IEEE J Biomed Health Inform. 2025 Apr 22;PP. doi: 10.1109/JBHI.2025.3563433. Online ahead of print.

ABSTRACT

Synergistic drug combinations have shown promising results in treating cancer cell lines by enhancing therapeutic efficacy and minimizing adverse reactions. The effects of a drug vary across cell lines, and cell lines respond differently to various drugs during treatment. Recently, many AI-based techniques have been developed for predicting synergistic drug combinations. However, existing computational models have not addressed this phenomenon, neglecting the refinement of features for the same drug and cell line in different scenarios. In this work, we propose a feature refinement deep learning framework, termed FRSynergy, to identify synergistic drug combinations. It can guide the refinement of drug and cell line features in different scenarios by capturing relationships among diverse drug-drug-cell line triplet features and learning feature contextual information. The heterogeneous graph attention network is employed to acquire topological information-based original features for drugs and cell lines from sampled sub-graphs. Then, the feature refinement network is designed by combining attention mechanism and context information, which can learn context-aware feature representations for each drug and cell line feature in diverse drug-drug-cell line triplet contexts. Extensive experiments affirm the strong performance of FRSynergy in predicting synergistic drug combinations and, more importantly, demonstrate the effectiveness of feature refinement network in synergistic drug combination prediction.

PMID:40261768 | DOI:10.1109/JBHI.2025.3563433

IEEE Trans Ultrason Ferroelectr Freq Control. 2025 Apr 22;PP. doi: 10.1109/TUFFC.2025.3562313. Online ahead of print.

ABSTRACT

Surgical tool tip localization and tracking are essential components of surgical and interventional procedures. The cross sections of tool tips can be considered as acoustic point sources to achieve these tasks with deep learning applied to photoacoustic channel data. However, source localization was previously limited to the lateral and axial dimensions of an ultrasound transducer. In this paper, we developed a novel deep learning-based three-dimensional (3D) photoacoustic point source localization system using an object detection-based approach extended from our previous work. In addition, we derived theoretical relationships among point source locations, sound speeds, and waveform shapes in raw photoacoustic channel data frames. We then used this theory to develop a novel deep learning instance segmentation-based 3D point source localization system. When tested with 4,000 simulated, 993 phantom, and 1,983 ex vivo channel data frames, the two systems achieved F1 scores as high as 99.82%, 93.05%, and 98.20%, respectively, and Euclidean localization errors (mean ± one standard deviation) as low as 1.46±1.11 mm, 1.58±1.30 mm, and 1.55±0.86 mm, respectively. In addition, the instance segmentation-based system simultaneously estimated sound speeds with absolute errors (mean ± one standard deviation) of 19.22±26.26 m/s in simulated data and standard deviations ranging 14.6-32.3 m/s in experimental data. These results demonstrate the potential of the proposed photoacoustic imaging-based methods to localize and track tool tips in three dimensions during surgical and interventional procedures.

PMID:40261767 | DOI:10.1109/TUFFC.2025.3562313

Database (Oxford). 2025 Apr 22;2025:baaf031. doi: 10.1093/database/baaf031.

ABSTRACT

As the importance of precision agriculture grows, scalable and efficient methods for real-time data collection and analysis have become essential. In this study, we developed a system to collect real-time crop images, focusing on physiological disorders in tomatoes. This system systematically collects crop images and related data, with the potential to evolve into a valuable tool for researchers and agricultural practitioners. A total of 58 479 images were produced under stress conditions, including bacterial wilt (BW), Tomato Yellow Leaf Curl Virus (TYLCV), Tomato Spotted Wilt Virus (TSWV), drought, and salinity, across seven tomato varieties. The images include front views at 0 degrees, 120 degrees, 240 degrees, and top views and petiole images. Of these, 43 894 images were suitable for labeling. Based on this, 24 000 images were used for AI model training, and 13 037 images for model testing. By training a deep learning model, we achieved a mean Average Precision (mAP) of 0.46 and a recall rate of 0.60. Additionally, we discussed data augmentation and hyperparameter tuning strategies to improve AI model performance and explored the potential for generalizing the system across various agricultural environments. The database constructed in this study will serve as a crucial resource for the future development of agricultural AI. Database URL: https://crops.phyzen.com/.

PMID:40261733 | DOI:10.1093/database/baaf031

IET Syst Biol. 2025 Apr 22:e12107. doi: 10.1049/syb2.12107. Online ahead of print.

ABSTRACT

Single-cell sequencing (scRNA-seq) allows researchers to study cellular heterogeneity in individual cells. In single-cell transcriptomics analysis, identifying the cell type of individual cells is a key task. At present, single-cell datasets often face the challenges of high dimensionality, large number of samples, high sparsity and sample imbalance. The traditional methods of cell type recognition have been challenged. The authors propose a deep residual generation model based on semi-supervised learning (scRSSL) to address these challenges. ScRSSL creatively introduces residual networks into semi-supervised generative models. The authors take advantage of its semi-supervised learning to solve the problem of sample imbalance. During the training of the model, the authors use a residual neural network to accomplish the inference of cell types so that local features of single-cell data can be extracted. Because of the semi-supervised learning approach, it can automatically and accurately predict individual cell types in datasets, even with only a small number of cell labels. Experimentally, the authors' method has proven to have better performance compared to other methods.

PMID:40261690 | DOI:10.1049/syb2.12107

Radiol Phys Technol. 2025 Apr 22. doi: 10.1007/s12194-025-00905-2. Online ahead of print.

ABSTRACT

This study aimed to develop and evaluate a deep-learning model for attenuation and scatter correction in whole-body 64Cu-based PET imaging. A swinUNETR model was implemented using the MONAI framework. Whole-body PET-nonAC and PET-CTAC image pairs were used for training, where PET-nonAC served as the input and PET-CTAC as the output. Due to the limited number of Cu-based PET/CT images, a model pre-trained on 51 Ga-PSMA PET images was fine-tuned on 15 Cu-based PET images via transfer learning. The model was trained without freezing layers, adapting learned features to the Cu-based dataset. For testing, six additional Cu-based PET images were used, representing 1-h, 12-h, and 48-h time points, with two images per group. The model performed best at the 12-h time point, with an MSE of 0.002 ± 0.0004 SUV2, PSNR of 43.14 ± 0.08 dB, and SSIM of 0.981 ± 0.002. At 48 h, accuracy slightly decreased (MSE = 0.036 ± 0.034 SUV2), but image quality remained high (PSNR = 44.49 ± 1.09 dB, SSIM = 0.981 ± 0.006). At 1 h, the model also showed strong results (MSE = 0.024 ± 0.002 SUV2, PSNR = 45.89 ± 5.23 dB, SSIM = 0.984 ± 0.005), demonstrating consistency across time points. Despite the limited size of the training dataset, the use of fine-tuning from a previously pre-trained model yielded acceptable performance. The results demonstrate that the proposed deep learning model can effectively generate PET-DLAC images that closely resemble PET-CTAC images, with only minor errors.

PMID:40261572 | DOI:10.1007/s12194-025-00905-2

Intern Med J. 2025 Apr 22. doi: 10.1111/imj.70051. Online ahead of print.

ABSTRACT

Pulmonary fibrosis care, affecting both idiopathic pulmonary fibrosis and other forms of interstitial lung disease (ILD) characterised by fibrosis, has transformed with a range of innovations that affect the diagnosis, treatment and prognosis of this condition. Pharmacotherapeutic options have expanded, with increased indications for the application of effective antifibrotic therapy in non-IPF progressive pulmonary fibrosis as a solo treatment or combined with immunosuppression, emerging evidence for immunomodulatory therapy including biologic agents and greater access to clinical trials. The diagnostic approach to unclassifiable ILD now includes transbronchial lung cryobiopsy, a less invasive method to obtain histopathology with reduced morbidity and mortality compared to surgical lung biopsy. A multidisciplinary approach optimises the care of people with ILD and includes non-pharmacological management, addressing significant comorbidities, symptom care and advanced care planning. This review will summarise recent updates in pulmonary fibrosis management.

PMID:40260907 | DOI:10.1111/imj.70051

ACS Synth Biol. 2025 Apr 22. doi: 10.1021/acssynbio.4c00868. Online ahead of print.

ABSTRACT

Researchers have invested much effort into developing kinetic models due to their ability to capture dynamic behaviors, transient states, and regulatory mechanisms of metabolism, providing a detailed and realistic representation of cellular processes. Historically, the requirements for detailed parametrization and significant computational resources created barriers to their development and adoption for high-throughput studies. However, recent advancements, including the integration of machine learning with mechanistic metabolic models, the development of novel kinetic parameter databases, and the use of tailor-made parametrization strategies, are reshaping the field of kinetic modeling. In this Review, we discuss these developments and offer future directions, highlighting the potential of these advances to drive progress in systems and synthetic biology, metabolic engineering, and medical research at an unprecedented scale and pace.

PMID:40262025 | DOI:10.1021/acssynbio.4c00868

Plant Cell. 2025 Apr 2;37(4):koaf056. doi: 10.1093/plcell/koaf056.

ABSTRACT

Plants use environmental cues to orient organ and plant growth, such as the direction of gravity or the direction, quantity, and quality of light. During the germination of Arabidopsis thaliana seeds in soil, negative gravitropism responses direct hypocotyl elongation such that the seedling can reach the light for photosynthesis and autotrophic growth. Similarly, hypocotyl elongation in the soil also requires mechanisms to efficiently grow around obstacles such as soil particles. Here, we identify KIPK (KINESIN-LIKE CALMODULIN-BINDING PROTEIN-INTERACTING PROTEIN KINASE) and the paralogous KIPKL1 (KIPK-LIKE1) as genetically redundant regulators of gravitropic hypocotyl bending. Moreover, we demonstrate that the homologous KIPKL2 (KIPK-LIKE2), which shows strong sequence similarity, must be functionally distinct. KIPK and KIPKL1 are polarly localized plasma membrane-associated proteins that can activate PIN-FORMED auxin transporters. KIPK and KIPKL1 are required to efficiently align hypocotyl growth with the gravity vector when seedling hypocotyls are grown on media plates or in soil, where contact with soil particles and obstacle avoidance impede direct negative gravitropic growth. Therefore, the polar KIPK and KIPKL1 kinases have different biological functions from the related AGC1 family kinases D6PK (D6 PROTEIN KINASE) or PAX (PROTEIN KINASE ASSOCIATED WITH BRX).

PMID:40261964 | DOI:10.1093/plcell/koaf056

Sci Signal. 2025 Apr 22;18(883):eads2547. doi: 10.1126/scisignal.ads2547. Epub 2025 Apr 22.

ABSTRACT

Adaptation to starvation is a multimolecular and temporally ordered process. We sought to elucidate how the healthy liver regulates various molecules in a temporally ordered manner during starvation and how obesity disrupts this process. We used multiomic data collected from the plasma and livers of wild-type and leptin-deficient obese (ob/ob) mice at multiple time points during starvation to construct a starvation-responsive metabolic network that included responsive molecules and their regulatory relationships. Analysis of the network structure showed that in wild-type mice, the key molecules for energy homeostasis, ATP and AMP, acted as hub molecules to regulate various metabolic reactions in the network. Although neither ATP nor AMP was responsive to starvation in ob/ob mice, the structural properties of the network were maintained. In wild-type mice, the molecules in the network were temporally ordered through metabolic processes coordinated by hub molecules, including ATP and AMP, and were positively or negatively coregulated. By contrast, both temporal order and coregulation were disrupted in ob/ob mice. These results suggest that the metabolic network that responds to starvation was structurally robust but temporally disrupted by the obesity-associated loss of responsiveness of the hub molecules. In addition, we propose how obesity alters the response to intermittent fasting.

PMID:40261956 | DOI:10.1126/scisignal.ads2547

PLoS Comput Biol. 2025 Apr 22;21(4):e1012925. doi: 10.1371/journal.pcbi.1012925. eCollection 2025 Apr.

ABSTRACT

Modern biological research is increasingly data-intensive, leading to a growing demand for effective training in biological data science. In this article, we provide an overview of key resources and best practices available within the Bioconductor project-an open-source software community focused on omics data analysis. This guide serves as a valuable reference for both learners and educators in the field.

PMID:40261894 | DOI:10.1371/journal.pcbi.1012925

Database (Oxford). 2025 Mar 21;2025:baaf020. doi: 10.1093/database/baaf020.

ABSTRACT

Ontologies are widely used in databases to standardize data, improving data quality, integration, and ease of comparison. Within ontologies tailored to diverse use cases, post-composing user-defined terms reconciles the demands for standardization on the one hand and flexibility on the other. In many instances of Breedbase, a digital ecosystem for plant breeding designed for genomic selection, the goal is to capture phenotypic data using highly curated and rigorous crop ontologies, while adapting to the specific requirements of plant breeders to record data quickly and efficiently. For example, post-composing enables users to tailor ontology terms to suit specific and granular use cases such as repeated measurements on different plant parts and special sample preparation techniques. To achieve this, we have implemented a post-composing tool based on orthogonal ontologies providing users with the ability to introduce additional levels of phenotyping granularity tailored to unique experimental designs. Post-composed terms are designed to be reused by all breeding programs within a Breedbase instance but are not exported to the crop reference ontologies. Breedbase users can post-compose terms across various categories, such as plant anatomy, treatments, temporal events, and breeding cycles, and, as a result, generate highly specific terms for more accurate phenotyping.

PMID:40261748 | DOI:10.1093/database/baaf020

Database (Oxford). 2025 Jan 22;2025:baae133. doi: 10.1093/database/baae133.

ABSTRACT

Ontologies and knowledge graphs (KGs) are general-purpose computable representations of some domain, such as human anatomy, and are frequently a crucial part of modern information systems. Most of these structures change over time, incorporating new knowledge or information that was previously missing. Managing these changes is a challenge, both in terms of communicating changes to users and providing mechanisms to make it easier for multiple stakeholders to contribute. To fill that need, we have created KGCL, the Knowledge Graph Change Language (https://github.com/INCATools/kgcl), a standard data model for describing changes to KGs and ontologies at a high level, and an accompanying human-readable Controlled Natural Language (CNL). This language serves two purposes: a curator can use it to request desired changes, and it can also be used to describe changes that have already happened, corresponding to the concepts of "apply patch" and "diff" commonly used for managing changes in text documents and computer programs. Another key feature of KGCL is that descriptions are at a high enough level to be useful and understood by a variety of stakeholders-e.g. ontology edits can be specified by commands like "add synonym 'arm' to 'forelimb'" or "move 'Parkinson disease' under 'neurodegenerative disease'." We have also built a suite of tools for managing ontology changes. These include an automated agent that integrates with and monitors GitHub ontology repositories and applies any requested changes and a new component in the BioPortal ontology resource that allows users to make change requests directly from within the BioPortal user interface. Overall, the KGCL data model, its CNL, and associated tooling allow for easier management and processing of changes associated with the development of ontologies and KGs. Database URL: https://github.com/INCATools/kgcl.

PMID:40261730 | DOI:10.1093/database/baae133

JCI Insight. 2025 Apr 22;10(8):e184544. doi: 10.1172/jci.insight.184544. eCollection 2025 Apr 22.

ABSTRACT

Autoimmune hepatitis (AIH) and primary biliary cholangitis (PBC) are autoimmune liver diseases with strong female predominance. They are caused by T cell-mediated injury of hepatic parenchymal cells, but the mechanisms underlying this sex bias are unknown. Here, we investigated whether testosterone contributes to T cell activation in women with PBC. Compared with sex- and age-matched healthy controls (n = 23), cisgender (cis) women with PBC (n = 24) demonstrated decreased testosterone serum levels and proinflammatory CD4+ T cell profile in peripheral blood. Testosterone suppressed the expression of TNF and IFN-γ by human CD4+ T cells in vitro. In trans men receiving gender-affirming hormone therapy (GAHT) (n = 25), testosterone affected CD4+ T cell function by inhibiting Th1 and Th17 differentiation and by supporting the differentiation into regulatory Treg. Mechanistically, we provide evidence for a direct effect of testosterone on T cells using mice with T cell-specific deletion of the cytosolic androgen receptor. Supporting a role for testosterone in autoimmune liver disease, we observed an improved disease course and profound changes in T cell states in a trans man with AIH/primary sclerosing cholangitis (PSC) variant syndrome receiving GAHT. We here report a direct effect of testosterone on CD4+ T cells that may contribute to future personalized treatment strategies.

PMID:40260919 | DOI:10.1172/jci.insight.184544

Emerg Microbes Infect. 2025 Apr 22:2470998. doi: 10.1080/22221751.2025.2470998. Online ahead of print.

ABSTRACT

From 2020 to 2022, a pulmonary tuberculosis (PTB) active case finding project based on chest X-ray (CXR) examination was conducted targeting individuals aged ≥ 65 years old in Jiangshan County, Quzhou City. The current study used computer-aided detection (CAD) software (JF CXR-1 v2) to retrospectively analyze the CXR images and to estimate its potential capacity for identifying PTB cases. The information of notified microbiologically confirmed PTB among the participants were exported from the Tuberculosis Information Management System. A total of 49,919 subjects participated in the 2020 examinations. Of these, 40,741 and 39,185 completed the follow-up surveys in 2021 and 2022, respectively. The pooled prevalence of suspected PTB reported by radiologists was 1.21% (1,579/129,776), compared with 12.43% (16,129/129,776) reported by CAD. Of 101 bacteriologically confirmed PTB cases notified over three years, radiologists and CAD reported 45.54% (46/101) and 83.16% (84/101) as suspected cases, respectively. Among subjects with abnormal CAD (CAD score>0.35), the majority of the notified confirmed PTB patients (63/84) had their CAD scores >75% quantiles (as＞0.75). With 3 years' results, their CAD scores exhibited dynamic changes along with disease progression or treatment with median scores peaking in the year of diagnosis. This intriguing finding suggests that CAD for CXR reading assisted radiologists in PTB screening by reducing workload and improving case finding. The CAD primary score may have the potential to identify high-risk individuals and early PTB patients, adding a new dimension to our understanding of disease progression.

PMID:40260691 | DOI:10.1080/22221751.2025.2470998

Clin Transl Sci. 2025 Apr;18(4):e70193. doi: 10.1111/cts.70193.

ABSTRACT

Medication prescribing is imperfect, and unintended side effects complicate patient care. Pharmacogenomics (PGx) is an emerging solution that associates genotypes with personalized drug-related outcomes, but it has not been widely adopted. We hypothesize that patient and provider attributes may predict and promote PGx utilization. We studied PGx using data from the ACCOuNT study, a multi-institutional prospective trial that implemented broad preemptive PGx result delivery for African American inpatients [Clinicaltrials.gov NCT03225820]. Patients were genotyped, and their PGx information was made available within an integrated informatics portal. Utilization of PGx data (defined as the active choice to review PGx information) was left to the enrolled provider's discretion. Our primary endpoint was to identify patient and care team attributes associated with PGx use. We identified statistically significant univariate predictors and utilized logistic regression to compare relative predictiveness. This study included 187 patients (60.4% female, median age 55, 75.4% treated at the University of Chicago, 17.6% at Northwestern University, and 7.0% at the University of Illinois Chicago) and 188 providers (63.8% MD, 22.3% PharmD, 6.4% PA, and 7.4% APN). In multivariate analysis, we found that the use of PGx information in a prior admission significantly predicted the use in subsequent admissions (OR 7.62, p < 0.05). Similarly, pharmacist participation on care teams significantly predicted PGx use (OR 4.52, p < 0.05). In the first systematic analysis of the impact of patient and care team factors on inpatient PGx clinical decision support (CDS) adoption, we found that actionable care team attributes, such as pharmacist participation or successful initial adoption measures, predict PGx CDS use.

PMID:40259529 | DOI:10.1111/cts.70193

Clin Transl Sci. 2025 Apr;18(4):e70209. doi: 10.1111/cts.70209.

ABSTRACT

Phenoconversion is the discrepancy between genotype-predicted phenotype and clinical phenotype, due to nongenetic factors. In oncology patients, the impact of phenoconversion on drug selection, efficacy, toxicity, and treatment outcomes is unknown. This study will assess acceptability and feasibility of investigating phenoconversion using probe medications in a pediatric and adolescent and young adult (AYA) oncology population. This prospective, single-arm, single-blind, nonrandomized feasibility study, will enroll individuals aged 6-25 years with a new diagnosis of Hodgkin Lymphoma or Non-Hodgkin Lymphoma. Genotyping will be performed at baseline using whole genome sequencing or targeted panel testing. Longitudinal phenotyping will be conducted throughout the cancer treatment using exogenous oral enzyme-specific probes, specifically subtherapeutic dextromethorphan (CYP2D6) and omeprazole (CYP2C19, CYP3A4) for enzyme activity assessment. The primary outcome measure will be the proportion of patients who consent to the study and successfully complete baseline and at least two longitudinal time points with valid probe drug metabolic ratio measurements. Secondary outcomes include classification of clinical phenotypes based on probe drug metabolic ratios, probe drug safety, barriers to consent, acceptability of pharmacogenomic and phenoconversion testing, longitudinal genotype/phenotype concordance, inflammatory profiles, and patient and disease factors influencing phenoconversion. The trial has received ethics approval (2023/ETH1954) and is registered at ClinicalTrials.gov (NCT06383338). Findings will be disseminated through peer-reviewed publications and professional conferences, providing critical insights to advance the understanding of phenoconversion in oncology from pediatrics to adults. These results will help shape future research and drive the implementation of more personalized precision medicine strategies for all people with cancer.

PMID:40259519 | DOI:10.1111/cts.70209

Macromol Biosci. 2025 Apr 22:e2500007. doi: 10.1002/mabi.202500007. Online ahead of print.

ABSTRACT

Computer-aided protein design (CAPD) has become a transformative field, harnessing advances in computational power and deep learning to deepen the understanding of protein structure, function, and design. This review provides a comprehensive overview of CAPD techniques, with a focus on their application to protein-based therapeutics such as monoclonal antibodies, protein drugs, antigens, and protein polymers. This review starts with key CAPD methods, particularly those integrating deep learning-based predictions and generative models. These approaches have significantly enhanced protein drug properties, including binding affinity, specificity, and the reduction of immunogenicity. This review also covers CAPD's role in optimizing vaccine antigen design, improving protein stability, and customizing protein polymers for drug delivery applications. Despite considerable progress, CAPD faces challenges such as model overfitting, limited data for rare protein families, and the need for efficient experimental validation. Nevertheless, ongoing advancements in computational methods, coupled with interdisciplinary collaborations, are poised to overcome these obstacles, advancing protein engineering and therapeutic development. In conclusion, this review highlights the future potential of CAPD to transform drug development, personalized medicine, and biotechnology.

PMID:40260555 | DOI:10.1002/mabi.202500007

IEEE Access. 2025;13:57780-57797. doi: 10.1109/access.2025.3556713. Epub 2025 Apr 1.

ABSTRACT

Glioma is the most common malignant tumor of the central nervous system, and diffuse Glioma is classified as grades II-IV by world health organization (WHO). In the the cancer genome atlas (TCGA) Glioma dataset, grade II and III Gliomas are classified as low-grade glioma (LGG), and grade IV Gliomas as glioblastoma multiforme (GBM). In clinical practice, the survival and treatment process with Glioma patients depends on properly diagnosing the subtype. With this background, there has been much research on Glioma over the years. Among these researches, the origin and evolution of whole slide images (WSIs) have led to many attempts to support diagnosis by image analysis. On the other hand, due to the disease complexities of Glioma patients, multimodal analysis using various types of data rather than a single data set has been attracting attention. In our proposed method, multiple deep learning models are used to extract features from histopathology images, and the features of the obtained images are concatenated with those of the clinical data in a fusion approach. Then, we perform patch-level classification by machine learning (ML) using the concatenated features. Based on the performances of the deep learning models, we ensemble feature sets from top three models and perform further classifications. In the experiments with our proposed ensemble fusion AI (EFAI) approach using WSIs and clinical data of diffuse Glioma patients on TCGA dataset, the classification accuracy of the proposed multimodal ensemble fusion method is 0.936 with an area under the curve (AUC) value of 0.967 when tested on a balanced dataset of 240 GBM, 240 LGG patients. On an imbalanced dataset of 141 GBM, 242 LGG patients the proposed method obtained the accuracy of 0.936 and AUC of 0.967. Our proposed ensemble fusion approach significantly outperforms the classification using only histopathology images alone with deep learning models. Therefore, our approach can be used to support the diagnosis of Glioma patients and can lead to better diagnosis.

PMID:40260100 | PMC:PMC12011355 | DOI:10.1109/access.2025.3556713

Front Cell Neurosci. 2025 Apr 7;19:1523149. doi: 10.3389/fncel.2025.1523149. eCollection 2025.

ABSTRACT

More than 5% of the global population suffers from disabling hearing loss, primarily sensorineural hearing loss (SNHL). SNHL is often caused by factors such as vascular disorders, viral infections, ototoxic drugs, systemic inflammation, age-related labyrinthine membrane degeneration, and noise-induced hearing loss (NIHL). NIHL, in particular, leads to changes in blood-labyrinth-barrier (BLB) physiology, increased permeability, and various health issues, including cardiovascular disease, hypertension, diabetes, neurological disorders, and adverse reproductive outcomes. Recent advances in neuromodulation and vector-based approaches offer hope for overcoming biological barriers such as the BLB in the development of innovative treatments. Computational methods, including molecular docking, molecular dynamics simulations, QSAR/QSPR analysis with machine/deep learning algorithms, and network pharmacology, hold potential for identifying drug candidates and optimizing their interactions with BLB transporters, such as the glutamate transporter. This paper provides an overview of NIHL, focusing on its pathophysiology; its impact on membrane transporters, ion channels, and BLB structures; and associated symptoms, comorbidities, and emerging therapeutic approaches. Recent advancements in neuromodulation and vector-based strategies show great promise in overcoming biological barriers such as BLB, facilitating the development of innovative treatment options. The primary aim of this review is to examine NIHL in detail and explore its underlying mechanisms, physiological effects, and cutting-edge therapeutic strategies for its effective management and prevention.

PMID:40260077 | PMC:PMC12009814 | DOI:10.3389/fncel.2025.1523149

J Biomed Phys Eng. 2025 Apr 1;15(2):137-158. doi: 10.31661/jbpe.v0i0.2408-1811. eCollection 2025 Apr.

ABSTRACT

BACKGROUND: Diabetic retinopathy (DR), a diabetes complication, causes blindness by damaging retinal blood vessels. While deep learning has advanced DR diagnosis, many models face issues like inconsistent performance, limited datasets, and poor interpretability, reducing their clinical utility.

OBJECTIVE: This research aimed to develop and evaluate a deep learning structure combining Convolutional Neural Networks (CNNs) and transformer architecture to improve the accuracy, reliability, and generalizability of DR detection and severity classification.

MATERIAL AND METHODS: This computational experimental study leverages CNNs to extract local features and transformers to capture long-range dependencies in retinal images. The model classifies five types of retinal images and assesses four levels of DR severity. The training was conducted on the augmented APTOS 2019 dataset, addressing class imbalance through data augmentation techniques. Performance metrics, including accuracy, Area Under the Curve (AUC), specificity, and sensitivity, were used for metric evaluation. The model's robustness was further validated using the IDRiD dataset under diverse scenarios.

RESULTS: The model achieved a high accuracy of 94.28% on the APTOS 2019 dataset, demonstrating strong performance in both image classification and severity assessment. Validation on the IDRiD dataset confirmed its generalizability, achieving a consistent accuracy of 95.23%. These results indicate the model's effectiveness in accurately diagnosing and assessing DR severity across varied datasets.

CONCLUSION: The proposed Artificial intelligence (AI)-powered diagnostic tool improves diabetic patient care by enabling early DR detection, preventing progression and reducing vision loss. The proposed AI-powered diagnostic tool offers high performance, reliability, and generalizability, providing significant value for clinical DR management.

PMID:40259941 | PMC:PMC12009469 | DOI:10.31661/jbpe.v0i0.2408-1811