Browse Articles

RareAgriDetectAI a generative deep learning framework using RareSimGAN for early detection and simulation of rare crop diseases

Red blood cell distribution width to albumin ratio and systemic immune-inflammatory index as predictors of mortality in severe pneumonia: A retrospective cohort analysis

Objective Severe pneumonia carries a high risk of mortality. There is a need for readily available prognostic biomarkers to improve risk stratification. This study evaluated the prognostic value of two novel composite indices, the red blood cell distribution width-to-albumin ratio (RAR) and the systemic immune-inflammation index (SII), in patients with severe pneumonia. Methods This retrospective cohort study extracted data from electronic medical records of 194 adult patients (age ≥ 18 years) with severe pneumonia (diagnosed per Chinese guidelines) admitted to Jinhua Hospital (January 2022 to December 2024). After screening 2,268 admissions, 194 patients with complete 24-hour data were classified into survivors (n = 147) and non-survivors (n = 47). Associations between RAR, SII, and in-hospital mortality were analyzed using multivariate logistic regression, receiver operating characteristic (ROC) curves, and Kaplan-Meier survival analysis. Results Compared with survivors, non-survivors had a significantly higher RAR (median: 0.44 vs. 0.37, p  < 0.001) and SII (median: 2389 vs. 1870, p  = 0.002). RAR was positively correlated with D-dimer ( r  = 0.254, p  < 0.001), and negatively correlated with uric acid (UA) ( r  = −0.147, p  = 0.042). SII was positively correlated with C-reactive protein (CRP) ( r  = 0.150, p  = 0.037) and interleukin-6 (IL-6) ( r  = 0.188, p  = 0.009). Advanced age ( OR =1.042; 95% CI :1.004–1.082; p  = 0.030), high RAR ( OR =2.492; 95% CI :1.642–3.781; p  < 0.001) and high SII ( OR =1.575; 95% CI :1.074–2.309; p  = 0.036) were independent risk factors for death in patients with severe pneumonia. The ROC of RAR and SII for predicting death in patients with severe pneumonia was 0.722 and 0.652, respectively. Patients with RAR < 0.43 had a higher cumulative survival than patients with RAR ≥ 0.43 (85.6% [119/139] vs. 50.9% [28/55]; HR  = 4.987; 95% CI : 2.592–9.593; p  < 0.001); Patients with SII < 2120 had a higher cumulative survival than patients with SII ≥ 2120 (86.9% [93/107] vs. 62.1% [54/87]; HR  = 2.745; 95% CI : 1.531–4.924; p  < 0.001). Conclusions Elevated RAR and SII are significantly associated with an increased risk of in-hospital death in severe pneumonia patients. These indices may therefore serve as useful, readily available, and inexpensive prognostic tools.

Explainable hourly global solar radiation forecasting using a CNN–BiLSTM model with temperature scaled softmax attention

Abstract Accurate global solar radiation (GSR) forecasting is vital for smart grids and resilient energy systems. However, the nonlinear and non-stationary nature of meteorological drivers challenges conventional approaches. This study proposes a lightweight, explainable hybrid deep learning architecture, CNN-BiLSTM-STAM, which integrates convolutional layers for inter-feature pattern extraction, bidirectional long short-term memory (BiLSTM) networks for temporal dependency learning, and a softmax temperature attention mechanism (STAM) with a learnable temperature to adaptively sharpen or smooth attention over time under varying weather conditions. The model is trained and evaluated using an hourly multivariate meteorological dataset collected at Alparslan Türkeş Science and Technology University in Sarıçam, Adana, Türkiye. Results show that CNN-BiLSTM-STAM outperforms classical machine-learning models, baseline deep networks, and recent attention-based variants for short and mid-term GSR forecasting, achieving RMSE = 66.62 W/m $$^{2}$$ , MAE = 43.29 W/m $$^{2}$$ , $$R^{2}$$ = 0.9381, and Pearson r = 0.9715. Additional validation on two independent public meteorological datasets, with the same architecture trained and evaluated separately on each dataset, yielded $$R^{2}$$ values of 0.9188 and 0.9537 and Pearson correlation coefficients of 0.9597 and 0.9768, supporting the external reproducibility of the proposed framework. To support operational trust, Shapley additive explanations (SHAP) are used to quantify feature importance and provide interpretable insights into seasonal and short-term atmospheric influences. With a compact footprint and strong predictive accuracy, the proposed framework supports deployable GSR forecasting for PV operation and scheduling, real-time energy management, and IoT-enabled monitoring systems.

Betrayal trauma and adult mental health: The role of mentalizing and dissociation

Background Trauma experienced across the lifespan has been linked to a wide range of adverse mental health outcomes. However, the psychological mechanisms connecting betrayal trauma to later psychopathology remain insufficiently understood. Objective This cross-sectional study investigated associations between betrayal trauma during childhood and adulthood and adult psychopathology—specifically depressive symptoms and level of personality functioning within a dimensional model of personality disorders. We tested a path model examining direct and indirect associations between betrayal trauma at different developmental periods and adult psychopathology via dissociation and hypomentalizing. Participants A sample of 209 adults (61% female; aged 18–45 years; M  = 29.7, SD  = 7.88) were recruited from community and clinical settings in Poland. Methods Participants completed validated self-report measures assessing betrayal trauma, depressive symptoms, personality functioning (ICD-11 model), dissociation, and mentalizing. Path analyses with parallel mediation were conducted using Satorra–Bentler estimation and 5,000 bootstrap resamples to examine both direct and indirect associations. Results Both childhood and adulthood betrayal trauma were significantly associated with depressive symptoms and PD severity through dissociation and hypomentalizing [χ²(6) = 13.68, p = .033; CFI = 0.989; TLI = 0.931; RMSEA = 0.078; SRMR = 0.038]. No significant direct effects were observed once psychological processes were included. Mentalizing consistently demonstrated a stronger indirect association than dissociation across models. Adulthood betrayal trauma showed a greater total effect on depressive symptoms (β = .30; p < .001) than childhood trauma (β =  .17; p = .043), whereas their effects on personality pathology were comparable (respectively, β =  .21; p = .006 for adult trauma and β = .22; p = .008 for childhood trauma). For adulthood trauma and PD severity, the direct association was small and non-significant (β = −.06), whereas indirect effects via dissociation (β = .11) and mentalizing (β = .16) were positive, resulting in a positive total effect. Conclusions These findings indicate that the link between betrayal trauma and adult psychopathology may be best conceptualised in terms of co-occurring psychological processes rather than direct exposure effects. Hypomentalizing, in particular, appears to represent a key transdiagnostic mechanism connecting relational trauma across developmental stages with both mood and personality pathology.

Analysis and optimization of conventional furrow irrigation systems using the WinSRFR simulation model

Abstract Surface irrigation systems continue to be the most popular irrigation systems worldwide, owing to their ability to save energy and ease of operation. They do, however, perform poorly as a result of the overall design and ineffective management. Therefore, the study aims to optimize the performance of conventional furrow irrigation systems in water constrained areas. Conventional furrow irrigation was used to collect field data and then to evaluate performance using the WinSRFR simulation model. The sensitivity analysis of WinSRFR revealed that the most sensitive parameters were inflow rate, cut-off time, and furrow spacing, respectively. The WinSRFR simulation model predicted that the conventional furrow design performed better in terms of application efficiency 84%, and achieved flow rates near the minimum allowable which is 0.0025m 3 /s in our case due to extreme water shortage. Therefore, given minimal runoff and percolation losses, with total maximum losses of around 16%, the best water application efficiency was achieved. Nevertheless, the lower quarter adequacy is 0.74, indicating that the field is under irrigated due to significant water constraints in the farm field. Simulation models of WinSRFR have proved to be an effective model for designing, forecasting, and optimizing the performance of conventional furrow irrigation systems. In earlier studies, researchers used fictitious scenarios to predict how well the furrow systems would perform by designing furrows with various lengths and flow rates on the same plot. The engineering approach used in this study was applied to actual crop fields, which greatly helped us predict the availability of the proper quantities of moisture to the crops and take the necessary action if the field was moisture deficient. Therefore, farmers can use our methodology to get deep insights into the performance of their fields and implement the necessary precautions to ensure the health of the crops.

Utility of HEARTSMAP-U for psychosocial screening and mental health resource navigation in the young adult population

Purpose Given the high prevalence of mental health struggles and long wait times for psychological assessment, validated digital self-assessment screening tools can help to address the gap. Our previously validated tool for ages 6–17, MyHEARTSMAP, was adapted to focus on the transition to university. This new tool, HEARTSMAP-U, captures the issues of older youth, addresses student-specific psychosocial needs, and recommends resources matching the type and urgency of their reported needs. Prior to widespread use in the public domain, we aim to validate the psychometric properties of HEARTSMAP-U as compared to a standard mental health intake assessment. Methods We conducted a prospective validation study of students at a Canadian university aged 17–29. Participants completed psychosocial self-assessments using HEARTSMAP-U, which were then directly compared to equivalent, standardized assessments conducted by clinical counselors. We reported the sensitivity and specificity of the participant self-assessments against that of a clinician’s intake evaluation. This considered each respondent’s degree of unmet needs, and through this, each person was provided with a catered list of local supports for each psychosocial domain. Result Of the 619 eligible participants, 536 completed baseline evaluations for analysis. Using HEARTSMAP-U, post-secondary students’ sensitivity of self-identifying any degree of psychiatric concern was 90% (95% CI 83–94%). When clinicians identified no psychiatric concerns, HEARTSMAP-U self-assessments similarly identified either no or mild concern in 70% (95% CI 65–74%) of these participants. Discussion Psychosocial screening with HEARTSMAP-U can be reliably implemented in a post-secondary population as compared to a clinical clinician evaluation. Interestingly, a large cohort of respondents (10%) were deemed to have no psychiatric concerns by clinician evaluation, but severe concerns based on HEARTSMAP-U self-assessment. This specific population may represent a target group for future screening interventions.

Mobile real-time detection transformer for computationally constrained devices

Editorial Note: Prevalence of Chinook salmon is higher for southern than for northern resident killer whales in summer hot-spot feeding areas

Prospective evaluation of axial length and refractive stability after small-incision lenticule extraction in young adults with progressive myopia

Sickle cell disease and maternity care: A qualitative synthesis of women’s and health providers experiences

Introduction Sickle Cell Disease (SCD) is one of the most prevalent genetic diseases in the world. For women with SCD or those with Sickle Cell Trait (SCT) reproductive choices not only require consideration of genetic inheritance but also the exacerbation of pregnancy induced SCD symptoms and potential birth complications. To explore these issues a qualitative synthesis was conducted incorporating the views of women with SCD or SCT as well as healthcare professionals working with these women in maternity settings. Methods Database searches were performed in MEDLINE, Embase, MIDIRS, CINAHL Ultimate, PsycINFO, Social Sciences Citation Index, Global Index Medicus and CNKI, as well as reference lists of included studies published January 2000–October 2024. Studies reporting qualitative data from women with SCD or SCT and health professionals providing care to these women during the maternity phase were included. Data Collection and Analysis Author findings were extracted, coded and synthesised using techniques derived from thematic synthesis. Confidence in the quality, coherence, relevance and adequacy of data underpinning the resulting findings was assessed using GRADE-CERQual. Results Eleven studies from four different countries (UK, Brazil, France and Uganda) were identified including eight focusing on the views of women, two reporting on the views of health professionals and one exploring both. From these four analytical themes were generated: Beyond the routine of antenatal screening; Myths, misunderstandings and submissiveness; Fear and uncertainty in the face of adversity; The importance of familial and organizational support . Confidence in the results was moderate to good. Conclusion The synthesis suggests that the intersection of SCD and maternity care is beset with a lack of understanding and inadequate health system support. In some contexts, women endure stigmatization, discrimination and poor quality care. Public awareness campaigns and educational initiatives, particularly amongst healthcare professionals, are urgently required to address these issues.

SLA-printed nanographite-reinforced UV-curable resin composites for dental applications

Abstract This study investigates stereolithography (SLA)-printed nanographite (NG)-reinforced UV-curable resin composites for dental applications. Anycubic plant-based resin was modified with 0, 0.5, 1, 3, and 5 wt% NG and evaluated for viscosity, UV absorbance, moisture content, water absorption, gel content, tensile, flexural, hardness, and microstructural behavior. The viscosity remained suitable for printing, decreasing slightly from 139 mPa·s for the control to 134 mPa·s at 5% NG. The 1% NG composite showed the best overall performance, with the highest tensile strength ( 20 MPa ) , compared to 18 MPa for the control, and the highest flexural stress ( 50 MPa ) and Shore D hardness (72). The control hardness was 70, while 5% NG dropped to 59. Gel content decreased from 99.86% (control) to 99.24% (5% NG), but higher loadings increased moisture and water uptake. Microscopy and SEM confirmed that 1% NG produced the most uniform morphology, whereas 3–5% NG showed agglomeration and defects. The results demonstrate that the controlled addition of NG enhances the mechanical performance of SLA-printed UV-curable resin composites, indicating their potential for provisional dental prosthetics applications.

Triggering of viral and bacterial respiratory infection hospitalizations by traffic pollution exposure in a cohort of hospitalized adults

The rate of respiratory viral infection (RVI) associated with acute air pollution exposure is well established, but whether bacterial and viral infections respond similarly to traffic related air pollution (TRAP) exposure is less well understood. Using a novel seasonal time-stratified case-crossover design and conditional logistic regression, we separately estimated the rate of hospitalization for 465 patients with RVI, respiratory bacterial infection (RBI), or combined respiratory viral and bacterial infection (RVBI) associated with increased ambient particulate matter ≤2.5 µm (PM 2.5 ), black carbon (BC), nitrogen dioxide (NO 2 ) and carbon monoxide (CO) concentrations in the previous 1, 2, and 3 weeks (lag days 0–6, 7–13, 14–20). In a novel approach, a four-physician panel adjudicated each case of infection to accurately classify the type of infection present and only patients with the highest diagnostic certainty were enrolled in this study. Associations were strongest between TRAP and RVI at the 0–6 lag period, with fewer, less precise associations at later lag times for RVBI and RBI. Each 2.6 µg/m 3 increase in PM 2.5 on lag days 0–6 was associated with a 22.1% increased rate of RVI hospitalization (95% CI: 1.6%, 46.7%). Each 0.1 µg/m 3 increase in BC was associated with a 30.0% increase (95% CI: 5.0%, 61.1%) in the rate of hospitalization for RVI. Rates of hospitalization for RVI associated with increased PM 2.5 were generally largest for lag days 0–6 and 7–13. The RVI/BC rate ratio was larger for females than males for days 0–13, but not for PM 2.5 and NO 2 . Short term increases in PM 2.5 , BC, NO 2 , and CO concentrations (markers of traffic pollution) were associated with an increased rate of RVI hospitalization, while sex-specific associations were observed between BC and RVI for females. Further study of the mechanism underlying the effect of TRAP on RVI is needed.

Adaptive Brownian motion and convergence-trend-driven strategies for enhancing the Besiege and Conquer algorithm

Optimization of low-carbon multi-temperature joint distribution for fresh agricultural products under 3D loading constraints

With the growing demand for fresh agricultural products, improving the efficiency and sustainability of cold-chain distribution has become increasingly important. Multi-temperature joint distribution provides an effective solution for serving products with different temperature requirements, yet its implementation remains challenging due to the need to coordinate vehicle routing, three-dimensional loading, and carbon-emission reduction objectives. To address this issue, this paper develops a low-carbon multi-temperature joint distribution optimization model under three-dimensional loading constraints. A hybrid algorithm integrating genetic algorithm and tabu search is proposed to solve the model efficiently. The proposed approach is validated using real-world data collected from a fresh agricultural products supply chain company. The results show that the multi-temperature joint distribution mode reduces total operating costs by 30.04% and carbon emissions by 30.62% compared with the conventional single-temperature distribution mode. Moreover, the proposed hybrid algorithm achieves faster convergence and better solution quality than the conventional genetic algorithm. These findings demonstrate the effectiveness of integrating three-dimensional loading, multi-temperature distribution, and low-carbon objectives within a unified optimization framework, providing practical support for distribution planning and decision-making in cold-chain logistics.

Comparative study of different methods for bathymetric mapping based on multi-source remote sensing data

Comparison of Moducare versus Wait-and-See approach for histologically proven Low-grade Cervical Intraepithelial Neoplasia (CIN1) (MODUCIN1 TRIAL) – Study protocol

Human Papillomavirus (HPV) is causally associated with cervical cancer and precancerous lesions (dysplasias) of the cervix. The treatment of choice for low-grade lesions is monitoring with no-treatment, because the majority of them will regress spontaneously. However, this wait-and-see approach can be assisted by nutritional supplements for immune support, like Moducare. The hypothesis of the trial is that Moducare can enhance the natural regression of CIN1. MODUCIN1 is a prospective, open-label, randomized trial where eligible patients will be randomized (1:1) to either the wait-and-see approach (control arm) or to the six months oral administration of Moducare capsules. The main inclusion criterion is newly histologically proven CIN1 and the main exclusion criterion is any previous cervical intraepithelial neoplasia with or without treatment or history of pelvic malignancy. The primary objective is to compare the regression rates of low-grade cervical intraepithelial neoplasia (CIN1) between the two groups: Wait-and-see approach and Moducare. The sample size is estimated at 182 eligible patients, while accrual is expected to last one year. The primary endpoint is expected to be reached after six months from last patient enrollment. The Trial Registration Number is NCT07379905.

The oral microbiome is associated with stress, adversity, and mental health in young adults

Abstract Acute stress responsivity and early-life adversity are both associated with oral microbiome differences that lead to increased mental and physical health risk. However, the joint association of stress responsivity and early adversity with the oral microbiome is not yet understood. Additionally, while the link between the oral microbiome and cortisol has been investigated, another major component of stress responsivity – the parasympathetic response – has been relatively neglected. Therefore, we examined parasympathetic functioning during an acute stressor, retrospective early adversity, oral microbiome (using the bacterial 16S gene), and anxiety and depression symptoms in 76 undergraduates. Early adversity was associated with lower microbiome diversity. Independently of adversity, parasympathetic withdrawal during the stressor was positively associated with Alysiella , a genus previously linked to latent viral infections. Early adversity and parasympathetic function did not significantly interact. Additionally, depressive symptoms were negatively associated with Butyrivibrio , which produces neuroprotective metabolites. Our findings suggest that childhood adversity and parasympathetic stress response are independently associated with oral microbiome differences, and that the oral microbiome is associated with mental health. By characterizing the associations of the oral microbiome with stress, adversity, and mental health, this study lays important groundwork for future research on psychophysiological causes and outcomes of oral microbiome differences.

Evolving optimal text clusters: A novel GA-driven framework for dynamic ensemble fusion of multi-model contextual embeddings

Text clustering is an essential activity in unsupervised natural language processing (NLP), and allows the automatic structure of large-scale textual collections (in natural language processing) in news classification, routing of technical questions, and text summarisation. With the emergence of contextual embedding models, such as SBERT, RoBERTa, and DistilBERT, there has been a significant improvement in the quality of clustering, with these models producing dynamic and context-sensitive representations that are more likely to reflect domain-specific semantics than the traditional word embeddings of Word2Vec and GloVe. Although the models of contextual embedding have their own advantages, they show varying performance in different domains and the current ensemble techniques propose fixed, flat fusion weights which do not utilize their complementary abilities. There is no current solution to dynamic, label-free optimisation of weight to multi-model contextual embedding fusion in unsupervised clustering which would bridge a major gap between fixed integrative approaches and adaptive, domain-accommodative model combination. This paper presents a new Genetic Algorithm (GA)-based ensemble model that dynamically optimizes the best fusion weights of SBERT, RoBERTa, and DistilBERT embeddings without ground-truth labels. The hypothesis is that evolutionary optimisation can discover domain-adaptive weight sets that outperform standalone models as well as fixed ensemble baselines on linguistically heterogeneous datasets. The framework uses L2-normalisation and topology in which the topology is a sum-to-one constraint so that the models can be fairly integrated, and a composite fitness measure based on Silhouette Score, Adjusted Rand Index, and Topic Coherence to direct the weight evolution through tournament selection, uniform crossover, and Gaussian mutation. The proposed framework on three heterogeneous benchmarks, AG News, 20 Newsgroups, and Stack Overflow, has Silhouette Score improvements of +14–16 percent, and Topic Coherence gains of +17 percent, all statistically significant at p < 0.05. Evolved weights can be completely understood, depicting domain-specific model roles, which guide future architecture choice. The framework is suggested as a scalable, modular system to practical unsupervised NLP problems, and its architecture can be easily extended to new transformer systems and semi-supervised systems.

Restriction spectrum imaging reveals brain microstructural correlates of obesity risk in early childhood

Transcriptomic characterization of key psoriasis-associated genes based on single-cell RNA-seq and machine learning

Background Psoriasis is a multifaceted skin and systemic disorder driven by a complex interplay of genetic, immunological, and environmental factors. Genetic predisposition plays a pivotal role, with the IL-17/IL-23 immune axis recognized as a central pathogenic pathway. Ongoing research, however, continues to uncover additional critical drivers, cytokines, intracellular signaling networks, and potential therapeutic targets. Methods Single-cell RNA sequencing (scRNA-seq) datasets comprising both psoriatic and healthy samples were obtained from the Gene Expression Omnibus (GEO). Cell-type proportions were estimated using Cell-type Identification by Estimating Relative Subsets of RNA Transcripts (CIBERSORT), and weighted gene co-expression network analysis (WGCNA) was applied to explore correlations between cell types and gene signatures. Machine learning algorithms were subsequently employed to identify four psoriasis-associated key genes: DEFB4A , GJB2 , SERPINB3 , and SERPINB13 . Their expression was validated in bulk RNA-seq datasets. Using scRNA-seq data, we further investigated the lesional regulatory roles of these genes and their associated pathway alterations, and we proposed targeted therapeutic strategies. Results A series of algorithms identified 271 hub genes significantly associated with psoriasis lesions and basal cells. Machine learning analysis refined this set to four key genes in psoriasis: DEFB4A , GJB2 , SERPINB3, and SERPINB13 . Conclusions These four psoriasis-associated driver genes were upregulated in lesional skin. We also screened small-molecule compounds targeting these genes, offering potential therapeutic strategies.