Jointly constrained group sparse connectivity representation improves early diagnosis of Alzheimer's disease on routinely acquired T1-weighted imaging-based brain network

Background

Radiomics-based morphological brain networks (radMBN) constructed from routinely acquired structural MRI (sMRI) data have gained attention in Alzheimer's disease (AD). However, the radMBN suffers from limited characterization of AD because sMRI only characterizes anatomical changes and is not a direct measure of neuronal pathology or brain activity.

Purpose

To establish a group sparse representation of the radMBN under a joint constraint of group-level white matter fiber connectivity and individual-level sMRI regional similarity (JCGS-radMBN).

Methods

Two publicly available datasets were adopted, including 120 subjects from ADNI with both T1-weighted image (T1WI) and diffusion MRI (dMRI) for JCGS-radMBN construction, 818 subjects from ADNI and 200 subjects solely with T1WI from AIBL for validation in early AD diagnosis. Specifically, the JCGS-radMBN was conducted by jointly estimating non-zero connections among subjects, with the regularization term constrained by group-level white matter fiber connectivity and individual-level sMRI regional similarity. Then, a triplet graph convolutional network was adopted for early AD diagnosis. The discriminative brain connections were identified using a two-sample t-test, and the neurobiological interpretation was validated by correlating the discriminative brain connections with cognitive scores.

Results

The JCGS-radMBN exhibited superior classification performance over five brain network construction methods. For the typical NC vs. AD classification, the JCGS-radMBN increased by 1-30% in accuracy over the alternatives on ADNI and AIBL. The discriminative brain connections exhibited a strong connectivity to hippocampus, parahippocampal gyrus, and basal ganglia, and had significant correlation with MMSE scores.

Conclusion

The proposed JCGS-radMBN facilitated the AD characterization of brain network established on routinely acquired imaging modality of sMRI.

Supplementary Information

The online version of this article (10.1007/s13755-023-00269-0) contains supplementary material, which is available to authorized users.

Cine-cardiac magnetic resonance to distinguish between ischemic and non-ischemic cardiomyopathies: a machine learning approach

OBJECTIVE

This work aimed to derive a machine learning (ML) model for the differentiation between ischemic cardiomyopathy (ICM) and non-ischemic cardiomyopathy (NICM) on non-contrast cardiovascular magnetic resonance (CMR).

METHODS

This retrospective study evaluated CMR scans of 107 consecutive patients (49 ICM, 58 NICM), including atrial and ventricular strain parameters. We used these data to compare an explainable tree-based gradient boosting additive model with four traditional ML models for the differentiation of ICM and NICM. The models were trained and internally validated with repeated cross-validation according to discrimination and calibration. Furthermore, we examined important variables for distinguishing between ICM and NICM.

RESULTS

A total of 107 patients and 38 variables were available for the analysis. Of those, 49 were ICM (34 males, mean age 60 ± 9 years) and 58 patients were NICM (38 males, mean age 56 ± 19 years). After 10 repetitions of the tenfold cross-validation, the proposed model achieved the highest area under curve (0.82, 95% CI [0.47-1.00]) and lowest Brier score (0.19, 95% CI [0.13-0.27]), showing competitive diagnostic accuracy and calibration. At the Youden's index, sensitivity was 0.72 (95% CI [0.68-0.76]), the highest of all. Analysis of predictions revealed that both atrial and ventricular strain CMR parameters were important for the identification of ICM patients.

CONCLUSION

The current study demonstrated that using a ML model, multi chamber myocardial strain, and function on non-contrast CMR parameters enables the discrimination between ICM and NICM with competitive diagnostic accuracy.

CLINICAL RELEVANCE STATEMENT

A machine learning model based on non-contrast cardiovascular magnetic resonance parameters may discriminate between ischemic and non-ischemic cardiomyopathy enabling wider access to cardiovascular magnetic resonance examinations with lower costs and faster imaging acquisition.

KEY POINTS

• The exponential growth in cardiovascular magnetic resonance examinations may require faster and more cost-effective protocols. • Artificial intelligence models can be utilized to distinguish between ischemic and non-ischemic etiologies. • Machine learning using non-contrast CMR parameters can effectively distinguish between ischemic and non-ischemic cardiomyopathies.

SpanSeq: similarity-based sequence data splitting method for improved development and assessment of deep learning projects

The use of deep learning models in computational biology has increased massively in recent years, and it is expected to continue with the current advances in the fields such as Natural Language Processing. These models, although able to draw complex relations between input and target, are also inclined to learn noisy deviations from the pool of data used during their development. In order to assess their performance on unseen data (their capacity to generalize), it is common to split the available data randomly into development (train/validation) and test sets. This procedure, although standard, has been shown to produce dubious assessments of generalization due to the existing similarity between samples in the databases used. In this work, we present SpanSeq, a database partition method for machine learning that can scale to most biological sequences (genes, proteins and genomes) in order to avoid data leakage between sets. We also explore the effect of not restraining similarity between sets by reproducing the development of two state-of-the-art models on bioinformatics, not only confirming the consequences of randomly splitting databases on the model assessment, but expanding those repercussions to the model development. SpanSeq is available at https://github.com/genomicepidemiology/SpanSeq.

The architecture of functional brain network modulated by driving under train running noise exposure

A noisy environment can considerably impact drivers' attention and fatigue, endangering driving safety. Consequently, this study designed a simulated driving experimental scenario to analyse the effects of noise generated during urban rail transit train operation on drivers' functional brain networks. The experiment recruited 16 participants, and the simulated driving scenario was conducted at noise levels of 50, 60, 70, and 80 dB. Functional connectivity between all electrode pairs across various frequency bands was evaluated using the weighted phase lag index (WPLI), and a brain network based on this was constructed. Graph theoretic analysis employed network global efficiency, degree, and clustering coefficient as metrics. Significant increases in the WPLI values of theta and alpha frequency bands were observed in high noise environments (70 dB, 80 dB), as well as enhanced brain synchronisation. Furthermore, concerning the topological metrics of brain networks, it was observed that the global efficiency of brain networks in theta and alpha frequency ranges, as well as the node degree and clustering coefficients, experienced substantial growth in high noise environments (70 dB, 80 dB) as opposed to 50 dB and 60 dB. This finding indicates that high-noise environments impact the reorganisation of functional brain networks, leading to a preference for network structures with improved global efficiency. Such findings may improve our understanding of the neural mechanisms of driving under noise exposure, and thus potentially reduce road accidents to some extent.

Pesticides in the population of European hedgehogs (Erinaceus europaeus) in Denmark

European hedgehogs (Erinaceus europaeus) inhabit most of Denmark, except for a few smaller islands. Research from other European countries has shown that the hedgehog populations are in decline. The exposure to chemicals might contribute to this development, although their role is currently unknown. Our research studied the occurrence of 19 selected pesticides in the Danish hedgehog population as well as factors potentially explaining the levels of chemicals detected. We analysed 115 liver samples obtained from dead hedgehogs in 2016 for seven rodenticides, four insecticides and eight herbicides commonly used in Denmark at the time of sampling, applying a high-performance liquid chromatography-tandem mass spectrometry (HPLC-MS/MS) method. Detection frequencies varied between 0.9% for fluroxypyr and trans-permethrin and 79% for bromadiolone. Rodenticides, insecticides and herbicides were detected in 84, 43, and 50% of the samples, respectively. The compounds most frequently detected included the insecticide imidacloprid (35%), the herbicide metamitron (29%) and the rodenticide bromadiolone (79%). Individual concentrations varied between non-detected to >2 μg/g. A total of 79% of the 115 hedgehogs contained more than one detectable pesticide, with up to nine of the 19 compounds detected in one individual. The detection frequencies were found to differ significantly between the Eastern and Western part of Denmark for difenacoum, difethialone and imidacloprid. However, no associations were found with sex, age, habitat type or the prevalence of mecC-MRSA and endoparasites in the hedgehogs tested. Whether or not the pesticide levels detected carry a health risk for the hedgehogs remains unknown as no adverse effect levels have yet been established for European hedgehogs for single compounds or pesticide mixtures.

Deep learning-based image quality assessment: impact on detection accuracy of prostate cancer extraprostatic extension on MRI

OBJECTIVE

To assess impact of image quality on prostate cancer extraprostatic extension (EPE) detection on MRI using a deep learning-based AI algorithm.

MATERIALS AND METHODS

This retrospective, single institution study included patients who were imaged with mpMRI and subsequently underwent radical prostatectomy from June 2007 to August 2022. One genitourinary radiologist prospectively evaluated each patient using the NCI EPE grading system. Each T2WI was classified as low- or high-quality by a previously developed AI algorithm. Fisher's exact tests were performed to compare EPE detection metrics between low- and high-quality images. Univariable and multivariable analyses were conducted to assess the predictive value of image quality for pathological EPE.

RESULTS

A total of 773 consecutive patients (median age 61 [IQR 56-67] years) were evaluated. At radical prostatectomy, 23% (180/773) of patients had EPE at pathology, and 41% (131/318) of positive EPE calls on mpMRI were confirmed to have EPE. The AI algorithm classified 36% (280/773) of T2WIs as low-quality and 64% (493/773) as high-quality. For EPE grade ≥ 1, high-quality T2WI significantly improved specificity for EPE detection (72% [95% CI 67-76%] vs. 63% [95% CI 56-69%], P = 0.03), but did not significantly affect sensitivity (72% [95% CI 62-80%] vs. 75% [95% CI 63-85%]), positive predictive value (44% [95% CI 39-49%] vs. 38% [95% CI 32-43%]), or negative predictive value (89% [95% CI 86-92%] vs. 89% [95% CI 85-93%]). Sensitivity, specificity, PPV, and NPV for EPE grades ≥ 2 and ≥ 3 did not show significant differences attributable to imaging quality. For NCI EPE grade 1, high-quality images (OR 3.05, 95% CI 1.54-5.86; P < 0.001) demonstrated a stronger association with pathologic EPE than low-quality images (OR 1.76, 95% CI 0.63-4.24; P = 0.24).

CONCLUSION

Our study successfully employed a deep learning-based AI algorithm to classify image quality of prostate MRI and demonstrated that better quality T2WI was associated with more accurate prediction of EPE at final pathology.

Trusted Information Sources About the COVID-19 Vaccine Vary in Underserved Communities

The COVID-19 pandemic was one of the deadliest global public health events. In the United States, over 1.1 million individuals have died, and now COVID-19 is the third leading cause of death (CDC, 2023). Vaccine uptake has stalled among different demographics. Vaccine hesitancy, a delay in accepting or refusing vaccines, poses a significant challenge regardless of the availability of safe and effective COVID-19 vaccines. This study aimed to identify disparate COVID-19 vaccine uptake among individuals in Western New York. The primary objective was to identify the factors contributing to lower rates of COVID-19 vaccination within this population.Data were collected from 585 adults recruited from 20 Niagara and Erie Counties sites using a self-administered survey on vaccine hesitancy, vaccination status, and COVID-19-related characteristics. The survey included the adult Vaccine Hesitancy Scale (aVHS) and acquired information on demographic characteristics and COVID-19 impact, knowledge, and information sources. Data were analyzed using descriptive statistics, a chi-squared test, a Wilcoxon rank-sum test, and a logistic regression model.Findings suggest that unvaccinated participants (n = 35) were concerned about vaccine side effects (48.6%). For vaccinated/unboosted participants (n = 52), they (40.0%) reported clinical concerns. After adjusting for gender and age, healthcare provider guidance and family guidance remained significant predictors of vaccination status, while clinical research studies were significant predictors of booster status. Findings from this study suggest public health interventions that target vaccine education and facilitate well-informed decisions about COVID-19 vaccines lead to less vaccine hesitancy.

Synthetic DNA barcodes identify singlets in scRNA-seq datasets and evaluate doublet algorithms

Single-cell RNA sequencing (scRNA-seq) datasets contain true single cells, or singlets, in addition to cells that coalesce during the protocol, or doublets. Identifying singlets with high fidelity in scRNA-seq is necessary to avoid false negative and false positive discoveries. Although several methodologies have been proposed, they are typically tested on highly heterogeneous datasets and lack a priori knowledge of true singlets. Here, we leveraged datasets with synthetically introduced DNA barcodes for a hitherto unexplored application: to extract ground-truth singlets. We demonstrated the feasibility of our framework, "singletCode," to evaluate existing doublet detection methods across a range of contexts. We also leveraged our ground-truth singlets to train a proof-of-concept machine learning classifier, which outperformed other doublet detection algorithms. Our integrative framework can identify ground-truth singlets and enable robust doublet detection in non-barcoded datasets.

Sensitivity of unconstrained quantitative magnetization transfer MRI to Amyloid burden in preclinical Alzheimer's disease

Magnetization transfer MRI is sensitive to semi-solid macromolecules, including amyloid beta, and has previously been used to discriminate Alzheimer's disease (AD) patients from controls. Here, we fit an unconstrained 2-pool quantitative MT (qMT) model, i.e., without constraints on the longitudinal relaxation rateR 1 s of semi-solids, and investigate the sensitivity of the estimated parameters to amyloid accumulation in preclinical subjects. We scanned 15 cognitively normal volunteers, of which 9 were amyloid positive by [18F]Florbetaben PET. A 12 min hybrid-state qMT scan with an effective resolution of 1.24 mm isotropic and whole-brain coverage was acquired to estimate the unconstrained 2-pool qMT parameters. Group comparisons and correlations with Florbetaben PET standardized uptake value ratios were analyzed at the lobar level. We find that the exchange rate and semi-solid pool'sR 1 s were sensitive to the amyloid concentration, while morphometric measures of cortical thickness derived from structural MRI were not. Changes in the exchange rate are consistent with previous reports in clinical AD, while changes inR 1 s have not been reported previously as its value is typically constrained in the literature. Our results demonstrate that qMT MRI may be a promising surrogate marker of amyloid beta without the need for contrast agents or radiotracers.

Flexible parametrization of graph-theoretical features from individual-specific networks for prediction

Statistical techniques are needed to analyze data structures with complex dependencies such that clinically useful information can be extracted. Individual-specific networks, which capture dependencies in complex biological systems, are often summarized by graph-theoretical features. These features, which lend themselves to outcome modeling, can be subject to high variability due to arbitrary decisions in network inference and noise. Correlation-based adjacency matrices often need to be sparsified before meaningful graph-theoretical features can be extracted, requiring the data analysts to determine an optimal threshold. To address this issue, we propose to incorporate a flexible weighting function over the full range of possible thresholds to capture the variability of graph-theoretical features over the threshold domain. The potential of this approach, which extends concepts from functional data analysis to a graph-theoretical setting, is explored in a plasmode simulation study using real functional magnetic resonance imaging (fMRI) data from the Autism Brain Imaging Data Exchange (ABIDE) Preprocessed initiative. The simulations show that our modeling approach yields accurate estimates of the functional form of the weight function, improves inference efficiency, and achieves a comparable or reduced root mean square prediction error compared to competitor modeling approaches. This assertion holds true in settings where both complex functional forms underlie the outcome-generating process and a universal threshold value is employed. We demonstrate the practical utility of our approach by using resting-state fMRI data to predict biological age in children. Our study establishes the flexible modeling approach as a statistically principled, serious competitor to ad-hoc methods with superior performance.

Sampling weighting strategies in causal mediation analysis

BACKGROUND

Causal mediation analysis plays a crucial role in examining causal effects and causal mechanisms. Yet, limited work has taken into consideration the use of sampling weights in causal mediation analysis. In this study, we compared different strategies of incorporating sampling weights into causal mediation analysis.

METHODS

We conducted a simulation study to assess 4 different sampling weighting strategies-1) not using sampling weights, 2) incorporating sampling weights into mediation "cross-world" weights, 3) using sampling weights when estimating the outcome model, and 4) using sampling weights in both stages. We generated 8 simulated population scenarios comprising an exposure (A), an outcome (Y), a mediator (M), and six covariates (C), all of which were binary. The data were generated so that the true model of A given C and the true model of A given M and C were both logit models. We crossed these 8 population scenarios with 4 different sampling methods to obtain 32 total simulation conditions. For each simulation condition, we assessed the performance of 4 sampling weighting strategies when calculating sample-based estimates of the total, direct, and indirect effects. We also applied the four sampling weighting strategies to a case study using data from the National Survey on Drug Use and Health (NSDUH).

RESULTS

Using sampling weights in both stages (mediation weight estimation and outcome models) had the lowest bias under most simulation conditions examined. Using sampling weights in only one stage led to greater bias for multiple simulation conditions.

DISCUSSION

Using sampling weights in both stages is an effective approach to reduce bias in causal mediation analyses under a variety of conditions regarding the structure of the population data and sampling methods.

Extracting interpretable signatures of whole-brain dynamics through systematic comparison

The brain's complex distributed dynamics are typically quantified using a limited set of manually selected statistical properties, leaving the possibility that alternative dynamical properties may outperform those reported for a given application. Here, we address this limitation by systematically comparing diverse, interpretable features of both intra-regional activity and inter-regional functional coupling from resting-state functional magnetic resonance imaging (rs-fMRI) data, demonstrating our method using case-control comparisons of four neuropsychiatric disorders. Our findings generally support the use of linear time-series analysis techniques for rs-fMRI case-control analyses, while also identifying new ways to quantify informative dynamical fMRI structures. While simple statistical representations of fMRI dynamics performed surprisingly well (e.g., properties within a single brain region), combining intra-regional properties with inter-regional coupling generally improved performance, underscoring the distributed, multifaceted changes to fMRI dynamics in neuropsychiatric disorders. The comprehensive, data-driven method introduced here enables systematic identification and interpretation of quantitative dynamical signatures of multivariate time-series data, with applicability beyond neuroimaging to diverse scientific problems involving complex time-varying systems.

Multi-risk factors joint prediction model for risk prediction of retinopathy of prematurity

Purpose

Retinopathy of prematurity (ROP) is a retinal vascular proliferative disease common in low birth weight and premature infants and is one of the main causes of blindness in children.In the context of predictive, preventive and personalized medicine (PPPM/3PM), early screening, identification and treatment of ROP will directly contribute to improve patients' long-term visual prognosis and reduce the risk of blindness. Thus, our objective is to establish an artificial intelligence (AI) algorithm combined with clinical demographics to create a risk model for ROP including treatment-requiring retinopathy of prematurity (TR-ROP) infants.

Methods

A total of 22,569 infants who underwent routine ROP screening in Shenzhen Eye Hospital from March 2003 to September 2023 were collected, including 3335 infants with ROP and 1234 infants with TR-ROP among ROP infants. Two machine learning methods of logistic regression and decision tree and a deep learning method of multi-layer perceptron were trained by using the relevant combination of risk factors such as birth weight (BW), gestational age (GA), gender, whether multiple births (MB) and mode of delivery (MD) to achieve the risk prediction of ROP and TR-ROP. We used five evaluation metrics to evaluate the performance of the risk prediction model. The area under the receiver operating characteristic curve (AUC) and the area under the precision-recall curve (AUCPR) were the main measurement metrics.

Results

In the risk prediction for ROP, the BW + GA demonstrated the optimal performance (mean ± SD, AUCPR: 0.4849 ± 0.0175, AUC: 0.8124 ± 0.0033). In the risk prediction of TR-ROP, reasonable performance can be achieved by using GA + BW + Gender + MD + MB (AUCPR: 0.2713 ± 0.0214, AUC: 0.8328 ± 0.0088).

Conclusions

Combining risk factors with AI in screening programs for ROP could achieve risk prediction of ROP and TR-ROP, detect TR-ROP earlier and reduce the number of ROP examinations and unnecessary physiological stress in low-risk infants. Therefore, combining ROP-related biometric information with AI is a cost-effective strategy for predictive diagnostic, targeted prevention, and personalization of medical services in early screening and treatment of ROP.

Estimating the health impacts of exposure to Air pollutants and the evaluation of changes in their concentration using a linear model in Iran

In big and industrial cities of developing countries, illness and mortality from long-term exposure to air pollutants have become a serious issue. This research was carried out in 2019-2020 to estimate the health impacts of PM10, NO2 and O3 pollutants by using AirQ+ and R statistical programming software in Arak, Isfahan, Tabriz, Shiraz, Karaj, and Mashhad. Mortality statistics, number of people in required age groups, and amount of pollutants were gathered respectively from different agencies like Statistics and Information Technology of the Ministry of Health, Statistical Center, and Department of Environment and by using Excel, the average 24-hour and 1-hour concentration and maximum 8-hour concentration for PM10, NO2 and O3 pollutants were gathered. We used linear mixed impacts model to account for the longitudinal observations and heterogeneity of the cities. The results of the study showed high number of deaths due to chronic bronchitis in adults, premature death of infants, and respiratory diseases in Mashhad. This research highlights the importance of estimation of health impacts from exposure to air pollutants on residents of the studied cities.

Social Network Negativity and Physical Activity: New Longitudinal Evidence for Young and Older Adults 2015-2018

Purpose: Physical activity (PA) has considerable public health benefits. Positive aspects of the interpersonal environment are known to affect PA, yet few studies have investigated whether negative dimensions also influence PA. This study examines the link between changing social network negativity and PA, net of stable confounding characteristics of persons and their environments. Method: Polling respondents in the San Francisco Bay Area over three waves (2015-2018), the UCNets project provides a panel study of social networks and health for two cohorts of adults. Respondents were recruited through stratified random address sampling, and supplemental sampling was conducted through Facebook advertising and referral. With weights, the sample is approximately representative of Californians aged 21-30 and 50-70. Personal social networks were measured using multiple name-generating questions. Fixed effects ordered logistic regression models provide parameter estimates. Results: Younger adults experience significant decreases in PA when network negativity increases, while changes in other network characteristics (e.g. support, size) did not significantly predict changes in PA. No corresponding association was found for older adults. Results are net of baseline covariate levels, stable social and individual differences, and select time-varying characteristics of persons and their environments. Conclusion: Leveraging longitudinal data from two cohorts of adults, this study extends understanding on interpersonal environments and PA by considering the social costs embedded in social networks. This is the first study to investigate how changes in network negativity pattern PA change. Interventions that help young adults resolve or manage interpersonal conflicts may have the benefit of helping to promote healthy lifestyle choices.

Deep Learning-Based T2-Weighted MR Image Quality Assessment and Its Impact on Prostate Cancer Detection Rates

BACKGROUND

Image quality evaluation of prostate MRI is important for successful implementation of MRI into localized prostate cancer diagnosis.

PURPOSE

To examine the impact of image quality on prostate cancer detection using an in-house previously developed artificial intelligence (AI) algorithm.

STUDY TYPE

Retrospective.

SUBJECTS

615 consecutive patients (median age 67 [interquartile range [IQR]: 61-71] years) with elevated serum PSA (median PSA 6.6 [IQR: 4.6-9.8] ng/mL) prior to prostate biopsy.

FIELD STRENGTH/SEQUENCE

3.0T/T2-weighted turbo-spin-echo MRI, high b-value echo-planar diffusion-weighted imaging, and gradient recalled echo dynamic contrast-enhanced.

ASSESSMENTS

Scans were prospectively evaluated during clinical readout using PI-RADSv2.1 by one genitourinary radiologist with 17 years of experience. For each patient, T2-weighted images (T2WIs) were classified as high-quality or low-quality based on evaluation of both general distortions (eg, motion, distortion, noise, and aliasing) and perceptual distortions (eg, obscured delineation of prostatic capsule, prostatic zones, and excess rectal gas) by a previously developed in-house AI algorithm. Patients with PI-RADS category 1 underwent 12-core ultrasound-guided systematic biopsy while those with PI-RADS category 2-5 underwent combined systematic and targeted biopsies. Patient-level cancer detection rates (CDRs) were calculated for clinically significant prostate cancer (csPCa, International Society of Urological Pathology Grade Group ≥2) by each biopsy method and compared between high- and low-quality images in each PI-RADS category.

STATISTICAL TESTS

Fisher's exact test. Bootstrap 95% confidence intervals (CI). A P value <0.05 was considered statistically significant.

RESULTS

385 (63%) T2WIs were classified as high-quality and 230 (37%) as low-quality by AI. Targeted biopsy with high-quality T2WIs resulted in significantly higher clinically significant CDR than low-quality images for PI-RADS category 4 lesions (52% [95% CI: 43-61] vs. 32% [95% CI: 22-42]). For combined biopsy, there was no significant difference in patient-level CDRs for PI-RADS 4 between high- and low-quality T2WIs (56% [95% CI: 47-64] vs. 44% [95% CI: 34-55]; P = 0.09).

DATA CONCLUSION

Higher quality T2WIs were associated with better targeted biopsy clinically significant cancer detection performance for PI-RADS 4 lesions. Combined biopsy might be needed when T2WI is lower quality.

LEVEL OF EVIDENCE

2 TECHNICAL EFFICACY: Stage 1.

Antenatal care coverage and early childhood mortality in Zimbabwe: new interpretations from nationally representative household surveys

Zimbabwe has implemented universal antenatal care (ANC) policies since 1980 that have significantly contributed to improvements in ANC access and early childhood mortality rates. However, Demographic and Health Surveys (DHS) and Multiple Indicator Cluster Surveys (MICS), two of Zimbabwe's main sources of health data and evidence, often provide seemingly different estimates of ANC coverage and under-five mortality rates. This creates confusion that can result in disparate policies and practices, with potential negative impacts on mother and child health in Zimbabwe. We conducted a comparability analysis of multiple DHS and MICS datasets to enhance the understanding of point estimates, temporal changes, rural-urban differences and reliability of estimates of ANC coverage and neonatal, infant and under-five mortality rates (NMR, IMR and U5MR, separately) from 2009 to 2019 in Zimbabwe. Our two samples z-tests revealed that both DHS and MICS indicated significant increases in ANC coverage and declines in IMR and U5MR but only from 2009 to 2015. NMR neither increased nor declined from 2009 to 2019. Rural-urban differences were significant for ANC coverage (2009-15 only) but not for NMR, IMR and U5MR. We found that there is a need for more precise DHS and MICS estimates of urban ANC coverage and all estimates of NMR, IMR and U5MR, and that shorter recall periods provide more reliable estimates of ANC coverage in Zimbabwe. Our findings represent new interpretations and clearer insights into progress and gaps around ANC coverage and under-five mortality rates that can inform the development, implementation, monitoring and evaluation of policy and practice responses and further research in Zimbabwe.

Comparison of Enhanced and Standard Data Sheets on Treatment Fidelity and Data Collection for Tact Training

Specifically designed data sheets have been recommended to assist with the fidelity of implementation of treatment procedures. The present study extended previous research (e.g., Bottini et al. Behavior Analysis: Research & Practice 21(2), 140-152, 2021; LeBlanc et al. Behavior Analysis in Practice 13(1), 53-62, 2020) by comparing an enhanced data sheet (i.e., the inclusion of randomized targets, prompts for treatment components of securing attending and reinforcement) to a standard data sheet (i.e., targets not preset, no prompts for treatment components) on the fidelity of tact training of features. Ten behavior therapists participated in each condition (n = 20). Participants first watched a brief instructional video explaining the teaching procedure and their assigned data sheet, followed by conducting a treatment session with a confederate serving as a child with autism spectrum disorder. The enhanced data sheet resulted in higher fidelity on multiple variables including randomizing of targets and data collection.

Safe Autonomous Driving with Latent Dynamics and State-Wise Constraints

Autonomous driving has the potential to revolutionize transportation, but developing safe and reliable systems remains a significant challenge. Reinforcement learning (RL) has emerged as a promising approach for learning optimal control policies in complex driving environments. However, existing RL-based methods often suffer from low sample efficiency and lack explicit safety constraints, leading to unsafe behaviors. In this paper, we propose a novel framework for safe reinforcement learning in autonomous driving that addresses these limitations. Our approach incorporates a latent dynamic model that learns the underlying dynamics of the environment from bird's-eye view images, enabling efficient learning and reducing the risk of safety violations by generating synthetic data. Furthermore, we introduce state-wise safety constraints through a barrier function, ensuring safety at each state by encoding constraints directly into the learning process. Experimental results in the CARLA simulator demonstrate that our framework significantly outperforms baseline methods in terms of both driving performance and safety. Our work advances the development of safe and efficient autonomous driving systems by leveraging the power of reinforcement learning with explicit safety considerations.

Survival analysis using deep learning with medical imaging

There is widespread interest in using deep learning to build prediction models for medical imaging data. These deep learning methods capture the local structure of the image and require no manual feature extraction. Despite the importance of modeling survival in the context of medical data analysis, research on deep learning methods for modeling the relationship of imaging and time-to-event data is still under-developed. We provide an overview of deep learning methods for time-to-event outcomes and compare several deep learning methods to Cox model based methods through the analysis of a histology dataset of gliomas.

Identifying latent genetic interactions in genome-wide association studies using multiple traits

The "missing" heritability of complex traits may be partly explained by genetic variants interacting with other genes or environments that are difficult to specify, observe, and detect. We propose a new kernel-based method called Latent Interaction Testing (LIT) to screen for genetic interactions that leverages pleiotropy from multiple related traits without requiring the interacting variable to be specified or observed. Using simulated data, we demonstrate that LIT increases power to detect latent genetic interactions compared to univariate methods. We then apply LIT to obesity-related traits in the UK Biobank and detect variants with interactive effects near known obesity-related genes (URL: https://CRAN.R-project.org/package=lit ).

Identifying covariate-related subnetworks for whole-brain connectome analysis

Whole-brain connectome data characterize the connections among distributed neural populations as a set of edges in a large network, and neuroscience research aims to systematically investigate associations between brain connectome and clinical or experimental conditions as covariates. A covariate is often related to a number of edges connecting multiple brain areas in an organized structure. However, in practice, neither the covariate-related edges nor the structure is known. Therefore, the understanding of underlying neural mechanisms relies on statistical methods that are capable of simultaneously identifying covariate-related connections and recognizing their network topological structures. The task can be challenging because of false-positive noise and almost infinite possibilities of edges combining into subnetworks. To address these challenges, we propose a new statistical approach to handle multivariate edge variables as outcomes and output covariate-related subnetworks. We first study the graph properties of covariate-related subnetworks from a graph and combinatorics perspective and accordingly bridge the inference for individual connectome edges and covariate-related subnetworks. Next, we develop efficient algorithms to exact covariate-related subnetworks from the whole-brain connectome data with an $\ell_0$ norm penalty. We validate the proposed methods based on an extensive simulation study, and we benchmark our performance against existing methods. Using our proposed method, we analyze two separate resting-state functional magnetic resonance imaging data sets for schizophrenia research and obtain highly replicable disease-related subnetworks.

Gender effect of glucose, insulin/glucagon ratio, lipids, and nitrogen-metabolites on serum HGF and EGF levels in patients with diabetes type 2

Hepatocyte growth factor (HGF) exhibits potent growth-inducing properties across various tissues, while epidermal growth factor (EGF) acts as a molecular integration point for diverse stimuli. HGF plays a crucial role in hepatic metabolism, tissue repair, and offers protective effects on epithelial and non-epithelial organs, in addition to its involvement in reducing apoptosis and inflammation, underscoring its anti-inflammatory capabilities. The HGF-Met system is instrumental in hepatic metabolism and enhancing insulin sensitivity in animal diabetes models. Similarly, the EGF and its receptor tyrosine kinase family (EGFR) are critical in regulating cell growth, proliferation, migration, and differentiation in both healthy and diseased states, with EGF also contributing to insulin sensitivity. In this observational study, we aimed to identify correlations between serum levels of HGF and EGF, insulin, glucagon, glucose, and primary serum lipids in patients with type 2 diabetes mellitus (DM), taking into account the impact of gender. We noted differences in the management of glucose, insulin, and glucagon between healthy men and women, potentially due to the distinct influences of sexual hormones on the development of type 2 DM. Additionally, metabolites such as glucose, albumin, direct bilirubin, nitrites, and ammonia might influence serum levels of growth factors and hormones. In summary, our results highlight the regulatory role of insulin and glucagon in serum glucose and lipids, along with variations in HGF and EGF levels, which are affected by gender. This link is especially significant in DM, where impaired cell proliferation or repair mechanisms lead to metabolic changes. The gender-based differences in growth factors point to their involvement in the pathophysiology of the disease.

From big data to big insights: statistical and bioinformatic approaches for exploring the lipidome

The goal of lipidomic studies is to provide a broad characterization of cellular lipids present and changing in a sample of interest. Recent lipidomic research has significantly contributed to revealing the multifaceted roles that lipids play in fundamental cellular processes, including signaling, energy storage, and structural support. Furthermore, these findings have shed light on how lipids dynamically respond to various perturbations. Continued advancement in analytical techniques has also led to improved abilities to detect and identify novel lipid species, resulting in increasingly large datasets. Statistical analysis of these datasets can be challenging not only because of their vast size, but also because of the highly correlated data structure that exists due to many lipids belonging to the same metabolic or regulatory pathways. Interpretation of these lipidomic datasets is also hindered by a lack of current biological knowledge for the individual lipids. These limitations can therefore make lipidomic data analysis a daunting task. To address these difficulties and shed light on opportunities and also weaknesses in current tools, we have assembled this review. Here, we illustrate common statistical approaches for finding patterns in lipidomic datasets, including univariate hypothesis testing, unsupervised clustering, supervised classification modeling, and deep learning approaches. We then describe various bioinformatic tools often used to biologically contextualize results of interest. Overall, this review provides a framework for guiding lipidomic data analysis to promote a greater assessment of lipidomic results, while understanding potential advantages and weaknesses along the way.

N-acyl homoserine lactone signaling modulates bacterial community associated with human dental plaque

N-acyl homoserine lactones (AHLs) are small diffusible signaling molecules that mediate a cell density-dependent bacterial communication system known as quorum sensing (QS). AHL-mediated QS regulates gene expression to control many critical bacterial behaviors including biofilm formation, pathogenicity, and antimicrobial resistance. Dental plaque is a complex multispecies oral biofilm formed by successive colonization of the tooth surface by groups of commensal, symbiotic, and pathogenic bacteria, which can contribute to tooth decay and periodontal diseases. While the existence and roles of AHL-mediated QS in oral microbiota have been debated, recent evidence indicates that AHLs play significant roles in oral biofilm development and community dysbiosis. The underlying mechanisms, however, remain poorly characterized. To better understand the importance of AHL signaling in dental plaque formation, we manipulated AHL signaling by adding AHL lactonases or exogenous AHL signaling molecules. We find that AHLs can be detected in dental plaque grown under 5% CO2 conditions, but not when grown under anaerobic conditions, and yet anaerobic cultures are still responsive to AHLs. QS signal disruption using lactonases leads to changes in microbial population structures in both planktonic and biofilm states, changes that are dependent on the substrate preference of the used lactonase but mainly result in the increase in the abundance of commensal and pioneer colonizer species. Remarkably, the opposite manipulation, that is the addition of exogenous AHLs increases the abundance of late colonizer bacterial species. Hence, this work highlights the importance of AHL-mediated QS in dental plaque communities, its potential different roles in anaerobic and aerobic parts of dental plaque, and underscores the potential of QS interference in the control of periodontal diseases.

Children's perception of food parenting practices: adaptation and validation of the comprehensive feeding practices questionnaire in Chilean adolescents

Introduction

Assessment of the Comprehensive Feeding Practices Questionnaire in adolescents (CFPQ-Teen) is still limited, with no evaluation of the measurement invariance. The participants comprised 473 Chilean adolescents of both sexes from dual-income nuclear families. The aims of this study were: (1) to adapt to Spanish and validate a model of five-factor version the CFPQ-Teen; (2) to examine the psychometric properties, (3) to evaluate the measurement invariance according to the adolescents' gender; and (4) to compare the scores of each factor between female and male adolescents.

Methods

The instrument was translated, back-translated, and adapted from the CFPQ-Teen, confirming the equivalence, conceptual, and face validity in a pilot sample of 40 adolescents. An exploratory factor analysis was performed on the five-factor model of the CFPQ-Teen: Monitoring, Adolescent Control, Restriction for weight control, Parental Modeling, and Environment. The Environment factor was eliminated as a result.

Results

The confirmatory factor analysis presented good reliability, convergent, discriminant, and concurrent validity values. In addition, medium to high goodness-of-fit levels were obtained by eliminating an item from the Adolescent Control factor. These results confirm a final 20-item model representing four factors. The multigroup invariance analysis of the measurement model verified configural, metric, scalar, and partial strict invariance. No significant differences were found between females and males in the scores on the four factors.

Discussion

These results enable comparisons by sex on the perceptions of Food Parenting Practices from the analyzed factors, primarily within the context of the Chilean sample.

EasyDAM_V4: Guided-GAN-based cross-species data labeling for fruit detection with significant shape difference

Traditional agriculture is gradually being combined with artificial intelligence technology. High-performance fruit detection technology is an important basic technology in the practical application of modern smart orchards and has great application value. At this stage, fruit detection models need to rely on a large number of labeled datasets to support the training and learning of detection models, resulting in higher manual labeling costs. Our previous work uses a generative adversarial network to translate the source domain to the target fruit images. Thus, automatic labeling is performed on the actual dataset in the target domain. However, the method still does not achieve satisfactory results for translating fruits with significant shape variance. Therefore, this study proposes an improved fruit automatic labeling method, EasyDAM_V4, which introduces the Across-CycleGAN fruit translation model to achieve spanning translation between phenotypic features such as fruit shape, texture, and color to reduce domain differences effectively. We validated the proposed method using pear fruit as the source domain and three fruits with large phenotypic differences, namely pitaya, eggplant, and cucumber, as the target domain. The results show that the EasyDAM_V4 method achieves substantial cross-fruit shape translation, and the average accuracy of labeling reached 87.8, 87.0, and 80.7% for the three types of target domain datasets, respectively. Therefore, this research method can improve the applicability of the automatic labeling process even if significant shape variance exists between the source and target domain.

Utilization of biochar for remediation of heavy metals in aqueous environments: A review and bibliometric analysis

Biochar usage for removing heavy metals from aqueous environments has emerged as a promising research area with significant environmental and economic benefits. Using the PICO approach, the research question aimed to explore using biochar to remove heavy metals from aqueous media. We merged the data from Scopus and the Web of Science Core Collection databases to acquire a comprehensive perspective of the subject. The PRISMA guidelines were applied to establish the search parameters, identify the appropriate articles, and collect the bibliographic information from the publications between 2010 and 2022. The bibliometric analysis showed that biochar-based heavy metal remediation is a research field with increasing scholarly attention. The removal of Cr(VI), Pb(II), Cd(II), and Cu(II) was the most studied among the heavy metals. We identified five main clusters centered on adsorption, water treatment, adsorption models, analytical techniques, and hydrothermal carbonization by performing keyword co-occurrence analysis. Trending topics include biochar reusability, modification, acid mine drainage (AMD), wastewater treatment, and hydrochar. The reutilization of heavy metal-loaded spent biochar includes transforming it into electrodes for supercapacitors or stable catalyst materials. This study provides a comprehensive overview of biochar-based heavy metal remediation in aquatic environments and highlights knowledge gaps and future research directions.

Intravenous versus intramuscular oxytocin injection for preventing uterine atonic primary postpartum haemorrhage in third stage of labour: A double-blind randomised controlled trial

Objectives

To compare the efficacy and safety of intravenous and intramuscular oxytocin in preventing atonic primary postpartum haemorrhage in the third stage of labour.

Methods

A double-blind randomised clinical study on consenting women without risk factors for primary postpartum haemorrhage in labour at term. Two hundred and thirty-two women were randomly allotted into intravenous (n = 115) and intramuscular (n = 117) oxytocin groups in the active management of the third stage of labour. All participants received 10 IU of oxytocin, either IV or IM, and 1 ml of water for injection as a placebo via a route alternate to that of administration of oxytocin within 1 min of the baby's delivery. The primary outcome measures were mean postpartum blood loss and haematocrit change. Trial Registration No.: PACTR201902721929705.

Results

The baseline socio-demographic and clinical characteristics were similar between the two groups (p > 0.05). There was no statistically significant difference between the two groups with regards to the mean postpartum blood loss (254.17 ± 34.85 ml versus 249.4 ± 39.88 ml; p = 0.210), haematocrit change (2.4 (0.8%) versus 2.1 (0.6%); p = 0.412) or adverse effects (p > 0.05). However, the use of additional uterotonics was significantly higher in the intravenous group (25 (21.73%) versus 17 (14.53%); p = 0.032).

Conclusion

Although oxytocin in both study groups showed similar efficacy in terms of preventing atonic primary postpartum haemorrhage, participants who received intravenous oxytocin were more likely to require additional uterotonics to reduce their likelihood of having an atonic primary postpartum haemorrhage. However, both routes have similar side effect profiles.

Latent Variable Machine Learning Framework for Catalysis: General Models, Transfer Learning, and Interpretability

Machine learning has been successfully applied in recent years to screen materials for a variety of applications. However, despite recent advances, most screening-based machine learning approaches are limited in generality and transferability, requiring new models to be created from scratch for each new application. This is particularly apparent in catalysis, where there are many possible intermediates and transition states of interest in addition to a large number of potential catalytic materials. In this work, we developed a new machine learning framework that is built on chemical principles and allows the creation of general, interpretable, reusable models. Our new architecture uses latent variables to create a set of submodels that each take on a relatively simple learning task, leading to higher data efficiency and promoting transfer learning. This architecture infuses fundamental chemical principles, such as the existence of elements as discrete entities. We show that this architecture allows for the creation of models that can be reused for many different applications, providing significant improvements in efficiency and convenience. For example, our architecture allows simultaneous prediction of adsorption energies for many adsorbates on a broad array of alloy surfaces with mean absolute errors (MAEs) around 0.20-0.25 eV. The integration of latent variables provides physical interpretability, as predictions can be explained in terms of the learned chemical environment as represented by the latent space. Further, these latent variables also serve as new feature representations, allowing efficient transfer learning. For example, new models with useful levels of accuracy can be created with less than 10 data points, including transfer learning to an experimental data set with an MAE less than 0.15 eV. Lastly, we show that our new machine learning architecture is general and robust enough to handle heterogeneous and multifidelity data sets, allowing researchers to leverage existing data sets to speed up screening using their own computational setup.

Glioblastoma multiforme influence on the elemental homeostasis of the distant organs: the results of inter-comparison study carried out with TXRF method

Glioblastoma (GBM) is a fast-growing and aggressive brain tumor which invades the nearby brain tissue but generally does not spread to the distant organs. Nonetheless, if untreated, GBM can result in patient death in time even less than few months from the diagnosis. The influence of the tumor progress on organs other than brain is obvious but still not well described. Therefore, we examined the elemental abnormalities appearing in selected body organs (kidney, heart, spleen, lung) in two rat models of GBM. The animals used for the study were subjected to the implantation of human GBM cell lines (U87MG and T98G) characterized by different levels of invasiveness. The elemental analysis of digested organ samples was carried out using the total reflection X-ray fluorescence (TXRF) method, independently, in three European laboratories utilizing various commercially available TXRF spectrometers. The comparison of the data obtained for animals subjected to T98G and U87MG cells implantation showed a number of elemental anomalies in the examined organs. What is more, the abnormalities were found for rats even if neoplastic tumor did not develop in their brains. The most of alterations for both experimental groups were noted in the spleen and lungs, with the direction of the found element changes in these organs being the opposite. The observed disorders of element homeostasis may result from many processes occurring in the animal body as a result of implantation of cancer cells or the development of GBM, including inflammation, anemia of chronic disease or changes in iron metabolism. Tumor induced changes in organ elemental composition detected in cooperating laboratories were usually in a good agreement. In case of elements with higher atomic numbers (Fe, Cu, Zn and Se), 88% of the results were classified as fully compliant. Some discrepancies between the laboratories were found for lighter elements (P, S, K and Ca). However, also in this case, the obtained results fulfilled the requirements of full (the results from three laboratories were in agreement) or partial agreement (the results from two laboratories were in agreement).

Identifying unique spectral fingerprints in cough sounds for diagnosing respiratory ailments

Coughing, a prevalent symptom of many illnesses, including COVID-19, has led researchers to explore the potential of cough sound signals for cost-effective disease diagnosis. Traditional diagnostic methods, which can be expensive and require specialized personnel, contrast with the more accessible smartphone analysis of coughs. Typically, coughs are classified as wet or dry based on their phase duration. However, the utilization of acoustic analysis for diagnostic purposes is not widespread. Our study examined cough sounds from 1183 COVID-19-positive patients and compared them with 341 non-COVID-19 cough samples, as well as analyzing distinctions between pneumonia and asthma-related coughs. After rigorous optimization across frequency ranges, specific frequency bands were found to correlate with each respiratory ailment. Statistical separability tests validated these findings, and machine learning algorithms, including linear discriminant analysis and k-nearest neighbors classifiers, were employed to confirm the presence of distinct frequency bands in the cough signal power spectrum associated with particular diseases. The identification of these acoustic signatures in cough sounds holds the potential to transform the classification and diagnosis of respiratory diseases, offering an affordable and widely accessible healthcare tool.

Age-related differences in structural and resting-state functional brain network organization across the adult lifespan: A cross-sectional study

We investigated age-related trends in the topology and hierarchical organization of brain structural and functional networks using diffusion-weighted imaging and resting-state fMRI data from a large cohort of healthy aging adults. At the cross-modal level, we explored age-related patterns in the RC involvement of different functional subsystems using a high-resolution functional parcellation. We further assessed age-related differences in the structure-function coupling as well as the network vulnerability to damage to rich club connectivity. Regardless of age, the structural and functional brain networks exhibited a rich club organization and small-world topology. In older individuals, we observed reduced integration and segregation within the frontal-occipital regions and the cerebellum along the brain's medial axis. Additionally, functional brain networks displayed decreased integration and increased segregation in the prefrontal, centrotemporal, and occipital regions, and the cerebellum. In older subjects, structural networks also exhibited decreased within-network and increased between-network RC connectivity. Furthermore, both within-network and between-network RC connectivity decreased in functional networks with age. An age-related decline in structure-function coupling was observed within sensory-motor, cognitive, and subcortical networks. The structural network exhibited greater vulnerability to damage to RC connectivity within the language-auditory, visual, and subcortical networks. Similarly, for functional networks, increased vulnerability was observed with damage to RC connectivity in the cerebellum, language-auditory, and sensory-motor networks. Overall, the network vulnerability decreased significantly in subjects older than 70 in both networks. Our findings underscore significant age-related differences in both brain functional and structural RC connectivity, with distinct patterns observed across the adult lifespan.

Magnetocardiography at rest predicts cardiac death in patients with acute chest pain

Introduction

Sudden cardiac arrest is a major cause of morbidity and mortality worldwide and remains a major public health problem for which better non-invasive prediction tools are needed. Primary preventive therapies, such as implantable cardioverter defibrillators, are not personalized and not predictive. Most of these devices do not deliver life-saving therapy during their lifetime. The individual relationship between fatal arrhythmias and cardiac function abnormalities in predicting cardiac death risk has rarely been explored.

Methods

We retrospectively analyzed the measurements at rest for 191 patients with acute chest pain (ACP) magnetocardiographically. Our recently introduced analyses are able to detect inhomogeneities of the depolarization and repolarization. Moreover, electrically silent phenomena-intracellular ionic currents as well as vortex currents-can be measured and quantified. All included ACP patients were recruited in 2009 at Yonsei University Hospital and were followed up until 2022.

Results

During half of the follow-up period (6.5 years), 11 patients died. Out of all the included nine clinical, eight magnetocardiographical, and nine newly introduced magnetoionographical parameters we tested in this study, three parameters revealed themselves to be outstanding at predicting death: heart rate-corrected QT (QTc) prolongation, depression of repolarization current IKr + IKs, and serum creatinine (all significant in Cox regression, p < 0.05). They clearly predicted cardiac death over the 6.5 years duration (sensitivity 90.9%, specificity 85.6%, negative predictive accuracy 99.4%). Cardiac death risk was more than ninefold higher in patients with low repolarization reserve and QTc prolongation in comparison with the remaining patients with ACP (p < 0.001). The non-parametric Kaplan-Meier statistics estimated significantly lower survival functions from their lifetime data (p < 0.001).

Discussion

To the best of our knowledge, these are the first data linking magnetocardiographical and magnetoionographical parameters and subsequent significant fatal events in people, suggesting structural and functional components to clinical life-threatening ventricular arrhythmogenesis. The findings support investigation of new prevention strategies and herald those new non-invasive techniques as complementary risk stratification tools.

Predicting cognitive dysfunction and regional hubs using Braak staging amyloid-beta biomarkers and machine learning

Mild cognitive impairment (MCI) is a transitional stage between normal aging and early Alzheimer's disease (AD). The presence of extracellular amyloid-beta (Aβ) in Braak regions suggests a connection with cognitive dysfunction in MCI/AD. Investigating the multivariate predictive relationships between regional Aβ biomarkers and cognitive function can aid in the early detection and prevention of AD. We introduced machine learning approaches to estimate cognitive dysfunction from regional Aβ biomarkers and identify the Aβ-related dominant brain regions involved with cognitive impairment. We employed Aβ biomarkers and cognitive measurements from the same individuals to train support vector regression (SVR) and artificial neural network (ANN) models and predict cognitive performance solely based on Aβ biomarkers on the test set. To identify Aβ-related dominant brain regions involved in cognitive prediction, we built the local interpretable model-agnostic explanations (LIME) model. We found elevated Aβ in MCI compared to controls and a stronger correlation between Aβ and cognition, particularly in Braak stages III-IV and V-VII (p < 0.05) biomarkers. Both SVR and ANN, especially ANN, showed strong predictive relationships between regional Aβ biomarkers and cognitive impairment (p < 0.05). LIME integrated with ANN showed that the parahippocampal gyrus, inferior temporal gyrus, and hippocampus were the most decisive Braak regions for predicting cognitive decline. Consistent with previous findings, this new approach suggests relationships between Aβ biomarkers and cognitive impairment. The proposed analytical framework can estimate cognitive impairment from Braak staging Aβ biomarkers and delineate the dominant brain regions collectively involved in AD pathophysiology.

OzNet: A New Deep Learning Approach for Automated Classification of COVID-19 Computed Tomography Scans

Coronavirus disease 2019 (COVID-19) is spreading rapidly around the world. Therefore, the classification of computed tomography (CT) scans alleviates the workload of experts, whose workload increased considerably during the pandemic. Convolutional neural network (CNN) architectures are successful for the classification of medical images. In this study, we have developed a new deep CNN architecture called OzNet. Moreover, we have compared it with pretrained architectures namely AlexNet, DenseNet201, GoogleNet, NASNetMobile, ResNet-50, SqueezeNet, and VGG-16. In addition, we have compared the classification success of three preprocessing methods with raw CT scans. We have not only classified the raw CT scans, but also have performed the classification with three different preprocessing methods, which are discrete wavelet transform (DWT), intensity adjustment, and gray to color red, green, blue image conversion on the data sets. Furthermore, it is known that the architecture's performance increases with the use of DWT preprocessing method rather than using the raw data set. The results are extremely promising with the CNN algorithms using the COVID-19 CT scans processed with the DWT. The proposed DWT-OzNet has achieved a high classification performance of more than 98.8% for each calculated metric.

A DYNAMIC ADDITIVE AND MULTIPLICATIVE EFFECTS NETWORK MODEL WITH APPLICATION TO THE UNITED NATIONS VOTING BEHAVIORS

Motivated by a study of United Nations voting behaviors, we introduce a regression model for a series of networks that are correlated over time. Our model is a dynamic extension of the additive and multiplicative effects network model (AMEN) of Hoff (2021). In addition to incorporating a temporal structure, the model accommodates two types of missing data thus allows the size of the network to vary over time. We demonstrate via simulations the necessity of various components of the model. We apply the model to the United Nations General Assembly voting data from 1983 to 2014 (Voeten, 2013) to answer interesting research questions regarding international voting behaviors. In addition to finding important factors that could explain the voting behaviors, the model-estimated additive effects, multiplicative effects, and their movements reveal meaningful foreign policy positions and alliances of various countries.

Joint Latent Space Model for Social Networks with Multivariate Attributes

In social, behavioral and economic sciences, researchers are interested in modeling a social network among a group of individuals, along with their attributes. The attributes can be responses to survey questionnaires and are often high dimensional. We propose a joint latent space model (JLSM) that summarizes information from the social network and the multivariate attributes in a person-attribute joint latent space. We develop a variational Bayesian expectation-maximization estimation algorithm to estimate the attribute and person locations in the joint latent space. This methodology allows for effective integration, informative visualization and prediction of social networks and attributes. Using JLSM, we explore the French financial elites based on their social networks and their career, political views and social status. We observe a division in the social circles of the French elites in accordance with the differences in their attributes. We analyze user networks and behaviors in multimodal social media systems like YouTube. A R package "jlsm" is developed to fit the models proposed in this paper and is publicly available from the CRAN repository https://cran.r-project.org/web/packages/jlsm/jlsm.pdf .

The gas stove-childhood asthma kerfuffle: A teaching opportunity

Several recent news stories have alarmed many politicians and members of the public by reporting that indoor air pollution from gas stoves causes about 13% of childhood asthma in the United States. Research on the reproducibility and trustworthiness of epidemiological risk assessments has identified a number of common questionable research practices (QRPs) that should be avoided to draw sound causal conclusions from epidemiological data. Examples of such QRPs include claiming causation without using study designs or data analyses that allow valid causal inferences; generalizing or transporting risk estimates based on data for specific populations, time periods, and locations to different ones without accounting for differences in the study and target populations; claiming causation without discussing or quantitatively correcting for confounding, external validity bias, or other biases; and not mentioning or resolving contradictory evidence. We examine the recently estimated gas stove-childhood asthma associations from the perspective of these QRPs and conclude that it exemplifies all of them. The quantitative claim that about 13% of childhood asthma in the United States could be prevented by reducing exposure to gas stove pollution is not supported by the data collected or by the measures of association (Population Attributable Fractions) used to analyze the data. The qualitative finding that reducing exposure to gas stove pollution would reduce the burden of childhood asthma in the United States has no demonstrated validity. Systematically checking how and whether QRPs have been addressed before reporting or responding to claims that everyday exposures cause substantial harm to health might reduce social amplification of perceived risks based on QRPs and help to improve the credibility and trustworthiness of published epidemiological risk assessments.

Advancing Computational Toxicology by Interpretable Machine Learning

Chemical toxicity evaluations for drugs, consumer products, and environmental chemicals have a critical impact on human health. Traditional animal models to evaluate chemical toxicity are expensive, time-consuming, and often fail to detect toxicants in humans. Computational toxicology is a promising alternative approach that utilizes machine learning (ML) and deep learning (DL) techniques to predict the toxicity potentials of chemicals. Although the applications of ML- and DL-based computational models in chemical toxicity predictions are attractive, many toxicity models are "black boxes" in nature and difficult to interpret by toxicologists, which hampers the chemical risk assessments using these models. The recent progress of interpretable ML (IML) in the computer science field meets this urgent need to unveil the underlying toxicity mechanisms and elucidate the domain knowledge of toxicity models. In this review, we focused on the applications of IML in computational toxicology, including toxicity feature data, model interpretation methods, use of knowledge base frameworks in IML development, and recent applications. The challenges and future directions of IML modeling in toxicology are also discussed. We hope this review can encourage efforts in developing interpretable models with new IML algorithms that can assist new chemical assessments by illustrating toxicity mechanisms in humans.

Using Machine Learning to Predict Adverse Effects of Metallic Nanomaterials to Various Aquatic Organisms

The wide production and use of metallic nanomaterials (MNMs) leads to increased emissions into the aquatic environments and induces high potential risks. Experimentally evaluating the (eco)toxicity of MNMs is time-consuming and expensive due to the multiple environmental factors, the complexity of material properties, and the species diversity. Machine learning (ML) models provide an option to deal with heterogeneous data sets and complex relationships. The present study established an in silico model based on a machine learning properties-environmental conditions-multi species-toxicity prediction model (ML-PEMST) that can be applied to predict the toxicity of different MNMs toward multiple aquatic species. Feature importance and interaction analysis based on the random forest method indicated that exposure duration, illumination, primary size, and hydrodynamic diameter were the main factors affecting the ecotoxicity of MNMs to a variety of aquatic organisms. Illumination was demonstrated to have the most interaction with the other features. Moreover, incorporating additional detailed information on the ecological traits of the test species will allow us to further optimize and improve the predictive performance of the model. This study provides a new approach for ecotoxicity predictions for organisms in the aquatic environment and will help us to further explore exposure pathways and the risk assessment of MNMs.

Cardiac magnetic field map topology quantified by Kullback-Leibler entropy identifies patients with clinically suspected myocarditis

Background

Myocarditis is a condition that can have severe adverse outcomes and lead to sudden cardiac death if remaining undetected. This study tested the capability of cardiac magnetic field mapping to detect patients with clinically suspected myocarditis. This could open up the way for rapid, non-invasive, and cost-effective screening of suspected cases before a gold standard assessment via endomyocardial biopsy.

Methods

Historical cardiac magnetic field maps (n = 97) and data from a state-of-the-art magnetocardiography device (n = 30) were analyzed using the Kullback-Leibler entropy (KLE) for dimensionality reduction and topological quantification. Linear discriminant analysis was used to discern between patients with ongoing myocarditis and healthy controls.

Results

The STT segment of a magnetocardiogram, i.e., the section between the end of the S wave and the end of the T wave, was best suited to discern both groups. Using a 250-ms excerpt from the onset of the STT segment gave a reliable classification between the myocarditis and control group for both historic data (sensitivity: 0.83, specificity: 0.85, accuracy: 0.84) and recent data (sensitivity: 0.69, specificity: 0.88, accuracy: 0.80) using the KLE to quantify the topology of the cardiac magnetic field map.

Conclusion

The implementation based on KLE can reliably distinguish between clinically suspected myocarditis patients and healthy controls. We implemented an automatized feature selection based on LDA to replace the observer-dependent manual thresholding in previous studies.

HB-DSBM: Modeling the Dynamic Complex Networks From Community Level to Node Level

A variety of methods have been proposed for modeling and mining dynamic complex networks, in which the topological structure varies with time. As the most popular and successful network model, the stochastic block model (SBM) has been extended and applied to community detection, link prediction, anomaly detection, and evolution analysis of dynamic networks. However, all current models based on the SBM for modeling dynamic networks are designed at the community level, assuming that nodes in each community have the same dynamic behavior, which usually results in poor performance on temporal community detection and loses the modeling of node abnormal behavior. To solve the above-mentioned problem, this article proposes a hierarchical Bayesian dynamic SBM (HB-DSBM) for modeling the node-level and community-level dynamic behavior in a dynamic network synchronously. Based on the SBM, we introduce a hierarchical Dirichlet generative mechanism to associate the global community evolution with the microscopic transition behavior of nodes near-perfectly and generate the observed links across the dynamic networks. Meanwhile, an effective variational inference algorithm is developed and we can easy to infer the communities and dynamic behaviors of the nodes. Furthermore, with the two-level evolution behaviors, it can identify nodes or communities with abnormal behavior. Experiments on simulated and real-world networks demonstrate that HB-DSBM has achieved state-of-the-art performance on community detection and evolution. In addition, abnormal evolutionary behavior and events on dynamic networks can be effectively identified by our model.

Delving into gene-set multiplex networks facilitated by a k-nearest neighbor-based measure of similarity

Gene sets are functional units for living cells. Previously, limited studies investigated the complex relations among gene sets, but documents about their altering patterns across biological conditions still need to be prepared. In this study, we adopted and modified a classical k-nearest neighbor-based association function to detect inter-gene-set similarities. Based on this method, we built multiplex networks of gene sets for the first time; these networks contain layers of gene sets corresponding to different populations of cells. The context-based multiplex networks can capture meaningful biological variation and have considerable differences from knowledge-based networks of gene sets built on Jaccard similarity, as demonstrated in this study. Furthermore, at the scale of individual gene sets, the structural coefficients of gene sets (multiplex PageRank centrality, clustering coefficient, and participation coefficient) disclose the diversity of gene sets from the perspective of structural properties and make it easier to identify unique gene sets. In gene set enrichment analysis (GSEA), each gene set is treated independently, and its contextual and relational attributes are ignored. The structural coefficients of gene sets can supplement GSEA with information about the overall picture of gene sets, promoting the constructive reorganization of the enriched terms and helping researchers better prioritize and select gene sets.

Drosophila CASK regulates brain size and neuronal morphogenesis, providing a genetic model of postnatal microcephaly suitable for drug discovery

BACKGROUND

CASK-related neurodevelopmental disorders are untreatable. Affected children show variable severity, with microcephaly, intellectual disability (ID), and short stature as common features. X-linked human CASK shows dosage sensitivity with haploinsufficiency in females. CASK protein has multiple domains, binding partners, and proposed functions at synapses and in the nucleus. Human and Drosophila CASK show high amino-acid-sequence similarity in all functional domains. Flies homozygous for a hypomorphic CASK mutation (∆18) have motor and cognitive deficits. A Drosophila genetic model of CASK-related disorders could have great scientific and translational value.

METHODS

We assessed the effects of CASK loss of function on morphological phenotypes in Drosophila using established genetic, histological, and primary neuronal culture approaches. NeuronMetrics software was used to quantify neurite-arbor morphology. Standard nonparametric statistics methods were supplemented by linear mixed effects modeling in some cases. Microfluidic devices of varied dimensions were fabricated and numerous fluid-flow parameters were used to induce oscillatory stress fields on CNS tissue. Dissociation into viable neurons and neurite outgrowth in vitro were assessed.

RESULTS

We demonstrated that ∆18 homozygous flies have small brains, small heads, and short bodies. When neurons from developing CASK-mutant CNS were cultured in vitro, they grew small neurite arbors with a distinctive, quantifiable "bushy" morphology that was significantly rescued by transgenic CASK+. As in humans, the bushy phenotype showed dosage-sensitive severity. To overcome the limitations of manual tissue trituration for neuronal culture, we optimized the design and operation of a microfluidic system for standardized, automated dissociation of CNS tissue into individual viable neurons. Neurons from CASK-mutant CNS dissociated in the microfluidic system recapitulate the bushy morphology. Moreover, for any given genotype, device-dissociated neurons grew larger arbors than did manually dissociated neurons. This automated dissociation method is also effective for rodent CNS.

CONCLUSIONS

These biological and engineering advances set the stage for drug discovery using the Drosophila model of CASK-related disorders. The bushy phenotype provides a cell-based assay for compound screening. Nearly a dozen genes encoding CASK-binding proteins or transcriptional targets also have brain-development mutant phenotypes, including ID. Hence, drugs that improve CASK phenotypes might also benefit children with disorders due to mutant CASK partners.

Inappropriate nighttime light reduces living comfort

Living comfort is an important aspect of human well-being and a critical index of sustainable environments. Many environmental factors are associated with living comfort. Nighttime light (NTL) is remote sensing data that is widely used to reflect development level and economic status, and it also represents the lighting intensity in living environments. However, the relationship between NTL and living comfort is poorly understood. Here, we employ linear regression and a random forest model to investigate the direct impact of NTL on living comfort. Our results show that increased NTL is negatively associated with living comfort, but this relationship may be obscured by other factors, such as infrastructure. According to the nonlinear relationship, when the NTL is approximately 10 nW/cm2∙sr, there is a peak in living comfort. Hence, ensuring a reasonable level of lighting is a key to promoting sustainable development. Our research offers crucial insights that can aid in developing sustainable development policies to enhance livability.

Anterior Segment Biometry in a Caucasian Population with Cataracts

PURPOSE

To investigate biometric factors of the anterior segment of phakic eyes with cataracts.

METHODS

This population-based study included Caucasian patients with cataracts in the University Eye Hospital, Goethe University Frankfurt, Germany. Biometric parameters were measured using the swept-source optical coherence tomography method. Patients were grouped into intermediate stages based on decades of life.

RESULTS

In total, 6289 eyes of 3615 patients (age: 70.67 ± 8.42 years) were included. Age-related reductions in the anterior chamber depth (mean ± standard deviation) decreased from 3.26 ± 0.42 mm (group A: 55-59 years) to 2.94 ± 0.4 mm (group G: 85-89 years), and those in the axial length decreased from 24.37 ± 1.87 mm (group A) to 23.39 ± 1.07 mm (group G). Likewise, the white-to-white distance decreased from 12.12 ± 0.48 mm (group A) to 11.96 ± 0.47 mm (group G). Lens thickness tended to increase accordingly from 4.39 ± 0.36 µm (group A) to 4.9 ± 0.40 µm (group G). A comparison of the eyes showed no detectable lateral difference regarding the biometric parameters between the groups (axial length: p = 0.26, Rosenthal effect size = 0.03; lens thickness: p = 0.12, R = 0.03; anterior chamber depth: p = 0.63, Rosenthal effect size = 0.01). The axial length and anterior chamber depth differed significantly between sexes (r = 0.22, p < 0.0001 and r = 0.16, p < 0.0001, respectively). Multiple regression analysis of the anterior chamber depth as a function of biometry parameters as well as age and sex additionally indicated a positive correlation of anterior chamber depth with white-to-white distance (b = 0.32, p = 10-5), axial length (b = 0.10, p = 10-5), keratometry (b = 0.07, p = 10-5), and lens thickness (b=-0.05, p = 10-5) with a high effect size (Cohen f2=1.866, p = 10-5) and strong multiple correlation coefficient (Rosenthal effect size = 0.80, p = 10-5).

CONCLUSIONS

In the anterior segment, there are age- and sex-dependent changes in biometric parameters. In addition, changes in anterior chamber depth were noted in relation to white-to-white distance, axial length, keratometry, and lens thickness. These data should be considered in lens calculation formulas.

Developmental coordination disorder subtypes in children: An unsupervised clustering

AIM

To identify subtypes of developmental coordination disorder (DCD) in children.

METHOD

Children with DCD diagnosed through comprehensive evaluation at Robert-Debré Children's University Hospital (Paris, France) were consecutively enrolled from February 2017 to March 2020. We performed an unsupervised hierarchical clustering based on principal component analysis using a large set of variables encompassing cognitive, motor, and visuospatial scores (Wechsler Intelligence Scale for Children, Fifth Edition; Developmental Neuropsychological Assessment, Second Edition; Movement Assessment Battery for Children, Second Edition).

RESULTS

One hundred and sixty-four children with DCD were enrolled (median age 10 years 3 months; male:female ratio 5.56:1). We identified distinct subgroups with mixed visuospatial and gestural disorders, or with pure gestural disorders that predominantly impaired either speed or precision. Associated neurodevelopmental disorders, such as attention-deficit/hyperactivity disorder, did not influence the results of the clustering. Importantly, we identified a subgroup of children with marked visuospatial impairment with the lowest scores in almost all of the evaluated domains, and the poorest school performance.

INTERPRETATION

The classification of DCD into distinct subgroups could be indicative of prognosis and provide critical information to guide patient management, taking into account the child's neuropsychological profile. Beyond this clinical interest, our findings also provide a relevant framework with homogeneous subgroups of patients for research on the pathogenesis of DCD.

WHAT THIS PAPER ADDS

Unsupervised hierarchical clustering identified four subgroups of children with developmental coordination disorder. Two subgroups had combined visuospatial/gestural difficulties, and two had pure gestural disorders. Severe visuospatial impairment was associated with poor performance in most domains including school. Difficulties in the gestural-only clusters were predominantly either gestural precision or speed.

Estimating contact network properties by integrating multiple data sources associated with infectious diseases

To effectively mitigate the spread of communicable diseases, it is necessary to understand the interactions that enable disease transmission among individuals in a population; we refer to the set of these interactions as a contact network. The structure of the contact network can have profound effects on both the spread of infectious diseases and the effectiveness of control programs. Therefore, understanding the contact network permits more efficient use of resources. Measuring the structure of the network, however, is a challenging problem. We present a Bayesian approach to integrate multiple data sources associated with the transmission of infectious diseases to more precisely and accurately estimate important properties of the contact network. An important aspect of the approach is the use of the congruence class models for networks. We conduct simulation studies modeling pathogens resembling SARS-CoV-2 and HIV to assess the method; subsequently, we apply our approach to HIV data from the University of California San Diego Primary Infection Resource Consortium. Based on simulation studies, we demonstrate that the integration of epidemiological and viral genetic data with risk behavior survey data can lead to large decreases in mean squared error (MSE) in contact network estimates compared to estimates based strictly on risk behavior information. This decrease in MSE is present even in settings where the risk behavior surveys contain measurement error. Through these simulations, we also highlight certain settings where the approach does not improve MSE.