Med Adv. 2024 Dec;2(4):336-348. doi: 10.1002/med4.86. Epub 2024 Dec 17.

ABSTRACT

BACKGROUND: Accurate staging systems are essential for assessing the severity of idiopathic pulmonary fibrosis (IPF) and guiding clinical management. This study aimed to evaluate the prognostic value of pulmonary comorbidities and body mass index (BMI) in IPF, develop a nomogram predicting overall survival (OS), and create a nomogram-based survival prediction model.

METHODS: Patients with IPF were identified from electronic medical records of the West Virginia hospital system. Least Absolute Shrinkage and Selection Operator (LASSO) Cox regression analysis was used for variable selection, and a nomogram was constructed. Risk groups were defined based on the nomogram's probability tertiles. The performance of the nomogram-based model was evaluated using Harrell's concordance index (C-index) and the Hosmer-Lemeshow test.

RESULTS: The study included 152 patients with IPF. The majority of the patients were elderly, male, and had a BMI above 24 kg/m2. The median survival duration was 7.6 years. The survival rates were 91% at 1 year, 78% at 3 years, and 68% at 5 years. LASSO regression selected carbon monoxide lung diffusion capacity percentage predicted (DLco%), BMI, pulmonary hypertension, pulmonary embolism, and sleep apnea as independent predictive variables. The nomogram demonstrated good discrimination (C-index = 0.71) and calibration.

CONCLUSIONS: Pulmonary comorbidities and BMI have significant prognostic value in IPF, emphasizing the necessity for consistent screening, assessment, and management of these factors in IPF care. Furthermore, the nomogram-based staging system showed promising performance in predicting OS and represents an actionable staging system that could potentially improve clinical management in IPF. Further validation of the nomogram is warranted to confirm its utility in clinical practice.

PMID:39931115 | PMC:PMC11809524 | DOI:10.1002/med4.86

Acta Physiol (Oxf). 2025 Mar;241(3):e70018. doi: 10.1111/apha.70018.

ABSTRACT

BACKGROUND: The distal convoluted tubule (DCT) plays an indispensable role in magnesium (Mg2+) reabsorption in the kidney. Yet, the extrusion mechanism of Mg2+ has not been identified. The solute carrier 41A3 (SLC41A3) has been suggested to be involved in Mg2+ extrusion, but this has never been conclusively demonstrated.

METHODS: Using available RNA-sequencing data and real-time quantitative PCR, expression of two alternative Slc41a3 transcripts, encoding isoform (Iso) 1 or 2, were assessed in kidney and isolated DCT tubules. HEK293 or HAP1 cells were transfected with plasmids expressing either of the isoforms, followed by 25Mg2+ transport studies. Identification of cis-regulatory elements (CRE) was achieved by combining data from publicly available ATAC sequencing data and luciferase assays.

RESULTS: Gene expression studies revealed a distinct transcript of Slc41a3 in the DCT with an alternative promoter, leading to a protein with a unique N-terminus; SLC41A3-Iso 2. HEK293 cells overexpressing SLC41A3-Iso 2, but not -Iso 1, exhibited 2.7-fold and 1.6-fold higher 25Mg2+ uptake and extrusion, compared to mock, respectively. The transport was independent of Na+, of the Mg2+ channel TRPM7 or of transporters CNNM3 and -4. We identified a CRE accessible in the DCT, ±2.8kb upstream of the transcript. The presence of the CRE increased the Slc41a3-Iso 2 promoter activity 3.8-fold following luciferase assays, indicating the CRE contains an enhancer function.

CONCLUSION: In conclusion, we identified two alternative transcripts of Slc41a3 in mouse. Slc41a3-Iso 2 is enriched within the DCT using specific gene regulatory elements. We speculate that specifically in the DCT, SLC41A3-Iso 2 orchestrates Mg2+ extrusion.

PMID:39931759 | DOI:10.1111/apha.70018

Arch Insect Biochem Physiol. 2025 Feb;118(2):e70039. doi: 10.1002/arch.70039.

ABSTRACT

Rhynchophorus ferrugineus (Olivier, 1790) (Coleoptera: Dryophthoridae), commonly known as the red palm weevil (RPW), is a globally significant pest that threatens economically important palm trees. Its cryptic infestation behavior leads to irreversible damage and eventual host plant death. Current control methods using broad-spectrum insecticides are largely ineffective due to resistance development and their adverse effects on nontarget organisms, necessitating novel strategies. This study integrates proteomics and transcriptomics data to explore the molecular landscape of RPW and identify pathways for targeted pest management. A total of 16,954 transcripts and 983 proteins were identified across three developmental stages (larvae, male adults, and female adults), with a notable decline in protein numbers from larvae to adult. Differential expression analysis revealed 7540 proteins varying significantly between developmental stages. Through subtractive analysis, 218 proteins meeting stringent inclusion and exclusion criteria were identified. These proteins underwent pathway enrichment analysis, mapping to 39 enriched pathways (p-value and an FDR of < 0.01). Among these, two pathways involving three key enzymes were highlighted as high-potential targets for developing insect-specific insecticides and diet-specific control strategies. This is the first comprehensive proteomics study analyzing the whole body of RPW across its developmental stages. The findings emphasize critical pathways, their enzyme components, and the regulation of these enzymes, offering novel insights for sustainable and targeted pest management solutions.

PMID:39930668 | DOI:10.1002/arch.70039

Sci Rep. 2025 Feb 10;15(1):4979. doi: 10.1038/s41598-025-87676-3.

ABSTRACT

Hepatocellular Carcinoma (HCC) is a malignancy with high mortality rates and limited treatment options. This study aimed to unearth the repurposable potential of FDA-approved drugs against specific genetic targets governing the HCC pathological pathways. The transcriptomics microarray datasets were explored to retrieve the HCC specific differentially expressed genes, and the significant genes were fed in Search Tool for the Retrieval of Interacting Genes/Proteins (STRING) database to capture the protein-protein interactions, which were visualized in Cytoscape. This revealed CCNA2, a cell cycle regulator, as a potential target, which mediates its action by interacting with CDK1 and CDK2. Further, with the intention of identifying inhibitors for CDK1 and CDK2, a drug library was created, and the drugs were virtually screened against their respective targets via molecular docking and dynamics studies. This captured the binding affinity of Steviolbioside towards CDK1 and Etravirine and Fludarabine towards CDK2. In vitro, validation confirmed the cytotoxic potential of Etravirine and Fludarabine in Huh-7 cell lines. Further, enzymatic assays, gene expression analysis, and cell cycle analysis signified the anti-proliferative potential of Etravirine in Huh-7 cells via inhibition of CDK2. In this drug repurposing venture, Etravirine, a non-nucleoside reverse transcriptase inhibitor indicated for the treatment of HIV, emerged as a promising candidate for HCC treatment. The findings warrant further preclinical and clinical investigations to ascertain the repurposable potential of Etravirine against HCC, particularly in patients with viral infections.

PMID:39929880 | DOI:10.1038/s41598-025-87676-3

Cell Death Discov. 2025 Feb 10;11(1):56. doi: 10.1038/s41420-025-02328-9.

ABSTRACT

The phenomenon of cell death has garnered significant scientific attention in recent years, emerging as a pivotal area of research. Recently, novel modalities of cellular death and the intricate interplay between them have been unveiled, offering insights into the pathogenesis of various diseases. This comprehensive review delves into the intricate molecular mechanisms, inducers, and inhibitors of the underlying prevalent forms of cell death, including apoptosis, autophagy, ferroptosis, necroptosis, mitophagy, and pyroptosis. Moreover, it elucidates the crosstalk and interconnection among the key pathways or molecular entities associated with these pathways, thereby paving the way for the identification of novel therapeutic targets, disease management strategies, and drug repurposing.

PMID:39929794 | DOI:10.1038/s41420-025-02328-9

J Cyst Fibros. 2025 Feb 9:S1569-1993(25)00047-5. doi: 10.1016/j.jcf.2025.01.014. Online ahead of print.

ABSTRACT

BACKGROUND: Increased variability in forced expiratory volume in 1 s of % predicted (FEV1pp) has been associated with accelerated lung function decline in individuals with cystic fibrosis (CF). Lung function variability is a leading predictor of decline, but the association between ivacaftor initiation and FEV1pp variability has not been characterized.

METHODS: We utilized the Cystic Fibrosis Foundation Patient Registry (2008-2020) to quantify this association and identify risk factors of increased variability. Linear mixed effects models were used to compare pre- and post-ivacaftor initiation periods for established outcome measures of FEV1pp variability: i) maximum and ii) median deviations from the best (highest) FEV1pp during each period; iii) maximum, iv) median, and v) standard deviation about the trendline of the FEV1pp trajectory in each period.

RESULTS: The analysis cohort included 527 individuals. Across outcomes, FEV1pp variability was reduced after ivacaftor initiation (median reduction: 1.85 % predicted). Reductions were robust with highest magnitudes of effect identified using maximum deviation from the best FEV1pp while most consistent findings were reached with trendline measures, particularly median deviation. Risk factors for increased FEV1pp variability differed between children and adults but were consistent between G551D and R117H subgroups. F508del homozygous patients followed contemporaneously exhibited minimal change in variability (median change: 0.25 % predicted). Reduced variability weakly correlated with changes in FEV1pp and slope, but higher levels of pre-ivacaftor variability were associated with greater reductions.

CONCLUSIONS: There was evidence that ivacaftor initiation reduces FEV1pp variability in people with CF. Quantifying FEV1pp variability may have utility as a marker of therapeutic effectiveness.

PMID:39929763 | DOI:10.1016/j.jcf.2025.01.014

Thorax. 2025 Feb 10:thorax-2024-221634. doi: 10.1136/thorax-2024-221634. Online ahead of print.

ABSTRACT

BACKGROUND: Early-life inflammation has long been recognised as a key pathophysiological process in the evolution of cystic fibrosis (CF) lung disease. Despite this, no CF-specific anti-inflammatory treatments have been developed. This is crucial even in the era of highly effective modulator therapy as recent evidence suggests that modulators alter, but may not fully resolve, pulmonary inflammation.

METHODS: In this study, we used clinical microbiology data, high-dimensional flow cytometry and multiplex immunoassays to compare pulmonary (bronchoalveolar lavage (BAL)) and systemic immunity in 70 preschool children with CF and a total of 32 age-matched preschool controls.

RESULTS: We show that inflammation in the early-life CF lung is characterised by innate cell infiltration (neutrophils: 31.31 vs 1.8% of BAL in CF compared with controls, FDRp=0.0001; eosinophils: 0.55 vs 0.06%, FDRp=0.001, and monocytes: 1.91 vs 0.45%, FDRp=0.004) and widespread upregulation of both traditional and type 2 inflammatory soluble signatures (40 analytes significantly elevated in BAL of CF compared with controls, all FDRp<0.1). Key targetable features of this response included pulmonary interleukin (IL)-8 and IL-13 which were most significantly associated with neutrophilic and eosinophilic infiltration, respectively (IL-8 and neutrophils; Spearman rho=0.68, FDRp=0.002: IL-13 and eosinophils; Spearman rho=0.75, FDRp=0.01). Signatures of type 2 inflammation, as identified by REACTOME pathway analysis, including IL-4, IL-13 and FGF-2, were highly elevated in both the lungs and circulation in early CF. When exploring the efficacy of Cystic Fibrosis Transmembrane Conductance Regulator modulators to resolve pulmonary and systemic inflammation in early life, we showed that different classes of modulators have varying effects on inflammation, with ivacaftor showing a more significant effect in the lungs and circulation than lumacaftor/ivacaftor. Finally, we showed that CF children with pathogen colonisation had similar levels of pulmonary inflammation as CF children without pathogen colonisation (no significant differences), and that inflammation was evident during infancy even without evidence of colonisation (as observed by significant increases in levels of SDF-1alpha, M-CSF, IL-2, IL-9, IL-12p40, IL-17, MCP-1 and LIGHT/TNFSF14, all FDRp<0.1), highlighting a role for intrinsic dysregulation of inflammation that begins in early life.

CONCLUSIONS: We provide a rationale for targeted anti-inflammatory intervention in early-life CF.

PMID:39929713 | DOI:10.1136/thorax-2024-221634

BMJ Open Respir Res. 2025 Feb 10;12(1):e002606. doi: 10.1136/bmjresp-2024-002606.

ABSTRACT

Cystic fibrosis (CF) treatment has revolutionised care over the past three decades with major advances in survival. Despite these advances, CF continues to create psychological and social challenges for people with CF (PWCF) throughout their life and is associated with worse health outcomes and higher healthcare costs. Anxiety and depression screening and management protocols are widely implemented within CF care; however, a much broader scope of psychosocial challenges exist which lack a standardised screening and management approach. The advent of CF transmembrane conductance regulator modulator therapies is transforming the psychosocial landscape for PWCF with new challenges and evolving psychosocial needs. What it means to have CF, the expectations, hopes and stressors are rapidly changing, and psychosocial care must keep pace if health outcomes are to be fully optimised. A symposium of international CF and psychosocial experts was convened in November 2022 to explore current and emerging issues in psychosocial health and identify opportunities and approaches to optimise psychosocial care. This state-of-the-art review summarises key symposium proceedings and highlights priorities for clinical practice and research in psychosocial health across the lifespan among PWCF. It also summarises state-of-the-art initiatives for screening and intervention to optimise CF psychosocial healthcare and patient outcomes.

PMID:39929550 | DOI:10.1136/bmjresp-2024-002606

BMC Oral Health. 2025 Feb 10;25(1):216. doi: 10.1186/s12903-025-05577-3.

ABSTRACT

BACKGROUND: The aim of this study was to evaluate the efficacy of detecting dental caries under fixed dental prostheses (FDPs) through the analysis of panoramic radiographs utilizing convolutional neural network (CNN) based You Only Look Once (YOLO) models. Deep learning algorithms can analyze datasets of dental images, such as panoramic radiographs to accurately identify and classify carious lesions. Using artificial intelligence, specifically deep learning methods, may help practitioners to detect and diagnose caries using radiograph images.

METHODS: The panoramic radiographs of 1004 patients, who had FDPs on their teeth and met the inclusion criteria, were divided into 904 (90%) images as training dataset and 100 (10%) images as the test dataset. Following the attainment of elevated detection scores with YOLOv7, regions of interest (ROIs) containing FDPs were automatically detected and cropped by the YOLOv7 model. In the second stage, 2467 cropped images were divided into 2248 (91%) images as the training dataset and 219 (9%) images as the test dataset. Caries under the FDPs were detected using both the YOLOv7 and the improved YOLOv7 (YOLOv7 + CBAM) models. The performance of the deep learning models used in the study was evaluated using recall, precision, F1, and mean average precision (mAP) scores.

RESULTS: In the first stage, the YOLOv7 model achieved 0.947 recall, 0.966 precision, 0.968 mAP and 0.956 F1 scores in detecting the FDPs. In the second stage the YOLOv7 model achieved 0.791 recall, 0.837 precision, 0.800 mAP and 0.813 F1 scores in detecting the caries under the FDPs, while the YOLOv7 + CBAM model achieved 0.827 recall, 0.834 precision, 0.846 mAP, and 0.830 F1 scores.

CONCLUSION: The use of deep learning models to detect dental caries under FDPs by analyzing panoramic radiographs has shown promising results. The study highlights that panoramic radiographs with appropriate image features can be used in combination with a detection system supported by deep learning methods. In the long term, our study may allow for accurate and rapid diagnoses that significantly improve the preservation of teeth under FDPs.

PMID:39930440 | DOI:10.1186/s12903-025-05577-3

BMC Med Imaging. 2025 Feb 10;25(1):44. doi: 10.1186/s12880-025-01566-8.

ABSTRACT

OBJECTIVES: This study aimed to investigate the diagnostic test accuracy of MRI-based radiomics studies for predicting EGFR mutation in brain metastasis originating from lung cancer.

METHODS: This meta-analysis, conducted following PRISMA guidelines, involved a systematic search in PubMed, Embase, and Web of Science up to November 3, 2024. Eligibility criteria followed the PICO framework, assessing population, intervention, comparison, and outcome. The RQS and QUADAS-2 tools were employed for quality assessment. A Bayesian model determined summary estimates, and statistical analysis was conducted using R and STATA software.

RESULTS: Eleven studies consisting of nine training and ten validation cohorts were included in the meta-analysis. In the training cohorts, MRI-based radiomics showed robust predictive performance for EGFR mutations in brain metastases, with an AUC of 0.90 (95% CI: 0.82-0.93), sensitivity of 0.84 (95% CI: 0.80-0.88), specificity of 0.86 (95% CI: 0.80-0.91), and a diagnostic odds ratio (DOR) of 34.17 (95% CI: 19.16-57.49). Validation cohorts confirmed strong performance, with an AUC of 0.91 (95% CI: 0.69-0.95), sensitivity of 0.79 (95% CI: 0.73-0.84), specificity of 0.88 (95% CI: 0.83-0.93), and a DOR of 31.33 (95% CI: 15.50-58.3). Subgroup analyses revealed notable trends: the T1C + T2WI sequences and 3.0 T scanners showed potential superiority, machine learning-based radiomics and manual segmentation exhibited higher diagnostic accuracy, and PyRadiomics emerged as the preferred feature extraction software.

CONCLUSION: This meta-analysis suggests that MRI-based radiomics holds promise for the non-invasive prediction of EGFR mutations in brain metastases of lung cancer.

PMID:39930347 | DOI:10.1186/s12880-025-01566-8

BMC Cancer. 2025 Feb 10;25(1):232. doi: 10.1186/s12885-025-13628-9.

ABSTRACT

BACKGROUND: Biochemical recurrence (BCR) occurs in 20%-40% of men with prostate cancer (PCa) who undergo radical prostatectomy. Predicting which patients will experience BCR in advance helps in formulating more targeted prostatectomy procedures. However, current preoperative recurrence prediction mainly relies on the use of the Gleason grading system, which omits within-grade morphological patterns and subtle histopathological features, leaving a significant amount of prognostic potential unexplored.

METHODS: We collected and selected a total of 1585 prostate biopsy images with tumor regions from 317 patients (5 Whole Slide Images per patient) to develop a deep learning system for predicting BCR of PCa before prostatectomy. The Inception_v3 neural network was employed to train and test models developed from patch-level images. The multiple instance learning method was used to extract whole slide image-level features. Finally, patient-level artificial intelligence models were developed by integrating deep learning -generated pathology features with several machine learning algorithms.

RESULTS: The BCR prediction system demonstrated great performance in the testing cohort (AUC = 0.911, 95% Confidence Interval: 0.840-0.982) and showed the potential to produce favorable clinical benefits according to Decision Curve Analyses. Increasing the number of WSIs for each patient improves the performance of the prediction system. Additionally, the study explores the correlation between deep learning -generated features and pathological findings, emphasizing the interpretative potential of artificial intelligence models in pathology.

CONCLUSIONS: Deep learning system can use biopsy samples to predict the risk of BCR in PCa, thereby formulating targeted treatment strategies.

PMID:39930342 | DOI:10.1186/s12885-025-13628-9

Med Phys. 2025 Feb 10. doi: 10.1002/mp.17685. Online ahead of print.

ABSTRACT

BACKGROUND: Sparse-view computed tomography (CT) reduces radiation exposure but suffers from severe artifacts caused by insufficient sampling and data scarcity, which compromise image fidelity. Recent advancements in deep learning (DL)-based methods for inverse problems have shown promise for CT reconstruction but often require high-quality paired datasets and lack interpretability.

PURPOSE: This paper aims to advance the field of CT reconstruction by introducing a novel unsupervised deep learning method. It builds on the foundation of Deep Radon Prior (DRP), which utilizes an untrained encoder-decoder network to extract implicit features from the Radon domain, and leverages Neural Architecture Search (NAS) to optimize network structures.

METHODS: We propose a novel unsupervised deep learning method for image reconstruction, termed NAS-DRP. This method leverages reinforcement learning-based NAS to explore diverse architectural spaces and integrates reinforcement learning with data inconsistency in the Radon domain. Building on previous DRP research, NAS-DRP utilizes an untrained encoder-decoder network to extract implicit features from the Radon domain. It further incorporates insights from studies on Deep Image Prior (DIP) regarding the critical impact of upsampling layers on image quality restoration. The method employs NAS to search for the optimal network architecture for upsampling unit tasks, while using Recurrent Neural Networks (RNNs) to constrain the optimization process, ensuring task-specific improvements in sparse-view CT image reconstruction.

RESULTS: Extensive experiments demonstrate that the NAS-DRP method achieves significant performance improvements in multiple CT image reconstruction tasks. The proposed method outperforms traditional reconstruction methods and other DL-based techniques in terms of both objective metrics (PSNR, SSIM, and LPIPS) and subjective visual quality. By automatically optimizing network structures, NAS-DRP effectively enhances the detail and accuracy of reconstructed images while minimizing artifacts.

CONCLUSIONS: NAS-DRP represents a significant advancement in the field of CT image reconstruction. By integrating NAS with deep learning and leveraging Radon domain-specific adaptations, this method effectively addresses the inherent challenges of sparse-view CT imaging. Additionally, it reduces the cost and complexity of data acquisition, demonstrating substantial potential for broader application in medical imaging. The evaluation code will be available at https://github.com/fujintao1999/NAS-DRP/.

PMID:39930320 | DOI:10.1002/mp.17685

J Med Syst. 2025 Feb 11;49(1):22. doi: 10.1007/s10916-025-02156-5.

ABSTRACT

This study aims to apply a multi-modal approach of the deep learning method for survival prediction in patients with non-small-cell lung cancer (NSCLC) using CT-based radiomics. We utilized two public data sets from the Cancer Imaging Archive (TCIA) comprising NSCLC patients, 420 patients and 516 patients for Lung 1 training and Lung 2 testing, respectively. A 3D convolutional neural network (CNN) survival was applied to extract 256 deep-radiomics features for each patient from a CT scan. Feature selection steps are used to choose the radiomics signatures highly associated with overall survival. Deep-radiomics and traditional-radiomics signatures, and clinical parameters were fed into the DeepSurv neural network. The C-index was used to evaluate the model's effectiveness. In the Lung 1 training set, the model combining traditional-radiomics and deep-radiomics performs better than the single parameter models, and models that combine all three markers (traditional-radiomics, deep-radiomics, and clinical) are most effective with C-index 0.641 for Cox proportional hazards (Cox-PH) and 0.733 for DeepSurv approach. In the Lung 2 testing set, the model combining traditional-radiomics, deep-radiomics, and clinical obtained a C-index of 0.746 for Cox-PH and 0.751 for DeepSurv approach. The DeepSurv method improves the model's prediction compared to the Cox-PH, and models that combine all three parameters with the DeepSurv have the highest efficiency in training and testing data sets (C-index: 0.733 and 0.751, respectively). DeepSurv CT-based deep-radiomics method outperformed Cox-PH in survival prediction of patients with NSCLC patients. Models' efficiency is increased when combining multi parameters.

PMID:39930275 | DOI:10.1007/s10916-025-02156-5

Commun Biol. 2025 Feb 10;8(1):209. doi: 10.1038/s42003-025-07479-0.

ABSTRACT

Quantifying emesis in Suncus murinus (S. murinus) has traditionally relied on direct observation or reviewing recorded behaviour, which are laborious, time-consuming processes that are susceptible to operator error. With rapid advancements in deep learning, automated animal behaviour quantification tools with high accuracy have emerged. In this study, we pioneere the use of both three-dimensional convolutional neural networks and self-attention mechanisms to develop the Automatic Emesis Detection (AED) tool for the quantification of emesis in S. murinus, achieving an overall accuracy of 98.92%. Specifically, we use motion-induced emesis videos as training datasets, with validation results demonstrating an accuracy of 99.42% for motion-induced emesis. In our model generalisation and application studies, we assess the AED tool using various emetics, including resiniferatoxin, nicotine, copper sulphate, naloxone, U46619, cyclophosphamide, exendin-4, and cisplatin. The prediction accuracies for these emetics are 97.10%, 100%, 100%, 97.10%, 98.97%, 96.93%, 98.91%, and 98.41%, respectively. In conclusion, employing deep learning-based automatic analysis improves efficiency and accuracy and mitigates human bias and errors. Our study provides valuable insights into the development of deep learning neural network models aimed at automating the analysis of various behaviours in S. murinus, with potential applications in preclinical research and drug development.

PMID:39930110 | DOI:10.1038/s42003-025-07479-0

Eur Spine J. 2025 Feb 10. doi: 10.1007/s00586-025-08708-0. Online ahead of print.

ABSTRACT

PURPOSE: Cervical spine injuries in the elderly (defined as individuals aged 65 years and older) are increasing, often resulting from falls and minor trauma. Prognosis varies widely, influenced by multiple factors. This study aimed to develop a deep-learning-based predictive model for post-injury outcomes.

METHODS: This study analyzed a nationwide dataset from the Japan Association of Spine Surgeons with Ambition, comprising 1512 elderly patients (aged 65 years and older) with cervical spine injuries from 2010 to 2020. Deep learning predictive models were constructed for residence, mobility, and the American Spinal Injury Association Impairment Scale (AIS). The model's performance was compared with that of a traditional statistical analysis.

RESULTS: The deep-learning model predicted the residence and AIS outcomes with varying accuracies. The highest accuracy was observed in predicting residence one year post-injury. The model also identified that the AIS score at discharge was significantly predicted by upper extremity trauma, mobility, and elbow extension strength. The deep learning model highlighted factors, such as upper extremity trauma, that were not considered significant in the traditional statistical analysis.

CONCLUSION: Our deep learning-based model offers a novel method for predicting outcomes following cervical spine injuries in the elderly population. The model is highly accurate and provides additional insights into potential prognostic factors. Such models can improve patient care and individualize future interventions.

PMID:39930051 | DOI:10.1007/s00586-025-08708-0

Sci Rep. 2025 Feb 10;15(1):4938. doi: 10.1038/s41598-025-89230-7.

ABSTRACT

Skin cancer represents a significant global health concern, where early and precise diagnosis plays a pivotal role in improving treatment efficacy and patient survival rates. Nonetheless, the inherent visual similarities between benign and malignant lesions pose substantial challenges to accurate classification. To overcome these obstacles, this study proposes an innovative hybrid deep learning model that combines ConvNeXtV2 blocks and separable self-attention mechanisms, tailored to enhance feature extraction and optimize classification performance. The inclusion of ConvNeXtV2 blocks in the initial two stages is driven by their ability to effectively capture fine-grained local features and subtle patterns, which are critical for distinguishing between visually similar lesion types. Meanwhile, the adoption of separable self-attention in the later stages allows the model to selectively prioritize diagnostically relevant regions while minimizing computational complexity, addressing the inefficiencies often associated with traditional self-attention mechanisms. The model was comprehensively trained and validated on the ISIC 2019 dataset, which includes eight distinct skin lesion categories. Advanced methodologies such as data augmentation and transfer learning were employed to further enhance model robustness and reliability. The proposed architecture achieved exceptional performance metrics, with 93.48% accuracy, 93.24% precision, 90.70% recall, and a 91.82% F1-score, outperforming over ten Convolutional Neural Network (CNN) based and over ten Vision Transformer (ViT) based models tested under comparable conditions. Despite its robust performance, the model maintains a compact design with only 21.92 million parameters, making it highly efficient and suitable for model deployment. The Proposed Model demonstrates exceptional accuracy and generalizability across diverse skin lesion classes, establishing a reliable framework for early and accurate skin cancer diagnosis in clinical practice.

PMID:39930026 | DOI:10.1038/s41598-025-89230-7

Sci Rep. 2025 Feb 10;15(1):4940. doi: 10.1038/s41598-025-89544-6.

ABSTRACT

Accurate space object pose estimation is crucial for various space tasks, including 3D reconstruction, satellite navigation, rendezvous and docking maneuvers, and collision avoidance. Many previous studies, however, often presuppose the availability of the space object's computer-aided design model for keypoint matching and model training. This work proposes a generalized pose estimation pipeline that is independent of 3D models and applicable to both instance- and category-level scenarios. The proposed framework consists of three parts based on deep learning approaches to accurately estimate space objects pose. First, a keypoints extractor is proposed to extract sub-pixel-level keypoints from input images. Then a multichannel matching network with triple loss is designed to obtain the matching pairs of keypoints in the body reference system. Finally, a pose graph optimization algorithm with a dynamic keyframes pool is designed to estimate the target pose and reduce long-term drifting pose errors. A space object dataset including nine different types of non-cooperative targets with 11,565 samples is developed for model training and evaluation. Extensive experimental results indicate that the proposed method demonstrates robust performance across various challenging conditions, including different object types, diverse illumination scenarios, varying rotation rates, and different image resolutions. To verify the demonstrated approach, the model is compared with several state-of-the-art approaches and shows superior estimation results. The mAPE and mMS scores of the proposed approach reach 0.63° and 0.767, respectively.

PMID:39930024 | DOI:10.1038/s41598-025-89544-6

Sci Rep. 2025 Feb 10;15(1):4931. doi: 10.1038/s41598-025-88451-0.

ABSTRACT

In the case of neonates, especially low birth weight preterm and high-risk infants, portable X-rays are frequently used. However, the image quality of portable X-rays is significantly lower compared to standard adult or pediatric X-rays, leading to considerable challenges in identifying abnormalities. Although attempts have been made to introduce deep learning to address these image quality issues, the poor quality of the images themselves hinders the training of deep learning models, further emphasizing the need for image enhancement. Additionally, since neonates have a high cell division rate and are highly sensitive to radiation, increasing radiation exposure to improve image quality is not a viable solution. Therefore, it is crucial to enhance image quality through preprocessing before training deep learning models. While various image enhancement methods have been proposed, Contrast Limited Adaptive Histogram Equalization (CLAHE) has been recognized as an effective technique for contrast-based image improvement. However, despite extensive research, the process of setting CLAHE's hyperparameters still relies on a brute force, manual approach, making it inefficient. To address this issue, we propose a method called Bayesian Optimization CLAHE(BO-CLAHE), which leverages Bayesian optimization to automatically select the optimal hyperparameters for X-ray images used in diagnosing lung diseases in preterm and high-risk neonates. The images enhanced by BO-CLAHE demonstrated superior performance across several classification models, with particularly notable improvements in diagnosing Transient Tachypnea of the Newborn (TTN). This approach not only reduces radiation exposure but also contributes to the development of AI-based diagnostic tools, playing a crucial role in the early diagnosis and treatment of preterm and high-risk neonates.

PMID:39929905 | DOI:10.1038/s41598-025-88451-0

Nature. 2025 Feb 10. doi: 10.1038/s41586-025-08707-7. Online ahead of print.

NO ABSTRACT

PMID:39930266 | DOI:10.1038/s41586-025-08707-7

NPJ Syst Biol Appl. 2025 Feb 10;11(1):17. doi: 10.1038/s41540-025-00497-y.

ABSTRACT

Microorganisms primarily utilize nutrients to generate biomass and replicate. When a single nutrient source is available, the produced biomass typically increases linearly with the initial amount of that nutrient. This linear trend can be accurately predicted by "black box models", which conceptualize growth as a single chemical reaction, treating nutrients as substrates and biomass as a product. However, natural environments usually present multiple nutrient sources, prompting us to extend the black box framework to incorporate catabolism, anabolism, and biosynthesis of biomass precursors. This modification allows for the quantification of co-utilization effects among multiple nutrients on microbial biomass production. The extended model differentiates between different types of nutrients: non-degradable nutrients, which can only serve as a biomass precursor, and degradable nutrients, which can also be used as an energy source. We experimentally demonstrated using Escherichia coli that, in contrast to initial model predictions, different nutrients affect each other's utilization in a mutually dependent manner; i.e., for some combinations, the produced biomass was no longer proportional to the initial amounts of nutrients present. To account for these mutual effects within a black box framework, we phenomenologically introduced an interaction between the metabolic processes involved in utilizing the nutrient sources. This phenomenological model qualitatively captures the experimental observations and, unexpectedly, predicts that the total produced biomass is influenced not only by the combination of nutrient sources but also by their relative initial amounts - a prediction we subsequently validated experimentally. Moreover, the model identifies which metabolic processes - catabolism, anabolism, or precursor biosynthesis-is affected in each specific nutrient combination, offering insights into microbial metabolic coordination.

PMID:39929850 | DOI:10.1038/s41540-025-00497-y