World J Biol Psychiatry. 2025 Jan 24:1-16. doi: 10.1080/15622975.2025.2453198. Online ahead of print.

ABSTRACT

BACKGROUND: Genes associated with global developmental delay (GDD) and intellectual disability (ID) are increasingly being identified through next-generation sequencing (NGS) technologies. This study aimed to identify novel mutations in GDD/ID phenotypes through whole-exome sequencing (WES) and additional in silico analyses.

MATERIAL AND METHODS: WES was performed on 27 subjects, among whom 18 were screened for potential novel mutations. In silico analyses included protein-protein interactions (PPIs), gene-miRNA interactions (GMIs), and enrichment analyses. The identified novel variants were further modelled using I-Tasser-MTD and SWISS-MODEL, with structural superimposition performed.

RESULTS: Novel mutations were detected in 18 patients, with 10 variants reported for the first time. Among these, three were classified as pathogenic (DNMT1:c.856dup, KCNQ2:c.1635_1636insT, and TMEM94:c.2598_2599insC), and six were likely pathogenic. DNMT1 and MRE11 were highlighted as key players in PPIs and GMIs. GMIs analysis emphasised the roles of hsa-miR-30a-5p and hsa-miR-185-5p. The top-scoring pathways included the neuronal system (R-HSA-112316, p = 7.73E-04) and negative regulation of the smooth muscle cell apoptotic process (p = 3.37E-06). Homology modelling and superimposition revealed a significant functional loss in the mutated DNMT1 enzyme structure.

CONCLUSION: This study identified 10 novel pathogenic/likely pathogenic variants associated with GDD/ID, supported by clinical findings and in silico analyses focused on DNMT1 mutations.

PMID:39853208 | DOI:10.1080/15622975.2025.2453198

Vaccines (Basel). 2025 Jan 1;13(1):33. doi: 10.3390/vaccines13010033.

ABSTRACT

Adjuvants are a diverse group of substances that can be added to vaccines to enhance antigen-specific immune responses and improve vaccine efficacy. The first adjuvants, discovered almost a century ago, were soluble crystals of aluminium salts. Over the following decades, oil emulsions, vesicles, oligodeoxynucleotides, viral capsids, and other complex organic structures have been shown to have adjuvant potential. However, the detailed mechanisms of how adjuvants enhance immune responses remain poorly understood and may be a barrier that reduces the rational selection of vaccine components. Previous studies on mechanisms of action of adjuvants have focused on how they activate innate immune responses, including the regulation of cell recruitment and activation, cytokine/chemokine production, and the regulation of some "immune" genes. This approach provides a narrow perspective on the complex events involved in how adjuvants modulate antigen-specific immune responses. A comprehensive and efficient way to investigate the molecular mechanism of action for adjuvants is to utilize systems biology approaches such as transcriptomics in so-called "systems vaccinology" analysis. While other molecular biology methods can verify if one or few genes are differentially regulated in response to vaccination, systems vaccinology provides a more comprehensive picture by simultaneously identifying the hundreds or thousands of genes that interact with complex networks in response to a vaccine. Transcriptomics tools such as RNA sequencing (RNA-Seq) allow us to simultaneously quantify the expression of practically all expressed genes, making it possible to make inferences that are only possible when considering the system as a whole. Here, we review some of the challenges in adjuvant studies, such as predicting adjuvant activity and toxicity when administered alone or in combination with antigens, or classifying adjuvants in groups with similar properties, while underscoring the significance of transcriptomics in systems vaccinology approaches to propel vaccine development forward.

PMID:39852812 | DOI:10.3390/vaccines13010033

Cells. 2025 Jan 15;14(2):119. doi: 10.3390/cells14020119.

ABSTRACT

As of 2023, there were 39.9 million people living with Human Immunodeficiency Virus type 1 (HIV-1). Although great strides have been made in treatment options for HIV-1, and our understanding of the HIV-1 life cycle has vastly improved since the start of this global health crisis, a functional cure remains elusive. One of the main barriers to a cure is latency, which allows the virus to persist despite combined antiretroviral therapy (cART). Recently, we have found that exosomes, which are small, membrane-enclosed particles released by virtually all cell types and known to mediate intercellular communication, caused an increase in RNA Polymerase II loading onto the HIV-1 promoter. This resulted in the production of both short- and long-length viral transcripts in infected cells under cART. This current study examines the effects of exosome-associated kinases on bystander cells. The phospho-kinase profiling of exosomes revealed differences in the kinase payload of exosomes derived from uninfected and HIV-1-infected cells, with CDK10, GSK3β, and MAPK8 having the largest concentration differences. These kinases were shown to be biologically active and capable of phosphorylating substrates, and they modulated changes in the cell cycle dynamics of exposed cells. Given the relevance of such effects for the immune response, our results implicate exosome-associated kinases as new possible key contributors to HIV-1 pathogenesis that affect bystander cells. These findings may guide new therapeutic avenues to improve the current antiretroviral treatment regimens.

PMID:39851547 | DOI:10.3390/cells14020119

Bioengineering (Basel). 2024 Dec 25;12(1):7. doi: 10.3390/bioengineering12010007.

ABSTRACT

In spite of significant advancements in diagnosis and treatment, cancer remains one of the major threats to human health due to its ability to cause disease with high morbidity and mortality. A multifactorial and multitargeted approach is required towards intervention of the multitude of signaling pathways associated with carcinogenesis inclusive of angiogenesis and metastasis. In this context, plants provide an immense source of phytotherapeutics that show great promise as anticancer drugs. There is increasing epidemiological data indicating that diets rich in vegetables and fruits could decrease the risks of certain cancers. Several studies have proved that natural plant polyphenols, such as flavonoids, lignans, phenolic acids, alkaloids, phenylpropanoids, isoprenoids, terpenes, and stilbenes, could be used in anticancer prophylaxis and therapeutics by recruitment of mechanisms inclusive of antioxidant and anti-inflammatory activities and modulation of several molecular events associated with carcinogenesis. The current review discusses the anticancer activities of principal phytochemicals with focus on signaling circuits towards targeted cancer prophylaxis and therapy. Also addressed are plant-derived anti-cancer vaccines, nanoparticles, monoclonal antibodies, and immunotherapies. This review article brings to light the importance of plants and plant-based platforms as invaluable, low-cost sources of anti-cancer molecules of particular applicability in resource-poor developing countries.

PMID:39851281 | DOI:10.3390/bioengineering12010007

Elife. 2025 Jan 24;12:RP88149. doi: 10.7554/eLife.88149.

ABSTRACT

Apart from ancestry, personal or environmental covariates may contribute to differences in polygenic score (PGS) performance. We analyzed the effects of covariate stratification and interaction on body mass index (BMI) PGS (PGSBMI) across four cohorts of European (N = 491,111) and African (N = 21,612) ancestry. Stratifying on binary covariates and quintiles for continuous covariates, 18/62 covariates had significant and replicable R2 differences among strata. Covariates with the largest differences included age, sex, blood lipids, physical activity, and alcohol consumption, with R2 being nearly double between best- and worst-performing quintiles for certain covariates. Twenty-eight covariates had significant PGSBMI-covariate interaction effects, modifying PGSBMI effects by nearly 20% per standard deviation change. We observed overlap between covariates that had significant R2 differences among strata and interaction effects - across all covariates, their main effects on BMI were correlated with their maximum R2 differences and interaction effects (0.56 and 0.58, respectively), suggesting high-PGSBMI individuals have highest R2 and increase in PGS effect. Using quantile regression, we show the effect of PGSBMI increases as BMI itself increases, and that these differences in effects are directly related to differences in R2 when stratifying by different covariates. Given significant and replicable evidence for context-specific PGSBMI performance and effects, we investigated ways to increase model performance taking into account nonlinear effects. Machine learning models (neural networks) increased relative model R2 (mean 23%) across datasets. Finally, creating PGSBMI directly from GxAge genome-wide association studies effects increased relative R2 by 7.8%. These results demonstrate that certain covariates, especially those most associated with BMI, significantly affect both PGSBMI performance and effects across diverse cohorts and ancestries, and we provide avenues to improve model performance that consider these effects.

PMID:39851248 | DOI:10.7554/eLife.88149

Front Pharmacol. 2025 Jan 9;15:1444311. doi: 10.3389/fphar.2024.1444311. eCollection 2024.

ABSTRACT

OBJECTIVE: The expanding field of hematopoietic cell transplantation (HCT) for non-malignant diseases, including those amenable to gene therapy or gene editing, faces challenges due to limited donor availability and the toxicity associated with cell collection methods. Umbilical cord blood (CB) represents a readily accessible source of hematopoietic stem and progenitor cells (HSPCs); however, the cell dose obtainable from a single cord blood unit is frequently insufficient. This limitation can be addressed by enhancing the potency of HSPCs, specifically their capacity to reconstitute hematopoiesis. In our study, we investigated the combined effects of treprostinil, a prostaglandin analog, and cinacalcet, a calcium-sensing receptor modulator, on the reconstitution of hematopoiesis.

METHODS: A Lineage Cell Depletion Kit was employed to isolate lineage-negative (lin-) HSPCs from mouse bone marrow. A Human CB CD34 Positive Selection Kit was utilized to isolate CD34+ cells from the CB of healthy donors. In vitro, the effects of treprostinil, cinacalcet, and their combination on the migration, adhesion, and differentiation of HSPCs were assessed. In vivo, homing and engraftment were examined. Eight-week-old female and male C57BL/6J, BALB/c, or female NSG mice served as recipient models.

RESULTS: When administered concomitantly, treprostinil and cinacalcet exhibited mutual antagonism: the survival of recipient animals was lower when both drugs were administered together compared to either agent alone. Conversely, a sequential regimen involving priming with treprostinil/forskolin followed by cinacalcet treatment in vivo enhanced survival, irrespective of whether hematopoiesis was reconstituted by human or murine HSPCs. In vitro assays demonstrated enhanced migration and adhesion in response to the presence of treprostinil and cinacalcet, suggesting potential synergistic effects. Colony formation confirmed synergism.

CONCLUSION: Augmenting the bone marrow reconstitution potential of HSPCs with treprostinil and cinacalcet shows promise for rescuing patients undergoing HCT. This approach is particularly beneficial for those patients at high risk of transplant failure due to limited numbers of available HSPCs. Furthermore, enhancing the potency of HSPCs has the potential to alleviate the burden and risks associated with HSPC donation, as it would reduce the number of cells needed for collection.

PMID:39850556 | PMC:PMC11755040 | DOI:10.3389/fphar.2024.1444311

J Biomol Struct Dyn. 2025 Jan 24:1-15. doi: 10.1080/07391102.2024.2335282. Online ahead of print.

ABSTRACT

The recent spread of SARS-CoV-2 has led to serious concerns about newly emerging infectious coronaviruses. Drug repurposing is a practical method for rapid development of antiviral agents. The viral spike protein of SARS-CoV-2 binds to its major receptor ACE2 to promote membrane fusion. Following the entry process, the spike protein is further activated by cellular proteases such as TMPRSS2 and Furin to promote viral entry into human cells. A crucial factor in preventing SARS-CoV-2 from entering target cells using HIV-1 fusion inhibitors is the similarity between the fusion mechanisms of SARS-CoV-2 and HIV-1. In this investigation, the HIV-1 fusion inhibitors CMK, Luteolin, and Naphthofluorescein were selected to understand the molecular mode of interactions and binding energy of Furin with these experimental inhibitors. The binding affinity of the three inhibitors with Furin was verified by molecular docking studies. The docking scores of CMK, Luteolin and Naphthofluorescein are -7.4 kcal/mol, -9.3 kcal/mol, and -10.7 kcal/mol, respectively. Therefore, these compounds were subjected to MD, drug-likeness, ADMET, and MM-PBSA analysis. According to the results of a 200 ns MD simulation, all tested compounds show stability with the complex and can be employed as promising inhibitors targeting SARS-CoV-2 Furin protease. In addition, pharmacokinetic analysis revealed that these compounds possess favorable drug-likeness properties. Thus, this study of Furin inhibitors helps in the evaluation of these compounds for use as novel drugs against SARS-CoV-2.

PMID:39849987 | DOI:10.1080/07391102.2024.2335282

Front Pharmacol. 2025 Jan 9;15:1397995. doi: 10.3389/fphar.2024.1397995. eCollection 2024.

ABSTRACT

INTRODUCTION: TNFα inhibitor (TNFi) immunogenicity in rheumatoid arthritis (RA) is a major obstacle to its therapeutic effectiveness. Although methotrexate (MTX) can mitigate TNFi immunogenicity, its adverse effects necessitate alternative strategies. Targeting nuclear factor of activated T cells (NFAT) transcription factors may protect against biologic immunogenicity. Therefore, developing a potent NFAT inhibitor to suppress this immunogenicity may offer an alternative to MTX.

METHODS: We performed a structure-based virtual screen of the NFATC2 crystal structure to identify potential small molecules that could interact with NFATC2. For validation, we investigated the effect of the identified compound on NFAT transcriptional activity, nuclear localization, and binding to the NFAT consensus sequence. In vivo studies assessed the ability of the compound to protect against TNFi immunogenicity, while ex vivo studies evaluated its effect on CD4+ T cell proliferation and B cell antibody secretion.

RESULTS: We identified duvelisib (DV) as a novel NFATC2 and NFATC1 inhibitor that attenuates NFAT transcriptional activity without inhibiting calcineurin or NFAT nuclear localization. Our results suggest that DV inhibits NFAT independently of PI3K by interfering with nuclear NFAT binding to the NFAT consensus promoter sequence. DV significantly protected mice from adalimumab immunogenicity and attenuated ex vivo CD4+ T cell proliferation and B cell antibody secretion.

DISCUSSION: DV is a promising NFAT inhibitor that can protect against TNFi immunogenicity without inhibiting calcineurin phosphatase activity. Our results suggest that the future development of DV analogs may be of interest as agents to attenuate unwanted immune responses.

PMID:39850568 | PMC:PMC11754251 | DOI:10.3389/fphar.2024.1397995

Front Genet. 2025 Jan 9;15:1523071. doi: 10.3389/fgene.2024.1523071. eCollection 2024.

NO ABSTRACT

PMID:39850490 | PMC:PMC11754187 | DOI:10.3389/fgene.2024.1523071

BMC Health Serv Res. 2025 Jan 23;25(1):133. doi: 10.1186/s12913-025-12292-w.

ABSTRACT

BACKGROUND: Remote patient monitoring implies continuous follow-up of health-related parameters of patients outside healthcare facilities. Patients share health-related data with their healthcare unit and obtain feedback (which may be automatically generated if data are within a predefined range). The goals of remote patient monitoring are improvements for patients and reduced healthcare costs. The aim of this paper is to provide an overview of systematic reviews regarding remote patient monitoring for selected patient groups currently considered for the introduction of remote patient monitoring in Region Västra Götaland, Sweden. The selected sixteen patient groups were: patients with asthma, chronic obstructive pulmonary disease, children and adolescents with complex needs, children and adolescents with cystic fibrosis, children and adolescents with periodic fever, elderly patients with multiple diseases, patients with eye diseases, heart failure, haematological disease, hypertension, inflammatory bowel disease, neurorehabilitation, Parkinson's disease, psoriasis, sleep apnea, and specialist maternity care. Outcomes considered in this overview were patient-relevant clinical benefits as well as risks.

METHODS: A literature search for systematic reviews of clinical trials on remote patient monitoring in the selected patient groups was conducted by two information specialists, followed by assessment of relevance by a team of clinical and methodological experts in Region Västra Götaland, Sweden. The methodological rigour of identified systematic reviews was assessed using QUICKSTAR - a tool for stepwise appraisal of systematic reviews. In a QUICKSTAR assessment, a level of at least five is considered a prerequisite for reliable conclusions regarding the question at issue.

RESULTS: The literature search resulted in 4,049 hits, of which 84 SRs were considered relevant for the question at issue. A QUICKSTAR level of at least five was reached by 13 (15%) of the relevant systematic reviews. Some patient benefit of remote patient monitoring was reported for five patient groups (asthma, chronic obstructive lung disease, heart failure, hypertension, and elderly patients with multiple diseases). For four patient groups (children with complex needs, children with cystic fibrosis, specialist maternity care, and sleep apnea), systematic reviews of adequate quality concluded that scientific evidence on clinical patient benefits of remote monitoring is very limited. For seven patient groups, no systematic reviews of sufficient quality were identified.

CONCLUSION: Clinical benefits and risks of remote patient monitoring as a replacement for, or in addition to, standard of care compared to standard of care (face-to-face visits) are poorly studied for most of the selected patient groups based on systematic reviews of acceptable quality. Patient-relevant clinical benefits are limited or impossible to evaluate for most diagnoses based on currently available scientific information. Possible clinical risks and costs are poorly studied.

PMID:39849519 | DOI:10.1186/s12913-025-12292-w

Brief Bioinform. 2024 Nov 22;26(1):bbaf023. doi: 10.1093/bib/bbaf023.

ABSTRACT

Antibody generation requires the use of one or more time-consuming methods, namely animal immunization, and in vitro display technologies. However, the recent availability of large amounts of antibody sequence and structural data in the public domain along with the advent of generative deep learning algorithms raises the possibility of computationally generating novel antibody sequences with desirable developability attributes. Here, we describe a deep learning model for computationally generating libraries of highly human antibody variable regions whose intrinsic physicochemical properties resemble those of the variable regions of the marketed antibody-based biotherapeutics (medicine-likeness). We generated 100000 variable region sequences of antigen-agnostic human antibodies belonging to the IGHV3-IGKV1 germline pair using a training dataset of 31416 human antibodies that satisfied our computational developability criteria. The in-silico generated antibodies recapitulate intrinsic sequence, structural, and physicochemical properties of the training antibodies, and compare favorably with the experimentally measured biophysical attributes of 100 variable regions of marketed and clinical stage antibody-based biotherapeutics. A sample of 51 highly diverse in-silico generated antibodies with >90th percentile medicine-likeness and > 90% humanness was evaluated by two independent experimental laboratories. Our data show the in-silico generated sequences exhibit high expression, monomer content, and thermal stability along with low hydrophobicity, self-association, and non-specific binding when produced as full-length monoclonal antibodies. The ability to computationally generate developable human antibody libraries is a first step towards enabling in-silico discovery of antibody-based biotherapeutics. These findings are expected to accelerate in-silico discovery of antibody-based biotherapeutics and expand the druggable antigen space to include targets refractory to conventional antibody discovery methods requiring in vitro antigen production.

PMID:39851074 | DOI:10.1093/bib/bbaf023

Food Chem X. 2024 Nov 13;24:101981. doi: 10.1016/j.fochx.2024.101981. eCollection 2024 Dec 30.

ABSTRACT

With the rising demand of saffron, it is essential to standardize the confirmation of its origin and identify any adulteration to maintain a good quality led market product. However, a rapid and reliable strategy for identifying the adulteration saffron is still lacks. Herein, a combination of headspace-gas chromatography-ion mobility spectrometry (HS-GC-IMS) and convolutional neural network (CNN) was developed. Sixty-nine volatile compounds (VOCs) including 7 groups of isomers were detected rapidly and directly. A CNN prediction model based on GC-IMS data was proposed. With the merit of minimal data prepossessing and automatic feature extraction capability, GC-IMS images were directly input to the CNN model. The origin prediction results were output with the average accuracy about 90 %, which was higher than traditional methods like PCA (61 %) and SVM (71 %). This established CNN also showed ability in identifying counterfeit saffron with a high accuracy of 98 %, which can be used to authenticate saffron.

PMID:39850938 | PMC:PMC11754009 | DOI:10.1016/j.fochx.2024.101981

Front Public Health. 2025 Jan 15;12:1426168. doi: 10.3389/fpubh.2024.1426168. eCollection 2024.

ABSTRACT

INTRODUCTION: The growing demand for real-time, affordable, and accessible healthcare has underscored the need for advanced technologies that can provide timely health monitoring. One such area is predicting arterial blood pressure (BP) using non-invasive methods, which is crucial for managing cardiovascular diseases. This research aims to address the limitations of current healthcare systems, particularly in remote areas, by leveraging deep learning techniques in Smart Health Monitoring (SHM).

METHODS: This paper introduces a novel neural network architecture, ResNet-LSTM, to predict BP from physiological signals such as electrocardiogram (ECG) and photoplethysmogram (PPG). The combination of ResNet's feature extraction capabilities and LSTM's sequential data processing offers improved prediction accuracy. Comprehensive error analysis was conducted, and the model was validated using Leave-One-Out (LOO) cross-validation and an additional dataset.

RESULTS: The ResNet-LSTM model showed superior performance, particularly with PPG data, achieving a mean absolute error (MAE) of 6.2 mmHg and a root mean square error (RMSE) of 8.9 mmHg for BP prediction. Despite the higher computational cost (~4,375 FLOPs), the improved accuracy and generalization across datasets demonstrate the model's robustness and suitability for continuous BP monitoring.

DISCUSSION: The results confirm the potential of integrating ResNet-LSTM into SHM for accurate and non-invasive BP prediction. This approach also highlights the need for accurate anomaly detection in continuous monitoring systems, especially for wearable devices. Future work will focus on enhancing cloud-based infrastructures for real-time analysis and refining anomaly detection models to improve patient outcomes.

PMID:39850864 | PMC:PMC11755415 | DOI:10.3389/fpubh.2024.1426168

Front Artif Intell. 2025 Jan 9;7:1498956. doi: 10.3389/frai.2024.1498956. eCollection 2024.

ABSTRACT

INTRODUCTION: Active learning can significantly decrease the labeling cost of deep learning workflows by prioritizing the limited labeling budget to high-impact data points that have the highest positive impact on model accuracy. Active learning is especially useful for semantic segmentation tasks where we can selectively label only a few high-impact regions within these high-impact images. Most established regional active learning algorithms deploy a static-budget querying strategy where a fixed percentage of regions are queried in each image. A static budget could result in over- or under-labeling images as the number of high-impact regions in each image can vary.

METHODS: In this paper, we present a novel dynamic-budget superpixel querying strategy that can query the optimal numbers of high-uncertainty superpixels in an image to improve the querying efficiency of regional active learning algorithms designed for semantic segmentation.

RESULTS: For two distinct datasets, we show that by allowing a dynamic budget for each image, the active learning algorithm is more effective compared to static-budget querying at the same low total labeling budget. We investigate both low- and high-budget scenarios and the impact of superpixel size on our dynamic active learning scheme. In a low-budget scenario, our dynamic-budget querying outperforms static-budget querying by 5.6% mIoU on a specialized agriculture field image dataset and 2.4% mIoU on Cityscapes.

DISCUSSION: The presented dynamic-budget querying strategy is simple, effective, and can be easily adapted to other regional active learning algorithms to further improve the data efficiency of semantic segmentation tasks.

PMID:39850848 | PMC:PMC11754207 | DOI:10.3389/frai.2024.1498956

Int J Burns Trauma. 2024 Dec 15;14(6):125-132. doi: 10.62347/VCJP9652. eCollection 2024.

ABSTRACT

PURPOSE: To evaluate the identification of nasal bone fractures and their clinical diagnostic significance for three-dimensional (3D) reconstruction of maxillofacial computed tomography (CT) images by applying artificial intelligence (AI) with deep learning (DL).

METHODS: CT maxillofacial 3D reconstruction images of 39 patients with normal nasal bone and 43 patients with nasal bone fracture were retrospectively analysed, and a total of 247 images were obtained in three directions: the orthostatic, left lateral and right lateral positions. The CT scan images of all patients were reviewed by two senior specialists to confirm the presence or absence of nasal fractures. Binary classification prediction was performed using the YOLOX detection model + GhostNetv2 classification model with a DL algorithm. Accuracy, sensitivity, and specificity were used to evaluate the efficacy of the AI model. Manual independent review, and AI model-assisted manual independent review were used to identify nasal fractures.

RESULTS: Compared with those of manual independent detection, the accuracy, sensitivity, and specificity of AI-assisted film reading improved between junior and senior physicians. The differences were statistically significant (P<0.05), and all were higher than manual independent detection.

CONCLUSIONS: Based on deep learning methods, an artificial intelligence model can be used to assist in the diagnosis of nasal bone fractures, which helps to promote the practical clinical application of deep learning methods.

PMID:39850782 | PMC:PMC11751554 | DOI:10.62347/VCJP9652

Int J Cardiol Heart Vasc. 2025 Jan 2;56:101593. doi: 10.1016/j.ijcha.2024.101593. eCollection 2025 Feb.

ABSTRACT

BACKGROUND: The National Lung Screening Trial (NLST) has shown that screening with low dose CT in high-risk population was associated with reduction in lung cancer mortality. These patients are also at high risk of coronary artery disease, and we used deep learning model to automatically detect, quantify and perform risk categorisation of coronary artery calcification score (CACS) from non-ECG gated Chest CT scans.

MATERIALS AND METHODS: Automated calcium quantification was performed using a neural network based on Mask regions with convolutional neural networks (R-CNN) for multiorgan segmentation. Manual evaluation of calcium was carried out using proprietary software. This study used 80 patients to train the segmentation model and randomly selected 1442 patients were used for the validation of the algorithm. We compared the model generated results with Ground Truth.

RESULTS: Automatic cardiac and aortic segmentation model worked well (Mean Dice score: 0.91). Cohen's kappa coefficient between the reference actual and the interclass computed predictive categories on the test set is 0.72 (95 % CI: 0.61-0.83). Our method correctly classifies the risk group in 78.8 % of the cases and classifies the subjects in the same group. F-score is measured as 0.78; 0.71; 0.81; 0.82; 0.92 in calcium score categories 0(CS:0), I (1-99), II (100-400), III (400-1000), IV (>1000), respectively. 79 % of the predictive scores lie in the same categories, 20 % of the predictive scores are one category up or down, and only 1.2 % patients were more than one category off. For the presence/absence of coronary artery calcifications, our deep learning model achieved a sensitivity of 90 % and a specificity of 94 %.

CONCLUSION: Fully automated model shows good correlation compared with reference standards. Automating the process could improve diagnostic ability, risk categorization, facilitate primary prevention intervention, improve morbidity and mortality, and decrease healthcare costs.

PMID:39850777 | PMC:PMC11754490 | DOI:10.1016/j.ijcha.2024.101593

Proc (IEEE Conf Multimed Inf Process Retr). 2024 Aug;2024:369-375. doi: 10.1109/mipr62202.2024.00065. Epub 2024 Oct 15.

ABSTRACT

Despite the prevalence of images and texts in machine learning, tabular data remains widely used across various domains. Existing deep learning models, such as convolutional neural networks and transformers, perform well however demand extensive preprocessing and tuning limiting accessibility and scalability. This work introduces an innovative approach based on a structured state-space model (SSM), MambaTab, for tabular data. SSMs have strong capabilities for efficiently extracting effective representations from data with long-range dependencies. MambaTab leverages Mamba, an emerging SSM variant, for end-to-end supervised learning on tables. Compared to state-of-the-art baselines, MambaTab delivers superior performance while requiring significantly fewer parameters, as empirically validated on diverse benchmark datasets. MambaTab's efficiency, scalability, generalizability, and predictive gains signify it as a lightweight, "plug-and-play" solution for diverse tabular data with promise for enabling wider practical applications.

PMID:39850741 | PMC:PMC11755428 | DOI:10.1109/mipr62202.2024.00065

Int J Remote Sens. 2024 Nov 19;46(2):811-834. doi: 10.1080/01431161.2024.2423909. eCollection 2025.

ABSTRACT

Tidal flat ecosystems, are under steady decline due to anthropogenic pressures including sea level rise and climate change. Monitoring and managing these coastal systems requires accurate and up-to-date mapping. Sediment characteristics and macrozoobenthos are major indicators of the environmental status of tidal flats. Field monitoring of these indicators is often restricted by low accessibility and high costs. Despite limitations in spectral contrast, integrating remote sensing with deep learning proved efficient for deriving macrozoobenthos and sediment properties. In this study, we combined deep-learning features derived from Sentinel-2 images and Object-Based Image Analysis (OBIA) to explicitly include spatial aspects in the prediction of tsediment and macrozoobenthos properties of tidal flats , as well as the distribution of four benthic species. The deep-learning features extracted from a convolutional autoencoder model were analysed with OBIA to include spatial, textural, and contextual information. Object sets of varying sizes and shapes based on the spectral bands and/or the deep-learning features, served as the spatial units. These object sets and the field-collected points were used to train the Random Forest prediction model. Predictions were made for the tidal basins Pinkegat and Zoutkamperlaag in the Dutch Wadden Sea for 2018 to 2020. The overall prediction scores of the environmental variables ranged between 0.31 and 0.54. The species-distribution prediction model achieved accuracies ranging from 0.54 to 0.68 for the four benthic species). There was an average improvement of 21% points on predictions using objects with deep learning features compared to the pixel-based predictions with just the spectral bands. The mean spatial unit that captured the patterns best ranged between 0.3 ha and 13 ha for the different variables. Overall, using both OBIA and deep-learning features consistently improved the predictions, making it a valuable combination for monitoring these important environmental variables of coastal regions.

PMID:39850715 | PMC:PMC11755323 | DOI:10.1080/01431161.2024.2423909

Indian Dermatol Online J. 2024 Dec 11;16(1):40-49. doi: 10.4103/idoj.idoj_460_24. eCollection 2025 Jan-Feb.

ABSTRACT

BACKGROUND: Artificial intelligence (AI) is revolutionizing healthcare by enabling systems to perform tasks traditionally requiring human intelligence. In healthcare, AI encompasses various subfields, including machine learning, deep learning, natural language processing, and expert systems. In the specific domain of onychology, AI presents a promising avenue for diagnosing nail disorders, analyzing intricate patterns, and improving diagnostic accuracy. This review provides a comprehensive overview of the current applications of AI in onychology, focusing on its role in diagnosing onychomycosis, subungual melanoma, nail psoriasis, nail fold capillaroscopy, and nail involvement in systemic diseases.

MATERIALS AND METHODS: A literature review on AI in nail disorders was conducted via PubMed and Google Scholar, yielding relevant studies. AI algorithms, particularly deep convolutional neural networks (CNNs), have demonstrated high sensitivity and specificity in interpreting nail images, aiding differential diagnosis as well as enhancing the efficiency of diagnostic processes in a busy clinical setting. In studies evaluating onychomycosis, AI has shown the ability to distinguish between normal nails, fungal infections, and other differentials, including nail psoriasis, with a high accuracy. AI systems have proven effective in identifying subungual melanoma. For nail psoriasis, AI has been used to automate the scoring of disease severity, reducing the time and effort required. AI applications in nail fold capillaroscopy have aided the analysis of diagnosis and prognosis of connective tissue diseases. AI applications have also been extended to recognize nail manifestations of systemic diseases, by analyzing changes in nail morphology and coloration. AI also facilitates the management of nail disorders by offering tools for personalized treatment planning, remote care, treatment monitoring, and patient education.

CONCLUSION: Despite these advancements, challenges such as data scarcity, image heterogeneity, interpretability issues, regulatory compliance, and poor workflow integration hinder the seamless adoption of AI in onychology practice. Ongoing research and collaboration between AI developers and nail experts is crucial to realize the full potential of AI in improving patient outcomes in onychology.

PMID:39850679 | PMC:PMC11753549 | DOI:10.4103/idoj.idoj_460_24

Comput Struct Biotechnol J. 2024 Dec 30;27:160-170. doi: 10.1016/j.csbj.2024.12.015. eCollection 2025.

ABSTRACT

Quality estimation of the predicted interaction interface of protein complex structural models is not only important for complex model evaluation and selection but also useful for protein-protein docking. Despite recent progress fueled by symmetry-aware deep learning architectures and pretrained protein language models (pLMs), existing methods for estimating protein complex quality have yet to fully exploit the collective potentials of these advances for accurate estimation of protein-protein interface. Here we present EquiRank, an improved protein-protein interface quality estimation method by leveraging the strength of a symmetry-aware E(3) equivariant deep graph neural network (EGNN) and integrating pLM embeddings from the pretrained ESM-2 model. Our method estimates the quality of the protein-protein interface through an effective graph-based representation of interacting residue pairs, incorporating a diverse set of features, including ESM-2 embeddings, and then by learning the representation using symmetry-aware EGNNs. Our experimental results demonstrate improved ranking performance on diverse datasets over existing latest protein complex quality estimation methods including the top-performing CASP15 protein complex quality estimation method VoroIF_GNN and the self-assessment module of AlphaFold-Multimer repurposed for protein complex scoring and across different performance evaluation metrics. Additionally, our ablation studies demonstrate the contributions of both pLMs and the equivariant nature of EGNN for improved protein-protein interface quality estimation performance. EquiRank is freely available at https://github.com/mhshuvo1/EquiRank.

PMID:39850657 | PMC:PMC11755013 | DOI:10.1016/j.csbj.2024.12.015