Int J Mol Sci. 2025 May 8;26(10):4487. doi: 10.3390/ijms26104487.

ABSTRACT

Accurate genetic diagnosis is essential for appropriate treatment in cystic fibrosis (CF). Large copy number variants like duplications in the CFTR gene are rare and often classified as variants of uncertain significance (VUSs) due to unknown characteristics of the inserted material, complicating diagnosis and treatment decisions. We identified a previously uncharacterized exon 22 duplication (CFTRdup22) in the CFTR gene in two anamnestically unrelated people with CF, both exhibiting a mild phenotype. Initial classification as a VUS was based on standard genetic testing. We employed a custom next-generation sequencing (NGS) panel to determine the exact breakpoints of the duplication and conducted mRNA sequencing to confirm its effect on splicing. DNA and RNA analyses allowed for precise breakpoint determination, confirming that the duplication was in tandem and the reading frame remained intact. This, as well as a residual CFTRdup22 function of ~30% as measured via intestinal current measurement, is consistent with a clinically milder CF phenotype. Collectively, the precise characterization of the variants' breakpoints, localization and orientation enabled us to reclassify the variant as likely pathogenic. This study highlights the importance of advanced genetic techniques, such as NGS and breakpoint analysis, in accurately identifying CF-causing variants. It underscores the importance of a comprehensive approach and persistence when suspecting a specific genetic condition. This can aid in reclassifying VUSs, providing a definitive diagnosis for the affected family and enabling appropriate therapeutic interventions, including the use of CFTR modulators.

PMID:40429633 | DOI:10.3390/ijms26104487

J Clin Med. 2025 May 16;14(10):3492. doi: 10.3390/jcm14103492.

ABSTRACT

People with CF (pwCF) have a significant risk for pulmonary infections with non-tuberculous mycobacteria (NTM), particularly Mycobacterium abscessus (Mab). Mab is an emerging pathogen, which causes pulmonary infections in patients with chronic lung diseases, particularly CF; Mab pulmonary disease leads to progressive pulmonary dysfunction and increased morbidity and mortality. Despite advances in CF care, including CFTR modulators (CFTRm), Mab continues to pose a therapeutic challenge, with significant long-term medical burden. This review provides insights into the complex host-pathogen interplay of Mab infections in pwCF. It provides a detailed overview of Mab bacterial virulence factors, including biofilm formation, secretion systems, the virulence-associated rough morphotype, and antibiotic resistance mechanisms. This review also summarizes features conferring susceptibility of the CF host to Mab infections, alongside the contribution of the CF-host environment to the pathogenesis of Mab infection, such as antibiotic-derived microbial selection, within-host mycobacterial evolution, and interactions with co-pathogens such as Pseudomonas aeruginosa (PA). Finally, the therapeutic implications and novel treatments for Mab are discussed, considering the complex host-pathogen interplay.

PMID:40429486 | DOI:10.3390/jcm14103492

Medicina (Kaunas). 2025 Apr 26;61(5):808. doi: 10.3390/medicina61050808.

ABSTRACT

Background and Objective: This study's objective was to determine the impact of the percentage of lung tissue within the normal density range (PLND) on exacerbations and hospitalizations compared with the modified Bhalla and Reiff scores. We also investigated the effects of these measures on pulmonary function tests (PFTs). Materials and Methods: This retrospective analysis involved adult cystic fibrosis (CF) patients who had thoracic computed tomography (CT) while in a stable clinical condition. A dedicated radiologist analyzed CT images and conducted modified Bhalla, Reiff, and PLND assessments. We analyzed the exacerbations and hospitalizations in the year after the CT scan. We also examined PFTs at the time of the CT scan and one year later. Results: This study's population consisted of 63 subjects (33 men), with a median age of 23.2 years. The median modified Bhalla score was 9.0 (IQR: 7.0-12.0), the median Reiff score was 11.0 (IQR: 8.0-15.0), and the median PLND was 79.4% (IQR: 74.5-82.0). The Bhalla score had the strongest relationship with both the number of exacerbations (p < 0.001, r: -0.559) and hospitalizations the following year (p < 0.001, r: -0.636), followed by the PLND score and the Reiff score. Youden's index shows that the optimum cut-off values for hospitalization at ≤2 and >2 are 6.5 for the modified Bhalla score, 13.5 for the Reiff score, and 76.5% for the PLND. Conclusions: The measurement of PLND may serve as a predictor for exacerbation and hospitalization rates, aligning with the modified Bhalla and Reiff scores, and shows potential for application in follow-up assessments.

PMID:40428766 | DOI:10.3390/medicina61050808

Genes (Basel). 2025 May 20;16(5):603. doi: 10.3390/genes16050603.

ABSTRACT

BACKGROUND/OBJECTIVES: Chronic pancreatitis (CP) is a progressive inflammatory condition of the pancreas that leads to irreversible changes in pancreatic structure. The pancreatic α and β cells secrete hormones such as insulin and glucagon into the bloodstream. The pancreatic acinar cells secrete digestive enzymes that break down macromolecules. When these digestive enzymes do not function properly, maldigestion, malabsorption, and malnutrition may result. Presented here is a case study of an individual newly diagnosed with chronic pancreatitis, along with a genetic analysis of his son and an in-silico analysis of two of the variant proteins.

METHODS: This study was conducted using human subjects, namely, the proband (father) and his son. Medical genetic testing of the proband (father) identified the presence of two variants in the cystic fibrosis transmembrane receptor gene (CFTR): variant rs213950, resulting in a single amino acid change (p. Val470Met), and variant rs74767530, a nonsense variant (Arg1162Ter) with known pathogenicity for cystic fibrosis. Medical testing also revealed an additional missense variant, rs515726209 (Ala73Thr), in the CTRC gene. Cheek cell DNA was collected from both the proband and his son to determine the inheritance pattern and identify any additional variants. A variant in the human leukocyte antigen (rs7454108), which results in the HLA-DQ8 haplotype, was examined in both the proband and his son due to its known association with autoimmune disease, a condition also linked to chronic pancreatitis. In silico tools were subsequently used to examine the impact of the identified variants on protein function.

RESULTS: Heterozygosity for all variants originally identified through medical genetic testing was confirmed in the proband and was absent in the son. Both the proband and his son were found to have the DRB1*0301 (common) haplotype for the HLA locus. However, the proband was also found to carry a linked noncoding variant, rs2647088, which was absent in the son. In silico analysis of variant rs213950 (Val470Met) in CFTR and rs515726209 (Ala73Thr) in CTRC revealed distinct changes in predicted ligand binding for both proteins, which may affect protein function and contribute to the development of CP.

CONCLUSIONS: This case study of a proband and his son provides additional evidence for a polygenic inheritance pattern in CP. The results also highlight new information on the role of the variants on protein function, suggesting additional testing of ligand binding for these variants should be done to confirm the functional impairments.

PMID:40428425 | DOI:10.3390/genes16050603

Antibiotics (Basel). 2025 May 10;14(5):486. doi: 10.3390/antibiotics14050486.

ABSTRACT

BACKGROUND: Mycobacterium abscessus (MABS) is an opportunistic pathogen that causes chronic, difficult-to-treat pulmonary infections, particularly in people with cystic fibrosis (PwCF), leading to rapid lung function decline and increased morbidity and mortality. Treatment is particularly challenging due to the pathogen's resistance mechanisms and the need for prolonged multidrug therapy, which is characterized by poor clinical outcomes and highlights the urgent need for novel therapeutic strategies. Imipenem/relebactam, a novel β-lactam-β-lactamase inhibitor combination, demonstrates in vitro activity against resistant MABS strains and effective pulmonary penetration. Prior research indicates synergistic activity of imipenem with various antibiotics against M. abscessus.

OBJECTIVES: This study aims to evaluate the in vitro activity of imipenem/relebactam, alone and in combination with various antibiotics, against MABS clinical isolates from PwCF (n = 28).

METHODS: Susceptibility and synergy were assessed using broth microdilution and checkerboard assays. Extracellular time-kill assays were performed to evaluate the bactericidal activity of synergistic three-drug combinations containing imipenem/relebactam.

RESULTS: Imipenem/relebactam demonstrated potent in vitro activity against clinical MABS isolates, exhibiting substantial synergy with cefuroxime, cefdinir, amoxicillin, and cefoxitin. Rifabutin, azithromycin, moxifloxacin, clofazimine, and minocycline also demonstrated additive effects with imipenem/relebactam. Extracellular time-kill assays identified imipenem/relebactam + cefoxitin + rifabutin and imipenem/relebactam + cefoxitin + moxifloxacin as the most effective combinations.

CONCLUSIONS: These findings suggest that imipenem/relebactam may offer a significant advancement in the management of MABS infections in PwCF. The promising efficacy of multidrug regimens combining imipenem/relebactam with agents like cefoxitin, azithromycin, moxifloxacin, clofazimine, and rifabutin highlights potential therapeutic strategies.

PMID:40426552 | DOI:10.3390/antibiotics14050486

Antibiotics (Basel). 2025 Apr 23;14(5):427. doi: 10.3390/antibiotics14050427.

ABSTRACT

Pseudomonas aeruginosa, a multidrug-resistant pathogen, significantly impacts patients with chronic respiratory conditions like cystic fibrosis (CF) and non-CF chronic suppurative lung disease (CSLD), contributing to progressive lung damage and poor clinical outcomes. This bacterium thrives in the airway environments of individuals with impaired mucociliary clearance, leading to persistent infections and increased morbidity and mortality. Despite advancements in management of these conditions, treatment failure remains common, emphasising the need for alternative or adjunctive treatment strategies. Bacteriophage therapy, an emerging approach utilising viruses that specifically target bacteria, offers a potential solution to combat P. aeruginosa infections resistant to conventional antibiotics. This review examines the prevalence and disease burden of P. aeruginosa in CF and CSLD, explores the mechanisms behind antibiotic resistance, the promising role of bacteriophage therapy and clinical trials in this sphere.

PMID:40426494 | DOI:10.3390/antibiotics14050427

Respirology. 2025 May 28. doi: 10.1111/resp.70057. Online ahead of print.

ABSTRACT

BACKGROUND AND OBJECTIVE: Iriscope, a 1.3 mm video endoscopic probe introduced through an r-EBUS catheter, allows for the direct visualisation of small peripheral pulmonary nodules (PPNs). This study assessed the ability of physicians with different levels of experience in bronchoscopy, and the ability of artificial intelligence (AI) to predict the malignant nature of small PPNs during Iriscope peripheral endoscopy.

METHODS: Patients undergoing bronchoscopy with r-EBUS and Iriscope for peripheral PPNs < 20 mm with a definite diagnosis were analysed. Senior and Junior physicians independently interpreted video-recorded Iriscope sequences, classifying them as tumoral (malignant) or non-tumoral, blind to the final diagnosis. A deep learning (DL) model was also trained on Iriscope images and tested on a different set of patients for comparison with human interpretation. Diagnostic accuracy, sensitivity, specificity, and F1 score were calculated.

RESULTS: Sixty-one patients with small PPNs (median size 15 mm, IQR: 11-20 mm) were included. The technique allowed for the direct visualisation of the lesions in all cases. The final diagnosis was cancer for 37 cases and a benign lesion in 24 cases. Senior physicians outperformed junior physicians in recognising tumoral Iriscope images, with a balanced accuracy of 85.4% versus 66.7%, respectively, when compared with the final diagnosis. The DL model outperformed junior physicians with a balanced accuracy of 71.5% but was not superior to senior physicians.

CONCLUSION: Iriscope could be a valuable tool in PPNs management, especially for experienced operators. Applied to Iriscope images, DL could enhance overall performance of less experienced physicians in diagnosing malignancy.

PMID:40433758 | DOI:10.1111/resp.70057

Front Neurol. 2025 May 13;16:1536751. doi: 10.3389/fneur.2025.1536751. eCollection 2025.

ABSTRACT

BACKGROUND: Accurate preoperative grading of meningiomas is crucial for selecting the most suitable treatment strategies and predicting patient outcomes. Traditional MRI-based assessments are often insufficient to distinguish between low- and high-grade meningiomas reliably. Deep learning (DL) models have emerged as promising tools for automated histopathological grading using imaging data. This systematic review and meta-analysis aimed to comprehensively evaluate the diagnostic performance of deep learning (DL) models for meningioma grading.

METHODS: This study was conducted in accordance with the PRISMA-DTA guidelines and was prospectively registered on the Open Science Framework. A systematic search of PubMed, Scopus, and Web of Science was performed up to March 2025. Studies using DL models to classify meningiomas based on imaging data were included. A random-effects meta-analysis was used to pool sensitivity, specificity, accuracy, and area under the receiver operating characteristic curve (AUC). A bivariate random-effects model was used to fit the summary receiver operating characteristic (SROC) curve. Study quality was assessed using the Newcastle-Ottawa Scale, and publication bias was evaluated using Egger's test.

RESULTS: Twenty-seven studies involving 13,130 patients were included. The pooled sensitivity was 92.31% (95% CI: 92.1-92.52%), specificity 95.3% (95% CI: 95.11-95.48%), and accuracy 97.97% (95% CI: 97.35-97.98%), with an AUC of 0.97 (95% CI: 0.96-0.98). The bivariate SROC curve demonstrated excellent diagnostic performance, characterized by a relatively narrow 95% confidence interval despite moderate to high heterogeneity (I2 = 79.7%, p < 0.001).

CONCLUSION: DL models demonstrate high diagnostic accuracy for automatic meningioma grading and could serve as valuable clinical decision-support tools.

SYSTEMATIC REVIEW REGISTRATION: DOI: 10.17605/OSF.IO/RXEBM.

PMID:40433621 | PMC:PMC12108801 | DOI:10.3389/fneur.2025.1536751

Front Artif Intell. 2025 May 13;8:1583459. doi: 10.3389/frai.2025.1583459. eCollection 2025.

ABSTRACT

This review provides a thorough and organized overview of machine learning (ML) applications in predicting heart disease, covering technological advancements, challenges, and future prospects. As cardiovascular diseases (CVDs) are the leading cause of global mortality, there is an urgent demand for early and precise diagnostic tools. ML models hold considerable potential by utilizing large-scale healthcare data to enhance predictive diagnostics. To systematically investigate this field, the literature is organized into five thematic categories such as "Heart Disease Detection and Diagnostics," "Machine Learning Models and Algorithms for Healthcare," "Feature Engineering and Optimization Techniques," "Emerging Technologies in Healthcare," and "Applications of AI Across Diseases and Conditions." The review incorporates performance benchmarking of various ML models, highlighting that hybrid deep learning (DL) frameworks, e.g., convolutional neural network-long short-term memory (CNN-LSTM) consistently outperform traditional models in terms of sensitivity, specificity, and area under the curve (AUC). Several real-world case studies are presented to demonstrate the successful deployment of ML models in clinical and wearable settings. This review showcases the progression of ML approaches from traditional classifiers to hybrid DL structures and federated learning (FL) frameworks. It also discusses ethical issues, dataset limitations, and model transparency. The conclusions provide important insights for the development of artificial intelligence (AI) powered, clinically applicable heart disease prediction systems.

PMID:40433606 | PMC:PMC12106346 | DOI:10.3389/frai.2025.1583459

Front Artif Intell. 2025 May 13;8:1561281. doi: 10.3389/frai.2025.1561281. eCollection 2025.

ABSTRACT

High-resolution digital elevation models (HRDEMs) from LiDAR and InSAR technologies have significantly improved the accuracies of mapping hydrographic features such as river boundaries, streamlines, and waterbodies over large areas. However, drainage crossings that facilitate the passage of drainage flows beneath roads are not often represented in HRDEMs, resulting in erratic or distorted hydrographic features. At present, drainage crossing datasets are largely missing or available with variable quality. While previous studies have investigated basic convolutional neural network (CNN) models for drainage crossing characterization, it remains unclear if advanced deep learning models will improve the accuracy of drainage crossing classification. Although HRDEM-derived geomorphological features have been identified to enhance feature extraction in other hydrography applications, the contributions of these features to drainage crossing image classification have yet to be sufficiently investigated. This study develops advanced CNN models, EfficientNetV2, using four co-registered 1-meter resolution geomorphological data layers derived from HRDEMs for drainage crossing classification. These layers include positive openness (POS), geometric curvature, and two topographic position index (TPI) layers utilizing 3 × 3 and 21 × 21 cell windows. The findings reveal that the advanced CNN models with HRDEM, TPI (21 × 21), and a combination of HRDEM, POS, and TPI (21 × 21) improve classification accuracy in comparison to the baseline model by 3.39, 4.27, and 4.93%, respectively. The study culminates in explainable artificial intelligence (XAI) for evaluating those most critical image segments responsible for characterizing drainage crossings.

PMID:40433605 | PMC:PMC12106317 | DOI:10.3389/frai.2025.1561281

Uncertain Safe Util Mach Learn Med Imaging (2024). 2025;15167:3-13. doi: 10.1007/978-3-031-73158-7_1. Epub 2024 Oct 3.

ABSTRACT

Supervised learning has become the dominant paradigm in computer-aided diagnosis. Generally, these methods assume that the training labels represent "ground truth" information about the target phenomena. In actuality, the labels, often derived from human annotations, are noisy/unreliable. This aleoteric uncertainty poses significant challenges for modalities such as electroencephalography (EEG), in which "ground truth" is difficult to ascertain without invasive experiments. In this paper, we propose a novel Bayesian framework to mitigate the effects of aleoteric label uncertainty in the context of supervised deep learning. Our target application is EEG-based epileptic seizure detection. Our framework, called BUNDL, leverages domain knowledge to design a posterior distribution for the (unknown) "clean labels" that automatically adjusts based on the data uncertainty. Crucially, BUNDL can be wrapped around any existing detection model and trained using a novel KL divergence-based loss function. We validate BUNDL on both a simulated EEG dataset and the Temple University Hospital (TUH) corpus using three state-of-the-art deep networks. In all cases, BUNDL improves seizure detection performance over existing noise mitigation strategies.

PMID:40433566 | PMC:PMC12107695 | DOI:10.1007/978-3-031-73158-7_1

Front Neurorobot. 2025 May 13;19:1568811. doi: 10.3389/fnbot.2025.1568811. eCollection 2025.

ABSTRACT

The number of music of different genres is increasing year by year, and manual classification is costly and requires professionals in the field of music to manually design features, some of which lack the generality of music genre classification. Deep learning has had a large number of scientific research results in the field of music classification, but the existing deep learning methods still have the problems of insufficient extraction of music feature information, low accuracy rate of music genres, loss of time series information, and slow training. To address the problem that different music durations affect the accuracy of music genre classification, we form a Log Mel spectrum with music audio data of different cut durations. After discarding incomplete audio, we design data enhancement with different slicing durations and verify its effect on accuracy and training time through comparison experiments. Based on this, the audio signal is divided into frames, windowed and short-time Fourier transformed, and then the Log Mel spectrum is obtained by using the Mel filter and logarithmic compression. Aiming at the problems of loss of time information, insufficient feature extraction, and low classification accuracy in music genre classification, firstly, we propose a Res-Transformer model that fuses the residual network with the Transformer coding layer. The model consists of two branches, the left branch is an improved residual network, which enhances the spectral feature extraction ability and network expression ability and realizes the dimensionality reduction; the right branch uses four Transformer coding layers to extract the time-series information of the Log Mel spectrum. The output vectors of the two branches are spliced and input into the classifier to realize music genre classification. Then, to further improve the classification accuracy of the model, we propose the TS-Resformer model based on the Res-Transformer model, combined with different attention mechanisms, and design the time-frequency attention mechanism, which employs different scales of filters to fully extract the low-level music features from the two dimensions of time and frequency as the input to the time-frequency attention mechanism, respectively. Finally, experiments show that the accuracy of this method is 90.23% on the FMA-small dataset, which is an improvement in classification accuracy compared with the classical model.

PMID:40433555 | PMC:PMC12106318 | DOI:10.3389/fnbot.2025.1568811

Front Plant Sci. 2025 May 13;16:1550302. doi: 10.3389/fpls.2025.1550302. eCollection 2025.

ABSTRACT

Global climate change and ecological degradation highlight the urgency of dealing with agricultural waste and ecological restoration. Traditional pollutant monitoring and ecological restoration methods face challenges in accuracy and adaptability, especially when dealing with complex environmental data. This paper proposes the Bio-DANN model, which combines biogeochemical models and deep learning techniques to improve the accuracy of pollutant monitoring and ecological restoration prediction. The model uses deep neural networks (DNNs) and attention mechanisms to process multidimensional environmental data in various agricultural and ecological scenarios in real time. Experimental results based on Open Soil Data and NEON datasets show that Bio-DANN performs well in pollutant prediction, with mean square errors (MSE) of 0.012 and 0.018, root mean square errors (RMSE) of 0.109 and 0.134, and accuracy of 0.92 and 0.90, respectively. In terms of ecological restoration assessment, Bio-DANN achieved ΔF and PIPGR of 0.15 and 18%, and 0.20 and 22%, respectively, and H' values of 1.5 and 1.7, which are better than other models. Bio-DANN provides a promising technical solution for environmental protection, resource recovery and sustainable agriculture, especially showing significant potential in pollutant monitoring, soil health assessment and ecological restoration evaluation.

PMID:40433163 | PMC:PMC12106413 | DOI:10.3389/fpls.2025.1550302

Front Plant Sci. 2025 May 13;16:1543986. doi: 10.3389/fpls.2025.1543986. eCollection 2025.

ABSTRACT

In order to enhance the accuracy of rice leaf disease detection in complex farmland environments, and facilitate the deployment of the deep learning model onto mobile terminals for rapid real-time inference, this paper introduces a disease detection network titled YOLOv11 Multi-scale Dynamic Feature Fusion for Rice Disease Detection (YOLOv11-MSDFF-RiceD). The model adopts the concept of ParameterNet to design the FlexiC3k2Net module, which replaces the neck feature extraction network, thereby bolstering the model's feature learning capabilities without significantly increasing computational complexity. Additionally, an efficient multi-scale feature fusion module (EMFFM) is devised, improving both the computational efficiency and feature extraction capabilities of the model, while simultaneously reducing the number of parameters and memory footprint. The bounding box regression loss function, inner-WIoU, utilizes auxiliary bounding boxes and scale factors. Finally, the Dependency Graph (DepGraph) pruning model is employed to minimize the model's size, computational load, and parameter count, with only a moderate sacrifice in accuracy. Compared to the original YOLOv11n model, the optimized model achieves reductions in computational complexity, parameter scale, and memory usage by 50.7%, 49.6%, and 36.9%, respectively, with only a 1.7% improvement in mAP@0.5:0.9. These optimizations enable efficient deployment on resource-constrained mobile devices, making the model highly suitable for real-time disease detection in practical agricultural scenarios where hardware limitations are critical. Consequently, the improved model proposed in this paper effectively detects rice disease targets in complex environments, providing theoretical and technical support for the deployment and application of mobile terminal detection devices, such as rice disease detectors, in practical scenarios.

PMID:40433155 | PMC:PMC12106424 | DOI:10.3389/fpls.2025.1543986

Front Med (Lausanne). 2025 May 13;12:1587417. doi: 10.3389/fmed.2025.1587417. eCollection 2025.

ABSTRACT

OBJECTIVE: In non-clinical safety evaluation of drugs, pathological result is one of the gold standards for determining toxic effects. However, pathological diagnosis might be challenging and affected by pathologist expertise. In carcinogenicity studies, drug-induced squamous cell carcinoma (SCC) of the mouse stomach represents a diagnostic challenge for toxicopathologists. This study aims to establish a detection model for mouse gastric squamous cell carcinoma (GSCC) using deep learning algorithms, to improve the accuracy and consistency of pathological diagnoses.

METHODS: A total of 93 cases of drug-induced mouse GSCC and 56 cases of normal mouse stomach tissue from carcinogenicity studies were collected. After scanning into digital slides, semi-automated data annotation was performed. All images underwent preprocessing, including tissue extraction, artifact removal, and exclusion of normal epithelial regions. The images were then randomly divided into training, validation, and test sets in an 8:1:1 ratio. Five different convolutional neural networks (CNNs)-FCN, LR-ASPP, DeepLabv3+, U-Net, and DenseNet were applied to identify GSCC and non-GSCC regions. Tumor prediction images (algorithm results shown as overlays) derived from the slide images were compared, and the performance of the constructed models was evaluated using Precision, Recall, and F1-score.

RESULTS: The Precision, Recall, and F1-scores of DenseNet, U-Net, and DeepLabv3 + algorithms were all above 90%. Specifically, the DenseNet model achieved an overall Precision of 0.9044, Recall of 0.9291, and F1-score of 0.9157 in the test set. Compared to the other algorithms, DenseNet exhibited the highest F1-score and Recall, demonstrating superior generalization ability.

CONCLUSION: The DenseNet algorithm model developed in this study shown promising application potential for assisting in the diagnosis of mouse GSCC. As artificial intelligence (AI) technology continues to advance in non-clinical safety evaluation of drugs, CNN-based toxicological pathology detection models will become essential tools to assist pathologists in precise diagnosis and consistency evaluation.

PMID:40432719 | PMC:PMC12106445 | DOI:10.3389/fmed.2025.1587417

Front Med (Lausanne). 2025 May 13;12:1599340. doi: 10.3389/fmed.2025.1599340. eCollection 2025.

ABSTRACT

Nanomedicines are nanoscale, biocompatible materials that offer promising alternatives to conventional treatment options for brain disorders. The recent technological developments in artificial intelligence (AI), particularly machine learning (ML) and deep learning (DL), are transforming the nanomedicine field by improving disease diagnosis, biomarker identification, prognostic assessment and disease monitoring, targeted drug delivery, and therapeutic intervention as well as contributing to computational and methodological developments. These advancements can be achieved by analysis of large clinical datasets and facilitating the design and optimization of nanomaterials for in vivo testing. Such advancement offers exciting possibilities for the improvement in the management of brain disorders, including brain cancer, Alzheimer's disease, Parkinson's disease, and multiple sclerosis, where early diagnosis, targeted delivery, and effective treatment strategies remain a great challenge. This review article provides an overview of recent advances in AI-based nanomedicine development to accelerate effective and quick diagnosis, biomarker identification, prognosis, drug delivery, methodological advancement and patient-specific therapies for managing brain disorders.

PMID:40432717 | PMC:PMC12106332 | DOI:10.3389/fmed.2025.1599340

ERJ Open Res. 2025 May 27;11(3):00826-2024. doi: 10.1183/23120541.00826-2024. eCollection 2025 May.

ABSTRACT

INTRODUCTION: Up to 11% of patients are left with residual lung abnormalities following COVID-19 infection. It is unclear whether these changes resolve over time or progress to fibrosis. The airway microbiome is altered in interstitial lung disease, potentially contributing to pathogenesis and disease progression. We hypothesised that the airway microbiome in patients with post-COVID-19 residual lung abnormalities may be altered.

METHODS: The POST COVID-19 interstitial lung DiseasE (POSTCODE) study recruited subjects with post-COVID-19 residual lung abnormalities for bronchoscopy. 16S ribosomal RNA gene amplicon sequencing was performed on DNA extracted from bronchoalveolar lavage fluid and compared with that from patients with idiopathic pulmonary fibrosis, fibrotic hypersensitivity pneumonitis and control subjects.

RESULTS: 28 subjects with post-COVID-19 residual lung abnormalities were recruited an average of 11 months after infection. No significant associations were found between the lower airway microbiome or bacterial burden and disease severity or trajectory. There was no difference in bacterial burden between post-COVID-19 patients and interstitial lung disease or control subjects. Furthermore, no differences in microbial composition were observed between these patients and those with fibrotic hypersensitivity pneumonitis or controls. However, compared with idiopathic pulmonary fibrosis, there was an increased abundance of Streptococcus and higher α-diversity in subjects with post-COVID-19 residual lung abnormalities.

CONCLUSIONS: The microbiome and bacterial burden in the lower airways of subjects with post-COVID-19 residual lung abnormalities do not differ from those of controls. The microbiome differs from idiopathic pulmonary fibrosis. This, and the absence of associations between microbial features and disease severity or clinical outcomes, suggests that the microbiome is unlikely to contribute to residual lung abnormalities in patients recovering from COVID-19 infection.

PMID:40432814 | PMC:PMC12107383 | DOI:10.1183/23120541.00826-2024

Medicina (Kaunas). 2025 May 14;61(5):892. doi: 10.3390/medicina61050892.

ABSTRACT

Background: Interstitial lung disease (ILD) is characterized by pulmonary inflammation and fibrosis associated with persistent and refractory cough that significantly hinders quality of life. Conventional treatments for ILD-associated cough have shown limited efficacy, necessitating alternative therapeutic approaches. Gefapixant, a P2X3 receptor antagonist, can potentially alleviate chronic cough by inhibiting the ATP-mediated activation of sensory C-fibers, but its efficacy in ILD-associated cough remains unclear. This study observed the effects of gefapixant on ILD-associated refractory chronic cough. Methods: This prospective study enrolled patients with ILD-associated refractory chronic cough who received gefapixant at Sapporo Medical University Hospital between July 2022 and November 2023. Cough frequency, Leicester Cough Questionnaire (LCQ) score, cough severity visual analog scale (Cough VAS), and taste VAS were evaluated at baseline and at 2, 4, and 8 weeks after gefapixant administration. Results: Six patients completed the study. Their ILD subtypes included idiopathic pulmonary fibrosis (IPF), nonspecific interstitial pneumonia (NSIP), and connective tissue disease-associated ILDs (CTD-ILDs). After 8 weeks, the cough frequency decreased from 88.5 to 44.3 episodes per 30 min, LCQ scores increased from 8.3 to 13.6, and cough VAS scores decreased from 75.8 to 40.2. However, statistical significance was not reached due to high interindividual variability, with gefapixant being effective in some and ineffective in others. The most common adverse event was taste disorder, leading to discontinuation in one patient, but symptoms tended to lessen over the course of treatment. Conclusions: Gefapixant appears to be effective in reducing refractory cough related to ILD, although these results were not statistically significant because its effectivity widely varied across individuals. Further investigation is needed to identify patient subgroups with the greatest potential for treatment responsiveness.

PMID:40428850 | DOI:10.3390/medicina61050892

Diagnostics (Basel). 2025 May 16;15(10):1267. doi: 10.3390/diagnostics15101267.

ABSTRACT

Background/Objectives: Hypersensitivity pneumonitis (HP), a subtype of interstitial lung disease (ILD), is often misdiagnosed as idiopathic pulmonary fibrosis (IPF), particularly when the causative antigen cannot be identified. Typically resulting from chronic exposure to inhaled organic particles smaller than 5 microns, HP presents a diagnostic challenge. This report outlines a case of fibrotic HP initially misclassified as asthma. No triggering antigen was identified despite extensive investigation. The disease progressed despite corticosteroid, immunosuppressive, and antifibrotic therapy, ultimately leading to an advanced fibrotic stage and requiring lung transplantation. This clinical course is rare and infrequently reported, particularly in cases requiring lung transplantation without an identifiable causative antigen. Such progression is uncommon and underreported, especially in patients initially misclassified as having asthma. Methods: Medical records of 24 patients diagnosed with HP were reviewed. Only one case demonstrated progression to fibrotic HP; this case was selected for detailed analysis. Results: Clinical and functional deterioration occurred despite standard therapy. Given the advanced stage of fibrosis and treatment resistance, lung transplantation was deemed the next appropriate therapeutic option. Conclusions: HP remains underdiagnosed due to difficulties in identifying the causative antigen and overlapping features with other ILDs. Early and accurate differentiation from IPF is essential, particularly in progressive fibrotic forms unresponsive to conventional therapies.

PMID:40428260 | DOI:10.3390/diagnostics15101267

Biomedicines. 2025 Apr 30;13(5):1096. doi: 10.3390/biomedicines13051096.

ABSTRACT

In the original publication, there was a mistake in Figure 11 as published [...].

PMID:40427093 | DOI:10.3390/biomedicines13051096