Subset Of Data Research Articles

AutoPeptideML: a study on how to build more trustworthy peptide bioactivity predictors.

Automated machine learning (AutoML) solutions can bridge the gap between new computational advances and their real-world applications by enabling experimental scientists to build their own custom models. We examine different steps in the development life-cycle of peptide bioactivity binary predictors and identify key steps where automation cannot only result in a more accessible method, but also more robust and interpretable evaluation leading to more trustworthy models. We present a new automated method for drawing negative peptides that achieves better balance between specificity and generalization than current alternatives. We study the effect of homology-based partitioning for generating the training and testing data subsets and demonstrate that model performance is overestimated when no such homology correction is used, which indicates that prior studies may have overestimated their performance when applied to new peptide sequences. We also conduct a systematic analysis of different protein language models as peptide representation methods and find that they can serve as better descriptors than a naive alternative, but that there is no significant difference across models with different sizes or algorithms. Finally, we demonstrate that an ensemble of optimized traditional machine learning algorithms can compete with more complex neural network models, while being more computationally efficient. We integrate these findings into AutoPeptideML, an easy-to-use AutoML tool to allow researchers without a computational background to build new predictive models for peptide bioactivity in a matter of minutes. Source code, documentation, and data are available at https://github.com/IBM/AutoPeptideML and a dedicated web-server at http://peptide.ucd.ie/AutoPeptideML. A static version of the software to ensure the reproduction of the results is available at https://zenodo.org/records/13363975.

Univariate and multivariate imputation methods evaluation for reconstructing climate time series data: A case study of Mosul station-Iraq

Comprehensive climate time series data is indispensable for monitoring the impacts of climate change. However, observational datasets often suffer from data gaps within their time series, necessitating imputation to ensure dataset integrity for further analysis. This study evaluated six univariate and multivariate imputation methods to infill missing values. These methods were applied to complete the subsets of time series data for precipitation, temperature, and relative humidity from Mosul station spanning 1980–2013. Artificial gaps of 5%, 10%, 20%, and 30% missing observations were introduced under scenarios of missing completely at random (MCAR) missing at random (MAR), and missing not at random (MNAR). Evaluation metrics including RMSE and Kling-Gupta Efficiency were utilized for performance evaluation. Results revealed that seasonal decomposition was the most effective univariate imputation method across all variables. For the multivariate imputation, kNN demonstrated superior performance in infilling the precipitation missing data under MCAR, while norm.predict exhibited optimal performance in the temperature missing data under all missing scenarios. Moreover, missForest was identified as the most suitable method for infilling missing relative humidity data. This study's methodology offers insights into selecting appropriate imputation methods for other climate stations, thereby enhancing the accuracy of the climate change effects analysis.

Characterising the stellar differential rotation based on largest-spot statistics from ground-based photometry

Aims. Stellar spot distribution has consequences on the observable periodic signals in long-time baseline ground-based photometry. We model the statistics of the dominating spots of two young and active Solar-type stars, V889 Her and LQ Hya, in order to obtain information on the underlying spot distribution, rotation of the star, as well as the orientation of the stellar axis of spin. Methods. By calculating estimates for spot-induced periodicities in independent subsets of photometric data, we obtain statistics based on the dominating spots in each subset, giving rise to largest-spot statistics accounting for stellar geometry and rotation, including differential rotation. Results. Our simple statistical models are able to reproduce the observed distribution of photometric signals rather well. This also enables us to estimate the dependence of angular velocity of the spots as a function of latitude. Our results indicate that V889 Her has a non-monotonic differential rotation curve with a maximum angular velocity between latitudes of 37–40 deg and lower angular velocity at the pole than the equator. Our results for LQ Hya indicate that the star rotates much like a rigid body. Furthermore, the results imply that the monotonic Solar differential rotation curve may not be a universal model for other solar-type stars. Conclusions. The non-monotonicity of the differential rotation of V889 Her is commonly produced in magnetohydrodynamic simulations, which indicates that our results are realistic from a theoretical perspective.

Empowering Research With the American Heart Association Get With The Guidelines Registries Through Integration of a Database and Research Tools.

The American Heart Association's Get With The Guidelines (GWTG) has emerged as a vital resource in advancing the standards and practices of inpatient care across stroke, heart failure, coronary artery disease, atrial fibrillation, and resuscitation focus areas. The GWTG registry data have also created new opportunities for secondary use of real-world clinical data in biomedical research. Our goal was to implement a scalable database with an integrated user interface (UI) to improve GWTG data management and accessibility. The curation of registry data begins by going through a data processing and quality control pipeline programmed in Python. This pipeline includes data cleaning and record exclusion, variable derivation and unit harmonization, limited data set preparation, and documentation generation of the registry data. The database was built using PostgreSQL, and integrations between the database and the UI were built using the Django Web Framework in Python. Smaller subsets of data were created using SQLite database files for distribution purposes. Use cases of these tools are provided in the article. We implemented an automated data curation pipeline, centralized database, and UI application for the American Heart Association GWTG registry data. The database and the UI are accessible through a Precision Medicine Platform workspace. As of March 2024, the database contains over 13.2 million cleaned GWTG patient records. The SQLite subsets benefit researchers by optimizing data extraction and manipulation using Structured Query Language. The UI improves accessibility for nontechnical researchers by presenting data in a user-friendly tabular format with intuitive filtering options. With the implementation of the GWTG database and UI application, we addressed data management and accessibility concerns despite its growing scale. We have launched tools to provide streamlined access and accessibility of GWTG registry data to all researchers, regardless of familiarity or experience in coding.

Forecasting Daily Fire Radiative Energy Using Data Driven Methods and Machine Learning Techniques

AbstractIncreasing impacts of wildfires on Western US air quality highlights the need for forecasts of smoke emissions based on dynamic modeled wildfires. This work utilizes knowledge of weather, fuels, topography, and firefighting, combined with machine learning and other statistical methods, to generate 1‐ and 2‐day forecasts of fire radiative energy (FRE). The models are trained on data covering 2019 and 2021 and evaluated on data for 2020. For the 1‐day (2‐day) forecasts, the random forest model shows the most skill, explaining 48% (25%) of the variance in observed daily FRE when trained on all available predictors compared to the 2% (<0%) of variance explained by persistence for the extreme fire year of 2020. The random forest model also shows improved skill in forecasting day‐to‐day increases and decreases in FRE, with 28% (39%) of observed increase (decrease) days predicted, and increase (decrease) days are identified with 62% (60%) accuracy. Error in the random forest increases with FRE, and the random forest tends toward persistence under severe fire weather. Sensitivity analysis shows that near‐surface weather and the latest observed FRE contribute the most to the skill of the model. When the random forest model was trained on subsets of the training data produced by agencies (e.g., the Canadian or US Forest Services), comparable if not better performance was achieved (1‐day R2 = 0.39–0.48, 2‐day R2 = 0.13–0.34). FRE is used to compute emissions, so these results demonstrate potential for improved fire emissions forecasts for air quality models.

A Comparative Analysis of Recruitment Methods to Reach Emerging Adults Outside the Clinical Setting.

Emerging adults are a hard-to-recruit population for health researchers, as many do not routinely access health care services and are best recruited outside clinical settings. Social media and research volunteer registries (e.g., ResearchMatch) offer great potential among this population, yet a comparison of these two recruitment methods has not been done. To compare participant enrollment and completion rates, participant demographics, and recruitment costs between recruitment methods (social media advertisements compared to ResearchMatch) deployed with a sample of female-bodied emerging adults. Female-bodied emerging adults were recruited from October to November 2022 via ResearchMatch and social media (Instagram and Snapchat) advertisements. This analysis involves a subset of recruitment data from a larger institutional review board-approved study. Enrollment and survey completion rates were calculated using the number of individuals contacted and survey completion data from Qualtrics. Chi-square and independent t-test analyses were used to compare demographic data. Advertisement data collected included total cost, cost per click, link clicks, and paid impressions. Two hundred and forty-five emerging adults completed the survey, and 24 completed follow-up interviews. ResearchMatch and social media enrollment rates differed (58% and 39%, respectively). Survey completion rates for both methods were the same (~93%). Participants' ages and levels of education were significantly different. Social media resulted in recruitment of younger participants (18-21 years), and ResearchMatch garnered participants with a higher level of education. Differences in race were also significant, as social media recruited higher numbers of White participants. Lastly, the researcher-incurred cost per survey was $0 for ResearchMatch versus $13 for social media. While social media and ResearchMatch are both successful tools for research recruitment, each provides distinct benefits for recruiting specific populations. ResearchMatch offers a lower-cost option and access to an older emerging adult population with higher education, while social media provides access to a younger emerging adult population. This knowledge can be imperative for deciding which recruitment methods best fit research study needs. Future research should explore differences in race by recruitment method to highlight potential sampling biases or recruitment opportunities.

Experimental unbalance: reflections on genetic parameters and corn selection gain

Genetic progress depends on the components of variance and genetic parameters. In this context, the objective of this work was to identify the maximum allowed percentage of experimental imbalance in the estimation of variance components, genetic parameters and selection gain in intervarietal corn hybrids. The experimental design used was randomized blocks, with 60 corn hybrids with three replications. Random subsets of data were created in order to express unbalance scenarios of the phenotypic matrix, we obtained 9 scenarios (0, 10, 20, 30, 40, 50, 60, 70 and 80% unbalance).Thus, the genetic variance of the paternal genitor, the genetic variance of the maternal genitor, additive variance, individual phenotypic variance, narrow-sense heritability of intervarietal additive effects for the paternal genitor were estimated, narrow-sense heritability of intervarietal additive effects for the maternal genitor, narrow-sense heritability, broad-sense heritability, genotypic variation coefficient between progenies and variation coefficient residual. Narrow sense heritability reveals high magnitude for the characters cob mass and hundred grain mass. Maternal effect is expressed through ear insertion height, ear grain mass, cob mass and diameter, number of rows, ear mass and length, and grain yield. The imbalance inflates the variance components and genetic parameters for the highlighted characters. It supports 10% imbalance in the data matrix without compromising the reliability of the estimates. Pronounceable selection gains are obtained for grain yield based on pressures of 1 and 5%. An unbalance of 10% is supported in the selection gain for cob mass, ear length and hundred grain mass.

Global soil respiration predictions with associated uncertainties from different spatio-temporal data subsets

Soil respiration (Rs), the second-largest flux in the global carbon cycle, is a crucial but uncertain component. To improve the understanding of global Rs, we constructed single global models, and specific models classified by climate type, land cover type, year of the data record, and elevation range using the random forest algorithm to predict global Rs values and explore the associated uncertainty in the models. The results showed a similar overall predictive performance for the models, with an R-squared value greater than 0.63; however, significant differences were observed compared to the global Rs estimate (23 Pg C). All the models estimated larger values of Rs than the single global model, mainly owing to imbalances in the sample data on which the prediction models were based. One exception to this result is the land cover model, which estimates a smaller global Rs for 2020 (95.1 Pg C). Overall, the single global model estimates were closer to those obtained for temperate zones owing to differences in the training data distribution, which resulted in smaller global estimates than those of other classification-specific models. Prediction models using observations before 2000 tend to underestimate the global Rs. However, the use of classification-specific Rs models proved helpful in addressing the persistent temporal and spatial imbalances in Rs sampling. Expanding the coverage of Rs records both temporally and spatially and updating the global Rs database promptly would improve the estimation accuracy of global Rs prediction models while enhancing the understanding of the overall global carbon budget and the feedback of soil carbon with regard to climate warming.

Blind spectral inversion of seismic data

AbstractReflectivity inversion is a key step in reservoir prediction. Conventional sparse‐spike deconvolution assumes that the reflectivity (reflection coefficient series) is sparse and solves for the reflection coefficients by an L1‐norm inversion process. Spectral inversion is an alternative to sparse‐spike deconvolution, which is based on the odd–even decomposition algorithm and can accurately identify thin layers and reduce the wavelet tuning effect without using constraints from logging data, from horizon interpretations or from an initial model of the reflectivity. In seismic processing, an error exists in wavelet extraction because of complex geological structures, resulting in the low accuracy of deconvolution and inversion. Blind deconvolution is an effective method for solving the problem mentioned above, which comprises seismic wavelet and reflectivity sequence, assuming that the wavelets that affect some subsets of the seismic data are approximately the same. Therefore, we combined blind deconvolution with spectral inversion to propose blind spectral inversion. Given an initial wavelet, we can calculate the reflectivity based on spectral inversion and update the wavelet for the next iteration. During the update processing, we add the smoothness of the wavelet amplitude spectrum as a regularization term, thus reducing the wavelet oscillation in the time domain, increasing the similarity between inverted and initial wavelets, and improving the stability of the solution. The blind spectral inversion method inherits the wavelet robustness of blind deconvolution and high resolution of spectral inversion, which is suitable for reflectivity inversion. Applications to synthetic and field seismic datasets demonstrate that the blind spectral inversion method can accurately calculate the reflectivity even when there is an error in wavelet extraction.

Enhanced IDOL segmentation framework using personalized hyperspace learning IDOL.

Adaptive radiotherapy (ART) workflows have been increasingly adopted to achieve dose escalation and tissue sparing under shifting anatomic conditions, but the necessity of recontouring and the associated time burden hinders a real-time or online ART workflow. In response to this challenge, approaches to auto-segmentation involving deformable image registration, atlas-based segmentation, and deep learning-based segmentation (DLS) have been developed. Despite the particular promise shown by DLS methods, implementing these approaches in a clinical setting remains a challenge, namely due to the difficulty of curating a data set of sufficient size and quality so as to achieve generalizability in a trained model. To address this challenge, we have developed an intentional deep overfit learning (IDOL) framework tailored to the auto-segmentation task. However, certain limitations were identified, particularly the insufficiency of the personalized dataset to effectively overfit the model. In this study, we introduce a personalized hyperspace learning (PHL)-IDOL segmentation framework capable of generating datasets that induce the model to overfit specific patient characteristics for medical image segmentation. The PHL-IDOL model is trained in two stages. In the first, a conventional, general model is trained with a diverse set of patient data (n=100 patients) consisting of CT images and clinical contours. Following this, the general model is tuned with a data set consisting of two components: (a) selection of a subset of the patient data (m<n) using the similarity metrics (mean square error (MSE), peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), and the universal quality image index (UQI) values); (b) adjust the CT and the clinical contours using a deformed vector generated from the reference patient and the selected patients using (a). After training, the general model, the continual model, the conventional IDOL model, and the proposed PHL-IDOL model were evaluated using the volumetric dice similarity coefficient (VDSC) and the Hausdorff distance 95% (HD95%) computed for 18 structures in 20 test patients. Implementing the PHL-IDOL framework resulted in improved segmentation performance for each patient. The Dice scores increased from 0.81 0.05 with the general model, 0.83 for the continual model, 0.83 for the conventional IDOL model to an average of 0.87 with the PHL-IDOL model. Similarly, the Hausdorff distance decreased from 3.06 with the general model, 2.84 for the continual model, 2.79 for the conventional IDOL model and 2.36 for the PHL-IDOL model. All the standard deviations were decreased by nearly half of the values comparing the general model and the PHL-IDOL model. The PHL-IDOL framework applied to the auto-segmentation task achieves improved performance compared to the general DLS approach, demonstrating the promise of leveraging patient-specific prior information in a task central to online ART workflows.

Effective Privacy Protection Strategies for Pregnancy and Gestation Information From Electronic Medical Records: Retrospective Study in a National Health Care Data Network in China.

Pregnancy and gestation information is routinely recorded in electronic medical record (EMR) systems across China in various data sets. The combination of data on the number of pregnancies and gestations can imply occurrences of abortions and other pregnancy-related issues, which is important for clinical decision-making and personal privacy protection. However, the distribution of this information inside EMR is variable due to inconsistent IT structures across different EMR systems. A large-scale quantitative evaluation of the potential exposure of this sensitive information has not been previously performed, ensuring the protection of personal information is a priority, as emphasized in Chinese laws and regulations. This study aims to perform the first nationwide quantitative analysis of the identification sites and exposure frequency of sensitive pregnancy and gestation information. The goal is to propose strategies for effective information extraction and privacy protection related to women's health. This study was conducted in a national health care data network. Rule-based protocols for extracting pregnancy and gestation information were developed by a committee of experts. A total of 6 different sub-data sets of EMRs were used as schemas for data analysis and strategy proposal. The identification sites and frequencies of identification in different sub-data sets were calculated. Manual quality inspections of the extraction process were performed by 2 independent groups of reviewers on 1000 randomly selected records. Based on these statistics, strategies for effective information extraction and privacy protection were proposed. The data network covered hospitalized patients from 19 hospitals in 10 provinces of China, encompassing 15,245,055 patients over an 11-year period (January 1, 2010-December 12, 2020). Among women aged 14-50 years, 70% were randomly selected from each hospital, resulting in a total of 1,110,053 patients. Of these, 688,268 female patients with sensitive reproductive information were identified. The frequencies of identification were variable, with the marriage history in admission medical records being the most frequent at 63.24%. Notably, more than 50% of female patients were identified with pregnancy and gestation history in nursing records, which is not generally considered a sub-data set rich in reproductive information. During the manual curation and review process, 1000 cases were randomly selected, and the precision and recall rates of the information extraction method both exceeded 99.5%. The privacy-protection strategies were designed with clear technical directions. Significant amounts of critical information related to women's health are recorded in Chinese routine EMR systems and are distributed in various parts of the records with different frequencies. This requires a comprehensive protocol for extracting and protecting the information, which has been demonstrated to be technically feasible. Implementing a data-based strategy will enhance the protection of women's privacy and improve the accessibility of health care services.

How Gaussian mixture modelling can help to verify reference intervals from laboratory data with a high proportion of pathological values

Abstract Objectives Although there are several indirect methods that can be used to verify reference limits, they have a common weakness in that they assume a low proportion of pathological values. This paper investigates whether a Gaussian decomposition algorithm can identify the non-pathological fraction even if it is not the main subset of mixed data. Methods All investigations are carried out in the R programming environment. The mclust package is used for Gaussian mixture modelling via the expectation maximization (EM) algorithm. For right-skewed distributions, logarithms of the original values are taken to approximate the Gaussian model. We use the Bayesian information criterion (BIC) for evaluation of the results. The reflimR and refineR packages serve as comparison procedures. Results We generate synthetic data mixtures with known normal distributions to demonstrate the feasibility and reliability of our approach. Application of the algorithm to real data from a Nigerian and a German population produces results, which help to interpret reference intervals of reflimR and refineR that are obviously too wide. In the first example, the mclust analysis of hemoglobin in Nigerian women supports the medical hypothesis that an anemia rate of more than 50 % leads to falsely low reference limits. Our algorithm proposes various scenarios based on the BIC values, one of which suggests reference limits that are close to published data for Nigeria but significantly lower than those established for the Caucasian population. In the second example, the standard statistical analysis of creatine kinase in German patients with predominantly cardiac diseases yields a reference interval that is clearly too wide. With mclust we identify overlapping fractions that explain this false result. Conclusions Gaussian mixture modelling does not replace standard methods for reference interval estimation but is a valuable adjunct when these methods produce discrepant or implausible results.

Risks for Enlisted Navy Divers Compared to Other Enlisted Sailors: An Examination of Illnesses That May Be Associated With Exposure to Contaminated Water Diving.

Illnesses among Navy divers degrade readiness, decrease manpower levels, and increase costs for medical care. Prior research has shown that Navy divers have high rates of the types of illnesses that might be because of diving in contaminated water. The objectives of this study were to examine medical records of U.S. Navy Sailors from 2016 to 2022 and determine if divers have higher incidence rates of health conditions that might be associated with contaminated water diving compared to non-divers. For this retrospective cohort study, we used data from the Defense Medical Epidemiology Database (DMED). The DMED is operated by the Armed Forces Health Surveillance Division and uses data from the Defense Manpower Data Center to classify occupations. The DMED provides free online access to a de-identified subset of data contained within the Defense Medical Surveillance System.The population was U.S. Navy enlisted males, aged 25 to 29 years. Divers were compared to non-divers using 8 selected diagnoses that may reasonably be associated with diving in contaminated water. During the study period, the database contained a total of 5,474 diver and 827,406 non-diver person-years. Of the 8 diagnoses, the ones with the largest number of cases for divers were upper respiratory infections with 128 and ear disorders with 62. The relative risks (RRs) for divers compared to non-divers were higher for otitis externa (RR = 1.44; confidence interval = 1.03, 2.01) and for ear disorders (RR = 1.15; confidence interval = 0.89, 1.47); for the other 6 diagnoses, the divers had lower rates than the non-divers. The high RRs found for otitis externa and ear disorders support the need to devote resources to better understand the reasons for these higher risks and to develop, test, and implement targeted risk-reduction strategies. Future studies should attempt to link verified contaminated water exposures with adverse health outcomes and calculate risks based on criteria such as age and dive factors.

Stack performance classification and fault diagnosis optimization of solid oxide fuel cell system based on bayesian artificial neural network and feature selection

Solid oxide fuel cell (SOFC) has attracted much attention because of its high efficiency and silent power generation, and can be applied to the field of fuel cell-powered unmanned boats. However, a fuel deficit failure in the system can lead to reduced stack performance, reducing the reliability of SOFC applications in the field of unmanned boats. Therefore, this paper proposes an efficient breakdown diagnosis model for SOFC system fault diagnosis. Firstly, Bayesian artificial neural network is constructed by using the best feature data subset after Relief-F combined with minimum Redundancy Maximum Relevance algorithm feature selecting. Secondly, the correct diagnosis rate under different number of optimal features is calculated, and the best feature combinations are combined to verify. Finally, the particle swarm algorithm selects the optimal hidden neuron count to optimization model. Experimental findings suggest that for correct diagnosis rate, the breakdown diagnosis model based on the optimal number of 3 features can reduce the training time and maintain high accuracy compared with the use of all 34 features. This research result provides a feasible way for the fault diagnosis application of SOFC system power generation in the field of unmanned boats.

Evaluating Binary Outcome Classifiers Estimated from Survey Data.

Surveys are commonly used to facilitate research in epidemiology, health, and the social and behavioral sciences. Often, these surveys are not simple random samples, and respondents are given weights reflecting their probability of selection into the survey. We show that using survey weights can be beneficial for evaluating the quality of predictive models when splitting data into training and test sets. In particular, we characterize model assessment statistics, such as sensitivity and specificity, as finite population quantities and compute survey-weighted estimates of these quantities with test data comprising a random subset of the original data. Using simulations with data from the National Survey on Drug Use and Health and the National Comorbidity Survey, we show that unweighted metrics estimated with sample test data can misrepresent population performance, but weighted metrics appropriately adjust for the complex sampling design. We also show that this conclusion holds for models trained using upsampling for mitigating class imbalance. The results suggest that weighted metrics should be used when evaluating performance on test data derived from complex surveys.

A Pilot Search for Gravitational Self-Lensing Binaries with the Zwicky Transient Facility

Binary systems containing a compact object may exhibit periodic brightening episodes due to gravitational lensing as the compact object transits the companion star. Such “self-lensing” signatures have been detected before for white dwarf binaries. We attempt to use these signatures to identify detached stellar-mass neutron star and black hole binaries using data from the Zwicky Transient Facility (ZTF). We present a systematic search for self-lensing signals in Galactic binaries from a subset of high-cadence ZTF data taken in 2018. We identify 12 plausible candidates from the search, although because each candidate is observed to only brighten once, other origins such as stellar flares are more likely. We discuss prospects for more comprehensive future searches of the ZTF data.

Investigating the association between symptoms and functional activity in brain regions in schizophrenia: A cross-sectional fmri-based neuroimaging study

Schizophrenia is a persistent neurological disorder profoundly affecting cognitive, emotional, and behavioral functions, prominently characterized by delusions, hallucinations, disordered speech, and abnormal motor activity. These symptoms often present diagnostic challenges due to their overlap with other forms of psychosis. Therefore, the implementation of automated diagnostic methodologies is imperative. This research leverages Functional Magnetic Resonance Imaging (fMRI), a neuroimaging modality capable of delineating functional activations across diverse brain regions. Furthermore, the utilization of evolving machine learning techniques for fMRI data analysis has significantly progressive. Here, our study stands as a novel attempt, focusing on the comprehensive assessment of both classical and atypical symptoms of schizophrenia. We aim to uncover associated changes in brain functional activity. Our study encompasses two distinct fMRI datasets (1.5T and 3T), each comprising 34 schizophrenia patients for the 1.5T dataset and 25 schizophrenia patients for the 3T dataset, along with an equal number of healthy controls. Machine learning algorithms are applied to assess data subsets, enabling an in-depth evaluation of the current functional condition concerning symptom impact. The identified voxels contribute to determining the brain regions most influenced by each symptom, as quantified by symptom intensity. This rigorous approach has yielded various new findings while maintaining an impressive classification accuracy rate of 97 %. By elucidating variations in activation patterns across multiple brain regions in individuals with schizophrenia, this study contributes to the understanding of functional brain changes associated with the disorder. The insights gained may inform differential clinical interventions and provide a means of assessing symptom severity accurately, offering new avenues for the management of schizophrenia.

Working Individually and Collectively: Assisting Young People with Cognitive Disability Transitioning from Statutory Systems

AbstractYoung people with cognitive disability exiting statutory child protection and/or youth justice systems are a particularly vulnerable group. They have varied, complex and dynamic needs. These are often poorly responded to, due in part to a lack of formal and informal supports. There remains a lack of specialised supports and a dearth of evidence regarding best practice in supporting this group. This paper explores social work practices which respond to the social isolation of this cohort and the gap in support as young people transition to adulthood. The paper focuses on a group program in Queensland (Australia) which was specifically designed to support young people with a cognitive disability leaving child protection and/or youth justice systems. It reports on a subset of data from a mixed-methods study. It presents the perspectives of the young people and their practitioners regarding the practices that supported the engagement of young people and created opportunities for connection and skill development within the group program. The findings highlight the importance of relationship-driven practices that are supported and resourced by the organisation, and the need for parallel individual and group work processes for achieving positive outcomes with young people with cognitive disability transitioning from statutory systems.

Illumination and Shadows in Head Rotation: Experiments with Denoising Diffusion Models

Accurately modeling the effects of illumination and shadows during head rotation is critical in computer vision for enhancing image realism and reducing artifacts. This study delves into the latent space of denoising diffusion models to identify compelling trajectories that can express continuous head rotation under varying lighting conditions. A key contribution of our work is the generation of additional labels from the CelebA dataset, categorizing images into three groups based on prevalent illumination direction: left, center, and right. These labels play a crucial role in our approach, enabling more precise manipulations and improved handling of lighting variations. Leveraging a recent embedding technique for Denoising Diffusion Implicit Models (DDIM), our method achieves noteworthy manipulations, encompassing a wide rotation angle of ±30°. while preserving individual distinct characteristics even under challenging illumination conditions. Our methodology involves computing trajectories that approximate clouds of latent representations of dataset samples with different yaw rotations through linear regression. Specific trajectories are obtained by analyzing subsets of data that share significant attributes with the source image, including light direction. Notably, our approach does not require any specific training of the generative model for the task of rotation; we merely compute and follow specific trajectories in the latent space of a pre-trained face generation model. This article showcases the potential of our approach and its current limitations through a qualitative discussion of notable examples. This study contributes to the ongoing advancements in representation learning and the semantic investigation of the latent space of generative models.

Prevalence and progression of chronic kidney disease among adults undergoing creatinine testing in South African public healthcare facilities: a study leveraging data from South Africa’s National Health Laboratory Service (NHLS)

BackgroundChronic kidney disease (CKD) has emerged as a substantial global health challenge, with a marked rise in associated mortality. However, it often goes undetected until advanced stages, particularly in low-income...