporal efficiency in the design communication phase of the initial architectural design process. The implementation and utilization of the proposed approach’s supplementary training model in this study proceeds as follows: (i) image data are collected from the target area using open-source street-view resources and preprocessed for conversion to a trainable format; (ii) textual data are prepared for pairing with preprocessed image data; (iii) additional training and outcome testing are performed using varied text prompts and images; and (iv) the ability to generate building façade images that reflect the identity of the collected locale by using the additional trained model is determined, as evidenced by the findings of the proposed application method study. This enables the generation of design alternatives that integrate regional styles and diverse design requirements for buildings. The training model implemented in this study can be leveraged through weight adjustments and prompt engineering to generate a greater number of design reference images, among other diverse approaches.

Group behavior recognition algorithm for basketball video based on hidden tag mining strategy under gamification teaching and learning

The rapid development of Artificial Intelligence has facilitated the development of multimedia teaching and learning in the field of education, as well as providing intelligent methods for gamified teaching methods in the field of basketball. Currently, research on recognizing basketball video behavior primarily focuses on group behavior recognition methods for key individuals. However, there is currently no group behavior recognition method that can effectively distinguish features that reflect different events for temporal interactive behaviors such as dunks and steals in videos, as well as situations where key players are obstructed. The paper suggests a group behavior identification algorithm for basketball game videos based on the hidden tag mining technique in order to perform intelligent analysis in the fields of supplemental training and tactical analysis of gamified instruction. And this algorithm is integrated with the fusion of individual features to create the basketball video's group behavior identification algorithm with hidden label mining approach. According to the study's findings, the distribution of motion pattern features is more agglomerated and regular when the merging threshold is 0.6 and the best hyperparameter is 3. After the study applied the crucial individual feature extraction module, the overall group behavior identification accuracy increased by 6.44 %. The group behavior recognition algorithm for basketball videos that incorporates individual features and hidden label mining techniques outperforms the most recent patio-temporal domain-based group behavior recognition algorithm by 15.56 % when compared to the accuracy of commonly used algorithms. In summary, the study proposes a basketball video group behavior recognition algorithm with better performance. This algorithm achieves group behavior recognition in basketball game videos, promotes auxiliary training for students in gamified teaching mode, and provides a practical and feasible approach for intelligent analysis of other sports events. It also provides technical support for coaches and referees.

Spirulina supplement and exercise training affect lipid droplets-related genes expression in visceral adipose tissue.

Disruption of lipid droplets (LDs) is associated with many metabolic diseases. Spirulina, as a natural bioactive dietary supplement, along with exercise training, may improve lipid metabolism; however, their effects on LDs-regulated genes in visceral adipose tissue are still unclear. This study aimed to investigate the effects of six-week Spirulina supplementation along with exercise training on LDs regulating gene expression. Fifty-six male Wistar rats were divided into six groups: saline (control), control+Spirulina (Spirulina), aerobic interval training (AIT), AIT+ Spirulina (AIT+Spirulina), resistance training and resistance+ Spirulina. The supplement groups consumed 500 mg/kg Spirulina five days per week. The training groups performed AIT (5 times per week) and resistance training (3 times per week) for 6 weeks. LDs regulating genes expression in visceral adipose tissue (Zw10, Bscl2, DFCP1, Rab18, Syntaxin 18, Acsl3, and Plin2) was analyzed by real-time PCR. Spirulina and exercise training had no significant effects on the gene expression of Syntaxin18 (p=0.69) and DFCP1 (p=0. 84), ACSL3 (p=0.98), or BSCL2 (p=0.58). In addition, Spirulina was found to significantly attenuate the expression of Plin2 (p=0.01) and Rab18 (p=0.01) genes compared to the control, AIT, and resistance training groups. However, Plin2 gene expression was higher in the resistance training than the AIT. Furthermore, Spirulina decreased ZW10 (p=0.03) gene expression in visceral adipose tissue compared to the control, AIT, and resistance training groups. Unexpectedly, Spirulina supplementation decreased the expression of these genes even more when taken without exercise training. Spirulina supplementation and exercise training have significant effects on LDs-regulated genes in visceral adipose tissue.

The effect of supplementing regular training with short-duration sprint-agility training on sprint-ability performance in university level badminton players

Abstract: BACKGROUND: The badminton being a highly explosive sport involves a unique movement technique and strength with a combination of speed (anaerobic fitness) and endurance (aerobic fitness). Strength, power, agility, and flexibility are key components of fitness as a part of a player’s fitness training. This training helps to promote recovery from exercise as well as restoring muscle energy for the next bout of activity. OBJECTIVE: The objective of this study was to evaluate the effect of supplementary regular training and short-duration sprint-agility training versus regular training on sprint-ability performance in university-level badminton players. METHODOLOGY: Thirty university-level badminton players were selected randomly and divided into Group A as regular training along with short-duration sprint-agility training and Group B as regular training group. Groups A and B received regular training for 5 days for 4 weeks and short-duration sprint-agility training for 2 days a week, respectively. Pre- and postset of performance tests were conducted which consist of 10-m sprint, 20-m sprint, 300-m shuttle run, badminton-specific repeated-agility sprint-ability test, and 20-m multistage shuttle run test for oxygen consumption (VO2). RESULTS: There was a significant increase between both the groups in badminton shuttle distance (Group-A 34.51% &gt;Group-B 13.87%), 20 m sprint time (Group-A 15.02% &gt;Group-B 9.57%), and VO2 max (Group-A 5.61% &gt;Group-B 3.94%). CONCLUSION: Supplementing regular training with sessions of short-duration sprint training led to substantial increase in repeated-agility sprint performance which helps to restore muscle energy and improve activity performance in university-level badminton players.

Beefing up communication skills of upper-level animal science students.

Animal scientists face an increasing need to communicate with the lay public because of the public's interest in the origin and production of animal-sourced foods. Consumers' increased interest infers a critical need for effective communication skills among animal science graduates. Effective communication skills are mandatory if students are to explain scientific information and mitigate misinformation about livestock production. The purpose of our study was to investigate the communication styles and communication effectiveness of upper-level animal science students enrolled in a beef cattle production and management course at Texas A&M University across five semesters (N = 241; spring 2018 = 61, summer 2018 = 15, Fall 2018 = 54, spring 2019 = 55, and fall 2019 = 56). Male animal science students (n = 25; 32.9%) preferred assertive and direct communication (a driver communication style) and female students (n = 32; 19.4%) preferred collaborative and accommodating communication (an amiable communication style). Students were moderately experienced with beef cattle production (M = 3.09, SD = 1.07) before enrolling in the course; however, former beef cattle experiences did not influence their preferred communication style [F(10, 230) = 0.36, P = 0.96]. Researchers also observed students' communication skills during an end-of-semester beef cattle production and management project presentation and identified strengths and weaknesses. Students demonstrated strong, in-depth animal industry knowledge, an ability to connect beef production techniques to management success, and critical thinking skills when answering questions. Oral communication skills warranting improvement included integrating visual aids and/or visual slides to support findings, using improved stage presence and confidence, and sharing responsibilities when presenting as a team. Finally, completion of a supplemental communication training module, intended to develop oral communication skills, significantly improved [F(1, 55) = 4.16, P = 0.046] students' beef cattle production and management project presentation scores. As students become aware of their communication preferences and tendencies, they become equipped to adjust their communication practices and techniques when needed. Through this study, we gained insight into students' communication tendencies and skills, which can be used to provide curricular recommendations and enhance students' workforce readiness.

Recruiting neural field theory for data augmentation in a motor imagery brain-computer interface.

We introduce a novel approach to training data augmentation in brain-computer interfaces (BCIs) using neural field theory (NFT) applied to EEG data from motor imagery tasks. BCIs often suffer from limited accuracy due to a limited amount of training data. To address this, we leveraged a corticothalamic NFT model to generate artificial EEG time series as supplemental training data. We employed the BCI competition IV '2a' dataset to evaluate this augmentation technique. For each individual, we fitted the model to common spatial patterns of each motor imagery class, jittered the fitted parameters, and generated time series for data augmentation. Our method led to significant accuracy improvements of over 2% in classifying the "total power" feature, but not in the case of the "Higuchi fractal dimension" feature. This suggests that the fit NFT model may more favorably represent one feature than the other. These findings pave the way for further exploration of NFT-based data augmentation, highlighting the benefits of biophysically accurate artificial data.

Addressing the SUD training gap: Two pilot feasibility studies in the Department of Veteran's Affairs Health Care System

IntroductionSubstance use disorders (SUDs) are an ongoing public health crisis in the United States. A large body of research indicates an urgent need for increased training in SUD research and treatment for trainees in mental health service disciplines. The VA Health Care System is well positioned, as the largest trainer and employer of health service psychologists and other mental health professionals, to address the SUD training gap and serve as a leader in training the upcoming health care workforce. MethodTo this end, we conducted two pilot studies to (1) examine the feasibility of implementing supplemental SUD training for VA health service trainees, among current VA mental health service providers in psychology, social work, and medical care (N = 37) and (2) the efficacy of a single 2-hour interdisciplinary SUD training seminar for VA health service trainees in mental health (N = 13). The training seminar consisted of several components including lecture, facilitated discussion, and role play, aimed at increasing trainee self-efficacy in assessing and diagnosing SUDs. ResultsFindings suggest that current providers are supportive of supplemental SUD training for VA trainees and believe that such training is beneficial for those wishing to pursue a career within the VA Health Care System. Additionally, results suggest that a single session didactic seminar improved trainees' self-reported efficacy in the assessment and referral of veterans diagnosed with SUDs. ConclusionsOverall, the above studies support additional feasibility investigations that would pave the way for successful implementation of widespread SUD training programs across the VA Health Care System and beyond. Successful implementation would then serve to reduce the increasingly critical SUD provider shortage, thus leading to significant public health gains.