Independent Test Research Articles

Leveraging Serial Low-Dose CT Scans in Radiomics-based Reinforcement Learning to Improve Early Diagnosis of Lung Cancer at Baseline Screening.

Purpose To evaluate the feasibility of leveraging serial low-dose CT (LDCT) scans to develop a radiomics-based reinforcement learning (RRL) model for improving early diagnosis of lung cancer at baseline screening. Materials and Methods In this retrospective study, 1951 participants (female patients, 822; median age, 61 years [range, 55-74 years]) (male patients, 1129; median age, 62 years [range, 55-74 years]) were randomly selected from the National Lung Screening Trial between August 2002 and April 2004. An RRL model using serial LDCT scans (S-RRL) was trained and validated using data from 1404 participants (372 with lung cancer) containing 2525 available serial LDCT scans up to 3 years. A baseline RRL (B-RRL) model was trained with only LDCT scans acquired at baseline screening for comparison. The 547 held-out individuals (150 with lung cancer) were used as an independent test set for performance evaluation. The area under the receiver operating characteristic curve (AUC) and the net reclassification index (NRI) were used to assess the performances of the models in the classification of screen-detected nodules. Results Deployment to the held-out baseline scans showed that the S-RRL model achieved a significantly higher test AUC (0.88 [95% CI: 0.85, 0.91]) than both the Brock model (AUC, 0.84 [95% CI: 0.81, 0.88]; P = .02) and the B-RRL model (AUC, 0.86 [95% CI: 0.83, 0.90]; P = .02). Lung cancer risk stratification was significantly improved by the S-RRL model as compared with Lung CT Screening Reporting and Data System (NRI, 0.29; P < .001) and the Brock model (NRI, 0.12; P = .008). Conclusion The S-RRL model demonstrated the potential to improve early diagnosis and risk stratification for lung cancer at baseline screening as compared with the B-RRL model and clinical models. Keywords: Radiomics-based Reinforcement Learning, Lung Cancer Screening, Low-Dose CT, Machine Learning © RSNA, 2024 Supplemental material is available for this article.

A protein sequence-based deep transfer learning framework for identifying human proteome-wide deubiquitinase-substrate interactions

Protein ubiquitination regulates a wide range of cellular processes. The degree of protein ubiquitination is determined by the delicate balance between ubiquitin ligase (E3)-mediated ubiquitination and deubiquitinase (DUB)-mediated deubiquitination. In comparison to the E3-substrate interactions, the DUB-substrate interactions (DSIs) remain insufficiently investigated. To address this challenge, we introduce a protein sequence-based ab initio method, TransDSI, which transfers proteome-scale evolutionary information to predict unknown DSIs despite inadequate training datasets. An explainable module is integrated to suggest the critical protein regions for DSIs while predicting DSIs. TransDSI outperforms multiple machine learning strategies against both cross-validation and independent test. Two predicted DUBs (USP11 and USP20) for FOXP3 are validated by “wet lab” experiments, along with two predicted substrates (AR and p53) for USP22. TransDSI provides new functional perspective on proteins by identifying regulatory DSIs, and offers clues for potential tumor drug target discovery and precision drug application.

The Effect of Squat Training with Barbell and Resistance Band on Leg Power of Volleyball Athletes

The purpose of this study was to determine (1) the effect of squat training with barbell on increasing leg power of volleyball athletes, (2) the effect of squat training with resistance band on increasing leg power of volleyball athletes, (3) the difference in the effect of squat training with barbell and resistance band squats on increasing leg power of volleyball athletes. The type of research is experimental. The sample used is volleyball athletes totalling 20 athletes with an age range of 14-16 years. The leg power test instrument uses a vertical jump. Data analysis techniques using Paired Sample Test and Independent Samples Test. The results showed that (1) There is a significant effect of squat training with barbell on leg power of volleyball athletes (p 0.000 &lt; 0.05), (2) There is a significant effect of squat with resistance band on leg power of volleyball athletes (p 0.000 &lt; 0.05), (3) There is a significant difference in squat training with barbell and resistance band squats on increasing leg power of volleyball athletes. Squat training with resistance band is better than squats with barbell on increasing the leg power of volleyball athletes, with a difference of 1.30. The implication of the research results that to increase the leg power of volleyball athletes can be done by applying squat training with barbell and resistance band. This means that athletes are given exercises that are in accordance with their characteristics so that in the training process they feel happy and motivated to follow the training process, so that the training objectives will be maximised. Then another implication is that by encouraging coaches to apply suitable exercises can trigger athlete involvement in training.

Trends in socio-demographic characteristics and substance use among high school learners in a selected district in Limpopo Province, South Africa.

Substance use is an escalating public health problem in South Africa resulting in risky behaviours and poor educational attainment among adolescents. There is a huge battle to overcome substance use among learners as more drugs become easily available with the mean age of drug experimentation reported to be at 12 years of age. It is important to continuously understand the trends in substance use in order to assess if there are positive changes and provide evidence for the development of context-specific effective interventions. This paper outlines the prevalence of substance use among selected high schools in a district in Limpopo province. To determine the prevalence of substance use among selected high school learners in a district in Limpopo Province, a cross-sectional school survey of 768 learners was conducted. Data was analysed using SPSS v 26. Descriptive analysis was used to describe the independent and dependent variables and Chi-Square test was used to investigate associations between demographic characteristics and substance use among high school learners. The most abused substances by learners were alcohol (49%), cigarettes (20.8%) and marijuana (dagga/cannabis) (16.8%). In a lifetime, there was a significant difference (P < 0.05) in cigarette smoking with gender, school, and grade; with more use in males (14.2%) than females (7.6%); in urban schools (14.6) than peri-urban (6.7%) and more in Grade 12 (6.4%). There was a significant difference (P < 0.05) in alcohol use with more use in Grade 10 (12.6%) and varied use among male and female learners but cumulatively more alcohol use in females (27.7%). Drug use varied, with an overall high drug use in urban schools (20.7%). Substance use is rife among high school learners in the district and health promotion initiatives need to be tailored within the context of socio-demographic characteristics of learners including the multiple levels of influence such as peer pressure, poverty, unemployment and child headed families. Additional research is required to investigate the factors leading to a notable gradual increase in use among female learners and into the environmental and family settings of learners in influencing substance use.

Identification and validation of gestational diabetes subgroups by data-driven cluster analysis.

Gestational diabetes mellitus (GDM) is a heterogeneous condition. Given such variability among patients, the ability to recognise distinct GDM subgroups using routine clinical variables may guide more personalised treatments. Our main aim was to identify distinct GDM subtypes through cluster analysis using routine clinical variables, and analyse treatment needs and pregnancy outcomes across these subgroups. In this cohort study, we analysed datasets from a total of 2682 women with GDM treated at two central European hospitals (1865 participants from Charité University Hospital in Berlin and 817 participants from the Medical University of Vienna), collected between 2015 and 2022. We evaluated various clustering models, including k-means, k-medoids and agglomerative hierarchical clustering. Internal validation techniques were used to guide best model selection, while external validation on independent test sets was used to assess model generalisability. Clinical outcomes such as specific treatment needs and maternal and fetal complications were analysed across the identified clusters. Our optimal model identified three clusters from routinely available variables, i.e. maternal age, pre-pregnancy BMI (BMIPG) and glucose levels at fasting and 60 and 120 min after the diagnostic OGTT (OGTT0, OGTT60 and OGTT120, respectively). Cluster 1 was characterised by the highest OGTT values and obesity prevalence. Cluster 2 displayed intermediate BMIPG and elevated OGTT0, while cluster 3 consisted mainly of participants with normal BMIPG and high values for OGTT60 and OGTT120. Treatment modalities and clinical outcomes varied among clusters. In particular, cluster 1 participants showed a much higher need for glucose-lowering medications (39.6% of participants, compared with 12.9% and 10.0% in clusters 2 and 3, respectively, p<0.0001). Cluster 1 participants were also at higher risk of delivering large-for-gestational-age infants. Differences in the type of insulin-based treatment between cluster 2 and cluster 3 were observed in the external validation cohort. Our findings confirm the heterogeneity of GDM. The identification of subgroups (clusters) has the potential to help clinicians define more tailored treatment approaches for improved maternal and neonatal outcomes.

Predictive machine learning model for mechanical dilatation in transvenous lead extraction procedures

Abstract Background Transvenous lead extraction (TLE) remains a procedure that requires a high level of expertise, with a doubled risk of death and clinical failure when performed in low-volume centers compared to high-volume ones (1). Purpose The aim of this study was to create a machine learning (ML)-based risk stratification system for predicting the need for mechanical dilatation in patients undergoing TLE due to infection. Methods We designed a ML-based risk stratification system trained with data from our registry to predict the need for mechanical dilatation in patients undergoing TLE for infection. An extensive evaluation of 5 different ML models (k-nearest neighbors, support vector machine, decision tree, and decision tree ensembles, such as random forest and gradient boosting machine) was conducted to identify a classifier with the highest potential to correctly predict previously unseen patients. Results Data to train the model was extracted from our 25-year registry of patients undergoing TLE (June 1998 – March 2023), for a total of 491 patients (77.8% male; age 69.7 ± 12.8 years) and 938 leads (ICD 21.2%; pacing 78.8%; indwelling time 61 ± 60 months) removed with success in 100% of cases. Each patient was represented by a set of 21 attributes (14 clinical, 7 device-related). Manual traction (MT) was used in 27.5% of cases, and mechanical dilatation (MD) was employed in the remaining 72.5% of cases. 5-fold nested cross validation was used to estimate performances: in turn, 393 patients were used for training and model selection, and 98 patients were used for independent testing. According to the evaluation, Gradient Boosting Machine performed best, achieving test accuracy of 89% (+/- 2% std. dev.), test sensitivity of 95% (+/- 3% std. dev.), test specificity of 73% (+/- 8% std. dev.), test AUROC of 92% (+/- 1% std. dev.). A further interpretability analysis on the best performing decision tree was conducted, showing remarkable adherence between the internal decisions taken by the model to make predictions and the current clinical practice for TLE. Conclusion ML models have enhanced the prediction of MD requirements in TLE procedures. This data may support the referral of patients to specialized and high-volume centers, thereby improving preoperative risk assessment.Feature importanceROC Curves

Utility of the Morgan Fingerprint in Structure-Based Virtual Ligand Screening.

In modern drug discovery, virtual ligand screening (VLS) is frequently applied to identify possible hits before experimental testing and refinement due to its cost-effective nature for large compound libraries. For decades, efforts have been devoted to developing VLS methods with high accuracy. These include the state-of-the-art FINDSITE suite of approaches FINDSITEcomb2.0, FRAGSITE, and FRAGSITE2 and the meta version FRAGSITEcomb that were developed in our lab. These methods combine ligand homology modeling (LHM), traditional ligand similarity methods, and more recently machine learning approaches to rank ligands and have proven to be superior to most recent deep learning and large language model-based approaches. Here, we describe further improvements to our previous best methods by combining the Morgan fingerprint (MF) with the originally used PubChem fingerprint and FP2 fingerprint. We then benchmarked FINDSITEcomb2.0M, FRAGSITEM, FRAGSITE2M, and the composite meta-approach FRAGSITEcombM. On the 102 target DUD-E set, the 1% enrichment factor (EF1%) and area under the precision-recall curve (AUPR) of FRAGSITEcomb increased from 42.0/0.59 to 47.6/0.72. This 0.72 AUPR is significantly better than that of the state-of-the-art deep learning-based method DenseFS's AUPR of 0.443. An independent test on the 81 targets DEKOIS2.0 set shows that EF1%/AUPR increases from 18.3/0.520 to 23.1/0.683. An ablation investigation shows that the MF contributes to most of the improvement of all four approaches. Thus, the MF is a useful addition to structure-based VLS.

#1770 Clinical characteristics and outcomes in patients with ANCA-associated vasculitis (AAV) and kidney involvement—a Swedish single-center cohort

Abstract Background and Aims Poor patient outcomes in ANCA-associated vasculitis (AAV) with kidney involvement is attributed to multiple factors such as delay in diagnosis, inadequate efficacy of treatments and long-term complications due to the disease as well as the toxic effects of immunosuppressive therapy. The aim of the present study was to evaluate the clinical characteristics of a Swedish cohort of patients with AAV (granulomatosis with polyangiitis; GPA and microscopic polyangiitis; MPA) and kidney involvement to study causes of death and predictors of all-cause mortality. Method This retrospective single-centre cohort study included 93 patients from the Uppsala region in mid-Sweden, diagnosed with AAV and kidney involvement between 1993 and 2023. Clinical and laboratory variables were obtained from review of electronic medical records as well as patient follow-up visits. Differences between groups were assessed using independent t-test and Chi-square test. Multivariable logistic regression analyses were performed to evaluate the influence of risk factors of interest on all-cause mortality. Results 93 patients, 71 (76%) were clinically diagnosed with MPA, and 22 (24%) with GPA. The median age at diagnosis was 66.5 ± 13 years. eGFR at diagnosis was 29 ± 23.5 ml/min/1.73 m2 and 15% of patients were dialysis-dependent AAV at diagnosis. Patients with MPA and GPA received comparable induction therapy except for PLEX which was significantly more frequent in patients with GPA (52% vs 26% respectively, p = 0.041). 56 (60%) of patients died during follow up and survival time was 7.1 ± 6.9 years. Baseline clinical and biochemical characteristics are shown in Table 1. A multivariate logistic regression showed that older age at diagnosis (OR 95% CI 1.012-1.110; p = 0.013) and being dialysis-dependent at diagnosis (OR 95% CI 1.343-16.079; p = 0.015) significantly predicted all-cause mortality (Table 2). Causes of death are presented in Fig. 1. Infections was the most common cause of death (30%). Conclusion Long-term prognosis and patient survival were significantly associated with age and dialysis-dependency at diagnosis in this cohort of patients diagnosed with AAV and kidney involvement. Infections was the most common cause of death.

#671 Perinatal factors, age of onset, early glycaemic control, sex and the development of microvascular complications in type 1 diabetes after 30 years

Abstract Background and Aims Long-term glycaemic control and duration of disease are both well-established risk factors for the development of complications in type 1 diabetes (T1D). The effect of perinatal factors, age at onset of T1D and early glycaemic control on development of diabetic complications have not been fully evaluated. The aim of this study was to investigate the long-term impact of such factors in childhood-onset type 1 diabetes. Method 90 subjects diagnosed with T1D between the ages of 0-14 years were included in this prospective observational cohort study in in a geographically defined area in northern Sweden. Baseline data for these subjects have previously been reported by Svensson M et al (Diabetes Care 2004). Outcome and follow-up data was obtained during approximately 30 years of follow-up from the Swedish National Diabetes Registry (NDR). Differences between groups were assessed using independent t-test and Chi-square test. Kaplan-Meier survival curves were used to illustrate time-to-diabetic nephropathy (DN) by sex and age at onset. Multivariable logistic regression analyses were performed to evaluate the influence of risk factors of interest on the development of DN, assessed as any degree of albuminuria without signs of other underlying conditions. Results Forty-one subjects (46%) developed any degree of DN during the follow-up period of mean 33 (range 19-40) years after T1D onset. Moreover, 80 subjects (89%) had any degree of retinopathy (RP) and among those, 18 (20%) had proliferative diabetic retinopathy (PDR), and 13 (4%) had both PDR and DN. Mean HbA1c during the first five and ten years after diagnosis was higher in subjects who developed DN or PDR compared to those who did not develop these complications; DN 58 ± 16 vs 51 ± 13 (p = 0.038) and 63 ± 16 vs 55 ± 11 mmol/mol (p = 0.007), respectively; PDR 60 ± 13 vs 53 ± 15 (p = 0.059) and 67 ± 10 vs 56 ± 14 mmol/mol (p = 0.002), respectively. Women had an increased risk of PDR compared to men (28% vs 11%, p = 0.045) and a near-significantly higher risk of DN (55% vs 36%, p = 0.087) (Table 1). Time to DN by sex and by age at onset are shown in Figure 1A and B. Women seemed to have a somewhat lower risk in the early years, but in the later years the risk was increased. A young age at onset of diabetes prolonged the time to development of DN but after twenty years of diabetes duration, no difference was seen. In a multivariate regression analysis, older age of gestation was negatively associated with (OR 95% CI 0.894-0.989, p = 0.017) and hyperglycaemia (higher HbA1c) during the first five years (OR 95% CI 1.004-1.078, p = 0.028) were positively and independently associated with development of DN (Fig. 1C). Conclusion Interestingly, longer gestational time at birth and, more well-known, poor early glycaemic control were associated with development of DN after 30 years of diabetes duration. However, there was no impact of age of onset or sex on the long-term risk for DN.

Automatic quantification of tumor-stroma ratio as a prognostic marker for pancreatic cancer.

This study aims to introduce an innovative multi-step pipeline for automatic tumor-stroma ratio (TSR) quantification as a potential prognostic marker for pancreatic cancer, addressing the limitations of existing staging systems and the lack of commonly used prognostic biomarkers. The proposed approach involves a deep-learning-based method for the automatic segmentation of tumor epithelial cells, tumor bulk, and stroma from whole-slide images (WSIs). Models were trained using five-fold cross-validation and evaluated on an independent external test set. TSR was computed based on the segmented components. Additionally, TSR's predictive value for six-month survival on the independent external dataset was assessed. Median Dice (inter-quartile range (IQR)) of 0.751(0.15) and 0.726(0.25) for tumor epithelium segmentation on internal and external test sets, respectively. Median Dice of 0.76(0.11) and 0.863(0.17) for tumor bulk segmentation on internal and external test sets, respectively. TSR was evaluated as an independent prognostic marker, demonstrating a cross-validation AUC of 0.61±0.12 for predicting six-month survival on the external dataset. Our pipeline for automatic TSR quantification offers promising potential as a prognostic marker for pancreatic cancer. The results underscore the feasibility of computational biomarker discovery in enhancing patient outcome prediction, thus contributing to personalized patient management.

Prognostic stratification of glioblastoma patients by unsupervised clustering of morphology patterns on whole slide images furthering our disease understanding

IntroductionGlioblastoma (GBM) is a highly aggressive malignant tumor of the central nervous system that displays varying molecular and morphological profiles, leading to challenging prognostic assessments. Stratifying GBM patients according to overall survival (OS) from H&amp;amp;E-stained whole slide images (WSI) using advanced computational methods is challenging, but with direct clinical implications.MethodsThis work is focusing on GBM (IDH-wildtype, CNS WHO Gr.4) cases, identified from the TCGA-GBM and TCGA-LGG collections after considering the 2021 WHO classification criteria. The proposed approach starts with patch extraction in each WSI, followed by comprehensive patch-level curation to discard artifactual content, i.e., glass reflections, pen markings, dust on the slide, and tissue tearing. Each patch is then computationally described as a feature vector defined by a pre-trained VGG16 convolutional neural network. Principal component analysis provides a feature representation of reduced dimensionality, further facilitating identification of distinct groups of morphology patterns, via unsupervised k-means clustering.ResultsThe optimal number of clusters, according to cluster reproducibility and separability, is automatically determined based on the rand index and silhouette coefficient, respectively. Our proposed approach achieved prognostic stratification accuracy of 83.33% on a multi-institutional independent unseen hold-out test set with sensitivity and specificity of 83.33%.DiscussionWe hypothesize that the quantification of these clusters of morphology patterns, reflect the tumor's spatial heterogeneity and yield prognostic relevant information to distinguish between short and long survivors using a decision tree classifier. The interpretability analysis of the obtained results can contribute to furthering and quantifying our understanding of GBM and potentially improving our diagnostic and prognostic predictions.

An automated hybrid approach via deep learning and radiomics focused on the midbrain and substantia nigra to detect early-stage Parkinson’s disease

ObjectivesThe altered neuromelanin in substantia nigra pars compacta (SNpc) is a valuable biomarker in the detection of early-stage Parkinson’s disease (EPD). Diagnosis via visual inspection or single radiomics based method is challenging. Thus, we proposed a novel hybrid model that integrates radiomics and deep learning methodologies to automatically detect EPD based on neuromelanin-sensitive MRI, namely short-echo-time Magnitude (setMag) reconstructed from quantitative susceptibility mapping (QSM).MethodsIn our study, we collected QSM images including 73 EPD patients and 65 healthy controls, which were stratified into training-validation and independent test sets with an 8:2 ratio. Twenty-four participants from another center were included as the external validation set. Our framework began with the detection of the brainstem utilizing YOLO-v5. Subsequently, a modified LeNet was applied to obtain deep learning features. Meanwhile, 1781 radiomics features were extracted, and 10 features were retained after filtering. Finally, the classified models based on radiomics features, deep learning features, and the hybrid of both were established through machine learning algorithms, respectively. The performance was mainly evaluated using accuracy, net reclassification improvement (NRI), and integrated discrimination improvement (IDI). The saliency map was used to visualize the model.ResultsThe hybrid feature-based support vector machine (SVM) model showed the best performance, achieving ACC of 96.3 and 95.8% in the independent test set and external validation set, respectively. The model established by hybrid features outperformed the one radiomics feature-based (NRI: 0.245, IDI: 0.112). Furthermore, the saliency map showed that the bilateral “swallow tail” sign region was significant for classification.ConclusionThe integration of deep learning and radiomic features presents a potent strategy for the computer-aided diagnosis of EPD. This study not only validates the accuracy of our proposed model but also underscores its interpretability, evidenced by differential significance across various anatomical sites.

A Method Based on Artificial Intelligence That Predicts Arabica Coffee Yield by Analyzing Abiotic Factors and the Prevalence of Coffee Leaf Rust

Coffee is a perennial crop that harbors infections throughout the plant, which may worsen illness under favorable circumstances. Coffee leaf rust, a widespread coffee disease and Arabica is susceptible to leaf rust. Disease incidence and severity depend on abiotic variables. Cloudy and constant South-West monsoon weather (June–September) promotes coffee leaf rust growth. In this five-model study, an Extra Tree and Gradient Boosting regression model predicted coffee crop output in Chikamagaluru, Karnataka, with the least error utilizing biotic and abiotic factors. We investigated additional tree, gradient boosting, RF, Decision Tree, and KNN models using biotic and abiotic predictors. Used the independent testing dataset's MSE, MAE, RMSE Root mean square errors, and R-squared errors to compare model performance. The extra tree (R²=0.98 kg/ha ˉ¹ and RMSE = 7.96 kg/ha ˉ¹) and gradient boosting (R²=0.96 kg/ha ˉ¹ and RMSE = 10.96 kg/ha ˉ¹) regression models used Group 1 and 2 characteristics as predictor variables and different parameter fine tuning functions to estimate coffee yield most accurately. Compared to the less precise probabilistic models utilized in this work, such as Random Forest, decision tree, and KNN models, shown in the results section. The optimum weather parameter for coffee production forecasts and biotic-CLR incidence data outperformed random forest, decision tree, and K-Nearest Neighbor models.

A longer time to relapse is associated with a larger increase in differences between paired primary and recurrent IDH wild-type glioblastomas at both the transcriptomic and genomic levels

Glioblastoma (GBM) is the most common malignant brain tumor in adults, which remains incurable and often recurs rapidly after initial therapy. While large efforts have been dedicated to uncover genomic/transcriptomic alternations associated with the recurrence of GBMs, the evolutionary trajectories of matched pairs of primary and recurrent (P-R) GBMs remain largely elusive. It remains challenging to identify genes associated with time to relapse (TTR) and construct a stable and effective prognostic model for predicting TTR of primary GBM patients. By integrating RNA-sequencing and genomic data from multiple datasets of patient-matched longitudinal GBMs of isocitrate dehydrogenase wild-type (IDH-wt), here we examined the associations of TTR with heterogeneities between paired P-R GBMs in gene expression profiles, tumor mutation burden (TMB), and microenvironment. Our results revealed a positive correlation between TTR and transcriptomic/genomic differences between paired P-R GBMs, higher percentages of non-mesenchymal-to-mesenchymal transition and mesenchymal subtype for patients with a short TTR than for those with a long TTR, a high correlation between paired P-R GBMs in gene expression profiles and TMB, and a negative correlation between the fitting level of such a paired P-R GBM correlation and TTR. According to these observations, we identified 55 TTR-associated genes and thereby constructed a seven-gene (ZSCAN10, SIGLEC14, GHRHR, TBX15, TAS2R1, CDKL1, and CD101) prognostic model for predicting TTR of primary IDH-wt GBM patients using univariate/multivariate Cox regression analyses. The risk scores estimated by the model were significantly negatively correlated with TTR in the training set and two independent testing sets. The model also segregated IDH-wt GBM patients into two groups with significantly divergent progression-free survival outcomes and showed promising performance for predicting 1-, 2-, and 3-year progression-free survival rates in all training and testing sets. Our findings provide new insights into the molecular understanding of GBM progression at recurrence and potential targets for therapeutic treatments.

The Relationship between Anthropometric, Biomotor, and Psychomotor Factors on the Performance of Paralympic 100 Meters Freestyle Swimming Athletes in National Paralympic Committee Indonesia

This research aims to relationship the anthropometric, biomotor, and psychomotor factors with disabled athlete's swimming speed in the National Paralympic Committee (NPC) (Indonesian) 100-meter freestyle competition in 2022. This research was a cross-sectional study conducted by the National Paralympic Committee (NPC) (Indonesia). The sample used in this research was 15 disabled athletes from NPC Indonesia with the S7-S10 classification who got medals at the ASEAN Para Games event in 2022. The data collection includes seven independent variable tests there are anthropometric factors (height, weight, body mass index, arm length, and leg length); biomotor factors (abdominal muscle strength and arm muscle power); psychomotor factors by measuring balance using Balance Tests; and dependent variables by measuring swimming speed using the 100-meter freestyle swimming ability test. Statistical analysis used the Pearson correlation coefficient test with a significance level of 5%. The results of the Pearson correlation coefficient analysis show that swimming speed was negatively related to body height, body weight, arm length, abdominal muscle strength, and arm muscle power indicating a moderate correlation between variables (p ≤ 0.001). However, unfortunately, other anthropometric variables such as leg length and age showed a weak negative correlation with swimming speed (p ≤ 0.05). Meanwhile, body mass index and balance did not show a significant correlation with swimming speed (p ≥ 0.05). Based on the research results, it was concluded that anthropometric and biomotor factors showed a negative relationship with swimming speed, while psychomotor factors did not. Keyword: Anthropometry, biomotor, psychomotor, disabled athletes, swimming speed, achievement.

Experimental environment for testing the shattered pellet injection of KSTAR

The dual shattered pellet injection (SPI) systems installed at the KSTAR (Korean Superconducting Tokamak Advanced Research) have been operational since 2019 to conduct disruption mitigation studies in support of ITER DMS (Disruption Mitigation System) design activities. The system has the advantage of firing pellets simultaneously from the two identical pellet injectors installed at 180-degree opposite positions on KSTAR. Each injector is capable of fabricating and firing three pellets of different sizes (diameter, length). The characteristics of the initial pellet (geometry, velocity, etc.) can be verified using a microwave cavity (MWC) system and an imaging optical pellet diagnostics (OPD) system.Each SPI system must achieve specific conditions related to pellet fabrication and firing prior to plasma experiments. We realized that we didn't have the sufficient time and conditions to do off-line testing in 2022, so we have developed a suitable solution. First, we have to disconnect the SPI system from the KSTAR vacuum vessel and build a separate test chamber in the injection line. Inside the new test chamber, we have to install the same shatter tube used in the current experiments and equip it with measuring devices to observe the fragmented pellets. We also have to switch the fabrication process of the pellets from manual to semi-automatic using a feedback pressure controller on the barrel pressure. In this paper, we will describe the new experimental environment for independent SPI testing and the future plan.

Prediction of DNA methylation-based tumor types from histopathology in central nervous system tumors with deep learning.

Precision in the diagnosis of diverse central nervous system (CNS) tumor types is crucial for optimal treatment. DNA methylation profiles, which capture the methylation status of thousands of individual CpG sites, are state-of-the-art data-driven means to enhance diagnostic accuracy but are also time consuming and not widely available. Here, to address these limitations, we developed Deep lEarning from histoPathoLOgy and methYlation (DEPLOY), a deep learning model that classifies CNS tumors to ten major categories from histopathology. DEPLOY integrates three distinct components: the first classifies CNS tumors directly from slide images ('direct model'), the second initially generates predictions for DNA methylation beta values, which are subsequently used for tumor classification ('indirect model'), and the third classifies tumor types directly from routinely available patient demographics. First, we find that DEPLOY accurately predicts beta values from histopathology images. Second, using a ten-class model trained on an internal dataset of 1,796 patients, we predict the tumor categories in three independent external test datasets including 2,156 patients, achieving an overall accuracy of 95% and balanced accuracy of 91% on samples that are predicted with high confidence. These results showcase the potential future use of DEPLOY to assist pathologists in diagnosing CNS tumors within a clinically relevant short time frame.

PREDICTIVE MACHINE LEARNING MODEL FOR MECHANICAL DILATATION IN TRANSVENOUS LEAD EXTRACTION PROCEDURES

Abstract Background Transvenous lead extraction (TLE) remains a procedure that requires a high level of expertise, with a doubled risk of death and clinical failure when performed in low–volume centers compared to high–volume ones. PURPOSE The aim of this study was to create a machine learning (ML)–based risk stratification system for predicting the need for mechanical dilatation in patients undergoing TLE due to infection. Methods We designed a ML–based risk stratification system trained with data from our registry to predict the need for mechanical dilatation in patients undergoing TLE for infection. An extensive evaluation of 5 different ML models (k–nearest neighbors, support vector machine, decision tree, and decision tree ensembles, such as random forest and gradient boosting machine) was conducted to identify a classifier with the highest potential to correctly predict previously unseen patients. Results Data to train the model was extracted from our 25–year registry of patients undergoing TLE (June 1998 – March 2023), for a total of 491 patients (77.8% male; age 69.7 ± 12.8 years) and 938 leads (ICD 21.2%; pacing 78.8%; indwelling time 61 ± 60 months) removed with success in 100% of cases. Each patient was represented by a set of 21 attributes (14 clinical, 7 device–related). Manual traction (MT) was used in 27.5% of cases, and mechanical dilatation (MD) was employed in the remaining 72.5% of cases. 5–fold nested cross validation was used to estimate performances: in turn, 393 patients were used for training and model selection, and 98 patients were used for independent testing. According to the evaluation, Gradient Boosting Machine performed best, achieving test accuracy of 89% (+/– 2% std. dev.), test sensitivity of 95% (+/– 3% std. dev.), test specificity of 73% (+/– 8% std. dev.), test AUROC of 92% (+/– 1% std. dev.). A further interpretability analysis on the best performing decision tree was conducted, showing remarkable adherence between the internal decisions taken by the model to make predictions and the current clinical practice for TLE. Conclusion ML models have enhanced the prediction of MD requirements in TLE procedures. This data may support the referral of patients to specialized and high–volume centers, thereby improving preoperative risk assessment.

Effect of apple pomace degraded by Pleurotus ostreatus on growth and meat quality parameters of broiler chickens

The objective of this work was to compare the growth and physicochemical parameters of the meat of broiler chickens (Gallus gallus), fed with a supplemented diet (SD) consisting of 3% pleurotin, compared to those obtained when using a traditional diet (CD). Pleurotin is the remaining material from the biodegradation of substrates such as apple pomace used to cultivate the Pleurotus ostreatus fungus. The experience lasted 48 days and in the first eight days, the birds were divided into two groups of 24 individuals, one group for each treatment. On day 12, each initial group was subdivided into four experimental units (replicates) of 6 chickens each. The growth parameters measured were total weight gain (TWG), final live weight (FLW), carcass weight (CW), average daily gain (ADG) in weight, and feed conversion ratio (FCR). Physicochemical parameters such as pH, water content (WC), CIE color, total fat (TF), and fatty acid composition (FAC) were also measured. Statistical analysis was carried out through the t-Student independent samples test. FLW was on average 7.6% significantly higher with SD than with CD, however, no difference was detected in CW. The total ADG was 7.4%, significantly higher with SD while the FCR was 32.0% lower with SD than with CD. No significant differences were found in any of the meat quality parameters measured for the same piece. Despite these latest results in terms of meat quality, it is concluded that the increase found in total ADG and FLW, and an improvement in FCR values with SD favor the use of this amendment in chicken rearing. In addition, the introduction of the by-product of the juice industries of the Río Negro Valley in other production cycles, such as edible mushrooms production and a supplement for bird diets (pleurotin), promotes a circular bioeconomic mechanism.

Breast Delineation in Full-Field Digital Mammography Using the Segment Anything Model

Breast cancer is a major health concern worldwide. Mammography, a cost-effective and accurate tool, is crucial in combating this issue. However, low contrast, noise, and artifacts can limit the diagnostic capabilities of radiologists. Computer-Aided Diagnosis (CAD) systems have been developed to overcome these challenges, with the accurate outlining of the breast being a critical step for further analysis. This study introduces the SAM-breast model, an adaptation of the Segment Anything Model (SAM) for segmenting the breast region in mammograms. This method enhances the delineation of the breast and the exclusion of the pectoral muscle in both medio lateral-oblique (MLO) and cranio-caudal (CC) views. We trained the models using a large, multi-center proprietary dataset of 2492 mammograms. The proposed SAM-breast model achieved the highest overall Dice Similarity Coefficient (DSC) of 99.22% ± 1.13 and Intersection over Union (IoU) 98.48% ± 2.10 over independent test images from five different datasets (two proprietary and three publicly available). The results are consistent across the different datasets, regardless of the vendor or image resolution. Compared with other baseline and deep learning-based methods, the proposed method exhibits enhanced performance. The SAM-breast model demonstrates the power of the SAM to adapt when it is tailored to specific tasks, in this case, the delineation of the breast in mammograms. Comprehensive evaluations across diverse datasets—both private and public—attest to the method’s robustness, flexibility, and generalization capabilities.