Separate Models Research Articles

Evaluation of the telemedical health care network “SAFE BIRTH” for pregnant women at risk, premature and sick newborns and their families: study protocol of a cluster-randomized controlled stepped-wedge trial

BackgroundThe Perinatal Center of the University Hospital Carl Gustav Carus Dresden has initiated the telemedical healthcare network “SAFE BIRTH” to coordinate and improve specialized care in non-metropolitan regions for pregnant women and newborns. The network incorporates five intervention bundles (IB): (1) Multi-professional, inter-disciplinary prenatal care plan; (2) Neonatal resuscitation; (3) Neonatal antibiotic stewardship; (4) Inter-facility transfer of premature and sick newborns; (5) Psycho-social support for parents. We evaluate if the network improves care close to home for pregnant women, premature and sick newborns.MethodsTo evaluate the complex healthcare intervention “SAFE BIRTH” we will conduct a cluster-randomized controlled stepped-wedge trial in five prenatal medical outpatient offices and eight non-metropolitan hospitals in Saxony, Germany. The offices and hospitals will be randomly allocated to five respectively eight sequential steps over a 30-month period to implement the telemedical IB. We define one specific primary process outcome for each IB (for instance IB#1: “Proportion of patients with inclusion criterion IB#1 who have a prenatal care plan and psychosocial counseling within one week”). We estimated a separate multilevel logistic regression model for each primary process outcome using the intervention status as a regressor (control or intervention group). Across all IB, a total of 1,541 and 1,417 pregnant women or newborns need to be included in the intervention and control group, respectively, for a power above 80% for small to medium intervention effects for all five hypothesis tests. Additionally, we will assess job satisfaction and sense of safety of health professionals caring for newborns (questionnaire survey) and we will assess families’ satisfaction, resilience, quality of life and depressive, anxiety and stress symptoms (questionnaire surveys). We will also evaluate the cost-effectiveness of ”SAFE BIRTH” (statutory health insurance routine data, process data) and barriers to its implementation (semi-structured interviews). We use multilevel regression models adjusting for relevant confounders (e.g. socioeconomic status, age, place of residence), as well as descriptive analyses and qualitative content analyses.DiscussionIf the telemedical healthcare network “SAFE BIRTH” proves to be effective and cost-efficient, strategies for its translation into routine care should be developed.Trial registrationGerman clinical trials register. DRKS-ID: DRKS00031482.

Revisiting column selectivity choices in ultra-high performance liquid chromatography–Using multidimensional analytical Design Spaces to identify column equivalency

Current guides and column selection system (CSS) platforms can provide some helpful insights with regard to the selection of alternative phases. Their practical reliability however, can also turn out to be questionable, especially considering the lack of detailed specifics, such as a clear definition of points of equivalence—appropriate running conditions under which the given analytical mixture can be satisfactorily resolved on various stationary phases. In this context, the use of multivariate modeling tools can be highly beneficial. These tools, when applied systematically, are ideal for uniquely characterizing complex LC-separation systems, a fact supported by numerous peer-reviewed papers.Revisiting our earlier work [1] and the applied systematic workflow [2], we used a Design Space modeling software (DryLab), with the main focus on building and comparing 3-dimensional separation models of amlodipine and its related impurities to identify shared method conditions under which columns are conveniently interchangeable. Our study comprised 5, C18-modified ultra-high performance liquid chromatography (UHPLC) columns in total, in some cases with surprising results. We identified several equivalences between the Design Spaces (DSs) of markedly different columns. Conversely, there were cases where, despite the predicted similarities in column data, the modeled DSs demonstrated clear differences between the selected stationary phases.

Mindfulness Practice Is Associated With Improved Well-Being and Reduced Injury Risk in Female NCAA Division I Athletes.

Injury in sport is an inherent risk to participation, and it can have devastating consequences for the athlete, both mentally and physically. Previous research has found that impairments in well-being can increase the risk of injury, and that various forms of mindfulness training and practice can improve well-being and mental health in various populations. Mindfulness would be associated with greater well-being and lower risk of injury. Cohort study. Level 3. A total of 21 female Division I athletes underwent a formal 6-week mindfulness training program and were encouraged to continue mindfulness exercises. The athletes completed daily surveys on their smartphones in relation to mood, muscle readiness (soreness), readiness to train, energy level, daily training load, and whether they had participated in mindfulness training that day. Linear mixed effects models were used to evaluate well-being variables and mindfulness state, and separate mixed effects logistics regression models were used to evaluate injury incidence and wellness variables. On days with mindfulness practice, athletes reported higher mood (19.6 [18.8-20.3] vs 19.4 [18.6-20.1, P = 0.03), muscle readiness (18.9 [17.8-20.0] vs 18.6 [17.5-19.6], P = 0.03), readiness to train (78.7 [75.9-81.5] vs 77.4 [74.7-80.2], P < 0.01), and energy level (19.3 [18.6-20.1] vs 18.8 [18.1-19.5, P < 0.01) than on the days when they did not participate in mindfulness training. Mindfulness practice was associated with significantly reduced likelihood of suffering an acute injury the following day (odds ratio, 0.42; 95% CI, 0.42-0.43; P < 0.01). On an individual level, participation in mindfulness by female collegiate athletes was associated with a dramatic reduction in injury risk the following day. In addition, mindfulness was associated with significantly improved mood, muscle readiness, readiness to train, and energy level. These findings suggest that mindfulness training in athletes may improve well-being and reduce the risk of injury among high-level athletes.

Dynamic structural equation models synthesize ecosystem dynamics constrained by ecological mechanisms

Abstract Ecological analyses typically involve many interacting variables. Ecologists often specify lagged interactions in community dynamics (i.e. vector‐autoregressive models) or simultaneous interactions (e.g. structural equation models), but there is less familiarity with dynamic structural equation models (DSEM) that can include any simultaneous or lagged effect in multivariate time‐series analysis. We propose a novel approach to parameter estimation for DSEM, which involves constructing a Gaussian Markov random field (GMRF) representing simultaneous and lagged path coefficients, and then fitting this as a generalized linear mixed model to missing and/or non‐normal data. We provide a new R‐package dsem, which extends the ‘arrow interface’ from path analysis to represent user‐specified lags when constructing the GMRF. We also outline how the resulting nonseparable precision matrix can generalize existing separable models, for example, for time‐series and species interactions in a vector‐autoregressive model. We first demonstrate dsem by simulating a two‐species vector‐autoregressive model based on wolf–moose interactions on Isle Royale. We show that DSEM has improved precision when data are missing relative to a conventional dynamic linear model. We then demonstrate DSEM via two contrasting case studies. The first identifies a trophic cascade where decreased sunflower starfish has increased urchin and decreased kelp densities, while sea otters have a simultaneous positive effect on kelp in the California Current from 1999 to 2018. The second estimates how declining sea ice has decreased cold‐water habitats, driving a decreased density for fall copepod predation and inhibiting early‐life survival for Alaska pollock from 1963 to 2023. We conclude that DSEM can be fitted efficiently as a GLMM involving missing data, while allowing users to specify both simultaneous and lagged effects in a time‐series structural model. DSEM then allows conceptual models (developed with stakeholder input or from ecological expertise) to be fitted to incomplete time series and provides a simple interface for granular control over the number of estimated time‐series parameters. Finally, computational methods are sufficiently simple that DSEM can be embedded as component within larger (e.g. integrated population) models. We therefore recommend greater exploration and performance testing for DSEM relative to familiar time‐series forecasting methods.

Landslide susceptibility assessment of South Korea using stacking ensemble machine learning

BackgroundLandslide susceptibility assessment (LSA) is a crucial indicator of landslide hazards, and its accuracy is improving with the development of artificial intelligence (AI) technology. However, the AI algorithms are inconsistent across regions and strongly dependent on input variables. Additionally, LSA must include historical data, which often restricts the assessment to the local scale and single landslide events.MethodsIn this study, we performed an LSA for the entirety of South Korea. A total of 30 input variables were constructed, consisting of 9 variables from past climate model data MK-PRISM, 12 topographical factors, and 9 environmental factors. Sixteen machine learning algorithms were used as basic classifiers, and a stacking ensemble was used on the four algorithms with the highest area under the curve (AUC). Additionally, a separate assessment model was established for areas with a risk of landslides affecting areas larger than 1 ha.ResultsThe highest-performing classifier was CatBoost, with an AUC of ~ 0.89 for both assessments. Among the input variables, distance of road, daily maximum precipitation, digital elevation model, and soil depth were the most influential. In all landslide events, CatBoost, lightGBM, XGBoost, and Random Forest had the highest AUC in descending order; in large landslide events, the order was CatBoost, XGBoost, Extra Tree, and lightGBM. The stacking ensemble enabled the construction of two landslide susceptibility maps.ConclusionsOur findings provide a statistical method for constructing a high-resolution (30 m) landslide susceptibility map on a country scale using diverse natural factors, including past climate data.

PSMOT: Online Occlusion-Aware Multi-Object Tracking Exploiting Position Sensitivity.

Models based on joint detection and re-identification (ReID), which significantly increase the efficiency of online multi-object tracking (MOT) systems, are an evolution from separate detection and ReID models in the tracking-by-detection (TBD) paradigm. It is observed that these joint models are typically one-stage, while the two-stage models become obsolete because of their slow speed and low efficiency. However, the two-stage models have naive advantages over the one-stage anchor-based and anchor-free models in handling feature misalignment and occlusion, which suggests that the two-stage models, via meticulous design, could be on par with the state-of-the-art one-stage models. Following this intuition, we propose a robust and efficient two-stage joint model based on R-FCN, whose backbone and neck are fully convolutional, and the RoI-wise process only involves simple calculations. In the first stage, an adaptive sparse anchoring scheme is utilized to produce adequate, high-quality proposals to improve efficiency. To boost both detection and ReID, two key elements-feature aggregation and feature disentanglement-are taken into account. To improve robustness against occlusion, the position-sensitivity is exploited, first to estimate occlusion and then to direct the post-process for anti-occlusion. Finally, we link the model to a hierarchical association algorithm to form a complete MOT system called PSMOT. Compared to other cutting-edge systems, PSMOT achieves competitive performance while maintaining time efficiency.

A novel CNN architecture for accurate early detection and classification of Alzheimer’s disease using MRI data

Alzheimer’s disease (AD) is a debilitating neurodegenerative disorder that requires accurate diagnosis for effective management and treatment. In this article, we propose an architecture for a convolutional neural network (CNN) that utilizes magnetic resonance imaging (MRI) data from the Alzheimer’s disease Neuroimaging Initiative (ADNI) dataset to categorize AD. The network employs two separate CNN models, each with distinct filter sizes and pooling layers, which are concatenated in a classification layer. The multi-class problem is addressed across three, four, and five categories. The proposed CNN architecture achieves exceptional accuracies of 99.43%, 99.57%, and 99.13%, respectively. These high accuracies demonstrate the efficacy of the network in capturing and discerning relevant features from MRI images, enabling precise classification of AD subtypes and stages. The network architecture leverages the hierarchical nature of convolutional layers, pooling layers, and fully connected layers to extract both local and global patterns from the data, facilitating accurate discrimination between different AD categories. Accurate classification of AD carries significant clinical implications, including early detection, personalized treatment planning, disease monitoring, and prognostic assessment. The reported accuracy underscores the potential of the proposed CNN architecture to assist medical professionals and researchers in making precise and informed judgments regarding AD patients.

Excitation of nonlinear longitudinal structures in spin‐1/2 quantum plasma in the presence of ion beam

AbstractThe formation of longitudinal, nonlinear structures in an interacting ion beam, spin‐1/2 quantum, electron‐ion plasma is reported by employing a separate spin evolution quantum hydrodynamic model (SSE‐QHD). The reductive perturbation method is followed to develop the KdV equations. In the presence of an ion beam and keeping the finite electron inertial effects, ion acoustic (IA) soliton and spin electron acoustic (SEA) soliton are found. The critical values of beam speed and spin polarization, required for the existence of solitary structures, are highlighted. It is prescribed that the present model supports rarefactive and compressive SEA soliton and compressive IA soliton. It is shown that the ion beam is essential for the existence of a compressive SEA solitary structure. We have also calculated and compared the energy densities of both solitons. Furthermore, the dependence of the nonlinear structures on the beam parameters and spin polarization are also examined. Our findings would be useful to understand the new spin‐dependent nonlinear structures as well as the features of nonlinear IA waves in ion beam–plasma interactions.

Maternal COVID-19 Vaccination and Prevention of Symptomatic Infection in Infants.

Maternal vaccination may prevent infant coronavirus disease 2019 (COVID-19). We aimed to quantify protection against infection from maternally derived vaccine-induced antibodies in the first 6 months of an infant's life. Infants born to mothers vaccinated during pregnancy with 2 or 3 doses of a messenger RNA COVID-19vaccine (nonboosted or boosted, respectively) had full-length spike (Spike) immunoglobulin G (IgG), pseudovirus 614D, and live virus D614G, and omicron BA.1 and BA.5 neutralizing antibody (nAb) titers measured at delivery. Infant severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection was determined by verified maternal-report and laboratory confirmation through prospective follow-up to 6 months of age between December 2021 and July 2022. The risk reduction for infection by dose group and antibody titer level was estimated in separate models. Infants of boosted mothers (n = 204) had significantly higher Spike IgG, pseudovirus, and live nAb titers at delivery than infants of nonboosted mothers (n = 271), and were 56% less likely to acquire infection in the first 6 months (P = .03). Irrespective of boost, for each 10-fold increase in Spike IgG titer at delivery, the infant's risk of acquiring infection was reduced by 47% (95% confidence interval 8%-70%; P = .02). Similarly, a 10-fold increase in pseudovirus titers against Wuhan Spike, and live virus nAb titers against D614G, and omicron BA.1 and BA.5 at delivery were associated with a 30%, 46%, 56%, and 60% risk reduction, respectively. Higher transplacental binding and nAb titers substantially reduced the risk ofSARS-CoV-2 infection in infants, and a booster dose amplified protection during a period of omicron predominance. Until infants are age-eligible for vaccination, maternal vaccination provides passive protection against symptomatic infection during early infancy.

Strategies to enhance treatment fidelity and music-based intervention reporting in dementia research.

Creative solutions are needed to address the well-being of the growing number of individuals living with dementia. Music-based interventions (MBIs) are promising and can be cost-effective; however, empirical evidence for MBIs is limited and published findings have not been widely translated into practice. Here, we describe how we implemented strategies to enhance rigor in a randomized clinical trial of an MBI for persons with dementia. We examined the impact of a singing-based MBI on feelings, emotions, and social engagement, relative to a non-music treatment (verbal discussion), delivered in small group format (25 minutes, 3 times/week for 2 weeks). We implemented National Institutes of Health Behavior Change Consortium strategies regarding: (i) design, (ii) interventionist training, (iii) treatment delivery, (iv) treatment receipt, and (v) treatment skills enactment. We applied the MBI Reporting Criteria including: (i) theoretical framework, (ii) musical content, (iii) dosage, (iv) interventionist, (v) treatment fidelity, (vi) setting, and (vii) delivery unit. We analyzed data with a separate linear mixed model for each dependent variable. 32 older adults with dementia (65-97 years) participated. The MBI yielded significant positive effects on all measured outcomes (all p's < .05). Application of established guidelines enhanced methodological rigor and MBI reproducibility. To support translation of research into practice, clinicians should understand how to implement an MBI reported in research. Our study illustrates practical steps to address the need for improved MBI research in persons with dementia and can provide a model for others to enhance evidence-based practice with this population.

Transliteration Characteristics in Romanized Assamese Language Social Media Text and Machine Transliteration

This article aims to understand different transliteration behaviors of Romanized Assamese text on social media. Assamese, a language that belongs to the Indo-Aryan language family, is also among the 22 scheduled languages in India. With the increasing popularity of social media in India and also the common use of the English Qwerty keyboard, Indian users on social media express themselves in their native languages, but using the Roman/Latin script. Unlike some other popular South Asian languages (say Pinyin for Chinese), Indian languages do not have a common standard romanization convention for writing on social media platforms. Assamese and English are two very different orthographical languages. Thus, considering both orthographic and phonemic characteristics of the language, this study tries to explain how Assamese vowels, vowel diacritics, and consonants are represented in Roman transliterated form. From a dataset of romanized Assamese social media texts collected from three popular social media sites: (Facebook, YouTube, and X (formerly known as Twitter)), 1 we have manually labeled them with their native Assamese script. A comparison analysis is also carried out between the transliterated Assamese social media texts with six different Assamese romanization schemes that reflect how Assamese users on social media do not adhere to any fixed romanization scheme. We have built three separate character-level transliteration models from our dataset. One using a traditional phrase-based statistical machine transliteration model, (1) PBSMT model and two separate neural transliteration models, (2) BiLSTM neural seq2seq model with attention, and (3) Neural transformer model. A thorough error analysis has been performed on the transliteration result obtained from the three state-of-the-art models mentioned above. This may help to build a more robust machine transliteration system for the Assamese social media domain in the future. Finally, an attention analysis experiment is also carried out with the help of attention weight scores taken from the character-level BiLSTM neural seq2seq transliteration model built from our dataset.

Comorbid Conditions Are Associated With Cognitive Impairment in Native Hawaiians and Pacific Islanders.

We examined the association between comorbid conditions and mild cognitive impairment (MCI) in Native Hawaiians and Pacific Islanders (NHPI) (n = 54). Cross-sectional, self-reported questionnaires were utilized to collect demographic, comorbid conditions, and MCI (via the AD8 index) data. Separate logistic regression models were conducted to investigate the relationship between comorbid conditions and MCI, adjusting for other covariates. We found significantly increased odds of MCI in those reporting high blood pressure (OR = 5.27; 95% CI: [1.36, 20.46]; p = 0.016), high cholesterol (OR = 7.30; 95% CI: [1.90, 28.14], p = 0.004), and prediabetes or borderline diabetes (OR = 4.53; 95% CI: [1.27, 16.16], p = 0.02) compared with those not reporting these respective conditions. These data show that hypertension, hypercholesterolemia, and prediabetes are associated with MCI in the NHPI community, suggesting that preventive strategies to reduce chronic conditions may also potentially slow cognitive decline in underrepresented/understudied NHPI.

Handwritten digit recognition based on deep learning techniques

The identification of handwritten digits in images recognition and machine learning is a prominent research area. In order to create a handwritten digit recognition model for this investigation, deep learning is introduced. The proposed approach integrates Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), and EfficientNetB0, three separate deep learning models. Specifically, the CNN model utilizes pooling layers and data augmentation techniques to enhance its classification ability, the RNN model takes advantage of its ability to process sequential data, and the EfficientNetB0 model benefits from a deeper and more complex network structure. These models are trained and evaluated using the Modified National Institute of Standards and Technology (MNIST) dataset. The experimental results demonstrate the efficacy of the proposed approach: the CNN model attains a remarkable accuracy of 98.9% on the test set, thereby showcasing its exceptional classification performance. Similarly, the RNN model achieves an accuracy of 96.7%, underscoring its suitability for analyzing sequential data. Furthermore, the EfficientNetB0 model attains an accuracy of 98.1%, thereby elucidating the benefits of the deeper network architecture. The models constructed in this study have significant real-world implications, such as improved object recognition systems, medical diagnostics, and autonomous driving. The EfficientNetB0 model produced an accuracy of 98.1% with its complex network architecture when applied to recognise handwritten digits.

Relationship of Visual Function with Incident Fall and Mortality among Patients with Anterior Ischemic Optic Neuropathy

The purpose of this study was to determine if worse visual acuity is associated with an increased risk of incident fall or mortality, independent of other relevant cofounders. This was a single-center retrospective cohort study of 428 new cases of anterior ischemic optic neuropathy (AION). Separate Cox proportional hazards models were constructed to evaluate the relationship between either logMAR visual acuity (VA) or legal blindness (20/200 or worse VA) and survival time to (1) encounter for fall, (2) mortality, and (3) a composite adverse outcome. Multivariable models were adjusted for a priori confounders. In adjusted models, a 1-unit increase in logMAR VA was associated with a significantly greater risk of an incident fall (adjusted HR 1.36, 95% CI (1.06–1.73), p = 0.014) and of mortality (adjusted HR 1.44, 95% CI (1.15–1.82), p = 0.002). Meeting criteria for legal blindness was also significantly associated with a higher risk of incident fall (HR 1.80, 95% CI (1.05–3.07), p = 0.032) and mortality (adjusted HR 2.16, 95% CI (1.29–3.63), p = 0.004). Among patients with AION, worse visual acuity or legal blindness conferred a significantly increased risk of falls and mortality, independent of coexistent comorbidities. Future studies should consider fall reduction interventions for patients with poor vision from severe eye disease such as AION.

Characterizing advanced heart failure risk and hemodynamic phenotypes using interpretable machine learning

BackgroundAlthough previous risk models exist for advanced heart failure with reduced ejection fraction (HFrEF), few integrate invasive hemodynamics or support missing data. This study developed and validated a heart failure (HF) hemodynamic risk and phenotyping score for HFrEF, using Machine Learning (ML). MethodsPrior to modeling, patients in training and validation HF cohorts were assigned to 1 of 5 risk categories based on the composite endpoint of death, left ventricular assist device (LVAD) implantation or transplantation (DeLvTx), and rehospitalization in 6 months of follow-up using unsupervised clustering. The goal of our novel interpretable ML modeling approach, which is robust to missing data, was to predict this risk category (1, 2, 3, 4, or 5) using either invasive hemodynamics alone or a rich and inclusive feature set that included noninvasive hemodynamics (all features). The models were trained using the ESCAPE trial and validated using 4 advanced HF patient cohorts collected from previous trials, then compared with traditional ML models. Prediction accuracy for each of these 5 categories was determined separately for each risk category to generate 5 areas under the curve (AUCs, or C-statistics) for belonging to risk category 1, 2, 3, 4, or 5, respectively. ResultsAcross all outcomes, our models performed well for predicting the risk category for each patient. Accuracies of 5 separate models predicting a patient's risk category ranged from 0.896 +/- 0.074 to 0.969 +/- 0.081 for the invasive hemodynamics feature set and 0.858 +/- 0.067 to 0.997 +/- 0.070 for the all features feature set. ConclusionNovel interpretable ML models predicted risk categories with a high degree of accuracy. This approach offers a new paradigm for risk stratification that differs from prediction of a binary outcome. Prospective clinical evaluation of this approach is indicated to determine utility for selecting the best treatment approach for patients based on risk and prognosis.

Protocol for spatial prediction of soil transmitted helminth prevalence in the Western Pacific region using a meta-analytical approach

BackgroundSoil transmitted helminth (STH) infections are estimated to impact 24% of the world’s population and are responsible for chronic and debilitating morbidity. Disadvantaged communities are among the worst affected and are further marginalized as infection prevalence fuels the poverty cycle. Ambitious targets have been set to eliminate STH infections, but accurate epidemiological data will be required to inform appropriate interventions. This paper details the protocol for an analysis that aims to produce spatial prediction mapping of STH prevalence in the Western Pacific Region (WPR).MethodsThe protocol follows the Preferred Reporting Items for Systematic Review and Meta-Analysis Protocol (PRISMA-P) guidelines. The study design will combine the principles of systematic review, meta-analysis, and geospatial analysis. Systematic searches will be undertaken in PubMed, Scopus, ProQuest, Embase, and Web of Science for studies undertaken post 2000, to identify surveys that enable the prevalence of human STH infection within the WPR to be calculated. Covariate data for multivariable analysis will be obtained from publicly accessible sources. Survey data will be geolocated, and STH prevalence and covariates will be linked to produce a spatially referenced dataset for analysis. Bayesian model-based geostatistics will be used to generate spatially continuous estimates of STH prevalence mapped to a resolution of 1 km2. A separate geospatial model will be constructed for each STH species. Predictions of prevalence will be made for unsampled locations and maps will be overlaid for each STH species to obtain co-endemicity maps.DiscussionThis protocol facilitates study replication and may be applied to other infectious diseases or alternate geographies. Results of the subsequent analysis will identify geographies with high STH prevalence’s and can be used to inform resource allocation in combating this neglected tropical disease.Trial registrationOpen Science Framework: osf.io/qmxcj.

Enhancing Streamflow Prediction Physically Consistently Using Process-Based Modeling and Domain Knowledge: A Review

Streamflow prediction (SFP) constitutes a fundamental basis for reliable drought and flood forecasting, optimal reservoir management, and equitable water allocation. Despite significant advancements in the field, accurately predicting extreme events continues to be a persistent challenge due to complex surface and subsurface watershed processes. Therefore, in addition to the fundamental framework, numerous techniques have been used to enhance prediction accuracy and physical consistency. This work provides a well-organized review of more than two decades of efforts to enhance SFP in a physically consistent way using process modeling and flow domain knowledge. This review covers hydrograph analysis, baseflow separation, and process-based modeling (PBM) approaches. This paper provides an in-depth analysis of each technique and a discussion of their applications. Additionally, the existing techniques are categorized, revealing research gaps and promising avenues for future research. Overall, this review paper offers valuable insights into the current state of enhanced SFP within a physically consistent, domain knowledge-informed data-driven modeling framework.

Uncertainty-aware deep-learning model for prediction of supratentorial hematoma expansion from admission non-contrast head computed tomography scan

Hematoma expansion (HE) is a modifiable risk factor and a potential treatment target in patients with intracerebral hemorrhage (ICH). We aimed to train and validate deep-learning models for high-confidence prediction of supratentorial ICH expansion, based on admission non-contrast head Computed Tomography (CT). Applying Monte Carlo dropout and entropy of deep-learning model predictions, we estimated the model uncertainty and identified patients at high risk of HE with high confidence. Using the receiver operating characteristics area under the curve (AUC), we compared the deep-learning model prediction performance with multivariable models based on visual markers of HE determined by expert reviewers. We randomly split a multicentric dataset of patients (4-to-1) into training/cross-validation (n = 634) versus test (n = 159) cohorts. We trained and tested separate models for prediction of ≥6 mL and ≥3 mL ICH expansion. The deep-learning models achieved an AUC = 0.81 for high-confidence prediction of HE≥6 mL and AUC = 0.80 for prediction of HE≥3 mL, which were higher than visual maker models AUC = 0.69 for HE≥6 mL (p = 0.036) and AUC = 0.68 for HE≥3 mL (p = 0.043). Our results show that fully automated deep-learning models can identify patients at risk of supratentorial ICH expansion based on admission non-contrast head CT, with high confidence, and more accurately than benchmark visual markers.

Cognitive, functional, and neuropsychiatric correlates of regional tau pathology in autopsy-confirmed chronic traumatic encephalopathy

BackgroundChronic traumatic encephalopathy (CTE) is a neurodegenerative disease characterized by hyperphosphorylated tau (p-tau) accumulation. The clinical features associated with CTE pathology are unclear. In brain donors with autopsy-confirmed CTE, we investigated the association of CTE p-tau pathology density and location with cognitive, functional, and neuropsychiatric symptoms.MethodsIn 364 brain donors with autopsy confirmed CTE, semi-quantitative p-tau severity (range: 0–3) was assessed in 10 cortical and subcortical regions. We summed ratings across regions to form a p-tau severity global composite (range: 0–30). Informants completed standardized scales of cognition (Cognitive Difficulties Scale, CDS; BRIEF-A Metacognition Index, MI), activities of daily living (Functional Activities Questionnaire), neurobehavioral dysregulation (BRIEF-A Behavioral Regulation Index, BRI; Barratt Impulsiveness Scale, BIS-11), aggression (Brown-Goodwin Aggression Scale), depression (Geriatric Depression Scale-15, GDS-15), and apathy (Apathy Evaluation Scale, AES). Ordinary least squares regression models examined associations between global and regional p-tau severity (separate models for each region) with each clinical scale, adjusting for age at death, racial identity, education level, and history of hypertension, obstructive sleep apnea, and substance use treatment. Ridge regression models that incorporated p-tau severity across all regions in the same model assessed which regions showed independent effects.ResultsThe sample was predominantly American football players (333; 91.2%); 140 (38.5%) had low CTE and 224 (61.5%) had high CTE. Global p-tau severity was associated with higher (i.e., worse) scores on the cognitive and functional scales: MI (β\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\beta$$\\end{document}standardized = 0.02, 95%CI = 0.01–0.04), CDS (β\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\beta$$\\end{document}standardized = 0.02, 95%CI = 0.01–0.04), and FAQ (β\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\beta$$\\end{document}standardized = 0.03, 95%CI = 0.01–0.04). After false-discovery rate correction, p-tau severity in the frontal, inferior parietal, and superior temporal cortex, and the amygdala was associated with higher CDS (β\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\beta$$\\end{document} sstandardized = 0.17–0.29, ps < 0.01) and FAQ (β\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\beta$$\\end{document} sstandardized = 0.21–0.26, ps < 0.01); frontal and inferior parietal cortex was associated with higher MI (β\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\beta$$\\end{document} sstandardized = 0.21–0.29, ps < 0.05); frontal cortex was associated with higher BRI (β\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\beta$$\\end{document}standardized = 0.21, p < 0.01). Regions with effects independent of other regions included frontal cortex (CDS, MI, FAQ, BRI), inferior parietal cortex (CDS) and amygdala (FAQ). P-tau explained 13–49% of variance in cognitive and functional scales and 6–14% of variance in neuropsychiatric scales.ConclusionAccumulation of p-tau aggregates, especially in the frontal cortex, are associated with cognitive, functional, and certain neurobehavioral symptoms in CTE.

Child surgency and child aggression: The moderating effect of parental nurturance, emotion coaching, and family income

According to the goodness-of-fit development theory, a mismatch between child characteristics and socialization processes tends to lead to child maladjustment. The present study aimed to examine whether the association between child surgency and child aggression varies as a function of parenting styles and practices such as parental nurturance and parental emotion coaching. In addition, family economic background was examined as a contextual moderator. Cross-sectional questionnaire data were collected from parents and class teachers of 288 preschoolers (Mage = 5.2 years; 53 % were boys) in Hong Kong, China. Separate multilevel models were run to test parental nurturance, emotion coaching, and family income level as moderators. Results indicated that controlling for confounding variables, child surgency was only positively associated with child aggression when parental nurturance was low, but not when parental nurturance was high. However, this pattern only emerged in high- and medium-income families, but not in low-income families. A similar but different pattern was observed for parental emotion coaching: regardless of family income level, child surgency was only associated with child aggression when parental emotion coaching was low, but not when it was high. Theoretically, our findings highlight the importance of considering the fit between child temperament and environmental features, such as parenting and family economic background, in understanding child development. Practically, our findings point to the utility of helping parents to express their love and affection and to talk to their children about managing emotions to reduce aggression in preschool-aged children, especially those with high surgency and economic advantages.