Independent Training Research Articles

Impact of Moderate-To-Vigorous Sports Participation Combined with Resistance Training on Metabolic and Cardiovascular Outcomes among Lean Adolescents: ABCD Growth Study.

To investigate the combined impact of being engaged in resistance training (RT) and meeting the physical activity guidelines through sports participation (SP) on cardiovascular and metabolic parameters in lean adolescents. A longitudinal study, part of the ongoing study entitled "ABCD Growth Study" (Analysis of Behaviors of Children During Growth), assessed data from 64 adolescents (23 from the sport group, 11 from the sport + RT group, and 30 from the control group). Metabolic and cardiovascular outcomes were analyzed as dependent variables. For the independent variables, sports participation and resistance training were considered, and for the covariates, sex, chronological age, body weight, height, and somatic maturation. After 12 months of follow-up, the RT + SP presented improvements in triglycerides (TG) and the SP presented a reduction in LDL-c, TG, and glucose when compared to the control group. Being engaged in RT and SP is a good strategy to improve health in eutrophic adolescents, with a great impact on TG from the lipid profile.

Embarrassingly Parallel Independent Training of Multi-Layer Perceptrons with Heterogeneous Architectures

In this paper we propose a procedure to enable the training of several independent Multilayer Perceptron Neural Networks with a different number of neurons and activation functions in parallel (ParallelMLPs) by exploring the principle of locality and parallelization capabilities of modern CPUs and GPUs. The core idea of this technique is to represent several sub-networks as a single large network and use a Modified Matrix Multiplication that replaces an ordinal matrix multiplication with two simple matrix operations that allow separate and independent paths for gradient flowing. We have assessed our algorithm in simulated datasets varying the number of samples, features and batches using 10,000 different models as well as in the MNIST dataset. We achieved a training speedup from 1 to 4 orders of magnitude if compared to the sequential approach. The code is available online.

Paradigm Shift in Vascular Surgery Training: Independent versus Integrated Match Outcomes

Currently, 2 predominant pathways exist for vascular surgery training: integrated and independent training pathways. We hypothesized that match rates would increase with time and be higher in the independent pathway than in the integrated pathway. The National Resident Matching Program provided data from the Vascular Surgery Match (VSM) (2008-2021). Match rates were defined as the percentage of applicants who matched. Chi-squared tests were used to evaluate temporal trends and interpathway differences. Over the study period, the annual number of training positions increased for both the independent (119 to 129, 8% increase) and integrated (9 to 79, 778% increase) training pathways. From 2008 to 2021, the annual match rate was stable in the independent pathway (97% to 96%, P>0.05). In the integrated pathway, the annual match rate increased from 29% to 44% (P<0.001). During each year, match rates in the independent pathway exceeded those in the integrated pathway (P<0.001). US allopathic graduates had higher match rates than non-US allopathic graduates in both the independent (92% vs. 82%, P<0.001) and the integrated pathway (70% vs. 17%, P<0.001). In the independent pathway, the percentage of applicants that matched at 1 of their top 3 choices decreased from 67% to 58% (P<0.001). Over the study period, more training positions went unmatched in the Independent (n=130, 8%) versus the Integrated (n=17, 3%) pathway (P<0.001). VSM match rates have increased for the integrated pathway and remains competitive especially for non-US allopathic graduates. More research is needed to understand applicant variables that modulate match rates.

Determination of Training Material and Organisational Culture Impact in Vocational Training Effectiveness in Bahrain

The focus of this study is on vocational training programs effectiveness related antecedents at the public sector in Bahrain. The study employed the Kirkpatrick model as the framework of the research and evaluated the vocational training effectiveness as the dependent variable. The study explores the relationship that exists between the independent variables, training material, and organizational culture together with the training effectiveness. For data collection, a survey instrument was developed from 46 items distributed to the Bahraini public sector employees to test the two hypotheses. One hundred and twenty-eight (128 questionnaires were the usable obtained total. The quantitative method is the applied design analyzed by the SPSS statistic software package. The findings indicate a positive and significant relationship from both factors at Kirkpatrick’s level of interest (result) and the training effectiveness. Also, unpredictably this study conquers a challenging and interesting area in the training setting for researchers in examining and optimizing the modality of training programmes. The study principally adds to the limited literature concerning vocational training effectiveness and training antecedents in the public sector. Effective training demands the organizations’ administration and specialists to optimize the antecedents of training to achieve the organization’s/training’s objectives. Comprehending the consequence of these specific variables will assist the establishment to increase the training benefits and accordingly the human resources performance. Thus, these variables’ importance should not be underestimated. The administration is supposed as well to take responsibility in promoting effective variables and drawing up an effective view.

Imaging biomarkers to stratify lymph node metastases in abdominal CT – Is radiomics superior to dual-energy material decomposition?

PurposeTo assess the potential of radiomic features in comparison to dual-energy CT (DECT) material decomposition to objectively stratify abdominal lymph node metastases. Materials and methodsIn this retrospective study, we included 81 patients (m, 57; median age, 65 (interquartile range, 58.7–73.3) years) with either lymph node metastases (n = 36) or benign lymph nodes (n = 45) who underwent contrast-enhanced abdominal DECT between 06/2015–07/2019. All malignant lymph nodes were classified as unequivocal according to RECIST criteria and confirmed by histopathology, PET-CT or follow-up imaging. Three investigators segmented lymph nodes to extract DECT and radiomics features. Intra-class correlation analysis was applied to stratify a robust feature subset with further feature reduction by Pearson correlation analysis and LASSO. Independent training and testing datasets were applied on four different machine learning models. We calculated the performance metrics and permutation-based feature importance values to increase interpretability of the models. DeLong test was used to compare the top performing models. ResultsDistance matrices and t-SNE plots revealed clearer clusters using a combination of DECT and radiomic features compared to DECT features only. Feature reduction by LASSO excluded all DECT features of the combined feature cohort. The top performing radiomic features model (AUC = 1.000; F1 = 1.000; precision = 1.000; Random Forest) was significantly superior to the top performing DECT features model (AUC = 0.942; F1 = 0.762; precision = 0.800; Stochastic Gradient Boosting) (DeLong < 0.001). ConclusionImaging biomarkers have the potential to stratify unequivocal lymph node metastases. Radiomics models were superior to DECT material decomposition and may serve as a support tool to facilitate stratification of abdominal lymph node metastases.

Comparing Match Outcomes in a Surgical Subspecialty: Independent Versus Integrated Training Pathways

In recent years, the Thoracic Surgery Match (TSM) has become increasingly competitive. The purpose of this study was to compare recent trends in application and match rates in the TSM by training pathway. This was a retrospective cohort study of all applicants to Integrated and Independent pathways for Thoracic Surgery training (2008-2021). Chi square tests were used to elucidate temporal trends and make comparisons by training pathway. Accreditation Council for Graduate Medical Education (ACGME)-accredited Thoracic Surgery training programs in the United States. 1500 Independent and 1242 Integrated pathway applicants for Thoracic Surgery training. From 2008 to 2021, the annual match rate decreased from 91% to 71% in the Independent pathway (p < 0.001). This was driven by a decrease in the number of training positions (130-101, 22% decrease) and increase in number of applicants (96-140, 46% increase). In the Integrated pathway, the annual match rate increased from 33% to 35% (p < 0.001) as did the number of training positions (3 to 46, 1430% increase) and applicants (9-129, 1333% increase). During each year, match rates in the Independent pathway exceeded those in the Integrated pathway (p < 0.001). U.S. Allopathic graduates had higher match rates than non-U.S. Allopathic graduates for both Integrated and Independent training pathways. The percentage of applicants in the Independent pathway matching at one of their top 3 choices decreased from 73% to 40% (p < 0.001). The percentage of Independent thoracic surgery training positions that went unmatched decreased from 28% to 2% (p < 0.001). This percentage was stable at an average of 1% in the Integrated pathway (p > 0.05). The TSM has become increasingly competitive for Independent pathway applicants and remains ultracompetitive for Integrated pathway applicants. More research is needed to understand disparities in match rates by Thoracic Surgery training pathway.

The vascular surgery in-training examination predicts performance on qualifying examination.

Vascular surgery trainees participate in the vascular surgery in-training examination (VSITE) during each year of their training. Although the VSITE was developed as a low-stakes, formative examination, performance on that examination might correlate with the pass rates for the Vascular Surgery Board written qualifying examination (VQE) and oral certifying examination (VCE) and might, therefore, guide both trainees and program directors. The present study was designed to examine the ability of the VSITE to predict trainees' performance on the VQE and VCE. All first-time candidates of the Vascular Surgery Board VQE and VCE were analyzed from 2016 to 2020, including those from both the integrated and independent training pathways. VSITE scores from the final year of training were associated with the VQE scores and the probability of passing the VQE and VCE both. Linear and logistic regression models were used to determine the ability of VSITE results to predict the VQE scores and the probability of passing each board examination. VSITE scores available for the 559 candidates (69.3% male; 30.7% female) who had completed the VQE and 369 candidates (66.7% male; 33.3% female) who had completed both the VQE and the VCE. The linear regression model results for the final year of training showed that the VSITE scores explained 34% of the variance in the VQE scores (29% for the integrated and 37% for the independent trainees). Logistic regression demonstrated that the final year VSITE scores were a significant predictor of passing the VQE for both integrated and independent trainees (P< .001). A VSITE score of 500 during the final year of training predicted a VQE passing probability of >90% for each group of candidates. The probability of passing the VQE decreased to 73% for candidates from integrated programs, 61% for candidates from independent programs, and 64% for the whole cohort when the score was 400. The VSITE scores were a significant predictor of passing the VCE only for the candidates from independent programs (odds ratio, 1.01; 95% confidence interval, 1.00-1.02; P< .01), for whom a VSITE score of 400 correlated with an 82% probability of passing the VCE. VSITE performance is predictive of passing the VQE for trainees from both integrated and independent training paradigms. Vascular surgery trainees and training programs should optimize their preparation and educational efforts to maximize performance on the VSITE during their final year of training to improve the likelihood of passing the VQE. Further analysis of the predictive value of VSITE scores during the earlier years of training might allow the board certification examinations to be administered earlier in the final year of training.

Predicting Amyloid Positivity from Hippocampal and Entorhinal Cortex Volume and APOE Genotype

AbstractBackgroundAccumulation of brain amyloid – an early indicator of AD – is assessed using PET or CSF samples, but such procedures are highly invasive. There is interest in using less invasive data, such as brain MRI, to predict β‐amyloid (Aβ) positivity, as a precursor to more invasive screening.Here we assessed different predictive models based on logistic regression, using readily measured indices from T1‐weighted MRI (T1w). We hypothesized that entorhinal cortex measures would outperform hippocampal measures in predicting amyloid positivity, given its role as a cortical area with early amyloid accumulation.MethodWe analyzed T1w from 724 subjects (Table 1) from the Alzheimer’s Disease Neuroimaging Initiative (ADNI). One cut‐off, for determining amyloid levels, was used based on PET cortical SUVR uptake (Αβ_1) determined by either mean 18F‐florbetapir (Aβ+ defined as &gt;1.11) or florbetaben (Aβ+ defined as &gt;1.20), normalized by using whole cerebellum reference region. After registering the T1w image to a common template, we split the data into independent training and testing sets. A logistic regression classifier was used, and test performance was assessed using balanced accuracy to compare the different predictive models.ResultFigure 1 shows classification results from the models. The balanced accuracy was highest (74.9%) for the logistic regression model including both left and right entorhinal cortex volumes, APOE status, age, and sex. This model outperformed models using hippocampal volume as the main imaging predictor (balanced accuracy 70.8%).ConclusionOptimal accuracy was obtained when predicting Aβ positivity from brain MRI using entorhinal cortical measures. Future work will test deep learning methods for Aβ prediction based on paired training data, and will use voxel‐based data and features from other imaging modalities, such as diffusion MRI, to predict amyloid status.

Usability of an exosuit in domestic and community environments

BackgroundExosuits have been shown to reduce metabolic cost of walking and to increase gait performance when used in clinical environment. Currently, these devices are transitioning to private use to facilitate independent training at home and in the community. However, their acceptance in unsupervised settings remains unclear. Therefore, the aim of this study was to investigate end-user perspectives and the adoption of an exosuit in domestic and community settings.MethodsWe conducted a mixed-method study to investigate the usability and user experience of an exosuit, the Myosuit. We leveraged on a cohort of seven expert users, who had the device available at home for at least 28 days. Each participant completed two standardized questionnaires (SUS and QUEST) and one personalized, custom questionnaire. Furthermore, a semi-structured interview with each participant was recorded, verbatim transcribed and analyzed using descriptive thematic analysis. Data collected from device sensors quantified the frequency of use.ResultsA mean SUS score of 75.4 out of 100 was reported. Five participants scored above the threshold for above-average usability. Participants also expressed high satisfaction with most of the technical features in the QUEST with an average score of 4.1 (3.86–4.71) out of 5. Participants used the Myosuit mainly for walking outside and exercising at home. However, the frequency of use did not meet the recommendations for physical activity established by the World Health Organization. Five participants used the Myosuit approximately once per week. The two other participants integrated the device in their daily life and used the Myosuit to a greater extent (approx. five times per week). Major factors that prevented an extensive use of the technology were: (i) difficulties in donning that led to (ii) lack of independence and (iii) lack of motivation in exercising.ConclusionsAlthough usable for various activities and well perceived, the adoption of the exosuit in domestic and community settings is yet limited. Use outside the clinic poses further challenges that should be considered when developing new wearable robots. Primarily, design should meet the users' claim for independence and increased adjustability of the device.

PENYUSUNAN KURIKULUM OPERASIONAL PADA SATUAN PAUD BERBASIS KURIKULUM MERDEKA

Curriculum is dynamic and it needed to change to adjust to the context and goals of the society, however it is also not always easy for teachers who implement the curriculum. This community service activity aims to help PAUD teachers, especially Kindergarten (TK) levels in understanding the existence of curriculum changes, namely the Kurikulum Merdeka so that teachers can understand, plan, and implement learning at the kindergarten level. The target of this community service (PKM) activity is 25 kindergarten teachers in Mojokerto City. The PKM design carried out were: socialization of the independent curriculum and training in preparing activity plans in learning in kindergarten. This community service uses the lecture, discussion, assignment, and simulation methods, this PKM is carried out both online and offline to provide experience in compiling and implementing learning in kindergarten. The results of this PKM can be seen from the results of the pre-test and post-test. Kindergarten teachers in the City of Mojokerto already have knowledge of the Independent Curriculum but not in its entirety. Based on the results of a questionnaire filled out by 25 kindergarten teachers in Mojokerto City, it was found that only 8.7% of institutions had used the Kurikulum Merdeka. 52.2% use a mixed curriculum (50% PAUD 2013 Curriculum and 50% Kurikulum Merdeka). As many as 39.1% still use the 2013 PAUD Curriculum, so it can be concluded from this PKM is the creation of the ability of kindergarten teachers in preparing, planning and implementing Kurikulum merdeka appropriately.

Arabic Expresion Teaching Model on Youtube “Muhaiban Channel”

Purpose - The objectives of this study are: (1) to describe the learning model of Arabic expressions in Muhaiban Channel (2) to find out the content of Arabic expressions in Muhaiban Channel&#x0D; Design/methodology/approach - This research used a descriptive qualitative method with the type of literacy study. The method used to collect research data is in the form of books about teaching Arabic, teaching vocabulary, and selected learning media, presented and analyzed, and processed to be concise and systematic and data analysis using content analysis.&#x0D; Findings/result - The results of this study are: (1) the learning model starts with orientation, presentation, guided training, independent training, and closing, (2) the content of Arabic expression material starts from simple material, namely from everyday expressions which are explained in detail.&#x0D; Originality/value, Utilization of YouTube as a medium for learning Arabic expressions in the era of technological development&#x0D; Paper type, Research paper

Correlation of Scholarly Activity and Departmental Clinical Productivity in a Surgical Subspecialty

IntroductionPromotion within academic surgery involves demonstrated excellence in administrative, clinical, and scholarly activities. The present study analyzes the relationship between scholarly and clinical productivity in the field of reconstructive microsurgery. MethodsThis is a retrospective cohort study of microsurgery fellowship directors (MFDs). Data on clinical productivity were obtained from the American Society for Reconstructive Microsurgery and scholarly productivity from Scopus. Outcomes were department annual free flap volume, number of publications, and h-index. Descriptive statistics were calculated, and nonparametric tests were used to compare continuous variables. ResultsThirty-nine MFDs were included in this study. All were plastic surgery residency trained and 38% trained under the independent training pathway. Most underwent formal fellowship training in reconstructive microsurgery (89%). The top three microsurgery fellowships trained 37% of all MFDs. Twenty-five percent of MFDs trained at the institution where they ultimately became program director. Twenty percent of MFDs had an additional degree (4 MS, 2 PhD, and 1 MBA). The median number of annual free flaps performed per institution was 175 (interquartile range [IQR] 122). The median h-index was 17 (IQR 13) resulting from 48 (IQR 99) publications. There was a correlation between department annual free flap volume and h-index (r = 0.333, P = 0.038). ConclusionsThere is a correlation between academic productivity of MFDs and the clinical productivity of their department. This study provides a benchmark for aspiring reconstructive microsurgeons.

Target-AMP: Computational prediction of antimicrobial peptides by coupling sequential information with evolutionary profile

Antimicrobial peptides (AMPs) are gaining a lot of attention as cutting-edge treatments for many infectious disorders. The effectiveness of AMPs against bacteria, fungi, and viruses has persisted for a long period, making them the greatest option for addressing the growing problem of antibiotic resistance. Due to their wide-ranging actions, AMPs have become more prominent, particularly in therapeutic applications. The prediction of AMPs has become a difficult task for academics due to the explosive increase of AMPs documented in databases. Wet-lab investigations to find anti-microbial peptides are exceedingly costly, time-consuming, and even impossible for some species. Therefore, in order to choose the optimal AMPs candidate before to the in-vitro trials, an efficient computational method must be developed. In this study, an effort was made to develop a machine learning-based classification system that is effective, accurate, and can distinguish between anti-microbial peptides. The position-specific-scoring-matrix (PSSM), Pseudo Amino acid composition, di-peptide composition, and combination of these three were utilized in the suggested scheme to extract salient aspects from AMPs sequences. The classification techniques K-nearest neighbor (KNN), Random Forest (RF), and Support Vector Machine (SVM) were employed. On the independent dataset and training dataset, the accuracy levels achieved by the suggested predictor (Target-AMP) are 97.07% and 95.71%, respectively. The results show that, when compared to other techniques currently used in the literature, our Target-AMP had the best success rate.

PEMILAHAN SAMPAH MANDIRI DAN TEKNIK PEMBUATAN PUPUK ORGANIK CAIR DARI SAMPAH ORGANIK DI DESA SIDOREJO, KECAMATAN BANDONGAN, MAGELANG, JAWA TENGAH

This community service aims to help train the community, especially housewives and farmer groups in Sidorejo Village in carrying out waste sorting independently and intensively as well as providing information on utilizing household organic waste as liquid organic fertilizer. This is because there is still no training on the importance of an effort to utilize waste, especially inorganic and organic waste produced by household waste. The methods used are lectures, questions and answers, forum discussions, and workshops on independent waste management training practices. The strategy for managing inorganic waste such as plastic can be done by recycling and depositing it in a waste bank to reduce environmental pollution. Inorganic waste is difficult to decompose by nature so that plastic waste can be used as handicraft products to reduce waste. Meanwhile, organic waste can be utilized by making liquid organic fertilizer based on EM4 bioactivator which can be applied to plants. With training and information on waste sorting independently and intensively, it is hoped that the community will be more concerned about the environment and be able to manage waste independently so that they can protect the environment and nature. Information in the form of processing organic waste into liquid fertilizer is expected to be continued into organic waste management into liquid fertilizer so that people can increase their income and become business opportunities that can improve people's welfare in the future.

Use of the vibroacoustic system for determining the range of a ski jump for training athletes

The principle of vibroacoustic systems operation for determining the distance of a ski jump from a springboard, the possible location of sensors on the springboard and sensor signals that occur when athlete lands are considered. The problems of calculating the jump distance and methods for solving these problems are described. The interrelation of the technique of performing a jump (the spatial position of the skis at the time of landing and the normal component of the landing speed relative to the surface of the springboard) with the form of sensor signals is considered. Real waveforms of signals obtained both during the summer artificial covering of the springboard and in winter, as well as generalized results of experimental operation of the system on springboards with different heights of the acceleration mountain are presented. It is shown that the use of vibroacoustic systems allows achieving the required accuracy of determining the ski jump distance – 0.5 m, and the integration of the system with the general jump monitoring system opens up new opportunities for independent training of athletes and training of a group of athletes under the guidance of a coach.

The Effects of Nintendo Wii Fit on Postural Balance Control Training in the Geriatric Population: A Review.

Elderly populations who engage in consistent, moderate-intensity exercise are more physically active and have better health than elders who have a sedentary lifestyle. Ageing causes the quality and number of muscle fibres to decline, leaving them with less endurance and ability to effectively work in synchronization and less strength and stamina to support weight or keep a sound body system. Medical practitioners often use the word "balance" across many therapeutic disciplines. Balance is commonly used in conjunction with other ideas like stability and postural control. The capacity of the physiological systems to keep the centre of mass within the base of support during static and dynamic postures and to govern physical alignment in an upright position is known as "balance." Impaired balance has a wide range of effects that can harm physical functionality. Falls in the elderly can result in hip fractures and significant morbidity and mortality. Balance dysfunction is one of the primary reasons behind decreased mobility and postural control in the elderly. It mainly affects the ability to walk and to maintain balance control in everyday life. Virtual reality (VR) can be defined as an interaction model between humans and computers that allows conventional computer-based training. It is a novel and expanding technology combining various characteristics like interactivity, independence, and rehabilitation training. These technologies replicate a seemingly natural environment. A fun and engaging aspect of VR technology is the Wii Fit games. These are enjoyable versions of the fundamental exercise and are widely used. A physiotherapy intervention programme can be structured using Wii Fit games to perform balance exercises. These games are widely used for balance training in the geriatric population.

Military and patriotic education of apprentice and student youth, cadets in the sports group «Combat Horting» under the conditions of marital state

The role of the «Combat Horting» sports clubs, especially in the conditions of martial law, is to promote the level of military-patriotic upbringing of school and student youth, cadets; forming among young people a persistent interest and need for regular classes in Ukrainian martial arts; raising the level of education in the field of physical culture, sports and a healthy lifestyle; improving the quality of the process of physical education and education among young people, etc.&#x0D; Scientific works are analyzed in the scientific article N., Dovgan, M., Zubalii, K., Kukushkin, O., Ostapenko, S., Prysiazhniuk L., Pustoliakova, T., Fedorchenko, A., Khatko and other which reveal some aspects of the military-patriotic education of schoolchildren and student youth, cadets in the «Combat Horting» sports club.&#x0D; Also, the concept of military-patriotic education of children and young people by means of combat horting (author E., Yeromenko) described by Z., Dikhtiarenko has been improved, as a predicted result of independent training with Combat Horting in conditions of martial law for school and student youth and cadets. The concept of «martial law» is singled out in the Law of Ukraine «On the Legal Regime of Martial Law».&#x0D; The authors of the publication proved that the national professional and applied sport of Ukraine is Combat Horting, which is based on the cultural, health and martial traditions of the Ukrainian people and contributes to the comprehensive education of the younger generation to ensure the security of the state independence of Ukraine, eliminating threats to the preservation of the integrity of Ukrainian lands. It is a multi-year specially organized process of learning, comprehensive development, moral and ethical education and improvement of children and youth.&#x0D; On the basis of the Concept of military-patriotic education of children and youth by means of combat horting (author E., Yeromenko) [5, p. 37-43] and the analysis of literary sources [1-23], Z., Dikhtiarenko determined the indicators for the predicted result of independent training with Combat Horting in conditions of martial law (to know; to be able to) for school and student youth and cadets.

Investigation of small lung lesion detection for lung cancer screening in low dose FDG PET imaging by deep neural networks.

FDG PET imaging is often recommended for the diagnosis of pulmonary nodules after indeterminate low dose CT lung cancer screening. Lowering FDG injecting is desirable for PET imaging. In this work, we aimed to investigate the performance of a deep learning framework in the automatic diagnoses of pulmonary nodules at different count levels of PET imaging. Twenty patients with 18F-FDG-avid pulmonary nodules were included and divided into independent training (60%), validation (20%), and test (20%) subsets. We trained a convolutional neural network (ResNet-50) on original DICOM images and used ImageNet pre-trained weight to fine-tune the model. Simulated low-dose PET images at the 9 count levels (20 × 106, 15 × 106, 10 × 106, 7.5 × 106, 5 × 106, 2 × 106, 1 × 106, 0.5 × 106, and 0.25 × 106 counts) were obtained by randomly discarding events in the PET list mode data for each subject. For the test dataset with 4 patients at the 9 count levels, 3,307 and 3,384 image patches were produced for lesion and background, respectively. The receiver-operator characteristic (ROC) curve of the proposed model under the different count levels with different lesion size groups were assessed and the areas under the ROC curve (AUC) were compared. The AUC values were >0.98 for all count levels except for 0.5 and 0.25 million true counts (0.975 (CL 95%, 0.953-0.992) and 0.963 (CL 95%, 0.941-0.982), respectively). The AUC values were 0.941(CL 95%, 0.923-0.956), 0.993(CL 95%, 0.990-0.996) and 0.998(CL 95%, 0.996-0.999) for different groups of lesion size with effective diameter (R) <10 mm, 10-20 mm, and >20 mm, respectively. The count limit for achieving high AUC (≥0.96) for lesions with size R < 10 mm and R > 10 mm were 2 million (equivalent to an effective dose of 0.08 mSv) and 0.25 million true counts (equivalent to an effective dose of 0.01 mSv), respectively. All of the above results suggest that the proposed deep learning based method may detect small lesions <10 mm at an effective radiation dose <0.1 mSv. We investigated the advantages and limitations of a fully automated lung cancer detection method based on deep learning models for data with different lesion sizes and different count levels, and gave guidance for clinical application.

Improving soft skills and hard skills Wagra Learning Package C through the independent education curriculum in the Merdeka Belajar Scheme

Education is an important component of the life of any member of society. Studying in an educational institution alone is not enough to be successful. There are other supporting skills that can be acquired by the community besides formal education. This is the reason why independent education is an ideal concept in the Merdeka Belajar scheme. The purpose of this work is to learn and apply the principles of self-education that focus on improving the soft skills and hard skills of residents learning package c in the province of North Sulawesi. This goal is achieved through pedagogical experiments carried out at learning activity center institutions (SKB) and community learning activity centers (PKBM), through surveys of the needs of learning civil service practitioners and learning residents at different levels of education. Statistical data on the dynamics of self-education are analyzed through statistical and descriptive methods. The results of measuring the need for soft skills and hard skills found that factors of age, gender, and employment status influenced the choice and lack in improvement of soft skills and hard skills in independent education training. Factors such as leadership, determination, self-control and self-organization, work independence, and work skills became the main foundation in the preparation of the self-education curriculum of citizens learning package C. The factors contained in the self-education curriculum material affect the level of knowledge and increase educational motivation, social interaction and goals, show in the knowledge gained and help apply the approach to learning package C residents. This study shows that an independent education curriculum based on the needs of soft skills and hard skills must be carried out consistently and regularly by non-formal educational institutions. In supporting the Merdeka Belajar Program, the independent education curriculum prepared from this work can be used as a reference for separate education policies in formal education schemes

Abstract 11648: ECG-Derived Features Enable Prediction of Sudden Death in Ischemic Cardiomyopathy

Introduction: Low left ventricular ejection fraction (LVEF) is an imperfect predictor of sudden cardiac death (SCD) in patients with ischemic cardiomyopathy. Novel features identified via automated ECG analysis might improve the prediction of sudden cardiac death risk. Hypothesis: We hypothesized that machine learning of the ECG can be used to predict SCD. Methods: We studied 5603 ECG Lead V1 beats in 41 patients (64±10 Y) with coronary disease and LVEF≤40% in steady-state pacing. Patients were randomly allocated to independent training and test cohorts in a 70:30 ratio, repeated K=10-fold. Support vector machines were trained to predict mortality at 3Y from the top 20 features derived from these beats (Fig C). Patient-level predictions were made by computing an ECG score that indicates the proportion of test set beats in that patient computed by the beat-level model to predict SCD. Results: Fig A shows the data flow in the study. Beat-level predictions in the validation (n=1678 Lead I beats) cohorts yielded c-statistics of 0.78 for SCD (95% CI, 0.62-0.91). In multivariable models, c-statistic was 0.87 for SCD (95% CI, 0.76-0.98) (Fig B). Conclusions: Machine learning of the ECG reveals novel predictors of SCD risk in patients with ischemic cardiomyopathy. This tool may improve risk stratification and allocation for ICD therapy beyond LVEF alone.