Literature Watch
Atypical Leber Hereditary Optic Neuropathy (LHON) Associated with a Novel MT-CYB:m.15309T>C(Ile188Thr) Variant
Genes (Basel). 2025 Jan 20;16(1):108. doi: 10.3390/genes16010108.
ABSTRACT
Background: The study presents a detailed examination and follow-up of a Slovenian patient with an Leber Hereditary Optic Neuropathy (LHON)-like phenotype and bilateral optic neuropathy in whom genetic analysis identified a novel variant MT-CYB:m.15309T>C (Ile188Thr). Methods: We provide detailed analysis of the clinical examinations of a male patient with bilateral optic neuropathy from the acute stage to 8 years of follow-up. Complete ophthalmological exam, electrophysiology and optical coherence tomography (OCT) segmentation were performed. The genotype analysis was performed with a complete screening of the mitochondrial genome. Furthermore, proteomic analysis of the protein structure and function was performed to assess the pathogenicity of a novel variant of unknown significance. Mitochondrial function analysis of the patient's peripheral blood mononuclear cells (PBMCs) was performed with the objective of evaluating the mutation effect on mitochondrial function using flow cytometry and high-resolution respirometry. Results: The patient had a profound consecutive bilateral visual loss at 19 years of age due to optic neuropathy with characteristics of LHON; however, unlike patients with typical LHON, the patient experienced a fluctuation in visual function and significant late recovery. He had a total of three visual acuity deteriorations and improvements in the left eye, with concomitant visual loss in the right eye and a final visual acuity drop reaching nadir 9 months after onset. The visual loss was characterized by centrocecal scotoma, abnormal color vision and abnormal VEP, while deterioration of PERG N95 followed with a lag of several months. The OCT examination showed retinal nerve fiber layer thinning matching disease progression. Following a two-year period of legal blindness, the patient's visual function started to improve, and over the course of 5 years, it reached 0.5 and 0.7 Snellen (0.3 and 0.15 LogMAR) visual acuity (VA). Mitochondrial sequencing identified a presumably pathogenic variant m.15309T>C in the MT-CYB gene at 65% heteroplasmy, belonging to haplogroup K. Mitochondrial function assessment of the patient's PBMCs showed a lower respiration rate, an increase in reactive oxygen species production and the presence of mitochondrial depolarization, compared to an age- and sex-matched healthy control's PBMCs. Conclusions: A novel variant in the MT-CYB:m.15309T>C (Ile188Thr) gene was identified in a patient with optic nerve damage and the LHON phenotype without any additional systemic features and atypical presentation of the disease with late onset of visual function recovery. The pathogenicity of the variant is supported by proteomic analysis and the mitochondrial dysfunction observed in the patient's PBMCs.
PMID:39858655 | DOI:10.3390/genes16010108
Recent Advances in Stroke Genetics-Unraveling the Complexity of Cerebral Infarction: A Brief Review
Genes (Basel). 2025 Jan 6;16(1):59. doi: 10.3390/genes16010059.
ABSTRACT
BACKGROUND/OBJECTIVES: Recent advances in stroke genetics have substantially enhanced our understanding of the complex genetic architecture underlying cerebral infarction and other stroke subtypes. As knowledge in this field expands, healthcare providers must remain informed about these latest developments. This review aims to provide a comprehensive overview of recent advances in stroke genetics, with a focus on cerebral infarction, and discuss their potential impact on patient care and future research directions.
METHODS: We reviewed recent literature about advances in stroke genetics, focusing on cerebral infarction, and discussed their potential impact on patient care and future research directions. Key developments include the identification of monogenic stroke syndromes, such as cerebral autosomal dominant arteriopathy with subcortical infarcts and leukoencephalopathy, and cerebral autosomal recessive arteriopathy with subcortical infarcts and leukoencephalopathy caused by mutations in the NOTCH3 and HTRA1 genes, respectively. In addition, the role of RNF213 in moyamoya disease and other cerebrovascular disorders, particularly in East Asian populations, has been elucidated. The development of polygenic risk scores for assessing genetic predisposition to stroke has demonstrated the potential to improve risk prediction beyond traditional factors. Genetic studies have also elucidated the distinct genetic architecture of stroke subtypes, including large artery atherosclerosis, small vessel disease, and cardioembolic stroke. Furthermore, the investigation of epigenetic modifications influencing stroke risk and its outcomes has revealed new research avenues, while advancements in pharmacogenomics highlight the potential for personalized stroke treatment based on individual genetic profiles.
CONCLUSIONS: These genetic discoveries have important clinical implications, including improved risk stratification, targeted prevention strategies, and the development of novel therapeutic approaches.
PMID:39858606 | DOI:10.3390/genes16010059
Pharmacogenetics of the Treatment of Neglected Diseases
Genes (Basel). 2025 Jan 5;16(1):54. doi: 10.3390/genes16010054.
ABSTRACT
BACKGROUND/OBJECTIVES: Pharmacogenetics (PGx) aims to identify individuals more likely to suffer from adverse reactions or therapeutic failure in drug treatments. However, despite most of the evidence in this area being from European populations, some diseases have also been neglected, such as HIV infection, malaria, and tuberculosis. With this review, we aim to emphasize which pharmacogenetic tests are ready to be implemented in treating neglected diseases that have some evidence and call attention to what is missing for these three diseases.
METHODS: A critical literature review on the PGx of HIV infection, malaria, and tuberculosis was performed.
RESULTS: There are three PGx guidelines for antiretroviral drugs used in HIV infection, one for malaria, and none for tuberculosis. Some evidence is already available, and some genes have already been identified, such as CYP2D6 for primaquine treatment and NAT2 for isoniazid. However, some barriers to the implementation are the lack of evidence due to the few studies on the diseases themselves and the admixture of the most affected populations, which must be considered, given the genetic differentiation of these populations.
CONCLUSIONS: PGx tests such as abacavir are already implemented in some places, and efavirenz/atazanavir is ready to implement if this medication is used. Other gene-drug associations were found but still do not present a clear recommendation. We call attention to the need to generate more evidence for testing treatments for other neglected diseases, such as malaria and tuberculosis, given their epidemiological importance and for the public health of less favored populations.
PMID:39858601 | DOI:10.3390/genes16010054
Association of Corticosteroid Inhaler Type with Saliva Microbiome in Moderate-to-Severe Pediatric Asthma
Biomedicines. 2025 Jan 2;13(1):89. doi: 10.3390/biomedicines13010089.
ABSTRACT
Background/Objectives: Metered-dose inhalers (MDIs) and dry powder inhalers (DPIs) are common inhaled corticosteroid (ICS) inhaler devices. The difference in formulation and administration technique of these devices may influence oral cavity microbiota composition. We aimed to compare the saliva microbiome in children with moderate-to-severe asthma using ICS via MDIs versus DPIs. Methods: Saliva samples collected from 143 children (6-17 yrs) with moderate-to-severe asthma across four European countries (The Netherlands, Germany, Spain, and Slovenia) as part of the SysPharmPediA cohort were subjected to 16S rRNA sequencing. The microbiome was compared using global diversity (α and β) between two groups of participants based on inhaler devices (MDI (n = 77) and DPI (n = 65)), and differential abundance was compared using the Analysis of Compositions of Microbiomes with the Bias Correction (ANCOM-BC) method. Results: No significant difference was observed in α-diversity between the two groups. However, β-diversity analysis revealed significant differences between groups using both Bray-Curtis and weighted UniFrac methods (adjusted p-value = 0.015 and 0.044, respectively). Significant differential abundance between groups, with higher relative abundance in the MDI group compared to the DPI group, was detected at the family level [Carnobacteriaceae (adjusted p = 0.033)] and at the genus level [Granulicatella (adjusted p = 0.021) and Aggregatibacter (adjusted p = 0.011)]. Conclusions: Types of ICS devices are associated with different saliva microbiome compositions in moderate-to-severe pediatric asthma. The causal relation between inhaler types and changes in saliva microbiota composition needs to be further evaluated, as well as whether this leads to different potential adverse effects in terms of occurrence and level of severity.
PMID:39857673 | DOI:10.3390/biomedicines13010089
How Antiretroviral Drug Concentrations Could Be Affected by Oxidative Stress, Physical Capacities and Genetics: A Focus on Dolutegravir Treated Male PLWH
Antioxidants (Basel). 2025 Jan 13;14(1):82. doi: 10.3390/antiox14010082.
ABSTRACT
High levels of reactive oxygen species (ROS) are present in people living with HIV (PLWH), produced by intense physical activity; in response, our body produces antioxidant molecules. ROS influence the expression of gene-encoding enzymes and transporters involved in drug biotransformation. In addition, pharmacogenetics can influence transporter activity, and thus drug exposure. Currently, no studies concerning this topic are present in the literature. The aim of this study was to investigate whether some antioxidant molecules, physical exercise, and genetic variants could affect dolutegravir (DTG) concentrations in PLWH, switching from triple to dual therapy. Thirty PLWH were recruited and analyzed at baseline (triple therapy), and 6 months after (dual therapy). Physical capacities were investigated using validated tools. Drug concentrations and oxidative stress biomarkers levels were evaluated through liquid chromatography coupled with tandem mass spectrometry, while genetic variants through real-time PCR. No statistical differences were suggested for drug concentrations, with the exception of intracellular DTG (p = 0.047). Statistically significant correlations between DTG plasma concentrations and white blood cells (p = 0.011; S = 0.480) and cytoplasmic N-acetyl-cysteine (p = 0.033; S = -0.419) were observed. Finally, white blood cells and BMI remained in the final multivariate regression model as predictors of DTG concentrations. This is the first study showing possible factors related to oxidative stress impacting DTG exposure.
PMID:39857416 | DOI:10.3390/antiox14010082
Pulmonary Delivery of Antibiotics to the Lungs: Current State and Future Prospects
Pharmaceutics. 2025 Jan 15;17(1):111. doi: 10.3390/pharmaceutics17010111.
ABSTRACT
This paper presents a comprehensive review of the current literature, clinical trials, and products approved for the delivery of antibiotics to the lungs. While there are many literature reports describing potential delivery systems, few of these have translated into marketed products. Key challenges remaining are the high doses required and, for powder formulations, the ability of the inhaler and powder combination to deliver the dose to the correct portion of the respiratory tract for maximum effect. Side effects, safety concerns, and disappointing clinical trial results remain barriers to regulatory approval. In this review, we describe some possible approaches to address these issues and highlight prospects in this area.
PMID:39861758 | DOI:10.3390/pharmaceutics17010111
VX-770, C<sub>act</sub>-A1, and Increased Intracellular cAMP Have Distinct Acute Impacts upon CFTR Activity
Int J Mol Sci. 2025 Jan 8;26(2):471. doi: 10.3390/ijms26020471.
ABSTRACT
The cystic fibrosis transmembrane conductance regulator (CFTR) is an anion channel that is dysfunctional in individuals with cystic fibrosis (CF). The permeability of CFTR can be experimentally manipulated though different mechanisms, including activation via inducing the phosphorylation of residues in the regulatory domain as well as altering the gating/open probability of the channel. Phosphorylation/activation of the channel is achieved by exposure to compounds that increase intracellular cAMP, with forskolin and IBMX commonly used for this purpose. Cact-A1 is a unique CFTR activator that does not increase intracellular cAMP, and VX-770 (ivacaftor) is a CFTR potentiator that is used experimentally and therapeutically to increase the open probability of the channel. Using primary human nasal epithelial cell (HNEC) cultures and Fischer rat thyroid (FRT) epithelial cells exogenously expressing functional CFTR, we examined the impact of VX-770, Cact-A1, and forskolin/IBMX on CFTR activity during analysis in an Ussing chamber. Relative contributions of these compounds to maximal CFTR activity were dependent on order of exposure, the presence of chemical and electrical gradients, the level of constitutive CFTR function, and the cell model tested. Increasing intracellular cAMP appeared to change cellular functions outside of CFTR activity that resulted in alterations in the drive for chloride through CFTR. These results demonstrate that one can utilize combinations of small-molecule CFTR activators and potentiators to provide detailed characterization of CFTR-mediated ion transport in primary HNECs and properties of these modulators in both primary HNECs and FRT cells. Future studies using these approaches may assist in the identification of novel defects in CFTR function and the identification of modulators with unique impacts on CFTR-mediated ion transport.
PMID:39859187 | DOI:10.3390/ijms26020471
Human Induced Lung Organoids: A Promising Tool for Cystic Fibrosis Drug Screening
Int J Mol Sci. 2025 Jan 7;26(2):437. doi: 10.3390/ijms26020437.
ABSTRACT
Cystic fibrosis (CF) is an autosomal recessive disorder caused by mutations in the CFTR gene. Currently, CFTR modulators are the most effective treatment for CF; however, they may not be suitable for all patients. A representative and convenient in vitro model is needed to screen therapeutic agents under development. This study, on the most common mutation, F508del, investigates the efficacy of human induced pluripotent stem cell-derived lung organoids (hiLOs) from NKX2.1+ lung progenitors and airway basal cells (hiBCs) as a 3D model for CFTR modulator response assessment by a forskolin-induced swelling assay. Weak swelling was observed for hiLOs from NKX2.1+ lung progenitors and hiBCs in response to modulators VX-770/VX-809 and VX-770/VX-661, whereas the VX-770/VX-661/VX-445 combination resulted in the highest swelling response, indicating superior CFTR function restoration. The ROC analysis of the FIS assay results revealed an optimal cutoff of 1.21, with 65.9% sensitivity and 71.8% specificity, and the predictive accuracy of the model was 76.4%. In addition, this study compared the response of hiLOs with the clinical response of patients to therapy and showed similar drug response dynamics. Thus, hiLOs can effectively model the CF pathology and predict patients' specific response to modulators.
PMID:39859153 | DOI:10.3390/ijms26020437
Rescue of Mutant CFTR Channel Activity by Investigational Co-Potentiator Therapy
Biomedicines. 2025 Jan 1;13(1):82. doi: 10.3390/biomedicines13010082.
ABSTRACT
Background: The potentiator VX-770 (ivacaftor) has been approved as a monotherapy for over 95 cystic fibrosis (CF)-causing variants associated with gating/conductance defects of the CF transmembrane conductance regulator (CFTR) channel. However, despite its therapeutic success, VX-770 only partially restores CFTR activity for many of these variants, indicating they may benefit from the combination of potentiators exhibiting distinct mechanisms of action (i.e., co-potentiators). We previously identified LSO-24, a hydroxy-1,2,3-triazole-based compound, as a modest potentiator of p.Arg334Trp-CFTR, a variant with a conductance defect for which no modulator therapy is currently approved. Objective/Methods: We synthesized a new set of LSO-24 structure-based compounds, screened their effects on p.Arg334Trp-CFTR activity, and assessed the additivity of hit compounds to VX-770, ABBV-974, ABBV-3067, and apigenin. After validation by electrophysiological assays, the most promising hits were also assessed in cells expressing other variants with defective gating/conductance, namely p.Pro205Ser, p.Ser549Arg, p.Gly551Asp, p.Ser945Leu, and p.Gly1349Asp. Results: We found that five compounds were able to increase p.Arg334Trp-CFTR activity with similar efficacy, but slightly greater potency promoted by LSO-150 and LSO-153 (EC50: 1.01 and 1.26 μM, respectively). These two compounds also displayed a higher rescue of p.Arg334Trp-CFTR activity in combination with VX-770, ABBV-974, and ABBV-3067, but not with apigenin. When tested in cells expressing other CFTR variants, LSO-24 and its derivative LSO-150 increased CFTR activity for the variants p.Ser549Arg, p.Gly551Asp, and p.Ser945Leu with a further effect in combination with VX-770 or ABBV-3067. No potentiator was able to rescue CFTR activity in p.Pro205Ser-expressing cells, while p.Gly1349Asp-CFTR responded to VX-770 and ABBV-3067 but not to LSO-24 or LSO-150. Conclusions: Our data suggest that these new potentiators might share a common mechanism with apigenin, which is conceivably distinct from that of VX-770 and ABBV-3067. The additive rescue of p.Arg334Trp-, p.Ser549Arg-, p.Gly551Asp-, and p.Ser945Leu-CFTR also indicates that these variants could benefit from the development of a co-potentiator therapy.
PMID:39857666 | DOI:10.3390/biomedicines13010082
Identifying protected health information by transformers-based deep learning approach in Chinese medical text
Health Informatics J. 2025 Jan-Mar;31(1):14604582251315594. doi: 10.1177/14604582251315594.
ABSTRACT
Purpose: In the context of Chinese clinical texts, this paper aims to propose a deep learning algorithm based on Bidirectional Encoder Representation from Transformers (BERT) to identify privacy information and to verify the feasibility of our method for privacy protection in the Chinese clinical context. Methods: We collected and double-annotated 33,017 discharge summaries from 151 medical institutions on a municipal regional health information platform, developed a BERT-based Bidirectional Long Short-Term Memory Model (BiLSTM) and Conditional Random Field (CRF) model, and tested the performance of privacy identification on the dataset. To explore the performance of different substructures of the neural network, we created five additional baseline models and evaluated the impact of different models on performance. Results: Based on the annotated data, the BERT model pre-trained with the medical corpus showed a significant performance improvement to the BiLSTM-CRF model with a micro-recall of 0.979 and an F1 value of 0.976, which indicates that the model has promising performance in identifying private information in Chinese clinical texts. Conclusions: The BERT-based BiLSTM-CRF model excels in identifying privacy information in Chinese clinical texts, and the application of this model is very effective in protecting patient privacy and facilitating data sharing.
PMID:39862116 | DOI:10.1177/14604582251315594
AVP-GPT2: A Transformer-Powered Platform for De Novo Generation, Screening, and Explanation of Antiviral Peptides
Viruses. 2024 Dec 25;17(1):14. doi: 10.3390/v17010014.
ABSTRACT
Human respiratory syncytial virus (RSV) remains a significant global health threat, particularly for vulnerable populations. Despite extensive research, effective antiviral therapies are still limited. To address this urgent need, we present AVP-GPT2, a deep-learning model that significantly outperforms its predecessor, AVP-GPT, in designing and screening antiviral peptides. Trained on a significantly expanded dataset, AVP-GPT2 employs a transformer-based architecture to generate diverse peptide sequences. A multi-modal screening approach, incorporating Star-Transformer and Vision Transformer, enables accurate prediction of antiviral activity and toxicity, leading to the identification of potent and safe candidates. SHAP analysis further enhances interpretability by explaining the underlying mechanisms of peptide activity. Our in vitro experiments confirmed the antiviral efficacy of peptides generated by AVP-GPT2, with some exhibiting EC50 values as low as 0.01 μM and CC50 values > 30 μM. This represents a substantial improvement over AVP-GPT and traditional methods. AVP-GPT2 has the potential to significantly impact antiviral drug discovery by accelerating the identification of novel therapeutic agents. Future research will explore its application to other viral targets and its integration into existing drug development pipelines.
PMID:39861804 | DOI:10.3390/v17010014
A Feature-Enhanced Small Object Detection Algorithm Based on Attention Mechanism
Sensors (Basel). 2025 Jan 20;25(2):589. doi: 10.3390/s25020589.
ABSTRACT
With the rapid development of AI algorithms and computational power, object recognition based on deep learning frameworks has become a major research direction in computer vision. UAVs equipped with object detection systems are increasingly used in fields like smart transportation, disaster warning, and emergency rescue. However, due to factors such as the environment, lighting, altitude, and angle, UAV images face challenges like small object sizes, high object density, and significant background interference, making object detection tasks difficult. To address these issues, we use YOLOv8s as the basic framework and introduce a multi-level feature fusion algorithm. Additionally, we design an attention mechanism that links distant pixels to improve small object feature extraction. To address missed detections and inaccurate localization, we replace the detection head with a dynamic head, allowing the model to route objects to the appropriate head for final output. We also introduce Slideloss to improve the model's learning of difficult samples and ShapeIoU to better account for the shape and scale of bounding boxes. Experiments on datasets like VisDrone2019 show that our method improves accuracy by nearly 10% and recall by about 11% compared to the baseline. Additionally, on the AI-TODv1.5 dataset, our method improves the mAP50 from 38.8 to 45.2.
PMID:39860960 | DOI:10.3390/s25020589
Intelligent Intrusion Detection System Against Various Attacks Based on a Hybrid Deep Learning Algorithm
Sensors (Basel). 2025 Jan 20;25(2):580. doi: 10.3390/s25020580.
ABSTRACT
The Internet of Things (IoT) has emerged as a crucial element in everyday life. The IoT environment is currently facing significant security concerns due to the numerous problems related to its architecture and supporting technology. In order to guarantee the complete security of the IoT, it is important to deal with these challenges. This study centers on employing deep learning methodologies to detect attacks. In general, this research aims to improve the performance of existing deep learning models. To mitigate data imbalances and enhance learning outcomes, the synthetic minority over-sampling technique (SMOTE) is employed. Our approach contributes to a multistage feature extraction process where autoencoders (AEs) are used initially to extract robust features from unstructured data on the model architecture's left side. Following this, long short-term memory (LSTM) networks on the right analyze these features to recognize temporal patterns indicative of abnormal behavior. The extracted and temporally refined features are inputted into convolutional neural networks (CNNs) for final classification. This structured arrangement harnesses the distinct capabilities of each model to process and classify IoT security data effectively. Our framework is specifically designed to address various attacks, including denial of service (DoS) and Mirai attacks, which are particularly harmful to IoT systems. Unlike conventional intrusion detection systems (IDSs) that may employ a singular model or simple feature extraction methods, our multistage approach provides more comprehensive analysis and utilization of data, enhancing detection capabilities and accuracy in identifying complex cyber threats in IoT environments. This research highlights the potential benefits that can be gained by applying deep learning methods to improve the effectiveness of IDSs in IoT security. The results obtained indicate a potential improvement for enhancing security measures and mitigating emerging threats.
PMID:39860948 | DOI:10.3390/s25020580
D-MGDCN-CLSTM: A Traffic Prediction Model Based on Multi-Graph Gated Convolution and Convolutional Long-Short-Term Memory
Sensors (Basel). 2025 Jan 19;25(2):561. doi: 10.3390/s25020561.
ABSTRACT
Real-time and accurate traffic forecasting aids in traffic planning and design and helps to alleviate congestion. Addressing the negative impacts of partial data loss in traffic forecasting, and the challenge of simultaneously capturing short-term fluctuations and long-term trends, this paper presents a traffic forecasting model, D-MGDCN-CLSTM, based on Multi-Graph Gated Dilated Convolution and Conv-LSTM. The model uses the DTWN algorithm to fill in missing data. To better capture the dual characteristics of short-term fluctuations and long-term trends in traffic, the model employs the DWT for multi-scale decomposition to obtain approximation and detail coefficients. The Conv-LSTM processes the approximation coefficients to capture the long-term characteristics of the time series, while the multiple layers of the MGDCN process the detail coefficients to capture short-term fluctuations. The outputs of the two branches are then merged to produce the forecast results. The model is tested against 10 algorithms using the PeMSD7(M) and PeMSD7(L) datasets, improving MAE, RMSE, and ACC by an average of 1.38% and 13.89%, 1% and 1.24%, and 5.92% and 1%, respectively. Ablation experiments, parameter impact analysis, and visual analysis all demonstrate the superiority of our decompositional approach in handling the dual characteristics of traffic data.
PMID:39860932 | DOI:10.3390/s25020561
A Deep Learning Approach for Mental Fatigue State Assessment
Sensors (Basel). 2025 Jan 19;25(2):555. doi: 10.3390/s25020555.
ABSTRACT
This study investigates mental fatigue in sports activities by leveraging deep learning techniques, deviating from the conventional use of heart rate variability (HRV) feature analysis found in previous research. The study utilizes a hybrid deep neural network model, which integrates Residual Networks (ResNet) and Bidirectional Long Short-Term Memory (Bi-LSTM) for feature extraction, and a transformer for feature fusion. The model achieves an impressive accuracy of 95.29% in identifying fatigue from original ECG data, 2D spectral characteristics and physiological information of subjects. In comparison to traditional methods, such as Support Vector Machines (SVMs) and Random Forests (RFs), as well as other deep learning methods, including Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM), the proposed approach demonstrates significantly improved experimental outcomes. Overall, this study offers a promising solution for accurately recognizing fatigue through the analysis of physiological signals, with potential applications in sports and physical fitness training contexts.
PMID:39860925 | DOI:10.3390/s25020555
Remaining Useful Life Prediction of Rolling Bearings Based on CBAM-CNN-LSTM
Sensors (Basel). 2025 Jan 19;25(2):554. doi: 10.3390/s25020554.
ABSTRACT
Predicting the Remaining Useful Life (RUL) is vital for ensuring the reliability and safety of equipment and components. This study introduces a novel method for predicting RUL that utilizes the Convolutional Block Attention Module (CBAM) to address the problem that Convolutional Neural Networks (CNNs) do not effectively leverage data channel features and spatial features in residual life prediction. Firstly, Fast Fourier Transform (FFT) is applied to convert the data into the frequency domain. The resulting frequency domain data is then used as input to the convolutional neural network for feature extraction; Then, the weights of channel features and spatial features are assigned to the extracted features by CBAM, and the weighted features are then input into the Long Short-Term Memory (LSTM) network to learn temporal features. Finally, the effectiveness of the proposed model is verified using the PHM2012 bearing dataset. Compared to several existing RUL prediction methods, the mean squared error, mean absolute error, and root mean squared error of the proposed method in this paper are reduced by 53%, 16.87%, and 31.68%, respectively, which verifies the superiority of the method. Meanwhile, the experimental results demonstrate that the proposed method achieves good RUL prediction accuracy across various failure modes.
PMID:39860924 | DOI:10.3390/s25020554
TBF-YOLOv8n: A Lightweight Tea Bud Detection Model Based on YOLOv8n Improvements
Sensors (Basel). 2025 Jan 18;25(2):547. doi: 10.3390/s25020547.
ABSTRACT
Tea bud localization detection not only ensures tea quality, improves picking efficiency, and advances intelligent harvesting, but also fosters tea industry upgrades and enhances economic benefits. To solve the problem of the high computational complexity of deep learning detection models, we developed the Tea Bud DSCF-YOLOv8n (TBF-YOLOv8n)lightweight detection model. Improvement of the Cross Stage Partial Bottleneck Module with Two Convolutions(C2f) module via efficient Distributed Shift Convolution (DSConv) yields the C2f module with DSConv(DSCf)module, which reduces the model's size. Additionally, the coordinate attention (CA) mechanism is incorporated to mitigate interference from irrelevant factors, thereby improving mean accuracy. Furthermore, the SIOU_Loss (SCYLLA-IOU_Loss) function and the Dynamic Sample(DySample)up-sampling operator are implemented to accelerate convergence and enhance both average precision and detection accuracy. The experimental results show that compared to the YOLOv8n model, the TBF-YOLOv8n model has a 3.7% increase in accuracy, a 1.1% increase in average accuracy, a 44.4% reduction in gigabit floating point operations (GFLOPs), and a 13.4% reduction in the total number of parameters included in the model. In comparison experiments with a variety of lightweight detection models, the TBF-YOLOv8n still performs well in terms of detection accuracy while remaining more lightweight. In conclusion, the TBF-YOLOv8n model achieves a commendable balance between efficiency and precision, offering valuable insights for advancing intelligent tea bud harvesting technologies.
PMID:39860916 | DOI:10.3390/s25020547
Zero-Shot Traffic Identification with Attribute and Graph-Based Representations for Edge Computing
Sensors (Basel). 2025 Jan 18;25(2):545. doi: 10.3390/s25020545.
ABSTRACT
With the proliferation of mobile terminals and the rapid growth of network applications, fine-grained traffic identification has become increasingly challenging. Methods based on machine learning and deep learning have achieved remarkable results, but they heavily rely on the distribution of training data, which makes them ineffective in handling unseen samples. In this paper, we propose AG-ZSL, a zero-shot learning framework based on traffic behavior and attribute representations for general encrypted traffic classification. AG-ZSL primarily learns two mapping functions: one that captures traffic behavior embeddings from burst-based traffic interaction graphs, and the other that learns attribute embeddings from traffic attribute descriptions. Then, the framework minimizes the distance between these embeddings within the shared feature space. The gradient rejection algorithm and K-Nearest Neighbors are introduced to implement a two-stage method for general traffic classification. Experimental results on IoT datasets demonstrate that AG-ZSL achieves exceptional performance in classifying both known and unknown traffic, highlighting its potential for enhancing secure and efficient traffic management at the network edge.
PMID:39860913 | DOI:10.3390/s25020545
PC-CS-YOLO: High-Precision Obstacle Detection for Visually Impaired Safety
Sensors (Basel). 2025 Jan 17;25(2):534. doi: 10.3390/s25020534.
ABSTRACT
The issue of obstacle avoidance and safety for visually impaired individuals has been a major topic of research. However, complex street environments still pose significant challenges for blind obstacle detection systems. Existing solutions often fail to provide real-time, accurate obstacle avoidance decisions. In this study, we propose a blind obstacle detection system based on the PC-CS-YOLO model. The system improves the backbone network by adopting the partial convolutional feed-forward network (PCFN) to reduce computational redundancy. Additionally, to enhance the network's robustness in multi-scale feature fusion, we introduce the Cross-Scale Attention Fusion (CSAF) mechanism, which integrates features from different sensory domains to achieve superior performance. Compared to state-of-the-art networks, our system shows improvements of 2.0%, 3.9%, and 1.5% in precision, recall, and mAP50, respectively. When evaluated on a GPU, the inference speed is 20.6 ms, which is 15.3 ms faster than YOLO11, meeting the real-time requirements for blind obstacle avoidance systems.
PMID:39860905 | DOI:10.3390/s25020534
Gender Differences Are a Leading Factor in 5-Year Survival of Patients with Idiopathic Pulmonary Fibrosis over Antifibrotic Therapy Reduction
Life (Basel). 2025 Jan 16;15(1):106. doi: 10.3390/life15010106.
ABSTRACT
BACKGROUND: Idiopathic pulmonary fibrosis (IPF) is a chronic, progressive lung disease with a median survival of 3-5 years. Antifibrotic therapies like pirfenidone and nintedanib slow progression, but the outcomes vary. Gender may influence disease presentation, progression, and response to treatment. This study evaluates the impact of gender on the 5-year survival, pharmacological management, and clinical outcomes of patients with IPF.
METHODS: A retrospective cohort study of 254 IPF patients was conducted, with 164 (131 males:33 females) having complete data. Patients underwent spirometry, DLCO, and 6 min walk tests. Data on comorbidities, smoking, antifibrotic therapy type, dosage adjustments, and adverse events were collected. We used Kaplan-Meier survival curves and logistic regression to assess gender-related differences in outcomes.
RESULTS: Men had worse lung function at diagnosis (FVC 74.9 ± 18.5 vs. 87.2 ± 20.1% of pred.; p < 0.001) and a higher smoking prevalence (74% vs. 30%; p < 0.001). Women had better survival (51.2 vs. 40.8 ± 19.2 months; p = 0.005) despite more frequent biopsy use (36% vs. 17%; p = 0.013). Women tolerated longer therapy better (p = 0.001). No differences were found between patients receiving reduced antifibrotic dosing and those receiving full dosing.
CONCLUSIONS: Gender has a significant impact on IPF outcomes, with women demonstrating better survival and tolerance to long-term therapy. In contrast, reducing antifibrotic treatment does not appear to significantly affect survival outcomes. These findings underscore the need for future research on gender-specific management approaches.
PMID:39860046 | DOI:10.3390/life15010106
Pages
