Innov Clin Neurosci. 2025 Mar 1;22(1-3):28-50. eCollection 2025 Jan-Mar.

ABSTRACT

BACKGROUND: Acute pain (AP) is a prevalent symptom in hospital settings, affecting up to 84 percent of the patients seeking healthcare services. It significantly impacts an individual's quality of life, with inadequate management resulting in slower recovery, increased cost of care, and a greater risk of developing chronic pain. While pharmacological approaches are effective, they are associated with numerous side effects, including nausea, addiction, and the possibility of fatal overdoses. Given this, virtual reality (VR) offers an innovative avenue to manage AP effectively while minimizing the effects of drugs.

OBJECTIVES: This study aims to map the extent of literature on utilizing VR as a tool for the nonpharmacological management of AP. Specifically, this review attempts to understand the characteristics of the populations using VR for AP management, the technical specifications and mechanisms used to alleviate AP, and the overall effectiveness of VR in managing AP.

METHODS: A scoping review was conducted to identify literature from the following electronic databases: PubMed, ScienceDirect, ERIC, and Google Scholar. To be included in this review, articles had to focus on AP in both adult and pediatric populations and address AP using VR in any clinical or care setting. The search was limited to peer-reviewed, English-language, quantitative research articles published between 2000 and 2024.

RESULTS: A total of 97 studies were identified. Sixty-six percent of studies demonstrated the efficacy of VR as an analgesic, outperforming traditional nonpharmacological approaches (eg, standard of care, mobile phones). Distraction was the most effective VR mechanism for pain management, showing efficacy in 86.9 percent of studies. The most common focus was on needle-related pain (30.9%), followed by dental and perioperative pain (15.5% each). VR was most effective in wound care (87.5%), followed by labor-related (83.33%) and dental (80%) pain.

CONCLUSION: VR is a promising tool for managing AP, offering considerable benefits in terms of patient care, patient experience, and reduction in drug-related side effects. The high efficacy rates for wound care, labor-related pain, and dental pain highlight the potential for VR to be integrated into standard pain management protocols. However, further research, with rigorous research design, is required to standardize VR interventions and optimize their effectiveness across different patient populations and pain contexts.

PMID:40213121 | PMC:PMC11980906

BMC Infect Dis. 2025 Apr 10;25(1):501. doi: 10.1186/s12879-025-10915-5.

ABSTRACT

BACKGROUND: Urinary tract infection (UTI) is one of the most common infectious diseases requiring convenient and appropriate treatment. Nemonoxacin is active against the common pathogens of UTIs. However, more clinical data are required to further support the utility of 500 mg nemonoxacin once daily in treatment of acute lower UTI.

METHODS: We conducted a prospective, single-arm, open-label, multicenter clinical trial in outpatients with acute lower UTI, including uncomplicated UTI (uUTI), recurrent UTI (rUTI), and complicated UTI (cUTI). The patients were prospectively enrolled to take 500 mg nemonoxacin capsules once daily for 3 days (uUTI and rUTI) or 14 days (cUTI). The baseline data, clinical symptoms, laboratory and microbiological tests were analyzed to evaluate the efficacy and safety of nemonoxacin. The clinical and microbiological efficacy were evaluated using the modified intent-to-treat (mITT) set and microbiologically modified intent-to-treat (m-mITT) set, respectively. The comprehensive efficacy and safety were assessed using microbiologically evaluable (ME) set and safety set (SS), respectively.

RESULTS: A total of 404 patients were enrolled. Majority (90.1%) of the patients were females. More than half (66.3%) of the patients were 20 to 40 years of age, and 19.1% were elderly patients (≥ 60 years). Most (83.2%) of the patients reported two or more urinary tract symptoms. The overall clinical efficacy rate of nemonoxacin was 83.9% (292/348) in mITT set, specifically, 83.9% (186/224) in uUTI, 84.4% (81/96) in rUTI and 89.3% (25/28) in cUTI. The overall microbiological efficacy rate was 76.8% (119/155) in m-mITT set. The overall comprehensive efficacy rate was 73.4% (102/139) in ME set. The incidence of clinical adverse reactions was 7.2% (29/404) in the safety set. Most of the adverse events were mild and transient, including pruritus, nausea, dizziness, and headache. No drug-related serious adverse events were observed.

CONCLUSIONS: Nemonoxacin capsules 500 mg once daily is effective, safe, and well-tolerated for treatment of mild-to-moderate acute lower UTIs in adult outpatients.

TRIAL REGISTRATION: Chinese Clinical Trial Registry (ChiCTR2100046585). Registered on May 22, 2021.

PMID:40211176 | DOI:10.1186/s12879-025-10915-5

Nat Commun. 2025 Apr 10;16(1):3420. doi: 10.1038/s41467-025-58804-4.

ABSTRACT

The rise in antimicrobial resistance poses a worldwide threat, reducing the efficacy of common antibiotics. Determining the antimicrobial activity of new chemical compounds through experimental methods remains time-consuming and costly. While compound-centric deep learning models promise to accelerate this search and prioritization process, current strategies require large amounts of custom training data. Here, we introduce a lightweight computational strategy for antimicrobial discovery that builds on MolE (Molecular representation through redundancy reduced Embedding), a self-supervised deep learning framework that leverages unlabeled chemical structures to learn task-independent molecular representations. By combining MolE representation learning with available, experimentally validated compound-bacteria activity data, we design a general predictive model that enables assessing compounds with respect to their antimicrobial potential. Our model correctly identifies recent growth-inhibitory compounds that are structurally distinct from current antibiotics. Using this approach, we discover de novo, and experimentally confirm, three human-targeted drugs as growth inhibitors of Staphylococcus aureus. This framework offers a viable, cost-effective strategy to accelerate antibiotic discovery.

PMID:40210659 | DOI:10.1038/s41467-025-58804-4

Expert Rev Respir Med. 2025 Apr 10. doi: 10.1080/17476348.2025.2491723. Online ahead of print.

ABSTRACT

INTRODUCTION: Respiratory diseases like pneumonia, asthma, and COPD are major global health concerns, significantly impacting morbidity and mortality rates worldwide.

AREAS COVERED: A selective search on PubMed, Google Scholar, and ScienceDirect (up to 2024) focused on AI in diagnosing and treating respiratory conditions like asthma, pneumonia, and COPD. Studies were chosen for their relevance to prediction models, AI-driven diagnostics, and personalized treatments. This narrative review highlights technological advancements, clinical applications, and challenges in integrating AI into standard practice, with emphasis on predictive tools, deep learning for imaging, and patient outcomes.

EXPERT OPINION: Despite these advancements, significant challenges remain in fully integrating AI into pulmonary healthcare. The need for large, diverse datasets to train AI models is critical, and concerns around data privacy, algorithmic transparency, and potential biases must be carefully managed. Regulatory frameworks also need to evolve to address the unique challenges posed by AI in healthcare. However, with continued research and collaboration between technology developers, clinicians, and policymakers, AI has the potential to revolutionize pulmonary healthcare, ultimately leading to more effective, efficient, and personalized care for patients.

PMID:40210489 | DOI:10.1080/17476348.2025.2491723

Best Pract Res Clin Gastroenterol. 2025 Feb;74:101975. doi: 10.1016/j.bpg.2025.101975. Epub 2025 Jan 4.

ABSTRACT

The integration of Artificial Intelligence (AI) in endoscopic ultrasound (EUS) represents a transformative advancement in the early detection and management of biliopancreatic lesions. This review highlights the current state of AI-enhanced EUS (AI-EUS) for diagnosing solid and cystic pancreatic lesions, as well as biliary diseases. AI-driven models, including machine learning (ML) and deep learning (DL), have shown significant improvements in diagnostic accuracy, particularly in distinguishing pancreatic ductal adenocarcinoma (PDAC) from benign conditions and in the characterization of pancreatic cystic neoplasms. Advanced algorithms, such as convolutional neural networks (CNNs), enable precise image analysis, real-time lesion classification, and integration with clinical and genomic data for personalized care. In biliary diseases, AI-assisted systems enhance bile duct visualization and streamline diagnostic workflows, minimizing operator dependency. Emerging applications, such as AI-guided EUS fine-needle aspiration (FNA) and biopsy (FNB), improve diagnostic yields while reducing errors. Despite these advancements, challenges remain, including data standardization, model interpretability, and ethical concerns regarding data privacy. Future developments aim to integrate multimodal imaging, real-time procedural support, and predictive analytics to further refine the diagnostic and therapeutic potential of AI-EUS. AI-driven innovation in EUS stands poised to revolutionize pancreatico-biliary diagnostics, facilitating earlier detection, enhancing precision, and paving the way for personalized medicine in gastrointestinal oncology and beyond.

PMID:40210329 | DOI:10.1016/j.bpg.2025.101975

J Invest Dermatol. 2025 Apr 8:S0022-202X(25)00396-3. doi: 10.1016/j.jid.2025.03.029. Online ahead of print.

NO ABSTRACT

PMID:40210113 | DOI:10.1016/j.jid.2025.03.029

Cell Mol Life Sci. 2025 Apr 10;82(1):156. doi: 10.1007/s00018-025-05652-6.

ABSTRACT

Rare disorders often represent a molecular deviation from hi-fidelity genomic integrity networks and are often perceived as too difficult or unimportant for further mechanistic studies. Here, we synthesize evidence demonstrating how valuable knowledge of biochemical pathways related to rare disorders can be for biomedicine. To this end, we describe several rare congenital lipid, protein, organic acid, and glycan metabolism disorders and discuss how rare phenotypes (such as "extreme responders") and case reports (such as the lenalidomide cases) have provided clues for drug discovery or repurposing. We also discuss how rare disorders such as Gaucher disease and ultra-rare genetic syndromes can provide insights into cancer and mTOR-driven metabolism, respectively. Our discussion highlights the continued value of biochemical pathways and studies in understanding human pathophysiology and drug discovery even in the genomics era.

PMID:40210765 | DOI:10.1007/s00018-025-05652-6

Med Mycol. 2025 Apr 10:myaf030. doi: 10.1093/mmy/myaf030. Online ahead of print.

ABSTRACT

Allergic bronchopulmonary aspergillosis (ABPA) is a significant complication in people with cystic fibrosis (pwCF), driven by hypersensitivity to Aspergillus fumigatus. This study aimed to identify factors associated with the development of ABPA in pwCF, using data from the French CF Registry (FCFR). We conducted a multicenter case-control study utilizing anonymized data from the FCFR, spanning the period from 2016 to 2021. A total of 312 ABPA cases were matched to 936 controls. Various clinical factors, including CFTR variants, nutritional status, glucose disorders, respiratory function, chronic bacterial colonization, and treatments such as antibiotics, corticosteroids, and antifungals, were analyzed. Multivariate analyses and logistic regression models were used to identify associations with ABPA. PwCF who received more frequent intravenous antibiotics (OR = 2.47, P = 0.013), long-term inhaled corticosteroids (OR = 1.82, P < 0.001), or antifungals (OR = 5.83, P < 0.0001) exhibited a higher likelihood of developing ABPA. Additionally, glucose disorders were significantly associated with ABPA (OR = 1.41, P = 0.03). In contrast, a higher BMI (> 25 kg/m²) appeared to be a protective factor (OR = 0.47, P = 0.03). No significant associations were observed with lung function, CFTR variants, or chronic P. aeruginosa colonization. These findings suggest that certain clinical factors and treatments, particularly glucose disorders, frequent antibiotic use, and corticosteroid therapy, are associated with the development of ABPA in pwCF. Notably, a higher BMI may have a protective effect. Further research is needed to explore the underlying mechanisms of these associations and optimize treatment strategies for ABPA in CF, especially as CF therapies continue to evolve.

PMID:40210589 | DOI:10.1093/mmy/myaf030

Arch Bronconeumol. 2025 Mar 28:S0300-2896(25)00111-5. doi: 10.1016/j.arbres.2025.03.014. Online ahead of print.

NO ABSTRACT

PMID:40210501 | DOI:10.1016/j.arbres.2025.03.014

Eur Respir J. 2025 Apr 10:2402435. doi: 10.1183/13993003.02435-2024. Online ahead of print.

ABSTRACT

AIMS: Elexacaftor/tezacaftor/ivacaftor (ELX/TEZ/IVA) was efficacious and safe in children aged 6-11 years with cystic fibrosis (CF) heterozygous for F508del and a minimal function CFTR variant (F/MF genotypes) in a 24-week, placebo-controlled trial. We conducted a 96-week open-label extension study for children who completed the 24-week parent study.

METHODS: In this phase 3b extension study, dosing was based on weight and age with children weighing <30 kg and aged <12 years receiving ELX 100 mg once daily (qd), TEZ 50 mg qd, and IVA 75 mg every 12 h (q12) and children ≥30 kg or ≥12 years receiving ELX 200 mg qd, TEZ 100 mg qd, and IVA 150 mg q12. Primary endpoint was safety and tolerability. Secondary and other efficacy endpoints included absolute changes from parent study baseline in sweat chloride concentration, LCI2.5, ppFEV1, and CFQ-R respiratory domain score.

RESULTS: A total of 120 children were enrolled and dosed. One hundred and eighteen children (98.3%) had adverse events (AEs), which for most were mild (43.3%) or moderate (48.3%) in severity. The most common AEs (≥20% of children) were COVID-19 (58.3%), cough (51.7%), nasopharyngitis (45.0%), pyrexia (40.0%), headache (37.5%), upper respiratory tract infection (30.8%), oropharyngeal pain (26.7%), rhinitis (24.2%), abdominal pain (22.5%), and vomiting (20.0%). Children who transitioned from the placebo and ELX/TEZ/IVA groups of the parent study had improvements from parent study baseline at Week 96 in mean sweat chloride concentration (-57.3 [95% CI: -61.6, -52.9] and -57.5 [95% CI: -62.0, -53.0] mmol·L-1), LCI2..5 (-1.74 [95% CI: -2.09, -1.38] and -2.35 [95% CI: -2.72, -1.97] units), ppFEV1 (6.1 [95% CI: 2.6, 9.7] and 6.9 [95% CI: 3.2, 10.5] percentage points), and CFQ-R respiratory domain score (6.6 [95% CI: 2.5, 10.8] and 2.6 [95% CI: -1.6, 6.8] points).

CONCLUSIONS: ELX/TEZ/IVA treatment was generally safe and well-tolerated, with a safety profile consistent with parent study and older age groups. After starting ELX/TEZ/IVA, children had robust improvements in sweat chloride concentration and lung function that were maintained through 96 weeks. These results demonstrate the safety and durable efficacy of ELX/TEZ/IVA in this pediatric population. (Clinical Trials.gov, NCT04545515; EudraCT, 2020-001404-42).

PMID:40210412 | DOI:10.1183/13993003.02435-2024

Eur Respir J. 2025 Apr 10:2401855. doi: 10.1183/13993003.01855-2024. Online ahead of print.

ABSTRACT

BACKGROUND: In people with cystic fibrosis (pwCF), human nasal epithelial cultures (HNECs) can be used to assess response to CFTR modulators. However, thresholds of in vitro responses that predict clinical benefit remain poorly understood. In this study we describe the concordance between in vitro response in HNECs and clinical outcomes in pwCF harbouring the F508del variant, treated with either Lumacaftor/Ivacaftor, Tezacaftor/Ivacaftor or Elexacaftor/Tezacaftor/Ivacaftor.

METHODS: Response of HNECs to CFTR modulators was assessed by CFTR-mediated chloride current stimulated by forskolin or inhibited by CFTRInh-172 in both pwCF and healthy controls. Clinical response was defined as the change in Forced Expiratory Volume in 1 s (FEV1), Lung Clearance Index (LCI), sweat chloride or the cystic fibrosis questionnaire respiratory domain (CFQr) between baseline and within 3 months after the start of modulator treatment.

RESULTS: In 58 unique in vitro:clinical pairs, in vitro measures of functional rescue correlated with changes in FEV1, LCI and sweat chloride, but not CFQr. The concordance between in vitro response and clinical outcomes was highest when a composite outcome was used. For example, an in vitro response of 10% of healthy controls had positive and negative predictive values of 90.5 and 100%, respectively, for a clinical response in either FEV1, LCI or sweat chloride.

CONCLUSIONS: We identified thresholds of nasal epithelial cell theratype response in pwCF to predict clinical benefit from CFTR modulator therapy. The utility of this therapy testing platform to predict a clinical response improves when multiple clinical outcome measures are combined.

PMID:40210411 | DOI:10.1183/13993003.01855-2024

J Adv Res. 2025 Apr 8:S2090-1232(25)00228-0. doi: 10.1016/j.jare.2025.04.009. Online ahead of print.

ABSTRACT

INTRODUCTION: Radiation enteritis is one of the most frequent clinical complications of radiotherapy (RT), yet few effective strategies currently exist to protect against that. Anoctamin 1 (ANO1) functions both as a chloride channel and a signal transduction protein, influencing numerous pathophysiological processes.

OBJECTIVES: This study aimed to investigate whether targeting ANO1 could mitigate radiation-induced enteritis while enhancing tumor radiosensitivity.

METHODS: Quantitative PCR (qPCR) and Western blot (WB) were used to assess ANO1 expression and its changes after irradiation. Survival rates were recorded to evaluate the effects of ANO1 agonist and inhibitors. A cystic fibrosis transmembrane conductance regulator (CFTR) inhibitor was administered to irradiated mice to investigate the role of chloride channel in radiation protection. qPCR and WB were executed to analyze the expression of relevant ion channels in intestinal epithelium. Functional validation was conducted using inhibitors in mice and 3D organoids. Fluorescent probe kits detected intracellular ion levels and membrane potential, and WB was performed to elucidate the underlying mechanisms. Finally, the radiosensitizing effect of CaCCinh-A01 was assessed in colorectal cancer (CRC) cells and validated in in vivo models.

RESULTS: Blocking the calcium-activated chloride channel (CaCC) protein ANO1, which is highly expressed in the colon, protects the intestine from radiation-induced damage. The ANO1 inhibitor CaCCinh-A01, suppresses CaCC currents, downregulates ANO1 protein expression, alleviates radiation-induced intestine injury, and enhances the radiosensitivity of CRC. Mechanistically, CaCCinh-A01 upregulates Na-K-Cl Cotransporter 1 (NKCC1) protein expression, leading to an increase in intracellular Cl- concentration and the inhibition of membrane depolarization in MODE-K cells. This subsequently inhibits p53-mediate DNA damage signaling, ultimately alleviating ionizing radiation-induced intestinal injury.

CONCLUSION: These findings suggest that targeting ANO1 not only alleviates radiation-induced intestinal injury in mice but also enhances CRC radiosensitivity. Thus, ANO1 represents a promising therapeutic target for mitigating the side effects of RT in CRC patients.

PMID:40210148 | DOI:10.1016/j.jare.2025.04.009

Respir Med. 2025 Apr 8:108091. doi: 10.1016/j.rmed.2025.108091. Online ahead of print.

ABSTRACT

BACKGROUND: Cystic fibrosis (CF) is a complex genetic disorder necessitating extensive treatment regimens leading to significant medication burden. The recent use of modulator therapies have questioned the necessity of traditional CF treatments, prompting re-evaluation of strategies to reduce treatment burden. This study aimed to identify the barriers and enablers to deprescribing from the perspectives of doctors, nurses, and pharmacists caring for people with CF (PwCF).

METHODS: A qualitative study design employing semi-structured interviews was utilised. Healthcare practitioners (HCPs) across Australia were recruited and interviewed. Interviews were transcribed and analysed using NVivo 1.3 software, guided by an existing framework focusing on self-efficacy, feasibility, inertia, and awareness.

RESULTS: Eleven HCP participated (doctors, n=3, nurses, n=4, pharmacists, n=4). Low self-efficacy was the most prominent barrier to deprescribing, founded on a perceived lack of evidence. Feasibility was an enabler when patient factors were present, particularly PwCF's experiences of reducing medications independently. Likewise, the presence of pharmacists in CF clinics and multidisciplinary team meetings were identified as facilitators. Inertia to continue entrenched prescribing habits and fear of adverse outcomes deterred deprescribing. Similarly, HCPs reported having little awareness of the need for deprescribing in daily practice, as their primary focus was on addressing acute problems.

CONCLUSIONS: Enhancing self-efficacy through evidence-based guidelines and increasing feasibility by fostering collaborative approaches among HCPs and PwCF may improve deprescribing practices in CF care. As evidence on the benefits and safety of deprescribing grows, it should be integrated into clinical guidelines to alleviate medication burden and improve quality of life for PwCF.

PMID:40210134 | DOI:10.1016/j.rmed.2025.108091

J Heart Lung Transplant. 2025 Apr 8:S1053-2498(25)01899-6. doi: 10.1016/j.healun.2025.04.001. Online ahead of print.

ABSTRACT

BACKGROUND: Childhood interstitial lung disease (chILD) is heterogeneous, associated with significant morbidity and can cause organ failure. In these cases, lung transplantation (LuTx) is a treatment option. Data on indications and outcome after LuTx for chILD is limited. We compared characteristics of LuTx for chILD to the indications cystic fibrosis (CF) and pulmonary hypertension (PH).

METHODS: chILD-patients <18 years who underwent LuTx at our center between Jan 1st, 2011 and Sep 30th, 2023, were retrospectively analysed and divided into two groups depending on their age at disease manifestation: Children in the chILD A group predominantly became ill during the first two years of life, chILD B patients thereafter. Outcomes were compared to patients with CF and PH.

RESULTS: 101 children were included (chILD A 12; chILD B 19; CF 49; PH 21). Patients in the chILD A group were younger (mean age 1.5 vs., 12.9, 15.2, 10.9 years) and frequently required mechanical ventilation before LuTx (41.7%, vs. 10.5%, 2%, 9.5%, respectively). Their median ICU stay (23 vs. 4, 2, 13 days) and median hospital stay (48 vs. 27, 30, 42 days) after LuTx was longer. Patients with chILD B had the lowest pre-transplant ICU requirement (21.1% vs. 66.7% for chILD A, 30.6% for CF and 47.6% for PH) and short median hospital stay. Five year survival was comparable in all groups (80.2%, 86.5%, 80.4%, and 81.2%).

CONCLUSION: LuTx for patients with chILD shows favourable outcome, although younger chILD A patients had a higher pre-transplant morbidity and longer ICU and hospital stay surrounding the transplantation.

PMID:40209866 | DOI:10.1016/j.healun.2025.04.001

Sci Rep. 2025 Apr 10;15(1):12296. doi: 10.1038/s41598-025-96974-9.

ABSTRACT

The widespread adoption of cloud services has posed several challenges, primarily revolving around energy and resource efficiency. Integrating cloud and fog resources can help address these challenges by improving fog-cloud computing environments. Nevertheless, the search for optimal task allocation and energy management in such environments continues. Existing studies have introduced notable solutions; however, it is still a challenging issue to efficiently utilize these heterogeneous cloud resources and achieve energy-efficient task scheduling in fog-cloud of things environment. To tackle these challenges, we propose a novel ML-based EcoTaskSched model, which leverages deep learning for energy-efficient task scheduling in fog-cloud networks. The proposed hybrid model integrates Convolutional Neural Networks (CNNs) with Bidirectional Log-Short Term Memory (BiLSTM) to enhance energy-efficient schedulability and reduce energy usage while ensuring QoS provisioning. The CNN model efficiently extracts workload features from tasks and resources, while the BiLSTM captures complex sequential information, predicting optimal task placement sequences. A real fog-cloud environment is implemented using the COSCO framework for the simulation setup together with four physical nodes from the Azure B2s plan to test the proposed model. The DeFog benchmark is used to develop task workloads, and data collection was conducted for both normal and intense workload scenarios. Before preprocessing the data was normalized, treated with feature engineering and augmentation, and then split into training and test sets. To evaluate performance, the proposed EcoTaskSched model demonstrated superiority by significantly reducing energy consumption and improving job completion rates compared to baseline models. Additionally, the EcoTaskSched model maintained a high job completion rate of 85%, outperforming GGCN and BiGGCN. It also achieved a lower average response time, and SLA violation rates, as well as increased throughput, and reduced execution cost compared to other baseline models. In its optimal configuration, the EcoTaskSched model is successfully applied to fog-cloud computing environments, increasing task handling efficiency and reducing energy consumption while maintaining the required QoS parameters. Our future studies will focus on long-term testing of the EcoTaskSched model in real-world IoT environments. We will also assess its applicability by integrating other ML models, which could provide enhanced insights for optimizing scheduling algorithms across diverse fog-cloud settings.

PMID:40211053 | DOI:10.1038/s41598-025-96974-9

Sci Rep. 2025 Apr 10;15(1):12334. doi: 10.1038/s41598-025-97034-y.

ABSTRACT

Stroke is a main risk to life and fitness in current society, particularly in the aging population. Also, the stroke is recognized as a cerebrovascular accident. It contains a nervous illness, which can result from haemorrhage or ischemia of the brain veins, and regular mains to assorted motor and cognitive damages that cooperate with functionality. Screening for stroke comprises physical examination, history taking, and valuation of risk features like age or certain cardiovascular illnesses. Symptoms and signs of stroke include facial weakness. Even though computed tomography (CT) and magnetic resonance imaging (MRI) are standard diagnosis techniques, artificial intelligence (AI) systems have been constructed based on these methods, which deliver fast detection. AI is gaining high attention and is being combined into numerous areas with medicine to enhance the accuracy of analysis and the quality of patient care. This paper proposes an enhancing neurological disease diagnostics fusion of transfer learning for acute brain stroke prediction using facial images (ENDDFTL-ABSPFI) method. The proposed ENDDFTL-ABSPFI method aims to enhance brain stroke detection and classification models using facial imaging. Initially, the image pre-processing stage applies the fuzzy-based median filter (FMF) model to eliminate the noise in input image data. Furthermore, fusion models such as Inception-V3 and EfficientNet-B0 perform the feature extraction. Moreover, the hybrid of convolutional neural network and bidirectional long short-term memory (CNN-BiLSTM) model is employed for the brain stroke classification process. Finally, the multi-objective sailfish optimization (MOSFO)-based hyperparameter selection process is carried out to optimize the classification outcomes of the CNN-BiLSTM model. The simulation validation of the ENDDFTL-ABSPFI technique is investigated under the Kaggle dataset concerning various measures. The comparative evaluation of the ENDDFTL-ABSPFI technique portrayed a superior accuracy value of 98.60% over existing methods.

PMID:40210979 | DOI:10.1038/s41598-025-97034-y

Sci Rep. 2025 Apr 10;15(1):12315. doi: 10.1038/s41598-025-95564-z.

ABSTRACT

Recognition is an extremely high-level computer vision evaluating task that primarily involves categorizing objects by identifying and evaluating their key distinguishing characteristics. Categorization is important in botany because it makes comprehending the relationships between various flower species easier to organize. Since there is a great deal of variability among flower species and some flower species may resemble one another, classifying flowers may become difficult. An appropriate technique for classification that uses deep learning technology is vital to categorize flower species effectively. This leads to the design of proposed Sobel Restricted Boltzmann VGG19 (SRB-VGG19), which is highly effective at classifying flower species and is inspired by VGG19 model. This research primarily contributes in three ways. The first contribution deals with the dataset preparation by means of feature extraction through the use of the Sobel filter and the Restricted Boltzmann Machine (RBM) neural network approach through unsupervised learning. The second contribution focuses on improving the VGG19 and DenseNet model for supervised learning, which is used to classify species of flowers into five groups. The third contribution overcomes the issue of data poisoning attack through Fast Gradient Sign Method (FGSM) to the input data samples. The FGSM attack was addressed by forming the Adversarial Noise Layer in the dense block. The Flowers Recognition KAGGLE dataset preprocessing was done to extract only the important features using the Sobel filter that computes the image intensity gradient at every pixel in the image. The Sobel filtered image was then applied to RBM to generate RBM Component Vectorized Flower images (RBMCV) which was divided into 3400 training and 850 testing images. To determine the best CNN, the training pictures are fitted with the existing CNN models. According to experiment results, VGG19 and DenseNet can classify floral species with an accuracy of above 80%. So, VGG19 and DenseNet were fine tuned to design the proposed SRB-VGG19 model. The Novelty of this research was explored by designing two sub models SRB-VGG FCL model, SRB-VGG Dense model and validating the security countermeasure of the model through FGSM attack. The proposed SRB-VGG19 initially begins by forming the RBMCV input images that only includes the essential flower edges. The RBMCV Flower images are trained with SRB-VGG FCL model, SRB-VGG Dense model and the performance analysis was done. When compared to the current deep learning models, the implementation results show that the proposed SRB-VGG19 Dense Model classifies the flower species with a high accuracy of 98.65%.

PMID:40210949 | DOI:10.1038/s41598-025-95564-z

Sci Rep. 2025 Apr 10;15(1):12344. doi: 10.1038/s41598-025-95895-x.

ABSTRACT

Fault diagnosis of wind turbine bearings is crucial for ensuring operational safety and reliability. However, traditional serial-structured deep learning models often fail to simultaneously extract spatio- temporal features from fault signals in noisy environments, leading to critical information loss. To address this limitation, this paper proposes a Wind Turbine Bearing Fault Diagnosis Model Based on Efficient Cross Space Multiscale CNN Transformer Parallelism (ECMCTP). The model first transforms one-dimensional vibration signals into two-dimensional time-frequency images using Continuous Wavelet Transform (CWT). Subsequently, parallel branches are employed to extract spatio-temporal features: the Convolutional Neural Network (CNN) branch integrates a multiscale feature extraction module, a Reversed Residual Structure (RRS), and an Efficient Multiscale Attention (EMA) mechanism to enhance local and global feature extraction capabilities; the Transformer branch combines Bidirectional Gated Recurrent Units (BiGRU) and Transformer to capture both local temporal dynamics and long-term dependencies. Finally, the features from both branches are concatenated along the channel dimension and classified using a softmax classifier. Experimental results on two publicly available bearing datasets demonstrate that the proposed model achieves 100% accuracy under noise-free conditions and maintains superior noise robustness under low signal-to-noise ratio (SNR) conditions, showcasing excellent robustness and generalization capabilities.

PMID:40210923 | DOI:10.1038/s41598-025-95895-x

Sci Rep. 2025 Apr 10;15(1):12245. doi: 10.1038/s41598-025-96557-8.

ABSTRACT

The integration of Artificial Intelligence (AI) techniques with medical kits has revolutionized disease diagnosis, enabling rapid and accurate identification of various conditions. We developed a novel deep learning model, namely DeepATsers based on a combination of CNN and GAN to employ a one-pot SERS biosensor to rapidly detect COVID-19 infection. The model accurately identifies each SARS-CoV-2 protein (S protein, N protein, VLP protein, Streptavidin protein, and blank signal) from its experimental fingerprint-like spectral data introduced in this study. Several augmentation techniques such as EMSA, Gaussian-noise, GAN, and K-fold cross-validation, and their combinations were utilized for the SERS spectral dataset generalization and prevented model overfitting. The original experimental dataset of 126 spectra was augmented to 780 spectra that resembled the original set by using GAN with a low KL divergence value of 0.02. This significantly improves the average accuracy of protein classification from 0.6000 to 0.9750. The deep learning model deployed optimal hyperparameters and outperformed in most measurements comparing supervised machine learning methods such as RF, GBM, SVM, and KNN, both with and without augmented spectral datasets. For model training, a whole range of spectra wavenumbers ([Formula: see text] to [Formula: see text]) as well as wavenumbers ([Formula: see text] and [Formula: see text]) only for fingerprint peak spectra were employed. The former led to highly accurate 0.9750 predictions in comparison to 0.4318 for the latter one. Finally, independent experimental spectra of SARS-CoV-2 Omicron variant were used in the model verification. Thus, DeepATsers can be considered a robust, generalized, and generative deep learning framework for 1D SERS spectral datasets of SARS-CoV-2.

PMID:40210912 | DOI:10.1038/s41598-025-96557-8

Sci Rep. 2025 Apr 11;15(1):12377. doi: 10.1038/s41598-025-92734-x.

ABSTRACT

Remotely sensed data have increasingly been used to improve flood mapping and modelling, providing much of the required information for delineating flood-affected areas and damage assessment. SAR satellite-based solutions have been proven to be among the most effective tools for flood extent detection because of their large spatial coverage, reasonable revisit time, and ability to penetrate through clouds and provide a full view of the Earth's surface regardless of atmospheric or lighting conditions. This research proposes an innovative approach to applying an attention U-Net on SAR datasets to detect and extract flood extent maps. The approach was developed and validated using the datasets collected during a flooding event after extreme rainfall hit the eastern coast of Australia on 18 March 2021. Sentinel-1 (S1) ground range detected (GRD) and single look complex (SLC) descending track of the pre-and post-event on the 12th and 24th of March 2021, have been pre-processed, coincide with labels area of the flood extension have been carefully delineated to feed the model. The attention U-Net approach on S1 cross-polarization of VH provided promising results to identify the flood extent with precision, recall, and F1-score of 0.90, 0.88, 0.89 correspondingly. At the same time the result of the unseen frame achieved precision, recall, and F1-score, of 0.63, 0.59, and 0.61 respectively. The approach was also successfully employed to detect flood extent over the study area in July 2022, and the proposed model gave an outstanding accuracy of over 0.84 F1-score.

PMID:40210907 | DOI:10.1038/s41598-025-92734-x