Res Sq [Preprint]. 2025 Feb 17:rs.3.rs-6025759. doi: 10.21203/rs.3.rs-6025759/v1.

ABSTRACT

Background Gene-environment interactions may enhance our understanding of hypertension. Our previous study highlighted the importance of considering psychosocial factors in gene discovery for blood pressure (BP) but was limited in statistical power and population diversity. To address these challenges, we conducted a multi-population genome-wide association study (GWAS) of BP accounting for gene-depressive symptomatology (DEPR) interactions in a larger and more diverse sample. Results Our study included 564,680 adults aged 18 years or older from 67 cohorts and 4 population backgrounds (African (5%), Asian (7%), European (85%), and Hispanic (3%)). We discovered seven novel gene-DEPR interaction loci for BP traits. These loci mapped to genes implicated in neurogenesis ( TGFA , CASP3 ), lipid metabolism ( ACSL1 ), neuronal apoptosis ( CASP3 ), and synaptic activity ( CNTN6 , DBI ). We also identified evidence for gene-DEPR interaction at nine known BP loci, further suggesting links between mood disturbance and BP regulation. Of the 16 identified loci, 11 loci were derived from African, Asian, or Hispanic populations. Post-GWAS analyses prioritized 36 genes, including genes involved in synaptic functions ( DOCK4 , MAGI2 ) and neuronal signaling ( CCK , UGDH , SLC01A2 ). Integrative druggability analyses identified 11 druggable candidate gene targets, including genes implicated in pathways linked to mood disorders as well as gene products targeted by known antihypertensive drugs. Conclusions Our findings emphasize the importance of considering gene-DEPR interactions on BP, particularly in non-European populations. Our prioritized genes and druggable targets highlight biological pathways connecting mood disorders and hypertension and suggest opportunities for BP drug repurposing and risk factor prevention, especially in individuals with DEPR.

PMID:40034430 | PMC:PMC11875294 | DOI:10.21203/rs.3.rs-6025759/v1

iScience. 2025 Feb 1;28(3):111943. doi: 10.1016/j.isci.2025.111943. eCollection 2025 Mar 21.

ABSTRACT

Small cell lung cancer (SCLC) is a highly aggressive form of lung cancer with limited treatment options. Patients often respond well to initial chemo-immunotherapy but relapse quickly, necessitating new strategies to enhance immune responsiveness. Recent research explores combining DNA-damaging therapies with immunotherapy to activate the STING pathway and improve the antitumor immune response. The addition of DNA Damage Repair (DDR) inhibitors, such as DNA-PKcs inhibitors, after chemotherapy has shown promise in activating innate immune sensors and enhancing CD8+ T cell and NK cell pathways in SCLC models. This approach could potentially reshape the tumor microenvironment and sustain an antitumor immune response, offering a maintenance strategy for SCLC treatment.

PMID:40034862 | PMC:PMC11875153 | DOI:10.1016/j.isci.2025.111943

Clin Pharmacol Ther. 2025 Mar 3. doi: 10.1002/cpt.3617. Online ahead of print.

ABSTRACT

Tailoring pharmacogenomic (PGx) implementation to diverse populations is vital to promoting health equity. We assessed prescriptions for medications with potentially actionable PGx information to identify patient characteristics associated with differential PGx medication exposure. We analyzed the nationally-representative MEPS dataset of adults who reported receiving prescriptions between 2014 and 2021. PGx medications include those the FDA and CPIC designate as having drug-gene associations supported by scientific evidence. With the primary outcome being PGx prescriptions, we performed Poisson regression adjusted for all other relevant covariates. In our final population (N = 119,722, 72% White/20% Black/4% Asian/8% Hispanic), 61% were prescribed a PGx medication, 56% were female, and 97% held health insurance coverage. Adults with private health insurance (65%) or public Medicaid/Medicare coverage (32%) were more likely to have PGx prescriptions than the uninsured (3%). Individuals with cardiovascular conditions [adjusted IRR (aIRR) = 1.45, 95% CI 1.41, 1.48], high cholesterol [aIRR = 1.37, 95% CI 1.35, 1.40], high blood pressure [aIRR = 1.14, 95% CI 1.12, 1.16], and cancer [aIRR = 1.02, 95% CI 1.00, 1.04] were more likely to receive PGx prescriptions. Self-reported Blacks were less likely than Whites to receive PGx medications [aIRR = 0.92, 95% CI 0.90, 0.94], and among those with health conditions, the likelihood of PGx medication exposure for underrepresented groups (Blacks, Hispanics, and Asians) was lower than for Whites. Our study using a comprehensive list of PGx medications in a nationally representative dataset indicates that certain populations are differentially exposed to genomically informed medications. This may suggest that if implementing a pharmacogenomics program based on reactive testing initiated by a prescription, a small underrepresentation of the Black population could be expected because of an underlying prescription disparity. Secondly, if implementing a pharmacogenomics program based on targeted preemptive testing, using clinical indication/comorbidity may be a reasonable way to enrich the population for prescriptions that would benefit from genotype tailoring.

PMID:40033674 | DOI:10.1002/cpt.3617

Res Sq [Preprint]. 2025 Feb 17:rs.3.rs-5938603. doi: 10.21203/rs.3.rs-5938603/v1.

ABSTRACT

BACKGROUND: In a healthy lung, the airway epithelium regulates glucose transport to maintain low glucose concentrations in the airway surface liquid (ASL). However, hyperglycemia and chronic lung diseases, such as cystic fibrosis (CF), can result in increased glucose in bronchial aspirates. People with CF are also at increased risk of lung infections caused by bacterial pathogens, including methicillin-resistant Staphylococcus aureus. Yet, it is not known how increased airway glucose availability affects bacteria in chronic CF lung infections or impacts treatment outcomes.

METHODS: To model the CF airways, we cultured immortalized CF (CFBE41o-) and non-CF (16HBE) human bronchial epithelial cells at air liquid interface (ALI). Glucose concentrations in the basolateral media were maintained at 5.5 mM or 12.5 mM, to mimic a normal and hyperglycemic milieu respectively. 2-deoxyglucose was added to high glucose culture media to restrict glucose availability. We collected ASL, basolateral media, and RNA from ALI cultures to assess the effects of elevated glucose. We also inoculated S. aureus onto the apical surface of normal or high glucose ALI cultures and observed the results of antibiotic treatment post-inoculation. S. aureus growth was measured by enumerating viable colony forming units (CFU) and with fluorescence microscopy. The effects of elevated glucose on in vitro growth and antibiotic treatment were also evaluated in standard bacterial culture medium and synthetic CF medium (SCFM).

RESULTS: We found that glucose concentrations in the ASL of ALI cultures maintained in normal or high glucose mimicked levels measured in breath condensate assays from people with CF and hyperglycemia. Additionally, we found hyperglycemia increased S. aureus aggregation and antibiotic resistance during infection of cells maintained in high glucose compared to normal glucose conditions. Heightened antibiotic tolerance or resistance as not observed during in vitro growth with elevated glucose. Limiting glucose with 2-deoxyglucose both decreased aggregation and reduced antibiotic resistance back to levels comparable to non-hyperglycemic conditions.

CONCLUSIONS: These data indicate hyperglycemia alters S. aureus growth during infection and may reduce efficacy of antibiotic treatment. Glucose restriction is a potential option that could be explored to limit bacterial growth and improve treatment outcomes in chronic airway infections.

PMID:40034435 | PMC:PMC11875303 | DOI:10.21203/rs.3.rs-5938603/v1

ANZ J Surg. 2025 Mar 3. doi: 10.1111/ans.70005. Online ahead of print.

ABSTRACT

BACKGROUND: Distal intestinal obstruction syndrome (DIOS) presents significant management challenges for people with cystic fibrosis (pwC). We evaluated the treatment outcomes and identified risk factors associated with the need for surgical intervention in patients admitted with DIOS.

METHOD: We conducted a retrospective case series of 96 encounters of DIOS over a 20-year period, observing outcomes between cases of medical management versus those requiring for operative intervention. To our knowledge, this is the largest Australian study to review intervention in DIOS.

RESULTS: Among the patients studied, 94.8% were successfully treated non-surgically. Using computed tomography (CT) confirmation of DIOS as the gold standard, only 9.1% of abdominal x-rays were accurate in finding DIOS. Gastrografin was used in half of cases and was associated with a shorter recovery time. One in 16 patients required operative management, with two cases experiencing surgery following prolonged medical treatment. A history of previous laparotomy increased the odds of requiring surgical intervention by 16 times (95% CI: 1.2-209.9, P = 0.035), while a history of meconium ileus increased the odds by 15.6 times (95% CI: 1.2-204.8, P = 0.036). All patients who underwent surgery also had pancreatic insufficiency.

CONCLUSION: Medical management was successful in the majority of DIOS presentations. Our study emphasizes a low threshold for abdominal CT scans to identify complete DIOS in high-risk patients, particularly those with a history of laparotomy or meconium ileus, who may require surgical intervention. Furthermore, we advocate for the adjunctive use of Gastrografin alongside medical management. Future research should refine protocols for these high-risk groups to improve outcomes and reduce morbidity.

PMID:40033632 | DOI:10.1111/ans.70005

J Hand Surg Eur Vol. 2025 Mar 4:17531934251322723. doi: 10.1177/17531934251322723. Online ahead of print.

ABSTRACT

Artificial intelligence has evolved significantly since its inception, becoming a powerful tool in medicine. This paper provides an overview of the core principles, applications and future directions of artificial intelligence in hand surgery. Artificial intelligence has shown promise in improving diagnostic accuracy, predicting outcomes and assisting in patient education. However, despite its potential, its application in hand surgery is still nascent, with most studies being retrospective and limited by small sample sizes. To harness the full potential of artificial intelligence in hand surgery and support broader adoption, more robust, large-scale studies are needed. Collaboration among researchers, through data sharing and federated learning, is essential for advancing artificial intelligence from experimental to clinically validated tools, ultimately enhancing patient care and clinical workflows.

PMID:40035151 | DOI:10.1177/17531934251322723

Digit Health. 2025 Mar 2;11:20552076251324456. doi: 10.1177/20552076251324456. eCollection 2025 Jan-Dec.

ABSTRACT

BACKGROUND: Mental health issues like insomnia, anxiety, and depression have increased significantly. Artificial intelligence (AI) has shown promise in diagnosing and providing personalized treatment.

OBJECTIVE: This study aims to systematically review the application of AI in addressing insomnia, anxiety, and depression, identifying key research hotspots, and forecasting future trends through bibliometric analysis.

METHODS: We analyzed a total of 875 articles from the Web of Science Core Collection (2000-2024) using bibliometric tools such as VOSviewer and CiteSpace. These tools were used to map research trends, highlight international collaboration, and examine the contributions of leading countries, institutions, and authors in the field.

RESULTS: The United States and China lead the field in terms of research output and collaborations. Key research areas include "neural networks," "machine learning," "deep learning," and "human-robot interaction," particularly in relation to personalized treatment approaches. However, challenges around data privacy, ethical concerns, and the interpretability of AI models need to be addressed.

CONCLUSIONS: This study highlights the growing role of AI in mental health research and identifies future priorities, such as improving data quality, addressing ethical challenges, and integrating AI more seamlessly into clinical practice. These advancements will be crucial in addressing the global mental health crisis.

PMID:40035038 | PMC:PMC11873874 | DOI:10.1177/20552076251324456

Cureus. 2025 Jan 31;17(1):e78313. doi: 10.7759/cureus.78313. eCollection 2025 Jan.

ABSTRACT

INTRODUCTION: The rise of artificial intelligence (AI), including generative chatbots like ChatGPT (OpenAI, San Francisco, CA, USA), has revolutionized many fields, including healthcare. Patients have gained the ability to prompt chatbots to generate purportedly accurate and individualized healthcare content. This study analyzed the readability and quality of answers to Achilles tendon rupture questions from six generative AI chatbots to evaluate and distinguish their potential as patient education resources.

METHODS: The six AI models used were ChatGPT 3.5, ChatGPT 4, Gemini 1.0 (previously Bard; Google, Mountain View, CA, USA), Gemini 1.5 Pro, Claude (Anthropic, San Francisco, CA, USA) and Grok (xAI, Palo Alto, CA, USA) without prior prompting. Each was asked 10 common patient questions about Achilles tendon rupture, determined by five orthopaedic surgeons. The readability of generative responses was measured using Flesch-Kincaid Reading Grade Level, Gunning Fog, and SMOG (Simple Measure of Gobbledygook). The response quality was subsequently graded using the DISCERN criteria by five blinded orthopaedic surgeons.

RESULTS: Gemini 1.0 generated statistically significant differences in ease of readability (closest to average American reading level) than responses from ChatGPT 3.5, ChatGPT 4, and Claude. Additionally, mean DISCERN scores demonstrated significantly higher quality of responses from Gemini 1.0 (63.0±5.1) and ChatGPT 4 (63.8±6.2) than ChatGPT 3.5 (53.8±3.8), Claude (55.0±3.8), and Grok (54.2±4.8). However, the overall quality (question 16, DISCERN) of each model was averaged and graded at an above-average level (range, 3.4-4.4).

DISCUSSION AND CONCLUSION: Our results indicate that generative chatbots can potentially serve as patient education resources alongside physicians. Although some models lacked sufficient content, each performed above average in overall quality. With the lowest readability and highest DISCERN scores, Gemini 1.0 outperformed ChatGPT, Claude, and Grok and potentially emerged as the simplest and most reliable generative chatbot regarding management of Achilles tendon rupture.

PMID:40034889 | PMC:PMC11872741 | DOI:10.7759/cureus.78313

Cureus. 2025 Jan 31;17(1):e78282. doi: 10.7759/cureus.78282. eCollection 2025 Jan.

ABSTRACT

Cardiotocography (CTG) has long been the standard method for monitoring fetal status during delivery. Despite its widespread use, human error and variability in CTG interpretation contribute to adverse neonatal outcomes, with over 70% of stillbirths, neonatal deaths, and brain injuries potentially avoidable through accurate analysis. Recent advancements in artificial intelligence (AI) offer opportunities to address these challenges by complementing human judgment. This study experimentally compared the diagnostic accuracy of AI and human specialists in predicting fetal asphyxia using CTG data. Machine learning (ML) and deep learning (DL) algorithms were developed and trained on 3,519 CTG datasets. Human specialists independently assessed 50 CTG figures each through web-based questionnaires. A total of 984 CTG figures from singleton pregnancies were evaluated, and outcomes were compared using receiver operating characteristic (ROC) analysis. Human diagnosis achieved the highest area under the curve (AUC) of 0.693 (p = 0.0003), outperforming AI-based methods (ML: AUC = 0.514, p = 0.788; DL: AUC = 0.524, p = 0.662). Although DL-assisted judgment improved sensitivity and identified cases missed by humans, it did not surpass the accuracy of human judgment alone. Combining human and AI predictions yielded a lower AUC (0.693) than human diagnosis alone, but improved specificity (91.92% for humans, 98.03% for humans and DL), highlighting AI's potential to complement human judgment by reducing false-positive rates. Our findings underscore the need for further refinement of AI algorithms and the accumulation of CTG data to enhance diagnostic accuracy. Integrating AI into clinical workflows could reduce human error, optimize resource allocation, and improve neonatal outcomes, particularly in resource-limited settings. These advancements promise a future where AI assists obstetricians in making more objective and accurate decisions during delivery.

PMID:40034878 | PMC:PMC11875211 | DOI:10.7759/cureus.78282

IEEE Open J Eng Med Biol. 2025 Feb 3;6:305-311. doi: 10.1109/OJEMB.2025.3537760. eCollection 2025.

ABSTRACT

Objective: Human movement augmentation through supernumerary effectors is an emerging field of research. However, controlling these effectors remains challenging due to issues with agency, control, and synchronizing movements with natural limbs. A promising control strategy for supernumerary effectors involves utilizing electroencephalography (EEG) through motor imagery (MI) functions. In this work, we investigate whether MI activity associated with a supernumerary effector could be reliably differentiated from that of a natural one, thus addressing the concern of concurrency. Twenty subjects were recruited to participate in a two-fold experiment in which they observed movements of natural and supernumerary thumbs, then engaged in MI of the observed movements, conducted in a virtual reality setting. Results: A lightweight deep-learning model that accounts for the temporal, spatial and spectral nature of the EEG data is proposed and called BandFocusNet, achieving an average classification accuracy of 70.9% using the leave-one-subject-out cross validation method. The trustworthiness of the model is examined through explainability analysis, and influential regions-of-interests are cross-validated through event-related-spectral-perturbation (ERSPs) analysis. Explainability results showed the importance of the right and left frontal cortical regions, and ERSPs analysis showed an increase in the delta and theta powers in these regions during the MI of the natural thumb but not during the MI of the supernumerary thumb. Conclusion: Evidence in the literature indicates that such activation is observed during the MI of natural effectors, and its absence could be interpreted as a lack of embodiment of the supernumerary thumb.

PMID:40034836 | PMC:PMC11875636 | DOI:10.1109/OJEMB.2025.3537760

Front Comput Neurosci. 2025 Feb 17;19:1490603. doi: 10.3389/fncom.2025.1490603. eCollection 2025.

ABSTRACT

Retinal imaging, used for assessing stroke-related retinal changes, is a non-invasive and cost-effective method that can be enhanced by machine learning and deep learning algorithms, showing promise in early disease detection, severity grading, and prognostic evaluation in stroke patients. This review explores the role of artificial intelligence (AI) in stroke patient care, focusing on retinal imaging integration into clinical workflows. Retinal imaging has revealed several microvascular changes, including a decrease in the central retinal artery diameter and an increase in the central retinal vein diameter, both of which are associated with lacunar stroke and intracranial hemorrhage. Additionally, microvascular changes, such as arteriovenous nicking, increased vessel tortuosity, enhanced arteriolar light reflex, decreased retinal fractals, and thinning of retinal nerve fiber layer are also reported to be associated with higher stroke risk. AI models, such as Xception and EfficientNet, have demonstrated accuracy comparable to traditional stroke risk scoring systems in predicting stroke risk. For stroke diagnosis, models like Inception, ResNet, and VGG, alongside machine learning classifiers, have shown high efficacy in distinguishing stroke patients from healthy individuals using retinal imaging. Moreover, a random forest model effectively distinguished between ischemic and hemorrhagic stroke subtypes based on retinal features, showing superior predictive performance compared to traditional clinical characteristics. Additionally, a support vector machine model has achieved high classification accuracy in assessing pial collateral status. Despite this advancements, challenges such as the lack of standardized protocols for imaging modalities, hesitance in trusting AI-generated predictions, insufficient integration of retinal imaging data with electronic health records, the need for validation across diverse populations, and ethical and regulatory concerns persist. Future efforts must focus on validating AI models across diverse populations, ensuring algorithm transparency, and addressing ethical and regulatory issues to enable broader implementation. Overcoming these barriers will be essential for translating this technology into personalized stroke care and improving patient outcomes.

PMID:40034651 | PMC:PMC11872910 | DOI:10.3389/fncom.2025.1490603

Environ Sci Ecotechnol. 2025 Feb 3;24:100538. doi: 10.1016/j.ese.2025.100538. eCollection 2025 Mar.

ABSTRACT

Precise identification and categorization of building materials are essential for informing strategies related to embodied carbon reduction, building retrofitting, and circularity in urban environments. However, existing building material databases are typically limited to individual projects or specific geographic areas, offering only approximate assessments. Acquiring large-scale and precise material data is hindered by inadequate records and financial constraints. Here, we introduce a novel automated framework that harnesses recent advances in sensing technology and deep learning to identify roof and facade materials using remote sensing data and Google Street View imagery. The model was initially trained and validated on Odense's comprehensive dataset and then extended to characterize building materials across Danish urban landscapes, including Copenhagen, Aarhus, and Aalborg. Our approach demonstrates the model's scalability and adaptability to different geographic contexts and architectural styles, providing high-resolution insights into material distribution across diverse building types and cities. These findings are pivotal for informing sustainable urban planning, revising building codes to lower carbon emissions, and optimizing retrofitting efforts to meet contemporary standards for energy efficiency and emission reductions.

PMID:40034611 | PMC:PMC11875798 | DOI:10.1016/j.ese.2025.100538

Front Oncol. 2025 Feb 17;15:1475133. doi: 10.3389/fonc.2025.1475133. eCollection 2025.

ABSTRACT

PURPOSE: Functional radiotherapy avoids the delivery of high-radiation dosages to high-ventilated lung areas. Methods to determine CT-ventilation imaging (CTVI) typically rely on deformable image registration (DIR) to calculate volume changes within inhale/exhale CT image pairs. Since DIR is a non-trivial task that can bias CTVI, we hypothesize that lung volume changes needed to calculate CTVI can be computed from AI-driven lobe segmentations in inhale/exhale phases, without DIR. We utilize a novel lobe segmentation pipeline (TriSwinUNETR), and the resulting inhale/exhale lobe volumes are used to calculate CTVI.

METHODS: Our pipeline involves three SwinUNETR networks, each trained on 6,501 CT image pairs from the COPDGene study. An initial network provides right/left lung segmentations used to define bounding boxes for each lung. Bounding boxes are resized to focus on lung volumes and then lobes are segmented with dedicated right and left SwinUNETR networks. Fine-tuning was conducted on CTs from 11 patients treated with radiotherapy for non-small cell lung cancer. Five-fold cross-validation was then performed on 51 LUNA16 cases with manually delineated ground truth. Breathing-induced volume change was calculated for each lobe using AI-defined lobe volumes from inhale/exhale phases, without DIR. Resulting lobar CTVI values were validated with 4DCT and positron emission tomography (PET)-Galligas ventilation imaging for 19 lung cancer patients. Spatial Spearman correlation between TriSwinUNETR lobe ventilation and ground-truth PET-Galligas ventilation was calculated for each patient.

RESULTS: TriSwinUNETR achieved a state-of-the-art mean Dice score of 93.72% (RUL: 93.49%, RML: 85.78%, RLL: 95.65%, LUL: 97.12%, LLL: 96.58%), outperforming best-reported accuracy of 92.81% for the lobe segmentation task. CTVI calculations yielded a median Spearman correlation coefficient of 0.9 across 19 cases, with 13 cases exhibiting correlations of at least 0.5, indicating strong agreement with PET-Galligas ventilation.

CONCLUSION: Our TriSwinUNETR pipeline demonstrated superior performance in the lobe segmentation task, while our segmentation-based CTVI exhibited strong agreement with PET-Galligas ventilation. Moreover, as our approach leverages deep-learning for segmentation, it provides interpretable ventilation results and facilitates quality assurance, thereby reducing reliance on DIR.

PMID:40034599 | PMC:PMC11872890 | DOI:10.3389/fonc.2025.1475133

J Alzheimers Dis Rep. 2025 Feb 13;9:25424823251317177. doi: 10.1177/25424823251317177. eCollection 2025 Jan-Dec.

ABSTRACT

BACKGROUND: Recently, microRNAs (miRNAs) have attracted significant interest as predictive biomarkers for various types of dementia, including Alzheimer's disease (AD), vascular dementia (VaD), dementia with Lewy bodies (DLB), normal pressure hydrocephalus (NPH), and mild cognitive impairment (MCI). Machine learning (ML) methods enable the integration of miRNAs into highly accurate predictive models of dementia.

OBJECTIVE: To investigate the differential expression of miRNAs across dementia subtypes compared to normal controls (NC) and analyze their enriched biological and disease pathways. Additionally, to evaluate the use of these miRNAs in binary and multiclass ML models for dementia prediction in both overall and sex-specific datasets.

METHODS: Using data comprising 1685 Japanese individuals (GSE120584 and GSE167559), we performed differential expression analysis to identify miRNAs associated with five dementia groups in both overall and sex-specific datasets. Pathway enrichment analyses were conducted to further analyze these miRNAs. ML classifiers were used to create predictive models of dementia.

RESULTS: We identified novel differentially expressed miRNA biomarkers distinguishing NC from five dementia subtypes. Incorporating these miRNAs into ML classifiers resulted in up to a 27% improvement in dementia risk prediction. Pathway analysis highlighted neuronal and eye disease pathways associated with dementia risk. Sex-specific analyses revealed unique biomarkers for males and females, with miR-128-1-5 as a protective factor for males in AD, VaD, and DLB, and miR-4488 as a risk factor for female AD, highlighting distinct pathways and potential therapeutic targets for each sex.

CONCLUSIONS: Our findings support existing dementia etiology research and introduce new potential and sex-specific miRNA biomarkers.

PMID:40034518 | PMC:PMC11864256 | DOI:10.1177/25424823251317177

Front Neuroinform. 2025 Feb 17;19:1527582. doi: 10.3389/fninf.2025.1527582. eCollection 2025.

ABSTRACT

INTRODUCTION: Neurodegenerative diseases such as Alzheimer's disease (AD) or frontotemporal lobar degeneration (FTLD) involve specific loss of brain volume, detectable in vivo using T1-weighted MRI scans. Supervised machine learning approaches classifying neurodegenerative diseases require diagnostic-labels for each sample. However, it can be difficult to obtain expert labels for a large amount of data. Self-supervised learning (SSL) offers an alternative for training machine learning models without data-labels.

METHODS: We investigated if the SSL models can be applied to distinguish between different neurodegenerative disorders in an interpretable manner. Our method comprises a feature extractor and a downstream classification head. A deep convolutional neural network, trained with a contrastive loss, serves as the feature extractor that learns latent representations. The classification head is a single-layer perceptron that is trained to perform diagnostic group separation. We used N = 2,694 T1-weighted MRI scans from four data cohorts: two ADNI datasets, AIBL and FTLDNI, including cognitively normal controls (CN), cases with prodromal and clinical AD, as well as FTLD cases differentiated into its phenotypes.

RESULTS: Our results showed that the feature extractor trained in a self-supervised way provides generalizable and robust representations for the downstream classification. For AD vs. CN, our model achieves 82% balanced accuracy on the test subset and 80% on an independent holdout dataset. Similarly, the Behavioral variant of frontotemporal dementia (BV) vs. CN model attains an 88% balanced accuracy on the test subset. The average feature attribution heatmaps obtained by the Integrated Gradient method highlighted hallmark regions, i.e., temporal gray matter atrophy for AD, and insular atrophy for BV.

CONCLUSION: Our models perform comparably to state-of-the-art supervised deep learning approaches. This suggests that the SSL methodology can successfully make use of unannotated neuroimaging datasets as training data while remaining robust and interpretable.

PMID:40034453 | PMC:PMC11873101 | DOI:10.3389/fninf.2025.1527582

Cureus. 2025 Jan 31;17(1):e78319. doi: 10.7759/cureus.78319. eCollection 2025 Jan.

ABSTRACT

Introduction Inflammatory cells play a role in several idiopathic pulmonary fibrosis (IPF) pathogenesis steps. We aimed to evaluate the predictive value of peripheral blood cell (PBC) counts and inflammation indexes in the prognosis and mortality of IPF. Materials and methods A total of 155 patients with IPF followed between 1 January 2016 and 1 January 2023 were evaluated retrospectively. The baseline values and annual changes for pulmonary function tests and the PBC counts, ratios, and inflammation indexes (leukocyte, neutrophil, platelet, monocyte, lymphocyte, red cell distribution width (RDW), neutrophil-to-lymphocyte ratio (NLR), derived neutrophil-to-lymphocyte ratio (dNLR), platelet-to-lymphocyte ratio (PLR), monocyte-to-lymphocyte ratio (MLR), Systemic Immune Inflammation (SII) index, Systemic Inflammation Response Index (SIRI), the Aggregate Index of Systemic Inflammation (AISI)) were recorded. The relation between PBC, ratios, and inflammatory indexes with functional parameters (forced vital capacity (FVC), diffusing capacity of the lung for carbon monoxide (DLCO), 6-minute walking test (6MWT), Gender, Age, and Physiology (GAP) index, GAP stage) and mortality were examined. Results It was found that baseline RDW and neutrophil count were negatively correlated with survival time. The prognosis was worse in patients who had an RDW>13.6% and a neutrophil count>5.26×109/L (p = 0.0005 and p = 0.037, respectively). Significant correlations were observed between baseline peripheral blood cell counts, ratios, and index values (leukocyte, monocyte, neutrophil, platelet, monocyte, lymphocyte, NLR, PLR, MLR, SII, SIRI, AISI) and functional parameters (FVC, DLCO, 6MWT, GAP index, GAP stage). However, there was no significant correlation between the yearly changes. Conclusions Increased neutrophils and RDW may be related to the poor prognosis in IPF. Peripheral blood cell counts and inflammatory indices may provide useful information in identifying patients with worse functional status.

PMID:40034886 | PMC:PMC11873667 | DOI:10.7759/cureus.78319

Front Mol Biosci. 2025 Feb 17;12:1507163. doi: 10.3389/fmolb.2025.1507163. eCollection 2025.

ABSTRACT

BACKGROUND: The idiopathic pulmonary fibrosis (IPF) is a progressive and lethal interstitial lung disease with high morbidity and mortality. IPF is characterized by excessive extracellular matrix accumulation (ECM) and epithelial-mesenchymal transformation (EMT). To date, few anti-fibrotic therapeutics are available to reverse the progression of pulmonary fibrosis, and it is important to explore new profibrotic molecular regulators mediating EMT and pulmonary fibrosis.

METHODS: Based on our model of TGF-β1-induced EMT in BEAS-2B cells, we performed the genome-wide CRISPR/Cas9 knockout (GeCKO) screening technique, pathway and functional enrichment analysis, loss-of-function experiment, as well as other experimental techniques to comprehensively investigate profibrotic regulators contributing to EMT and the pathogenesis of pulmonary fibrosis.

RESULTS: Utilizing the GeCKO library screening, we identified 76 top molecular regulators. Ten candidate genes were subsequently confirmed by integrating the high-throughput data with findings from pathway and functional enrichment analysis. Among the candidate genes, knockout of COL20A1 and COL27A1 led to decreased mRNA expression of ECM components (Fibronectin and Collagen-I), as well as an increased rate of cell apoptosis. The mRNA expression of Collagen-I, together with the cell viability and migration, were inhibited when knocking out the WNT11. In addition, a decrease in the protein deposition of ECM components was observed by suppressing the expression of COL20A1, COL27A1, and WNT11.

CONCLUSION: Our study demonstrates that the COL20A1, COL27A1, and WNT11 serve as key profibrotic regulators of EMT. Gaining understanding and insights into these key profibrotic regulators of EMT paves the way for the discovery of new therapeutic targets against the onset and progression of IPF.

PMID:40034336 | PMC:PMC11872725 | DOI:10.3389/fmolb.2025.1507163

Br J Pharmacol. 2025 Mar 4. doi: 10.1111/bph.17470. Online ahead of print.

ABSTRACT

BACKGROUND AND PURPOSE: Idiopathic pulmonary fibrosis (IPF) is a fatal disease characterized by fibroblast activation and abnormal accumulation of extracellular matrix in the lungs. We previously demonstrated the importance of the heat shock protein αB-crystallin (HSPB5) in TGF-β1 profibrotic signalling, which suggests that HSPB5 could be a new therapeutic target for the treatment of IPF. The purpose of this study was thus to develop antisense oligonucleotides targeting HSPB5 and to study their effects on the development of experimental pulmonary fibrosis.

EXPERIMENTAL APPROACH: Specific antisense oligonucleotides (ASO) were designed and screened in vitro, based on their ability to inhibit human and murine HSPB5 expression. The selected ASO22 was characterized in vitro in human fibroblast CCD-19Lu cells and A549 epithelial pulmonary cells, as well as in vivo using a mouse model of bleomycin-induced pulmonary fibrosis.

KEY RESULTS: ASO22 was selected for its capacity to inhibit TGF-β1-induced expression of HSPB5 and additional key markers of fibrosis such as plasminogen activator inhibitor-1, collagen, fibronectin and α-smooth muscle actin in fibroblastic human CCD-19Lu cells as well as plasminogen activator inhibitor-1 and α-smooth muscle actin in pulmonary epithelial A549 cells. Intra-tracheal or intravenous administration of ASO22 in bleomycin-induced pulmonary fibrotic mice decreased HSPB5 expression and reduced fibrosis, as demonstrated by decreased pulmonary remodelling, collagen accumulation and Acta2 and Col1a1 expression.

CONCLUSION AND IMPLICATIONS: Our results suggest that an antisense oligonucleotide strategy targeting HSPB5 could be of interest for the treatment of IPF.

PMID:40033950 | DOI:10.1111/bph.17470

Biotechnol Rep (Amst). 2025 Feb 9;45:e00882. doi: 10.1016/j.btre.2025.e00882. eCollection 2025 Mar.

ABSTRACT

Quality by design (QbD) is applied to the upstream process to maximize the RBD-Fc fusion protein production in CHO cells. The three factors (culture duration, temperature, and polyethyleneimine to plasmid DNA (PEI-Max/pDNA) ratio) were identified as critical process attributes based on risk analysis (FMEA) and further optimized by response surface to maximize the protein yields. Using a Box-Behnken design, the optimal conditions for RBD-Fc production were determined to be a culture duration of 5 days, a culture temperature of 34.4 °C, and a PEI-Max/pDNA ratio of 4.2:1 (w/w) with a predictive value of 48 mg/L (desirability of 92.8 %). The PEI-Max/pDNA ratio and its interaction with culture duration to express the highest yield (47.78 ± 2.30 mg/l). In addition, the purified CHO-produced RBD-Fc fusion protein was highly pure and strongly bound to its receptor, ACE2. Our finding demonstrated that the QBD tools can identify the critical parameters to facilitate scaling-up production.

PMID:40034964 | PMC:PMC11872631 | DOI:10.1016/j.btre.2025.e00882

J Pharm Anal. 2025 Feb;15(2):101047. doi: 10.1016/j.jpha.2024.101047. Epub 2024 Jul 25.

ABSTRACT

Image 1.

PMID:40034864 | PMC:PMC11874559 | DOI:10.1016/j.jpha.2024.101047