Browse Articles

Applying ensemble machine learning techniques to MRI scans to predict Alzheimer’s disease

Correction: Determining farm surface porcine reproductive and respiratory syndrome virus (PRRSV) contamination through viability RT-qPCR

AI-enhanced inverse design of photonic crystal fiber optical modulator using deep reinforcement learning technique

Abstract This paper presents a reinforcement learning (RL)-based inverse design framework for photonic device optimization, where a Deep Q-Network (DQN-RL) agent is directly coupled with three-dimensional finite-difference time-domain (3D-FDTD) simulation environment. The proposed approach eliminates the need for pre-collected training data by enabling autonomous, target-driven exploration of a discrete design space. The framework is applied to optimize a silicon-based D-shaped photonic crystal fiber optical modulator (PCF-OM) incorporating a VO₂ phase-change layer, with the objective of minimizing insertion loss (IL). The proposed DQN-RL model demonstrates fast, stable, and consistent convergence behavior. Across multiple independent training runs with different random seeds, all runs converge to the same optimal solution with negligible variation, confirming the robustness of the learned policy. A comprehensive comparative study against particle swarm optimization (PSO), random search, grid search, and Bayesian optimization (BO), performed under identical design space, computational budget, and hardware conditions, demonstrates that the proposed DQN-RL framework achieves the fastest convergence, reaching the optimal solution within only 12 iterations (~ 3 min), compared to 42, 104, 21, and 103 iterations for PSO, random search, grid search, and BO, respectively. reaching an ultra-low IL of 0.935 dB/mm, significantly outperforming the target value of 2 dB/mm. Using the optimized geometry obtained from DQN-RL framework, the PCF-OM exhibits excellent modulation performance, with an extinction ratio exceeding 280 dB/mm, a maximum modulation depth of 99.9%, and broadband operation. Furthermore, fabrication tolerance analysis confirms robust performance, with IL remaining below 1 dB/mm under ± 5% parameter variations. These results demonstrate that DQN-RL provides a fast, robust, and highly effective inverse-design strategy for complex photonic devices.

Retraction: In silico investigation of novel Plasmodium Falciparum glycogen synthase kinase (pfGSk3β) inhibitors for the treatment of malaria infection

Evaluating guided viewing strategies to enhance well-being effects of art viewing: a three-arm randomised controlled trial

Modelling Hepatitis B virus related hospital discharges in Spain: ARIMAX based liver disease forecasting tool for hospital workload and mortality progression

Introduction Chronic hepatitis B (CHB) virus infection leads to severe complications, cirrhosis and hepatocellular carcinoma (HCC). The main objective of this study was to develop an ARIMA-based model to forecast the progression of global hospital discharges, due to cirrhosis and HCC related to chronic hepatitis B. Methods Retrospective observational study of monthly incidence of CHB related hospitalization discharges from 2005 to 2021 in Spain. Data were obtained through the Spanish Minimum dataset of hospital discharge registry (CMBDH) of the Health Ministry. Main diagnosis of CHB, liver cirrhosis and HCC encoded by International Medical codes (ICM–9 and ICM-10) were used. Descriptive and time series analysis was performed with forecasts made for 2022 using seasonal ARIMA and ARIMAX models. Data stationarity was achieved via a square root Box-Cox transformations and differencing. Model selection used was AIC, BIC, MAPE, and forecasting precision. Analysis was performed in R (version 4.5.0). Results The total number of discharges related to hepatitis B was 6743, 58% were due to HCC and 42% to cirrhosis diagnosis. Median age was 59 years (range: 7 to > 100), being 83.4% men. The global chronic hepatitis B (CHB) related workload values range from 10 to 55 monthly discharges, while hepatitis B related to HCC and cirrhosis range from 4 to 34 and 1–29 discharges, respectively. The best fit and 2022 forecasts found for CHB and HCC time series was obtained with the approximate Gaussian Y -ARIMAX (6,0,0) (0,1,1) _12 model. This model after treating outliers, removes seasonal patterns and captures the series’ autoregressive dynamics with an AR(6) and seasonal MA(1) noise with expression: ( 1   −   ϕ 1 B   −   ϕ 2 B 2   −   . . .   −   ϕ 6 B 6 ) ( y t   − y t − 1 2 )   =   ε t   +   Θ 1   ε t − 1 2 with ε ~ N(0, σ²) and in the square root scale. Conclusion Both ARIMA and ARIMAX models play critical roles in forecasting CHB-related HCC and cirrhosis, enabling better disease monitoring, healthcare resources, and intervention assessment. ARIMAX provided more accurate context-aware predictions, making it especially valuable for public health decision-making.

In vivo exposure to cranberry juice suppresses dental plaque regrowth and acid production in adults and children: a PGRM study

Retraction: The effect of biosynthesized silver nanoparticles on Pseudomonas aeruginosa-infected dogs wounds

Integrated bioinformatics, machine learning, and experimental validation identify a four-gene diagnostic signature for cervical cancer associated with PI3K/AKT signaling

Retraction: Unlocking the power of L1 regularization: A novel approach to taming overfitting in CNN for image classification

A sonoelectric artificial meningeal device for enhanced implantable electric field ablation of glioblastoma

Retraction: Edge computing based english translation model using fuzzy semantic optimal control technique

Developing species-specific welfare scoresheets for the African Turquoise Killifish

Abstract The African turquoise killifish Nothobranchius furzeri has emerged as a valuable vertebrate model for ageing research. Despite its increasing use in laboratory studies, systematic welfare monitoring approaches in N. furzeri is still emerging, and only a limited number of structured health-assessment frameworks have been proposed. Here, we present a welfare scoring system designed for daily monitoring of N. furzeri across its entire lifespan under laboratory conditions. Building on established zebrafish welfare frameworks and adapting them to the biological and ethological characteristics of N. furzeri , we identified a set of morphometric, behavioural and clinical parameters, including body condition score, external appearance, food intake, respiratory pattern, swimming activity, tank occupancy and clinical signs. Each parameter was assigned a numerical score ranging from 0 to 3, reflecting increasing degrees of welfare impairment. We further defined standardized intervention criteria, including humane endpoints, to support decision-making in cases of compromised welfare. Importantly, we established five distinct age stages to enable age-specific welfare assessment in two widely used wild-type strains, GRZ/GRZ-AD and MZM04-10. This scoring system provides a practical, reproducible, and easily implementable tool that can be seamlessly integrated into routine husbandry procedures. Its application is expected to promote standardized welfare assessment, improve experimental reproducibility, and enhance animal welfare standards in research using N. furzeri .

Exploring the potential of community health workers in type-2 diabetes and hypertension management in Cambodia

The burden of type-2 diabetes (T2D) and hypertension (HTN) in Cambodia is a major concern. The government and donors have introduced several interventions, yet human resource shortages hamper their implementation. Community health workers (CHWs) can be a valuable additional resource for health in T2D and HTN management. The current study aimed to assess (1) CHWs’ knowledge, attitude, and practices (KAP) in T2D and HTN management and (2) the potential health system barriers for incorporating CHWs in T2D and HTN management. This mixed-method study comprised a survey among 153 active CHWs to assess their KAP towards T2D and HTN, and semi-structured interviews with key informants were conducted to understand the challenges of the health system and propose solutions in incorporating CHWs in T2D and HTN management. Approximately 90% of CHWs correctly answered general knowledge questions on NCDs, risk factors, and prevention; however, only around 20–40% correctly answered questions on family history or tobacco use as risk factors. Most respondents appeared to have positive attitudes and have been practicing some activities related to T2D and HTN. Both financial and non-financial resource constraints were cited as challenges of the health system; therefore, re-structuring the definition of CHWs’ roles and responsibilities, and assessing the need and workload have been proposed as ways forward to effectively incorporate CHWs in T2D and HTN care. CHWs in Cambodia have shown their potential in T2D and HTN management; however, a well-designed strategy, including technical training, clearly defined roles and responsibilities, and strong support structure, is important to maximize their potential in the health system.

Pilot metaproteomic profiling reveals bacterial diversity and potential medical and veterinary relevance of tick microbiomes in northern Algeria

Correction: Health insurance enrollment and maternal health service utilization using Ghana Demographic and Health Survey, 2022

Patterns and influencing factors of dental implant anxiety in China

Design and validation of an integrated meta-instrument for nursing assessment in home hospitalization: A study protocol

Background Hospital-at-home (HaH) programs provide an effective and safe alternative to conventional hospitalization, particularly for patients with multimorbidity or complex chronic conditions. In this setting, nursing assessment plays a key role, given the intermittent nature of care and the limited presence of other professionals. However, nursing documentation in HaH remains challenging because of organizational heterogeneity, fragmented records, and the coexistence of multiple assessment tools that create redundancy and compromise information quality. The overall objective of this study is to develop and validate a meta-instrument (VALENF-HAD) that integrates the assessment of functional capacity, pressure injury risk, fall risk, frailty, nutritional status, and sleep quality in patients admitted to hospital-at-home units on the basis of the analysis of other validated measurement instruments used in nursing assessment. Methods A multicentre, cross-sectional study will be conducted in four public hospitals in Castellón Province, Spain. Participants will include adults (≥18 years) admitted to HaH units. Sociodemographic and care-related variables, along with risk-related variables, will be collected using the following instruments: functional capacity (Barthel Index and Lawton & Brody Scale), risk of pressure injuries (Braden Scale), risk of falls (STRATIFY Scale), frailty (FRAIL questionnaire), nutritional status (Nutritional Screening Initiative tool), and sleep quality (Athens Insomnia Scale). The development process of the meta-instrument consists of four phases: (I) analysis of instruments, constructs, and items; (II) meta-instrument design; (III) initial validation; and (IV) determination of clinimetric properties. Discussion This study is expected to produce a parsimonious and specific meta-instrument for hospital-at-home settings that is capable of integrating functional, nutritional, sleep, fall risk, frailty, and pressure injury assessments. Its implementation will enhance the quality and standardization of nursing documentation, reduce administrative workload, facilitate early risk detection, and free up time for direct patient care. Ultimately, this study will contribute to advancing evidence-based nursing practices in home hospitalization.

Hypertuned boosting approach with Local Binary Pattern and Pivot Distribution Count method feature extractor for glaucoma identification

Abstract Glaucoma, the second largest cause of irreversible blindness worldwide, causes significant damage to the optic nerve. Early diagnosis of glaucoma is crucial since without it, there will be continuous deterioration of vision. Manual detection of glaucoma based on fundus images is a tedious and potentially inaccurate process, making it important to develop computer-aided glaucoma detection systems. This paper introduces a hybrid approach to glaucoma detection that involves the use of Local Binary Pattern (LBP) and Pivot Distribution Count (PDC) feature extraction methods for the analysis of retinal fundus images. LBP is a technique that involves the extraction of texture-based features, whereas PDC is a feature extraction algorithm that involves the extraction of white-pixel intensity and fractal dimension from retinal fundus images. In this study, features were extracted and classified using different machine learning algorithms such as SVM, Decision Trees (DT), Random Forest (RF), KNN, Adaboost, Gradient Boosting, XGboost, Light Gradient Boosting Machine, and CatBoost. Moreover, grid search cross validation, randomized search cross validation, genetic algorithm, and Bayesian optimization were also applied to optimize the performance of LightGBM and Catboost classifiers. The proposed Hybrid LBP-PDC method provided maximum classification accuracy of 97.55% using the CatBoost and LightGBM classifiers. Moreover, we have developed a robust and efficient methodology for the automatic glaucoma screening using the retinal fundus image analysis.

A new species of Dendropsophus (Anura, Hylidae) of the D. ruschii group from the Atlantic Forest in Serra da Mantiqueira, Minas Gerais, Brazil

The Dendropsophus ruschii species group currently comprises two species with disjunct distributions between the Atlantic Forest and the Amazon. Based on an integrative approach combining morphological, acoustic, and molecular data (mtDNA barcoding), we describe a new species from the Serra da Mantiqueira, Minas Gerais, Brazil. Dendropsophus liliae sp. nov. is diagnosed by its small size, rounded digital discs, presence of a calcar appendage, dark red iris, and a distinct white stripe from the snout to the upper eyelid. This discovery expands the known diversity of the group and represents its most inland record within the Atlantic Forest.