Orphanet J Rare Dis. 2025 Mar 11;20(1):117. doi: 10.1186/s13023-025-03618-2.

ABSTRACT

BACKGROUND: The current development of gynecology services for children and adolescents seeks to meet needs both in the overall population and in patients with rare diseases. In France, the referral center for rare gynecological diseases specializes in four major types of conditions, namely, uterovaginal malformations, hereditary hemorrhagic diseases, rare benign breast diseases, and gynecological repercussions of rare chronic diseases.

OBJECTIVE: To describe consecutive patients who had a first visit in 2018-2023 at the referral center for rare gynecological diseases at the Necker Pediatric University Hospital in Paris, France, and who were diagnosed with a condition in any of the four categories listed above.

MATERIAL AND METHODS: For this single-center retrospective observational cohort study, data from the referral-center database were collected and reviewed. These data included year of birth, age at and reason for first gynecology visit, and rare chronic disease and referring rare-disease center for patients seen for gynecological repercussions of rare chronic diseases.

RESULTS: The 704 included patients had a median age of 15.2 years (interquartile range 3.8) at the first visit. Among them, 100 (14.2%) had uterovaginal malformations, 32 (4.6%) hereditary hemorrhagic diseases, 17 (2.4%) rare benign breast diseases, and 555 (78.8%) gynecological repercussions of rare chronic diseases. The leading reasons for the visit were dysmenorrhea (15.6%), menorrhagia (15.5%), uterovaginal malformations (15.2%), and irregular periods (14.9%).

CONCLUSION: Repercussions of rare chronic diseases managed at rare-disease referral centers were by far the leading reason for seeking gynecological expertise in rare diseases. In this complex situation, the underlying disease and its treatments interact with the gynecological manifestations and their treatment, requiring close collaboration among all specialists caring for each patient.

PMID:40069734 | DOI:10.1186/s13023-025-03618-2

Balkan J Med Genet. 2025 Mar 6;27(2):69-75. doi: 10.2478/bjmg-2024-0012. eCollection 2024 Dec.

ABSTRACT

Clopidogrel, a P2Y12 receptor antagonist, is widely used to prevent cardiovascular events, but significant variability in its efficacy persists among patients. AKR1D1, involved in bile acid synthesis and regulation of CYP enzymes, may contribute to this variability. This study aims to investigate whether clopidogrel and its inactive metabolite, 2-oxoclopidogrel, interact with AKR1D1 at the enzymatic or transcriptional level. Enzymatic activity assays demonstrated that neither clopidogrel nor 2-oxoclopidogrel acts as a substrate or inhibitor of AKR1D1. Expression studies in HepG2 cells further revealed no significant changes in AKR1D1 mRNA levels following treatment with these compounds. These findings indicate that clopidogrel does not directly influence AKR1D1's metabolic functions, including bile acid synthesis, steroid hormone clearance, or the production of 5β-reduced steroids, which regulate CYP enzyme expression. From a physiological perspective, the absence of interaction minimizes the risk of adverse effects on CYP-mediated drug metabolism, nutrient absorption, lipid digestion, and the absorption of lipophilic drugs. Future research should explore AKR1D1's broader substrate specificity, particularly focusing on non-steroidal compounds, and investigate the clinical implications of AKR1D1 polymorphisms in clopidogrel-treated patients to enhance personalized therapeutic strategies.

PMID:40070864 | PMC:PMC11892939 | DOI:10.2478/bjmg-2024-0012

Balkan J Med Genet. 2025 Mar 6;27(2):77-85. doi: 10.2478/bjmg-2024-0015. eCollection 2024 Dec.

ABSTRACT

The CYP2C19*2 c.681G>A (rs4244285) loss-of-function (LOF) allele has been associated with reduced clopidogrel efficacy and increased risk of major adverse cardiovascular events (MACE). PGx-guided treatment, despite the recommendations, is not fully implemented in routine clinical practice. The primary aim of this hybrid retrospective-prospective study was to determine whether identifying CYP2C19 LOF patients may benefit the antiplatelet drug prescribing decisions made in Kosovo. The study cohort consisted of clopidogrel treated patients presenting at the University Clinical Center in the period from December 2023 to May 2024. To evaluate the correlation between CYP2C19 LOF and the treatment outcome in a follow-up period of 2 years, we first assessed the CYP2C19*2 genotype using the Taq Man Real Time PCR method. Among 150 patients, 58 (19.33%) were identified as carriers CYP2C19*2 LOF allele. The observed allele distribution was significantly different when compared with the one reported for a healthy Kosovar population (13.03%). CYP2C19*2 LOF carriers exhibited a 1.6-fold higher probability of developing cardiovascular disease compared to non-carriers, based on allelic and codominant model of statistical analysis (OR=1.60; 95% CI=1.08-2.37; p=0.018 and OR=1.64; 95% CI=1.04-2.57; p=0.031, respectively). The median observation time of follow up was not reached until this analysis was conducted. Our data supports the potential association of the CYP2C19*2 LOF allele with an increased risk for CVD in the population of Kosovo. Our data add to the evidence advising careful consideration of CYP2C19 genetic diversity when recommending PGx-guided clopidogrel therapy, particularly in populations, such the Kosovar, where genetic determinants are not yet fully elucidated.

PMID:40070858 | PMC:PMC11892937 | DOI:10.2478/bjmg-2024-0015

Front Pharmacol. 2025 Feb 12;16:1523399. doi: 10.3389/fphar.2025.1523399. eCollection 2025.

ABSTRACT

Proton pump inhibitors (PPIs) are widely prescribed medications for the management of acid-related disorders, due to their effectiveness and favorable pharmacokinetics. However, the occurrence and severity of adverse drug reactions (ADRs) in patients using PPIs, particularly in relation to their association with CYP2C19 polymorphisms, are of great concern. This association has largely been investigated through observational studies, which have shown conflicting or weak findings. Therefore, this review aims to examine the current evidence regarding the long-term ADRs of PPIs and their link to CYP2C19 variants.

PMID:40070570 | PMC:PMC11894441 | DOI:10.3389/fphar.2025.1523399

Curr Drug Saf. 2025 Mar 11. doi: 10.2174/0115748863355987250223072145. Online ahead of print.

ABSTRACT

The growing popularity of personalized medicine presents new hazards and difficulties for pharmacovigilance. This implies that it needs to modify its current approach. This research examines how drug safety monitoring for certain medications evolves over time. We briefly discuss the connection between meticulous pharmacovigilance procedures and adaptable treatment approaches. We describe how pharmacogenetics may be used to make drugs safer and how genetic testing may be used to forecast a drug's potential side effects. With an emphasis on post-marketing monitoring in phase IV, we address shortcomings of research on pre-marketing and the need for a comprehensive strategy for medication safety. The significance of pharmacogenetics in reducing risk before exposure and the need to reconsider pharmacoepidemiological techniques for monitoring outcomes after exposure are discussed in the study. We emphasize the significance of including genetic patient-specific profiles in publications related to tailored therapy and the use of state-of-the-art computer techniques for data processing. We also discuss privacy, ethical, and data security issues that arise with precision medicine, emphasizing the consequences for patient consent and data management.

PMID:40070333 | DOI:10.2174/0115748863355987250223072145

Pharmacol Rep. 2025 Mar 12. doi: 10.1007/s43440-025-00707-8. Online ahead of print.

ABSTRACT

BACKGROUND: OSU6162, a monoamine stabilizer, has demonstrated efficacy in reducing alcohol and anxiety-related behaviors in preclinical settings. In a previous randomized, double-blind, placebo-controlled trial involving patients with alcohol dependence (AD), OSU6162 significantly reduced craving for alcohol but did not alter drinking behaviors. This retrospective secondary analysis explores whether genetic predispositions related to AD and associated traits might influence the response to OSU6162 treatment in original trial participants.

METHODS: Polygenic risk scores (PRSs) were calculated for 48 AD patients using PRSice-2 and genome-wide association study (GWAS) data for (i) alcohol use disorder and alcohol consumption, (ii) problematic alcohol use, (iii) drinks per week, (iv) major depression, and (v) anxiety (case-control comparisons and quantitative anxiety factor scores). Linear regression analyses, adjusted for population stratification, assessed interaction effects between PRSs and treatment type (OSU6162 or placebo) on various clinical outcomes.

RESULTS: Significant interactions were found between treatment type and anxiety factor score PRS at the genome-wide significance threshold. In the OSU6162-treated group, a higher anxiety PRS was associated with reductions in the number of drinks consumed (FDR = 0.0017), percentage of heavy drinking days (FDR = 0.0060), and percentage of drinking days (FDR = 0.0017), with a trend toward reduced blood phosphatidylethanol (PEth) levels (FDR = 0.068). These associations were absent in the placebo group.

CONCLUSIONS: These preliminary findings suggest that anxiety PRS may help predict response to OSU6162 treatment in AD. Further research with larger cohorts and more comprehensive genetic data is needed to confirm these results and advance personalized medicine approaches for alcohol use disorder.

PMID:40069537 | DOI:10.1007/s43440-025-00707-8

Am J Respir Crit Care Med. 2025 Mar 12. doi: 10.1164/rccm.202409-1824OC. Online ahead of print.

ABSTRACT

RATIONALE: Mycobacterium abscessus group bacteria (MABS) cause lethal infections in people with chronic lung diseases. Transmission mechanisms remain poorly understood; the detection of dominant circulating clones (DCCs) has suggested potential for person-to-person transmission.

OBJECTIVES: This study aimed to determine the role of drinking water in the transmission of MABS.

METHODS: A total of 289 isolates were cultured from respiratory samples (231) and drinking water sources (58) across Queensland, Australia.

MEASUREMENTS AND MAIN RESULTS: Whole genome sequences were analysed to identify DCCs and determine relatedness. Half of the isolates (144, 49·8%) clustered with previously described DCCs, of which 30 formed a clade within DCC5. Pangenomic analysis of the water-associated DCC5 clade revealed an enrichment of genes associated with copper resistance. Four instances of plausible epidemiological links were identified between genomically-related clinical and water isolates.

CONCLUSIONS: We provide evidence that drinking water is a reservoir for MABS and may be a vector in the chain of MABS infection.

PMID:40072241 | DOI:10.1164/rccm.202409-1824OC

Pediatr Pulmonol. 2025 Mar;60(3):e71044. doi: 10.1002/ppul.71044.

ABSTRACT

BACKGROUND: People with cystic fibrosis (pwCF) often have multifactorial peripheral muscle abnormalities attributed to, for example, malnutrition, steroid use, altered redox balance and, potentially, CF-specific intrinsic alterations. Malnutrition in CF now includes an increasing prevalence of overweight and obesity, particularly in those receiving CF transmembrane conductance regulator (CFTR) modulator therapy (CFTRm). We aimed to characterise peripheral muscle function and body composition in pwCF on Elexacaftor/Tezacaftor/Ivacaftor (ETI) CFTRm, compared to healthy controls.

METHODS: Fifteen pwCF on ETI, and 15 healthy age- and sex-matched controls (CON), underwent whole-body dual-energy X-ray absorptiometry scans, and a comprehensive evaluation of peripheral muscle function. Tests included quadriceps maximal isometric force measurement, an intermittent isometric quadriceps fatiguing protocol, handgrip strength dynamometry, squat jump height assessment, and 1-min sit-to-stand testing.

RESULTS: No significant differences in quadriceps maximal isometric force (CON: 181.60 ± 92.90 Nm vs. CF: 146.15 ± 52.48 Nm, p = 0.21, d = 0.47), handgrip strength (CON: 34 ± 15 kg vs. CF: 31 ± 11 kg, p = 0.62, d = 0.18), peripheral muscle endurance, fatigue, or power were observed between the groups. Moreover, no significant differences in whole-body, trunk or limb lean mass, fat-free mass, fat mass, or whole-body bone mineral density were evident.

CONCLUSION: Comparable peripheral muscle mass and function has been demonstrated in pwCF on ETI, albeit a group with good lung function. Research is needed to confirm these findings longitudinally in pwCF, including those with more severe lung disease, who are less physically active, and have less optimal nutrition and exercise support.

PMID:40071679 | DOI:10.1002/ppul.71044

Pediatr Pulmonol. 2025 Mar;60(3):e71042. doi: 10.1002/ppul.71042.

ABSTRACT

BACKGROUND: Genetic modifiers have been identified that increase the risks of lung disease and other complications, such as diabetes in people with cystic fibrosis (CF). Variants in the hemochromatosis gene (HFE) were reported in a study of adults to be associated with worse lung disease.

OBJECTIVES: To ascertain the frequency of HFE variants, particularly C282Y (c.845G > A) and H63D (c.187C > G) and to determine if they are associated with variations in the onset and early severity of CF lung disease as well as abnormalities in iron status.

DESIGN: We studied with whole genome sequencing and clinical outcome measures in a cohort of 104 children with CF at 5-6 years old who were previously found to show an association between aggregated genetic modifiers and an earlier onset and a more severe lung disease phenotype.

RESULTS: In our cohort, 23% have H63D and 11% have C282Y. Lung function at age 6 years and Pseudomonas aeruginosa infections did not differ by HFE variants, but having C282Y was associated with more pulmonary exacerbations in the first 6 years of life. Three patients have H63D/C282Y genotype, and all showed phenotypic expression of hemochromatosis with abnormal iron indices.

CONCLUSION: Our study revealed that the presence of HFE variant C282Y in people with CF may lead to more severe lung disease manifestations beginning in early childhood. There is a risk of hemochromatosis in CF patients with two HFE variants, and thus they should be followed for evidence of iron overload.

PMID:40071665 | DOI:10.1002/ppul.71042

Ther Adv Respir Dis. 2025 Jan-Dec;19:17534666251323181. doi: 10.1177/17534666251323181. Epub 2025 Mar 12.

ABSTRACT

Nontuberculous mycobacteria (NTM) are ubiquitous, opportunistic pathogens that can cause lung disease in people with non-cystic fibrosis bronchiectasis (NCFB) and cystic fibrosis (CF). The incidence of NTM pulmonary infections and lung disease has continued to increase worldwide over the last decade among both groups. Notably, women with NCFB NTM pulmonary disease (NTM-PD) bear a disproportionate burden with NTM rates increasing in this population as well as having consistently higher incidence of NTM-PD compared to men. In contrast, among people with CF, an overall increased risk among women has not been observed. In the United States, the majority of people with CF are taking highly effective cystic fibrosis transmembrane conductance regulator (CFTR) modulators, and these numbers are increasing worldwide. The long-term impact of CFTR modulator medications on NTM infections is not entirely understood. Guidelines for the screening, diagnosis, and management of NTM-PD exist for people with NCFB and CF, but do not consider unique implications relevant to women. This review highlights aspects of NTM-PD among women with NCFB and CF, including the epidemiology of NTM infection, special considerations for treatment, and unmet research needs relevant to women with NTM-PD.

PMID:40071337 | DOI:10.1177/17534666251323181

Ital J Pediatr. 2025 Mar 11;51(1):71. doi: 10.1186/s13052-025-01918-8.

ABSTRACT

INTRODUCTION: Children with congenital lung disease (CLD) may suffer from long-term complications, such as impairments in lung growth, decreased total lung volume, recurrent lower respiratory tract infections and, in some cases, malignant transformation.

OBJECTIVE AND METHODS: we described retrospective data on diagnostic process, clinical and functional data regarding a cohort of symptomatic and asymptomatic children with CLD followed in a single third level center in the last twenty years.

RESULTS: 91 children were included in the study. Five classes of disease were examined. Bronchial tree and pulmonary abnormalities represent the most common anomalies. Despite the improved resolution of prenatal diagnosis, most of patients underwent chest CT scan to confirm the initial diagnostic suspicion. The most reported symptoms were wheezing, recurrent respiratory infections and acute respiratory failure. According to malformation type, patients underwent to surgery, endoscopic and/or medical treatment. Improvement of symptoms occurred faster in patients surgically and endoscopically treated. No statistical difference in the number of exacerbations before and after treatment was recorded, as well as no differences in spirometry values were observed among surgically and non-surgically treated children. No malignant transformation was observed in two patients with intra-lobar sequestration and hybrid lesion during the follow up period.

CONCLUSION: the clinical presentation of congenital airway and lung disorders varies significantly depending on the type of malformation, making it challenging to standardize treatment strategies and follow-up programs. Based on our experience, prompt surgical or endoscopic intervention in early symptomatic children leads to faster symptom improvement and normal lung function in the follow-up period. However, further prospective studies are needed to better define optimal treatment strategies for these rare conditions, particularly for asymptomatic patients, for whom management approaches remain poorly established.

PMID:40069796 | DOI:10.1186/s13052-025-01918-8

Orphanet J Rare Dis. 2025 Mar 11;20(1):117. doi: 10.1186/s13023-025-03618-2.

ABSTRACT

BACKGROUND: The current development of gynecology services for children and adolescents seeks to meet needs both in the overall population and in patients with rare diseases. In France, the referral center for rare gynecological diseases specializes in four major types of conditions, namely, uterovaginal malformations, hereditary hemorrhagic diseases, rare benign breast diseases, and gynecological repercussions of rare chronic diseases.

OBJECTIVE: To describe consecutive patients who had a first visit in 2018-2023 at the referral center for rare gynecological diseases at the Necker Pediatric University Hospital in Paris, France, and who were diagnosed with a condition in any of the four categories listed above.

MATERIAL AND METHODS: For this single-center retrospective observational cohort study, data from the referral-center database were collected and reviewed. These data included year of birth, age at and reason for first gynecology visit, and rare chronic disease and referring rare-disease center for patients seen for gynecological repercussions of rare chronic diseases.

RESULTS: The 704 included patients had a median age of 15.2 years (interquartile range 3.8) at the first visit. Among them, 100 (14.2%) had uterovaginal malformations, 32 (4.6%) hereditary hemorrhagic diseases, 17 (2.4%) rare benign breast diseases, and 555 (78.8%) gynecological repercussions of rare chronic diseases. The leading reasons for the visit were dysmenorrhea (15.6%), menorrhagia (15.5%), uterovaginal malformations (15.2%), and irregular periods (14.9%).

CONCLUSION: Repercussions of rare chronic diseases managed at rare-disease referral centers were by far the leading reason for seeking gynecological expertise in rare diseases. In this complex situation, the underlying disease and its treatments interact with the gynecological manifestations and their treatment, requiring close collaboration among all specialists caring for each patient.

PMID:40069734 | DOI:10.1186/s13023-025-03618-2

J Med Internet Res. 2025 Mar 12;27:e68442. doi: 10.2196/68442.

ABSTRACT

BACKGROUND: Hypertension is a major global health issue and a significant modifiable risk factor for cardiovascular diseases, contributing to a substantial socioeconomic burden due to its high prevalence. In China, particularly among populations living near desert regions, hypertension is even more prevalent due to unique environmental and lifestyle conditions, exacerbating the disease burden in these areas, underscoring the urgent need for effective early detection and intervention strategies.

OBJECTIVE: This study aims to develop, calibrate, and prospectively validate a 2-year hypertension risk prediction model by using large-scale health examination data collected from populations residing in 4 regions surrounding the Taklamakan Desert of northwest China.

METHODS: We retrospectively analyzed the health examination data of 1,038,170 adults (2019-2021) and prospectively validated our findings in a separate cohort of 961,519 adults (2021-2023). Data included demographics, lifestyle factors, physical examinations, and laboratory measurements. Feature selection was performed using light gradient-boosting machine-based recursive feature elimination with cross-validation and Least Absolute Shrinkage and Selection Operator, yielding 24 key predictors. Multiple machine learning (logistic regression, random forest, extreme gradient boosting, light gradient-boosting machine) and deep learning (Feature Tokenizer + Transformer, SAINT) models were trained with Bayesian hyperparameter optimization.

RESULTS: Over a 2-year follow-up, 15.20% (157,766/1,038,170) of the participants in the retrospective cohort and 10.50% (101,077/961,519) in the prospective cohort developed hypertension. Among the models developed, the CatBoost model demonstrated the best performance, achieving area under the curve (AUC) values of 0.888 (95% CI 0.886-0.889) in the retrospective cohort and 0.803 (95% CI 0.801-0.804) in the prospective cohort. Calibration via isotonic regression improved the model's probability estimates, with Brier scores of 0.090 (95% CI 0.089-0.091) and 0.102 (95% CI 0.101-0.103) in the internal validation and prospective cohorts, respectively. Participants were ranked by the positive predictive value calculated using the calibrated model and stratified into 4 risk categories (low, medium, high, and very high), with the very high group exhibiting a 41.08% (5741/13,975) hypertension incidence over 2 years. Age, BMI, and socioeconomic factors were identified as significant predictors of hypertension.

CONCLUSIONS: Our machine learning model effectively predicted the 2-year risk of hypertension, making it particularly suitable for preventive health care management in high-risk populations residing in the desert regions of China. Our model exhibited excellent predictive performance and has potential for clinical application. A web-based application was developed based on our predictive model, which further enhanced the accessibility for clinical and public health use, aiding in reducing the burden of hypertension through timely prevention strategies.

PMID:40072485 | DOI:10.2196/68442

J Biomol Struct Dyn. 2025 Mar 12:1-13. doi: 10.1080/07391102.2025.2475229. Online ahead of print.

ABSTRACT

Prediction of protein-ligand interactions is critical for drug discovery and repositioning. Traditional prediction methods are computationally intensive and limited in modeling structural changes. In contrast, data-driven deep learning methods significantly reduce computational costs and offer a more efficient approach for drug discovery. However, existing models often fail to fully exploit metadata and low-frequency features, leading to suboptimal performance on sparse, imbalanced datasets. To address these challenges, this paper proposes a novel interaction prediction model based on heterogeneous graphs and data enhancement, named Heterogeneous Graph Enhanced Fusion Network (HGEF-Net). The model utilizes a heterogeneous information learning module, which deeply analyzes molecular subgraphs and substructures, fully leveraging metadata features to better capture the biological interactions between ligands and proteins. Additionally, to address the issue of low-frequency category features, a data enhancement strategy based on multi-level contrastive learning is proposed. Furthermore, a heterogeneous attention integration framework is presented, which uses multi-level attention to assign different weights to various features. This approach efficiently fuses both intramolecular and intermolecular features, enhancing the model's ability to capture key information and improving its performance on sparse, imbalanced datasets. Experimental results show that HGEF-Net outperforms other state-of-the-art models. On the BindingDB dataset (1:100 positive-to-negative ratio), HGEF-Net achieves an AUC of 0.826, AUPRC of 0.811, Precision of 0.715, and Recall of 0.709. On the Davis dataset (1:10 ratio), the data enhancement module improves AUC, AUPRC, Precision, and Recall by 11.7%, 9.7%, 10.5%, and 16.3%, respectively, validating the model's effectiveness.

PMID:40072484 | DOI:10.1080/07391102.2025.2475229

Am J Respir Crit Care Med. 2025 Mar 12. doi: 10.1164/rccm.202409-1847OC. Online ahead of print.

ABSTRACT

RATIONALE: Quantifying functional small airways disease (fSAD) requires additional expiratory computed tomography (CT) scan, limiting clinical applicability. Artificial intelligence (AI) could enable fSAD quantification from chest CT scan at total lung capacity (TLC) alone (fSADTLC).

OBJECTIVES: To evaluate an AI model for estimating fSADTLC, compare it with dual-volume parametric response mapping fSAD (fSADPRM), and assess its clinical associations and repeatability in chronic obstructive pulmonary disease (COPD).

METHODS: We analyzed 2513 participants from the SubPopulations and InteRmediate Outcome Measures in COPD Study (SPIROMICS). Using a randomly sampled subset (n = 1055), we developed a generative model to produce virtual expiratory CTs for estimating fSADTLC in the remaining 1458 SPIROMICS participants. We compared fSADTLC with dual volume, parametric response mapping fSADPRM. We investigated univariate and multivariable associations of fSADTLC with FEV1, FEV1/FVC, six-minute walk distance (6MWD), St. George's Respiratory Questionnaire (SGRQ), and FEV1 decline. The results were validated in a subset (n = 458) from COPDGene study. Multivariable models were adjusted for age, race, sex, BMI, baseline FEV1, smoking pack years, smoking status, and percent emphysema.

MEASUREMENTS AND MAIN RESULTS: Inspiratory fSADTLC showed a strong correlation with fSADPRM in both SPIROMICS (Pearson's R = 0.895) and COPDGene (R = 0.897) cohorts. Higher fSADTLC levels were significantly associated with lower lung function, including lower postbronchodilator FEV1 (L) and FEV1/FVC ratio, and poorer quality of life reflected by higher total SGRQ scores, independent of percent CT emphysema. In SPIROMICS, individuals with higher fSADTLC experienced an annual decline in FEV1 of 1.156 mL (relative decrease; 95% CI: 0.613, 1.699; P < 0.001) per year for every 1% increase in fSADTLC. The rate of decline in COPDGene was slightly lower at 0.866 mL / year (relative decrease; 95% CI: 0.345, 1.386; P < 0.001) for percent increase in fSADTLC. Inspiratory fSADTLC demonstrated greater consistency between repeated measurements with a higher intraclass correlation coefficient (ICC) of 0.99 (95% CI: 0.98, 0.99) compared to fSADPRM [ICC: 0.83 (95% CI: 0.76, 0.88)].

CONCLUSIONS: Small airways disease can be reliably assessed from a single inspiratory CT scan using generative AI, eliminating the need for an additional expiratory CT scan. fSAD estimation from inspiratory CT correlates strongly with fSADPRM, demonstrates a significant association with FEV1 decline, and offers greater repeatability.

PMID:40072247 | DOI:10.1164/rccm.202409-1847OC

ACS Appl Mater Interfaces. 2025 Mar 12. doi: 10.1021/acsami.4c17414. Online ahead of print.

ABSTRACT

Current anticounterfeiting technologies rely on deterministic processes that are easily replicable, require specialized devices for authentication, and involve complex manufacturing, resulting in high costs and limited scalability. This study presents a low-cost, mass-producible structural color-based anticounterfeiting pattern and a simple algorithm for discrimination. Nanopatterns aligned with the direction of incident light were fabricated by electrospinning, while CuO and ZnO were grown independently through a solution process. CuO acts as a reflective layer, imparting an angle-dependent color dependence, while ZnO allows the structural color to be tuned by controlling the hydrothermal synthesis time. The inherent randomness of electrospinning enables the creation of unclonable patterns, providing a robust anticounterfeiting solution. The fabricated CuO/ZnO nanopatterns exhibit strong angular color dependence and are capable of encoding high-density information. It uses deep learning algorithms to achieve an average discrimination accuracy of 94%, with a streamlined computational structure based on shape and color features to achieve a processing speed of 80 ms per sample. The training images are acquired with standard high-resolution cameras, ensuring accessibility and practicality. This approach offers an efficient and scalable next-generation solution for anticounterfeiting applications, including documents, currency, and brand labels.

PMID:40072024 | DOI:10.1021/acsami.4c17414

Can Assoc Radiol J. 2025 Mar 12:8465371251322054. doi: 10.1177/08465371251322054. Online ahead of print.

ABSTRACT

Purpose: This study investigates the impact of deep learning-based contrast boosting (DL-CB) on image quality and measurement reliability in low-contrast media (low-CM) CT for pre-transcatheter aortic valve replacement (TAVR) assessment. Methods: This retrospective study included TAVR candidates with renal dysfunction who underwent low-CM (30-mL: 15-mL bolus of contrast followed by 50-mL of 30% iomeprol solution) pre-TAVR CT between April and December 2023, along with matched standard-CM controls (n = 68). Low-CM images were reconstructed as conventional, 50-keV, and DL-CB images. Qualitative and quantitative image quality were compared among image sets. The aortic annulus was measured by 2 independent readers on low-CM CT images, and interobserver reliability was assessed. Results: DL-CB significantly improved contrast-to-noise ratio (CNR) and signal-to-noise ratio (SNR) compared to conventional and 50-keV images (CNR: 12.5-13.4, 18-19.8, and 21.9-24; SNR: 10.8-15.5, 10.7-15.5, and 16.8-26.7 on conventional, 50-keV, and DL-CB images, respectively; P < .001). DL-CB achieved comparable CNR (21.9-24 vs 27-27.7, P = .39-.61) and comparable to slightly higher SNR (16.8-26.7 vs 15.7-20.2, P = .003-.80) to standard-CM images. For aortic annular measurement, DL-CB demonstrated high interobserver reliability, with an intraclass correlation coefficient (ICC) of .96 and small mean differences (area: 0.01 cm², limits of agreement [LoA]: -0.52 to 0.55 cm²; perimeter: 0.02 mm, LoA: -4.49 to 4.53 mm). Conclusions: DL-CB improves image quality and provides high measurement reliability in low-CM CT for pre-TAVR assessment in patients with renal dysfunction, without requiring dual-energy CT.

PMID:40071690 | DOI:10.1177/08465371251322054

MethodsX. 2025 Feb 15;14:103207. doi: 10.1016/j.mex.2025.103207. eCollection 2025 Jun.

ABSTRACT

This study presents a novel deep learning approach for surface electromyography (sEMG) gesture recognition using stacked autoencoder neural network (SAE)s. The method leverages hierarchical representation learning to extract meaningful features from raw sEMG signals, enhancing the precision and robustness of gesture classification.•Feature Extraction and Classification MODWT Decomposition: The sEMG signals were decomposed using the MODWT DECOMPOSITION(Maximal Overlap Discrete Wavelet Transform) to capture various frequency components.•Time Domain Parameters: A total of 28 features per subject were extracted from the time domain, including statistical and spectral features.•Classifier Evaluation: Initial evaluations involved Autoencoder and LDA (Linear Discriminant Analysis) classifiers, with Autoencoder achieving an average accuracy of 77.96 % ± 1.24, outperforming LDA's 65.36 % ± 1.09.Advanced Neural Network Approach: Stacked Autoencoder Neural Network: To address challenges in distinguishing similar gestures within grasp groups, a Stacked Autoencoder Neural Network was employed. This advanced neural network architecture improved classification accuracy to over 100 %, demonstrating its effectiveness in handling complex gesture recognition tasks. These findings emphasize the significant potential of deep learning models in enhancing prosthetic control and rehabilitation technologies. . To verify these findings, we developed a 3d hand module in ADAMS software that is simulated using Matlab-ADAMS cosimulation.

PMID:40071216 | PMC:PMC11894319 | DOI:10.1016/j.mex.2025.103207

Front Neurosci. 2025 Feb 25;19:1469244. doi: 10.3389/fnins.2025.1469244. eCollection 2025.

ABSTRACT

Easing the behavioral restrictions of those in need of care not only improves their own quality of life (QoL) but also reduces the burden on care workers and may help reduce the number of care workers in countries with declining birthrates. The brain-machine interface (BMI), in which appliances and machines are controlled only by brain activity, can be used in nursing care settings to alleviate behavioral restrictions and reduce stress for those in need of care. It is also expected to reduce the workload of care workers. In this study, we focused on motor imagery (MI) classification by deep-learning to construct a system that can identify MI obtained by electroencephalography (EEG) measurements with high accuracy and a low latency response. By completing the system on the edge, the privacy of personal MI data can be ensured, and the system is ubiquitous, which improves user convenience. On the other hand, however, the edge is limited by hardware resources, and the implementation of models with a huge number of parameters and high computational cost, such as deep-learning, on the edge is challenging. Therefore, by optimizing the MI measurement conditions and various parameters of the deep-learning model, we attempted to reduce the power consumption and improve the response latency of the system by minimizing the computational cost while maintaining high classification accuracy. In addition, we investigated the use of a 3-dimension convolutional neural network (3D CNN), which can retain spatial locality as a feature to further improve the classification accuracy. We propose a method to maintain a high classification accuracy while enabling processing on the edge by optimizing the size and number of kernels and the layer structure. Furthermore, to develop a practical BMI system, we introduced dry electrodes, which are more comfortable for daily use, and optimized the number of parameters and memory consumption size of the proposed model to maintain classification accuracy even with fewer electrodes, less recall time, and a lower sampling rate. Compared to EEGNet, the proposed 3D CNN reduces the number of parameters, the number of multiply-accumulates, and memory footprint by approximately 75.9%, 16.3%, and 12.5%, respectively, while maintaining the same level of classification accuracy with the conditions of eight electrodes, 3.5 seconds sample window size, and 125 Hz sampling rate in 4-class dry-EEG MI.

PMID:40071135 | PMC:PMC11893816 | DOI:10.3389/fnins.2025.1469244

Front Oncol. 2025 Feb 25;15:1492758. doi: 10.3389/fonc.2025.1492758. eCollection 2025.

ABSTRACT

PURPOSE: In the context of lung cancer screening, the scarcity of well-labeled medical images poses a significant challenge to implement supervised learning-based deep learning methods. While data augmentation is an effective technique for countering the difficulties caused by insufficient data, it has not been fully explored in the context of lung cancer screening. In this research study, we analyzed the state-of-the-art (SOTA) data augmentation techniques for lung cancer binary prediction.

METHODS: To comprehensively evaluate the efficiency of data augmentation approaches, we considered the nested case control National Lung Screening Trial (NLST) cohort comprising of 253 individuals who had the commonly used CT scans without contrast. The CT scans were pre-processed into three-dimensional volumes based on the lung nodule annotations. Subsequently, we evaluated five basic (online) and two generative model-based offline data augmentation methods with ten state-of-the-art (SOTA) 3D deep learning-based lung cancer prediction models.

RESULTS: Our results demonstrated that the performance improvement by data augmentation was highly dependent on approach used. The Cutmix method resulted in the highest average performance improvement across all three metrics: 1.07%, 3.29%, 1.19% for accuracy, F1 score and AUC, respectively. MobileNetV2 with a simple data augmentation approach achieved the best AUC of 0.8719 among all lung cancer predictors, demonstrating a 7.62% improvement compared to baseline. Furthermore, the MED-DDPM data augmentation approach was able to improve prediction performance by rebalancing the training set and adding moderately synthetic data.

CONCLUSIONS: The effectiveness of online and offline data augmentation methods were highly sensitive to the prediction model, highlighting the importance of carefully selecting the optimal data augmentation method. Our findings suggest that certain traditional methods can provide more stable and higher performance compared to SOTA online data augmentation approaches. Overall, these results offer meaningful insights for the development and clinical integration of data augmented deep learning tools for lung cancer screening.

PMID:40071099 | PMC:PMC11893409 | DOI:10.3389/fonc.2025.1492758