Sci Rep. 2025 Mar 19;15(1):9486. doi: 10.1038/s41598-025-93695-x.

ABSTRACT

Cutaneous melanoma (CM) is an aggressive skin cancer with high metastatic potential and poor prognosis. Splicing factors, which regulate pre-mRNA alternative splicing (AS) events, have been suggested as potential therapeutic targets in CM. The objective of this study was to identify candidate splicing factors involved in CM through a systems biology approach and to elucidate their roles in CM progression. 390 AS events associated with patient survival were identified using bivariate Cox regression and receiver operating characteristic (ROC) analyses. 121 splicing factors significantly associated with patient prognosis were screened by univariate Cox regression analysis. A bipartite association network between AS events and splicing factors was constructed using Spearman correlation analysis. Based on the network topology, five candidate splice factors were identified. Among them, U2SURP, a poorly characterized serine/arginine-rich protein family member, was selected for further analysis in CM. Results indicated that U2SURP gene expression was significantly negatively correlated with the Immune Infiltration Score, the infiltration levels of dendritic cells, gamma-delta T cells, natural killer (NK) cells, and cytotoxic cells, as well as the expression of the immune checkpoint gene PD-1, suggesting that U2SURP may serve as a potential target for CM immunotherapy. Experimental validation showed that U2SURP mRNA and protein were overexpressed in CM cells, and silencing of U2SURP using siRNA significantly reduced CM cell survival, proliferation and migration. Furthermore, single-cell functional analysis showed that U2SURP gene expression was positively correlated with CM cell proliferation and differentiation. This study systematically identified candidate splicing factors involved in CM and provided new insights into the role of U2SURP in CM progression. These findings contribute to a deeper understanding of the pathogenesis of CM and establish new approaches for identifying splicing-related cancer therapeutic targets.

PMID:40108329 | DOI:10.1038/s41598-025-93695-x

Zhongguo Dang Dai Er Ke Za Zhi. 2025 Mar 15;27(3):373-376. doi: 10.7499/j.issn.1008-8830.2409076.

ABSTRACT

The patient is a male neonate born at term. He was admitted 16 minutes after birth due to stridor and inspiratory respiratory distress. Physical examination revealed a cleft palate, and a grade II systolic ejection murmur was audible at the left sternal border. Whole exome sequencing identified a heterozygous variant in the SON gene, c.5753-5756del (p.Val1918GlufsTer87), which was absent in either parent, indicating a de novo mutation. According to the guidelines of the American College of Medical Genetics and Genomics, this was classified as a "pathogenic variant" leading to a diagnosis of Zhu-Tokita-Takenouchi-Kim (ZTTK) syndrome. Upon admission, symptomatic supportive treatment was provided. Follow-up at the age of 8 months revealed persistent stridor; the infant could only consume small amounts of milk and was unable to sit steadily. This patient represents the youngest reported case to date, and his symptoms expand the clinical spectrum of the disease, providing valuable insights for clinical diagnosis and treatment.

PMID:40105086 | DOI:10.7499/j.issn.1008-8830.2409076

Arq Neuropsiquiatr. 2025 Feb;83(2):1-6. doi: 10.1055/s-0045-1804920. Epub 2025 Mar 19.

ABSTRACT

BACKGROUND: Patients with neuromuscular diseases (NMDs) often face swallowing difficulties (dysphagia) as part of their condition.

OBJECTIVE: To determine the prevalence of self-reported swallowing disorders in patients with rare NMDs and examine their correlation with related quality of life (QoL).

METHODS: The study included 103 patients with confirmed rare NMDs. Dysphagia risk was assessed using the validated Eating Assessment Tool-10 (EAT-10), and QoL related to swallowing was measured with the SWAL-QoL survey. Correlations between EAT-10 and SWAL-QoL scores were analyzed. Additionally, the mean questionnaire scores were compared among patients classified as dysphagic, dysphagic with high aspiration risk, and nondysphagic.

RESULTS: The estimated prevalence of dysphagia in the cohort, based on EAT-10, was 52.4%. Higher scores were significantly correlated with poorer swallowing-related QoL, except for the sleep domain. The most affected SWAL-QoL domains were burden, eating desire, eating duration, food selection, communication, fear, mental health, social functioning, and dysphagia battery score (DBS), with significant differences observed among the classifications (p < 0.001 for most domains, and p = 0.015 for eating desire). No statistically significant difference in swallowing QoL was found between sitters and walkers.

CONCLUSION: Dysphagia is a prevalent symptom in patients with rare NMDs, affecting 52.4% of the cohort and significantly impacting QoL in nearly all domains except sleep.

PMID:40107292 | DOI:10.1055/s-0045-1804920

Endocr Pract. 2025 Mar 17:S1530-891X(25)00073-4. doi: 10.1016/j.eprac.2025.03.005. Online ahead of print.

ABSTRACT

OBJECTIVE: We evaluated the efficacy of somapacitan in a 24-week, randomized, active-controlled study in patients with growth hormone deficiency (GHD) who experienced fatigue from daily growth hormone (GH) injections.

METHODS: 29 adult patients with GHD, pre-treated with daily GH for ≥ 5 years, who had reported treatment-related fatigue, were randomized to somapacitan or daily GH. Outcome measures were changes in treatment satisfaction assessed by Treatment Satisfaction Questionnaire for Medication-9 (TSQM-9), IGF-1 SDS, glucose and lipid parameters, body composition, bone mineral density (BMD), carotid intima media thickness and reactive hyperaemia index, from baseline to week 24.

RESULTS: The difference in change in TSQM-9 score for convenience was significant, in favor of somapacitan (estimated difference, somapacitan-daily GH [95% CI]:23.2 [7.9; 38.4] points, P=0.004). No differences between treatment arms in estimated changes from baseline to study-end were observed for IGF-1 levels, glucose and lipid profile, visceral adipose tissue, fat mass (%), lean body mass, and vascular parameters. There was significant difference in BMD of the lumbar spine (estimated difference, somapacitan-daily GH [95% CI]-0.036 (-0.064, -0.009) gr/cm2, P=0.011).

CONCLUSION: In AGHD patients who were fatigued from the long-term daily GH injections, somapacitan was reported to be more convenient than daily GH. It was effective in maintaining IGF-1 levels and body composition, glucose, lipids, and vascular parameters, comparable to daily GH. Non-significant decrease in BMD with somapacitan could reflect a favorable increase in bone metabolic units, as previously observed in naïve patients with GHD during the initial 6-month period of GH therapy.

PMID:40107502 | DOI:10.1016/j.eprac.2025.03.005

Transplant Cell Ther. 2025 Mar 17:S2666-6367(25)01095-4. doi: 10.1016/j.jtct.2025.03.007. Online ahead of print.

ABSTRACT

Chimeric antigen receptor-T (CAR-T) cell therapy is a novel therapy for the treatment of different hematological malignancies. Besides its efficiency, CAR-T cell therapy is associated with significant toxicity, primarily manifested as cytokine release syndrome (CRS) and neurotoxicity. However, there are reports that CAR-T cell therapy is also nephrotoxic and this aspect attracted so far less attention. In this review, we focus on the incidence and association between CAR-T cell therapy and kidney injury. Here, we describe risk factors, biomarkers, and potential reasons for acute kidney injury (AKI) and chronic kidney disease (CKD) related to CAR-T cell therapy to shed light on pathomechanisms leading to renal impairment, as well as to the association of kidney failure with other side effects of CAR-T cell therapy. We also review the toxicity of different types of CAR-T cell products, the impact of nephrotoxicity on CAR-T cell therapy efficacy, and the safety of lymphodepletion in patients with baseline AKI or CKD.

PMID:40107382 | DOI:10.1016/j.jtct.2025.03.007

J Cyst Fibros. 2025 Mar 18:S1569-1993(25)00058-X. doi: 10.1016/j.jcf.2025.02.009. Online ahead of print.

ABSTRACT

INTRODUCTION: The Liverpool Epidemic Strain (LES) of Pseudomonas aeruginosa is one of several known strains to be transmissible between persons with cystic fibrosis (CF) (pwCF) and the only known strain to have infected large proportions of CF populations on two continents. Despite its prevalence, efforts to understand its spread have proven elusive.

METHODS: We leveraged a prospective collection of P. aeruginosa isolates from pwCF attending the Southern Alberta Adult CF clinic from 1986 to 2020 to identify all individuals with LES infection. LES isolates collected every 1-2 years from each pwCF were sequenced and compared with 171 published LES genomes by phylogenetic analysis.

RESULTS: Of 395 pwCF screened, ten pwCF infected with the LES were identified, from whom 46 LES isolates were sequenced. The earliest LES isolate was recovered in 1986, ∼2 years earlier than the previously oldest published LES isolate recovered in the UK. Phylogenetic analysis identified a diverse set of isolates at the root of the LES phylogeny that formed four clades, one of which gave rise to a "classic LES" clade. Canadian isolates formed a paraphyletic group that included the root of this clade and out of which the UK LES clade emerged. We estimated the date of the most recent common ancestor (MRCA) of the UK LES clade as 1977.

CONCLUSIONS: Our study provides genomic evidence in support of a silent epidemic of LES infection occurring in the late 1970s among pwCF first originating in Canada and being spread to the UK, where transmission markedly accelerated.

PMID:40107913 | DOI:10.1016/j.jcf.2025.02.009

J Cyst Fibros. 2025 Mar 18:S1569-1993(25)00072-4. doi: 10.1016/j.jcf.2025.03.005. Online ahead of print.

NO ABSTRACT

PMID:40107911 | DOI:10.1016/j.jcf.2025.03.005

J Dent. 2025 Mar 17:105690. doi: 10.1016/j.jdent.2025.105690. Online ahead of print.

ABSTRACT

OBJECTIVES: The graded diagnosis of periodontitis has always been a difficulty for dentists. This systematic review aimed to investigate the performance of artificial intelligence (AI) models for periodontitis classification.

DATA: This review includes original studies that explore the application of AI in periodontitis classification systems.

SOURCES: Two reviewers independently conducted a comprehensive search of literature published up to April 2024 in databases including PubMed, Web of Science, MEDLINE, Scopus, and Cochrane Library.

STUDY SELECTION: A total of 28 articles were eventually included in this study, from which 10 mapping parameters were extracted and evaluated separately for each article.

RESULTS: AI's diagnostic capabilities are comparable to those of a general dentist/periodontist, achieving an overall diagnostic accuracy rate of over 70% for periodontitis classification, with some reaching 80-90%. Variations in diagnosis accuracy rates were observed across different stages of periodontitis.

CONCLUSIONS: The AI model provides a novel and relatively reliable method for periodontitis classification. However, several key issues remain to be addressed, including access to and quality of data, interpretation of the decision-making process of the model, the ability of the model to generalize, and ethical and privacy considerations.

CLINICAL SIGNIFICANCE: The development of AI models for periodontitis classification is expected to assist dentists in improving diagnostic efficiency and enhancing diagnostic accuracy, and further development is expected to assist telemedicine and home self-testing.

PMID:40107599 | DOI:10.1016/j.jdent.2025.105690

Prog Retin Eye Res. 2025 Mar 17:101353. doi: 10.1016/j.preteyeres.2025.101353. Online ahead of print.

ABSTRACT

BACKGROUND: AI-powered image generation technology holds the potential to dramatically reshape clinical ophthalmic practice. The adoption of this technology relies on clinician acceptance, yet it is an unfamiliar technology for both ophthalmic researchers and clinicians. In this work we present a literature review on the application of image generation technology in ophthalmology to discuss its theoretical applications and future role.

METHODS: First, we explore the key model designs used for image synthesis, including generative adversarial networks, autoencoders, and diffusion models. We then perform a survey of the literature for image generation technology in ophthalmology prior to September 2024, collecting the type of model used, as well as its clinical application, for each study. Finally, we discuss the limitations of this technology, the risks of its misuse and the future directions of research in this field.

RESULTS: Applications of this technology include improving diagnostic model performance, inter-modality image transformation, treatment and disease prognosis, image denoising, and education. Key challenges for integration of this technology into ophthalmic clinical practice include bias in generative models, risk to patient data security, computational and logistical barriers to model development, challenges with model explainability, inconsistent use of validation metrics between studies and misuse of synthetic images. Looking forward, researchers are placing a further emphasis on clinically grounded metrics, the development of image generation foundation models and the implementation of methods to ensure data provenance.

CONCLUSION: It is evident image generation technology has the potential to benefit the field of ophthalmology for many tasks, however, compared to other medical applications of AI, it is still in its infancy. This review aims to enable ophthalmic researchers to identify the optimal model and methodology to best take advantage of this technology.

PMID:40107410 | DOI:10.1016/j.preteyeres.2025.101353

Heart Rhythm. 2025 Mar 17:S1547-5271(25)02192-7. doi: 10.1016/j.hrthm.2025.03.1955. Online ahead of print.

ABSTRACT

BACKGROUND: CARTONET is a cloud-based system for the analysis of ablation procedures using the CARTO system. The current CARTONET R14 model employs deep learning, but its accuracy and positive predictive value (PPV) remain under-evaluated.

OBJECTIVE: This study aimed to compare the characteristics of the CARTONET system between the R12.1 and the R14 models.

METHODS: Data from 396 atrial fibrillation ablation cases were analyzed. Using a CARTONET R14 model, the sensitivity and PPV of the automated anatomical location model were investigated. The distribution of potential reconnection sites and confidence level for each site were investigated. We also compared the difference in that data between the CARTONET R12.1, the previous CARTONET version, and the CARTONET R14 models.

RESULTS: We analyzed the overall tags of 39169 points and the gap prediction of 625 segments using the CARTONET R14 model. The sensitivity and PPV of the R14 model significantly improved compared to that of the R12.1 model (R12.1 vs. R14; sensitivity, 71.2% vs. 77.5%, p<0.0001; PPV, 85.6 % vs. 86.2 %, p=0.0184). The incidence of reconnections was highly observed in the posterior area of the RPVs and LPVs (RPV, 98/238 [41.2%]; LPV 190/387 [49.1%]). On the other hand, the possibility of reconnection was highest in the roof area for the RPVs and LPVs (%; RPV, 14 [5.5-41]; LPV, 16 [8-22]).

CONCLUSION: The R14 model significantly improved sensitivity and PPV compared to the R12.1 model. The tendency for predicting potential reconnection sites was similar to the previous version, the R12 model.

PMID:40107403 | DOI:10.1016/j.hrthm.2025.03.1955

Comput Med Imaging Graph. 2025 Mar 15;123:102526. doi: 10.1016/j.compmedimag.2025.102526. Online ahead of print.

ABSTRACT

In Pancreatic Ductal Adenocarcinoma (PDAC), predicting genetic mutations directly from histopathological images using Deep Learning can provide valuable insights. The combination of several omics can provide further knowledge on mechanisms underlying tumor biology. This study aimed at developing an explainable multimodal pipeline to predict genetic mutations for the KRAS, TP53, SMAD4, and CDKN2A genes, integrating pathomic features with transcriptomics from two independent datasets, the TCGA-PAAD, assumed as training set, and the CPTAC-PDA, as external validation set. Large and small configurations of CLAM (Clustering-constrained Attention Multiple Instance Learning) models were evaluated with three different feature extractors (ResNet50, UNI, and CONCH). RNA-seq data were pre-processed both conventionally and using three autoencoder architectures. The processed transcript panels were input into machine learning (ML) models for mutation classification. Attention maps and SHAP were employed, highlighting significant features from both data modalities. A fusion layer or a voting mechanism combined the outputs from pathomic and transcriptomic models, obtaining a multimodal prediction. Performance comparisons were assessed by Area Under Receiver Operating Characteristic (AUROC) and Precision-Recall (AUPRC) curves. On the validation set, for KRAS, multimodal ML achieved 0.92 of AUROC and 0.98 of AUPRC. For TP53, the multimodal voting model achieved 0.75 of AUROC and 0.85 of AUPRC. For SMAD4 and CDKN2A, transcriptomic ML models achieved AUROC of 0.71 and 0.65, while multimodal ML showed AUPRC of 0.39 and 0.37, respectively. This approach demonstrated the potential of combining pathomics with transcriptomics, offering an interpretable framework for predicting key genetic mutations in PDAC.

PMID:40107149 | DOI:10.1016/j.compmedimag.2025.102526

Comput Med Imaging Graph. 2025 Mar 13;123:102525. doi: 10.1016/j.compmedimag.2025.102525. Online ahead of print.

ABSTRACT

Accurate segmentation of the tumor regions of nasopharyngeal carcinoma (NPC) is of significant importance for radiotherapy of NPC. However, the precision of existing automatic segmentation methods for NPC remains inadequate, primarily manifested in the difficulty of tumor localization and the challenges in delineating blurred boundaries. Additionally, the black-box nature of deep learning models leads to insufficient quantification of the confidence in the results, preventing users from directly understanding the model's confidence in its predictions, which severely impacts the clinical application of deep learning models. This paper proposes an automatic segmentation model for NPC based on confidence quantitative evaluation (CQENet). To address the issue of insufficient confidence quantification in NPC segmentation results, we introduce a confidence assessment module (CAM) that enables the model to output not only the segmentation results but also the confidence in those results, aiding users in understanding the uncertainty risks associated with model outputs. To address the difficulty in localizing the position and extent of tumors, we propose a tumor feature adjustment module (FAM) for precise tumor localization and extent determination. To address the challenge of delineating blurred tumor boundaries, we introduce a variance attention mechanism (VAM) to assist in edge delineation during fine segmentation. We conducted experiments on a multicenter NPC dataset, validating that our proposed method is effective and superior to existing state-of-the-art models, possessing considerable clinical application value.

PMID:40107148 | DOI:10.1016/j.compmedimag.2025.102525

Artif Intell Med. 2025 Mar 15;163:103114. doi: 10.1016/j.artmed.2025.103114. Online ahead of print.

ABSTRACT

OBJECTIVE: Malaria remains a leading cause of global morbidity and mortality, responsible for approximately 5,97,000 deaths according to World Malaria Report 2024. The study aims to systematically review current methodologies for automated analysis of the Plasmodium genus in malaria diagnostics. Specifically, it focuses on computer-assisted methods, examining databases, blood smear types, staining techniques, and diagnostic models used for malaria characterization while identifying the limitations and contributions of recent studies.

METHODS: A systematic literature review was conducted following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. Peer-reviewed and published studies from 2020 to 2024 were retrieved from Web of Science and Scopus. Inclusion criteria focused on studies utilizing deep learning and machine learning models for automated malaria detection from microscopic blood smears. The review considered various blood smear types, staining techniques, and diagnostic models, providing a comprehensive evaluation of the automated diagnostic landscape for malaria.

RESULTS: The NIH database is the standardized and most widely tested database for malaria diagnostics. Giemsa stained-thin blood smear is the most efficient diagnostic method for the detection and observation of the plasmodium lifecycle. This study has been able to identify three categories of ML models most suitable for digital diagnostic of malaria, i.e., Most Accurate- ResNet and VGG with peak accuracy of 99.12 %, Most Popular- custom CNN-based models used by 58 % of studies, and least complex- CADx model. A few pre and post-processing techniques like Gaussian filter and auto encoder for noise reduction have also been discussed for improved accuracy of models.

CONCLUSION: Automated methods for malaria diagnostics show considerable promise in improving diagnostic accuracy and reducing human error. While deep learning models have demonstrated high performance, challenges remain in data standardization and real-world application. Addressing these gaps could lead to more reliable and scalable diagnostic tools, aiding global malaria control efforts.

PMID:40107120 | DOI:10.1016/j.artmed.2025.103114

Artif Intell Med. 2025 Mar 17;163:103110. doi: 10.1016/j.artmed.2025.103110. Online ahead of print.

ABSTRACT

Deep learning has been successfully applied to histopathology image classification tasks. However, the performance of deep models is data-driven, and the acquisition and annotation of pathological image samples are difficult, which limit the model's performance. Compared to whole slide images (WSI) of patients, histopathology image datasets of animal models are easier to acquire and annotate. Therefore, this paper proposes an unsupervised domain adaptation method based on semantic correlation clustering for histopathology image classification. The aim is to utilize Minmice model histopathology image dataset to achieve the classification and recognition of human WSIs. Firstly, the multi-scale fused features extracted from the source and target domains are normalized and mapped. In the new feature space, the cosine distance between class centers is used to measure the semantic correlation between categories. Then, the domain centers, class centers, and sample distributions are self-constrainedly aligned. Multi-granular information is applied to achieve cross-domain semantic correlation knowledge transfer between classes. Finally, the probabilistic heatmap is used to visualize the model's prediction results and annotate the cancerous regions in WSIs. Experimental results show that the proposed method has high classification accuracy for WSI, and the annotated result is close to manual annotation, indicating its potential for clinical applications.

PMID:40107119 | DOI:10.1016/j.artmed.2025.103110

Med Image Anal. 2025 Mar 13;102:103541. doi: 10.1016/j.media.2025.103541. Online ahead of print.

ABSTRACT

The understanding of the convoluted evolution of infant brain networks during the first postnatal year is pivotal for identifying the dynamics of early brain connectivity development. Thanks to the valuable insights into the brain's anatomy, existing deep learning frameworks focused on forecasting the brain evolution trajectory from a single baseline observation. While yielding remarkable results, they suffer from three major limitations. First, they lack the ability to generalize to multi-trajectory prediction tasks, where each graph trajectory corresponds to a particular imaging modality or connectivity type (e.g., T1-w MRI). Second, existing models require extensive training datasets to achieve satisfactory performance which are often challenging to obtain. Third, they do not efficiently utilize incomplete time series data. To address these limitations, we introduce FedGmTE-Net++, a federated graph-based multi-trajectory evolution network. Using the power of federation, we aggregate local learnings among diverse hospitals with limited datasets. As a result, we enhance the performance of each hospital's local generative model, while preserving data privacy. The three key innovations of FedGmTE-Net++ are: (i) presenting the first federated learning framework specifically designed for brain multi-trajectory evolution prediction in a data-scarce environment, (ii) incorporating an auxiliary regularizer in the local objective function to exploit all the longitudinal brain connectivity within the evolution trajectory and maximize data utilization, (iii) introducing a two-step imputation process, comprising a preliminary K-Nearest Neighbours based precompletion followed by an imputation refinement step that employs regressors to improve similarity scores and refine imputations. Our comprehensive experimental results showed the outperformance of FedGmTE-Net++ in brain multi-trajectory prediction from a single baseline graph in comparison with benchmark methods. Our source code is available at https://github.com/basiralab/FedGmTE-Net-plus.

PMID:40107118 | DOI:10.1016/j.media.2025.103541

Eur J Cancer. 2025 Mar 15;220:115367. doi: 10.1016/j.ejca.2025.115367. Online ahead of print.

ABSTRACT

BACKGROUND: Decisions on the best available treatment in clinical oncology are based on expert opinions in multidisciplinary cancer conferences (MCC). Artificial intelligence (AI) could increase evidence-based treatment by generating additional treatment recommendations (TR). We aimed to develop such an AI system for urothelial carcinoma (UC) and renal cell carcinoma (RCC).

METHODS: Comprehensive data of patients with histologically confirmed UC and RCC who received MCC recommendations in the years 2015 - 2022 were transformed into machine readable representations. Development of a two-step process to train a classifier to mimic TR was followed by identification of superordinate and detailed categories of TR. Machine learning (CatBoost, XGBoost, Random Forest) and deep learning (TabPFN, TabNet, SoftOrdering CNN, FCN) techniques were trained. Results were measured by F1-scores for accuracy weights.

RESULTS: AI training was performed with 1617 (UC) and 880 (RCC) MCC recommendations (77 and 76 patient input parameters). The AI system generated fully automated TR with excellent F1-scores for UC (e.g. 'Surgery' 0.81, 'Anti-cancer drug' 0.83, 'Gemcitabine/Cisplatin' 0.88) and RCC (e.g. 'Anti-cancer drug' 0.92 'Nivolumab' 0.78, 'Pembrolizumab/Axitinib' 0.89). Explainability is provided by clinical features and their importance score. Finally, TR and explainability were visualized on a dashboard.

CONCLUSION: This study demonstrates for the first time AI-generated, explainable TR in UC and RCC with excellent performance results as a potential support tool for high-quality, evidence-based TR in MCC. The comprehensive technical and clinical development sets global reference standards for future AI developments in MCC recommendations in clinical oncology. Next, prospective validation of the results is mandatory.

PMID:40107091 | DOI:10.1016/j.ejca.2025.115367

Comput Biol Med. 2025 Mar 18;190:110029. doi: 10.1016/j.compbiomed.2025.110029. Online ahead of print.

ABSTRACT

BACKGROUND: Neurological disorders, particularly Parkinson's Disease (PD), are serious and progressive conditions that significantly impact patients' motor functions and overall quality of life. Accurate and timely diagnosis is still crucial, but it is quite challenging. Understanding the changes in the brain linked to PD requires using neuroimaging modalities like magnetic resonance imaging (MRI). Artificial intelligence (AI), particularly deep learning (DL) methods, can potentially improve the precision of diagnosis.

METHOD: In the current study, we present a novel approach that integrates T1-weighted structural MRI and rest-state functional MRI using multi-site-cum-multi-modality neuroimaging data. To maximize the richness of the data, our approach integrates deep feature-level fusion across these modalities. We proposed a custom multi-scale 2D Convolutional Neural Network (CNN) architecture that captures features at different spatial scales, enhancing the model's capacity to learn PD-related complex patterns.

RESULTS: With an accuracy of 97.12 %, sensitivity of 97.26 %, F1-Score of 97.63 %, Area Under the Curve (AUC) of 0.99, mean average precision (mAP) of 99.53 %, and Dice Coefficient of 0.97, the proposed Neuro_DeFused-Net diagnostic model performs exceptionally well. These results highlight the model's robust ability to distinguish PD patients from Controls (Normal), even across a variety of datasets and neuroimaging modalities.

CONCLUSIONS: Our findings demonstrate the transformational ability of AI-driven models to facilitate the early diagnosis of PD. The proposed Neuro_DeFused-Net model enables the rapid detection of health markers through fast analysis of complicated neuroimaging data. Thus, timely intervention and individualized treatment strategies lead to improved patient outcomes and quality of life.

PMID:40107026 | DOI:10.1016/j.compbiomed.2025.110029

Eur Respir Rev. 2025 Mar 19;34(175):240147. doi: 10.1183/16000617.0147-2024. Print 2025 Jan.

ABSTRACT

Heat shock protein 90 (HSP 90) and its isoforms are a group of homodimeric proteins that regulate several cellular processes, such as the elimination of misfolded proteins, cell development and post-translational modifications of kinase proteins and receptors. Due to its involvement in extracellular matrix (ECM) remodelling, myofibroblast differentiation and apoptosis, HSP 90 has been investigated as a key player in the pathogenesis of lung fibrosis. Idiopathic pulmonary fibrosis (IPF) is the most common and deadly interstitial lung disease, due to the progressive distortion of lung parenchyma related to the overproduction and deposition of altered ECM, driven by transforming growth factor-β (TGF-β) dependent and independent pathways. The inhibition or induction of HSP 90 is associated with a reduced or increased expression of TGF-β receptors, respectively, suggesting a role for HSP 90 as a biomarker and therapeutic target in IPF. Experimental drugs such as geldanamycin and its derivatives 17-AAG (17-N-allylamino-17-demethoxygeldanamicin) and 17-DMAG (17-dimethylaminoethylamino-17-demethoxigeldanamycin), along with AUY-922, 1G6-D7, AT-13387, TAS-116 and myricetin, have been found to reduce lung fibrosis in both in vivo and in vitro models, supporting the role of this emerging target. This review aims to illustrate the structure and biological function of HSP 90 in the context of IPF pathobiology, as well as perspective application of this molecule as a biomarker and therapeutic target for IPF.

PMID:40107664 | DOI:10.1183/16000617.0147-2024

Eur Respir Rev. 2025 Mar 19;34(175):240238. doi: 10.1183/16000617.0238-2024. Print 2025 Jan.

ABSTRACT

BACKGROUND: Comorbidities can affect drug tolerability and health outcomes in patients with fibrotic interstitial lung disease. This systematic review and meta-analysis evaluated the types and prevalence of comorbidities amongst participants in pharmaceutical randomised controlled trials (RCTs) of idiopathic pulmonary fibrosis (IPF) and progressive pulmonary fibrosis (PPF).

METHODS: Ovid Medline, Embase and CENTRAL databases were searched to identify phase II and III pharmaceutical RCTs of IPF or PPF. Reporting of comorbidities was evaluated, with meta-analyses being performed for the prevalence of different conditions.

RESULTS: 34 articles were included, with 23 unique trials for IPF and one for PPF. A mean of 14 (range 1-44) comorbidities per study was reported in the IPF RCTs, with 11 being reported in the PPF RCT. Common comorbidities in the IPF RCT cohorts were systemic hypertension (pooled prevalence 45%, 95% CI 39-50%), hyperlipidaemia (38%, 95% CI 27-49%), gastro-oesophageal reflux disease (45%, 95% CI 36-54%), ischaemic heart disease (18%, 95% CI 13-42%) and diabetes mellitus (16%, 95% CI 13-20%). The PPF trial cohort had similar types and prevalence of comorbidities to those reported in the IPF trial cohorts.

CONCLUSIONS: Reporting of comorbidities varied across previous IPF RCTs, with limited data available for PPF. Prevalence of comorbidities reported in the IPF and PPF trial cohorts appear to be lower than those reported in prospective patient registries. There is a need for careful consideration of trial eligibility criteria with detailed reporting of comorbidities in future pharmaceutical RCTs to better understand the applicability of trial findings to real-world patients.

PMID:40107663 | DOI:10.1183/16000617.0238-2024

Respir Investig. 2025 Mar 18;63(3):394-398. doi: 10.1016/j.resinv.2025.03.006. Online ahead of print.

ABSTRACT

Both serum and bronchoalveolar lavage fluid levels of galectin-3 (Gal-3) are elevated in patients with idiopathic pulmonary fibrosis (IPF). Phase II study on inhaler with Gal-3 inhibitor for IPF has been ongoing. In this study, 30 treatment-naive patients of IPF were prospectively enrolled and their sera were stored before and after nintedanib treatment. Though Gal-3 levels tended to increase after nintedanib treatment, in some patients, Gal-3 levels decreased immediately after the treatment. Patients whose serum Gal-3 levels decreased 1 month after nintedanib treatment tended to experience a smaller annual decline in forced vital capacity (FVC) than patients with increased Gal-3 levels. Furthermore, the rate of change in Gal-3 levels 1 month after nintedanib treatment positively correlated with the rate of annual FVC decline, whereas that of other fibrotic markers did not correlate with the rate of annual FVC decline. This study suggested that a decline in serum Gal-3 levels immediately after nintedanib treatment may predict less progression of IPF treated with nintedanib.

PMID:40107223 | DOI:10.1016/j.resinv.2025.03.006