Chronic obstructive pulmonary disease (COPD) is a progressive respiratory condition, contributing significantly to global morbidity and mortality. Traditional diagnostic tools are effective in diagnosing COPD. However, these tools demand specialized equipment and expertise. Advances in artificial intelligence (AI) provide a platform for enhancing COPD diagnosis by leveraging diverse data modalities. The existing reviews primarily focus on single modalities and lack information on interpretability and explainability. Thus, this review intends to synthesize the AI-powered frameworks for COPD identification, focusing on data modalities, methodological innovation, evaluation strategies, and reporting limitations and potential biases. By adhering to Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, a systematic search was conducted across multiple repositories. From an initial pool of 1978 records, 22 studies were included in this review. The included studies demonstrated exceptional performance in specific settings. Most studies were retrospective and limited in diversity, lacking generalizability and external or prospective validation. This review presents a roadmap for advancing AI-assisted COPD detection. By highlighting the strengths and limitations of existing studies, it supports the development of future research. Future studies can utilize the findings to build models using prospective, multicenter, and multi-ethnic validations, ensuring generalizability and fairness.
BACKGROUND: Down syndrome (DS) is one of the most prevalent chromosomal abnormalities affecting global healthcare. Recent advances in artificial intelligence (AI) and machine learning (ML) have enhanced DS diagnostic accuracy. However, there is a lack of thorough evaluations analyzing the overall impact and effectiveness of AI-based DS diagnostic approaches. OBJECTIVES: This review intends to identify methodologies and technologies used in AI-driven DS diagnostics. It evaluates the performance of AI models in terms of standard evaluation metrics, highlighting their strengths and limitations. METHODOLOGY: In order to ensure transparency and rigor, the authors followed the preferred reporting items for systematic reviews and meta-analyses (PRISMA) guidelines. They extracted 1175 articles from major academic databases. By leveraging inclusion and exclusion criteria, a final set of 25 articles was selected. OUTCOMES: The findings revealed significant advancements in AI-powered DS diagnostics across diverse data modalities. The modalities, including facial images, ultrasound scans, and genetic data, demonstrated strong potential for early DS diagnosis. Despite these advancements, this review outlined the limitations of AI approaches. Small and imbalanced datasets reduce the generalizability of the AI models. The authors present actionable strategies to enhance the clinical adoptions of these models.
Down syndromeartificial intelligencemachine learningprenatal diagnosis
Congenital diaphragmatic hernia (CDH) is a rare but critical surgical disorder that can be managed using either open or thoracoscopic surgical approaches. However, the optimal approach remains a topic of debate. This study aimed to evaluate the efficacy and safety of thoracoscopic repair compared to open repair in patients with CDH. An extensive literature search was conducted across four databases (PubMed, Web of Science, Scopus, and Cochrane Library) from inception to May 2024, including all relevant studies comparing the two surgical modalities. Key outcomes assessed were hospital stay duration, operation time, mortality, and recurrence. Categorical outcomes were analyzed using the risk ratio (RR) with 95% confidence intervals (CI), while continuous outcomes were analyzed using the mean difference (MD) with 95% CI. Data analysis was performed using Review Manager (RevMan, Version 5.3). A total of 35 studies involving 1,680 individuals with CDH were included in our analysis. The pooled results revealed that thoracoscopic repair was associated with a shorter hospital stay (MD=-6.80, 95% CI [-9.39, -4.21], p< 0.0001) but a longer operation time (MD=23.30, 95% CI [7.22, 39.38], p=0.005) compared to the open approach. Additionally, thoracoscopic repair demonstrated lower mortality rates (RR=0.43, 95% CI [0.24, 0.76], p=0.004) but higher recurrence rates (RR=2.24, 95% CI [1.56, 3.21], p<0.0001) than open repair. Our findings suggest that thoracoscopic repair offers shorter hospital stays and lower mortality rates but involves longer operation times and higher recurrence rates compared to the open approach. These results highlight the need for further large, multicenter, randomized controlled trials to validate our findings and guide clinical decision-making.
congenital diaphragmatic herniathoracoscopic repairopen surgical repairminimally invasive surgery
Frontiers in Veterinary Science · مجلد 12 · 1558954-1558954
Introduction Our investigations utilized computed tomography (CT), magnetic resonance imaging (MRI), and ultrasonography (US) to provide detailed anatomical information on the pes region of a one-humped camel, with a particular focus on 3D reconstruction volume-rendered CT (3DVR-CT). Methods This research utilized 16 pes regions from adult male Camelus dromedaries aged 8–10 years. Results A CT scan revealed a vertical bony septum that completely divides the internal medullary cavity of the fused large metatarsal bones along the fusion line, except for the distal one-fifth portion, where the septum was absent. MRI identified the ligaments of the fetlock joint, which include the axial and abaxial collateral ligaments, collateral sesamoidean ligaments, and palmar ligaments. US demonstrated that the deep digital flexor tendon (DDFT) had higher echogenicity than the superficial digital flexor tendon (SDFT) at all imaging levels, with the SDFT paratendon appearing hyperechoic, which differentiated it from both the SDFT and the suspensory ligament. Our application of CT and MRI imaging techniques revealed that the Manica flexoria and distal sesamoid bone were not observed. On MRI, the sole appeared as a layer of low signal intensity, while the digital cushion exhibited heterogeneous high signal intensity. Discussion the evaluation of anatomical regions in Camelus dromedaries can now be performed using CT, MRI, and US with 3DVR-CT, greatly improving the diagnosis and treatment of various conditions and facilitating the interpretation of some clinical diseases in the pes region. These imaging modalities, particularly 3DVR-CT, serve as valuable tools for veterinary clinicians and researchers studying camel anatomy and pathology.
Camelus dromedariusfoot anatomymetatarsalsdeep digital flexor tendon
BACKGROUND: The World Health Organization defines health as complete physical, mental, and social well-being. Chronic diseases impact health-related quality of life (QoL). Health services for ill populations, including end-stage renal disease (ESRD), focus on QoL issues and mental health promotion. Kidney transplantation is the optimal form, but most patients require dialysis, which can be hemodialysis (HD) or peritoneal dialysis (PD). It is believed that choosing the proper modality will help in improving patient's QoL and satisfaction rate. To help patients select the mode of dialysis that best meets their needs while they have ESRD, this study intends to investigate differences in QoL between dialysis modalities. METHODOLOGY: It was a multicenter cross-sectional study conducted in Saudi Arabia, focusing on HD and PD patients in specific hospitals. Data was collected through a specially designed online questionnaire and analyzed with IBM SPSS 29 (IBM Corp. Released 2023. IBM SPSS Statistics for Windows, Version 29.0.2.0 Armonk, NY: IBM Corp). RESULTS: Our study, including 307 dialysis patients in Saudi Arabia, revealed a male predominance (56.0%), primarily aged 45-64 years (43.0%), with 91.5% Saudi nationals. Employment varied (27.4% professionals), and most earned 10,000-20,000 SAR monthly (50.5%). Positive life changes post-dialysis were reported by 98.7%, with 94.5% not requiring post-dialysis absence from work. Incenter HD patients constitute 45.3% while PD patients constitute 54.7% of the study sample. Physical well-being showed significant differences in nausea (p=0.035). Social and emotional well-being exhibited acceptance variations (p=0.012) and coping satisfaction (p=0.014). Linear regression indicated monthly income impact on HD QoL (B=-3.706, p=0.075), while age influenced PD QoL (B=0.113, p=0.927). CONCLUSION: Our study underscores positive life changes and minimal work absence is prevalent among dialysis patients. PD exhibits higher nausea and lower family acceptance. HD participants report greater coping satisfaction. The study reveals nuanced differences in well-being dimensions, contributing insights for tailored interventions and patient-centered care in renal replacement therapies.
health-related quality of lifeperitoneal dialysishemodialysisend-stage renal disease
Brain Research Bulletin · مجلد 233 · 111645-111645
Epilepsy is a critical neurological disorder that requires accurate and privacy-preserving diagnostic solutions to enable early detection and effective management. However, existing approaches face key challenges, including reliance on centralized data, poor generalizability across modalities, suboptimal feature extraction, and vulnerability to noise. To address these issues, we propose MultiEpilepsyNet, a novel multimodal seizure detection framework that integrates federated learning with hybrid deep learning models. At its core, the system introduces SeizureFed-Net, a federated architecture that enables collaborative learning from EEG and MRI data while safeguarding patient privacy. For detection, we design SeizureShieldNet, a hybrid model that fuses the temporal learning capabilities of BBIDNet (Boosted BiLSTM Intrusion Detector Network) with the adaptive decision-making of FD-TMS (Fuzzy-DQN Threat Mitigation System) under uncertainty. To further enhance model efficiency, a Jackal-Wolf Hybrid Optimizer (JWHO)-a novel combination of Golden Jackal Optimization and Grey Wolf Optimizer-is employed for optimal feature subset selection. On the imaging side, MRI preprocessing is improved through EpiSkullNet+ +, a modified 3D UNet+ + architecture tailored for precise brain segmentation. Extensive experiments on two benchmark datasets demonstrate the superiority of our approach, achieving 99.36 % accuracy on the CHB-MIT EEG dataset and 99.38 % accuracy on an epilepsy MRI dataset. Beyond accuracy, MultiEpilepsyNet demonstrates improved robustness to missing modalities, reduced training overhead via federated aggregation, and enhanced privacy preservation compared to centralized deep learning models, thereby addressing critical barriers in practical clinical deployment. These outcomes highlight the effectiveness, scalability, and real-world clinical potential of the proposed framework for epilepsy diagnosis and management.
Current Medical Imaging Formerly Current Medical Imaging Reviews · مجلد 21 · e15734056391923-e15734056391923
INTRODUCTION: Accurate interpretation of medical images is vital for diagnosis and treatment planning. However, noise in medical imaging significantly hampers this process, leading to potential diagnostic errors. Traditional denoising techniques often require large datasets or compromise diagnostic details. METHOD: This study proposes a Distribution-based Compressed Denoising Scheme (DCDS) leveraging transfer learning to enhance diagnostic precision. The framework analyzes pixel distributions to distinguish normal and noisy pixels using incremental and decremental distribution verification. A chest CT scan dataset with Gaussian-like noise was used to train the model, employing correlation mapping between training and target images for effective variance estimation. RESULT: Experimental analysis showed that DCDS significantly improves noise reduction, variance detection, and diagnostic precision. The peak signal-tonoise ratio improved across all evaluated ranges (24-32 dB), with a noise reduction rate exceeding 82% in optimal conditions. DCDS reduced mean error and analysis time, enhancing overall system efficiency. Transfer learning allowed for effective pixel classification and noise prediction with fewer data and computational resources. DISCUSSION: Compared to existing denoising methods, DCDS offers better generalization through statistical modeling and knowledge-sharing between training and learning states. However, current validation is limited to CT imaging with Gaussian noise. Broader modality testing and integration of perceptual and clinical grading metrics are needed. CONCLUSION: The DCDS framework presents a promising, lightweight, adaptive, and accurate solution for medical image denoising. It holds potential for realtime diagnostic support, but further optimization and clinical validation are necessary to ensure generalizability across diverse imaging modalities and noise types.
medical image denoisingtransfer learningchest CTGaussian noise
A particular type of dermatosis known as prurigo of pregnancy (PP) is typified by highly itchy papulonodules that primarily affect the extremities' extensor surfaces and the hand and feet dorsum. Despite PP not being a rare illness, there is surprisingly a distinct lack of studies exploring its depth. Therefore, this study seeks to thoroughly describe the clinical manifestation and treatment of pregnancy-related prurigo. Additionally, it aims to provide a comprehensive and up-to-date assessment of the effectiveness of different approaches to pregnancy prurigo therapy. This systematic review was conducted according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. The systematic review searched PubMed, EMBASE, Web of Science, and Cochrane databases from the databases' establishment to 13 August 2024. The studies were deemed included if they were randomized controlled trials (RCTs), cohort studies, case-control, cross-sectional, case series, and case reports; if they reported clinical manifestations and treatment for PP; and if they were written in the English language. Studies were excluded if they did not meet the aforementioned inclusion criteria; moreover, they were excluded if they were of high risk of bias or low quality. The articles included were assessed using the Newcastle-Ottawa scale and methodological quality, and the synthesis of non-randomized studies. Four different studies, with a total of 63 patients, were included in our article. The typical rash of PP is described in most patients with variable onset and distribution on the body, from the extremities to the back to the buttocks. PP can be associated with a variety of conditions, including a history of other skin conditions, such as intrahepatic cholestasis and other medical conditions. Different treatments for PP in pregnant women were reported across the included studies, most commonly a combination of topical steroids, emollients, oral antihistamines, oral corticosteroids, and ultraviolet narrow band (UVB). The effectiveness of the various therapies is variable; some patients recover before delivery, while others recover months postpartum. This systematic review emphasizes how complicated PP is in terms of both its clinical manifestations, associations, and management. The evidence points to the urgent need for a more uniform approach to diagnosis and management due to substantial variability in the clinical features, onset, and treatment responses. The study emphasizes the need for additional, larger-scale research using standardized outcome measures to identify characteristics that predict treatment success and allow for more robust comparisons of treatment modalities.
prurigo of pregnancyprurigo nodularisprurituspregnancy
Journal of Advanced Trends in Medical Research · مجلد 2 (4) · 671-681
Hair loss, or alopecia, encompasses a diverse range of conditions including both cicatricial (scarring) and non-cicatricial (non-scarring) forms, with significant implications for patients’ physical appearance, psychological well-being and overall quality of life. The limitations of traditional therapies such as topical agents, oral medications and hair transplantation have led to increasing interest in regenerative approaches. Amongst these, platelet-rich plasma (PRP) and exosome-based therapies have emerged as promising biologic interventions. PRP, derived from autologous blood, contains a high concentration of platelets rich in growth factors that support hair follicle regeneration, angiogenesis and cellular proliferation. Evidence suggests its potential benefits in various types of hair loss particularly androgenetic alopecia, alopecia areata and telogen effluvium, although standardised protocols, optimal dosing and long-term outcomes remain uncertain. Exosomes are small extracellular vesicles secreted by stem cells that offer a novel cell-free alternative capable of delivering complex molecular signals to modulate inflammation, stimulate follicular stem cells, and promote dermal remodeling. Early findings indicate possible applications across a range of alopecias including chemotherapy-induced hair loss, autoimmune related alopecia and structural hair shaft disorders such as trichorrhexis nodosa and monilethrix. This narrative review provides an updated overview of PRP and exosome-based therapies, outlining their mechanisms of action, clinical applications and current limitations. While both modalities show therapeutic promise, their biologic variability, lack of regulatory standardisation and need for comparative trials highlight critical gaps in evidence. Further research is warranted to establish reproducible treatment protocols and determine long-term efficacy and safety for clinical use.
International Journal of Imaging Systems and Technology · مجلد 35 (5)
ABSTRACT Recent advancements in Deep Learning (DL) have enabled the development of Computer‐Aided Diagnosis (CAD) systems for detecting Acute Lymphoblastic Leukemia (ALL) and its subtypes. However, this field faces challenges, particularly due to limited annotated datasets and a lack of efficient modalities. To address these issues, we propose MHAOSL‐net, a novel hybrid DL model specifically designed for the accurate classification of B‐ALL, T‐ALL, and normal cells in blood smear images. The key contributions lie in the integration of four primary components: (1) lightweight MobileNetV2 for backbone feature extraction, (2) a Global Context Information Convolutional Block Attention Module (GCI‐CBAM) for refined local representation using contextual information, (3) an Attention‐Free Transformer (AFT) that captures global dependencies replacing traditional self‐attention, and (4) an Orthogonal SoftMax Layer (OSL) that improves class separability by enforcing orthogonality in the decision space. This unified architecture not only reduces computational overhead but also improves classification performance and generalizability. To the best of our knowledge, this is the first framework that combines an AFT with an OSL in the context of leukemia subtype detection. The performance analysis of the proposed 3‐class classification scheme has been assessed on two novel datasets, namely BBCI_B&T_ALL_2024 and heterogeneous datasets. The experimental results show that the proposed scheme provides better performance, with 99.52% accuracy, 99.36% average precision, and 99.36% average F1‐score on the BBCI_B&T_ALL_2024. Similarly, it achieves better performance with 99.55% accuracy, 99.40% average precision, and 99.40% average F1‐score on the heterogeneous dataset. The qualitative investigation using Gradient‐weighted Class Activation Mapping (Grad‐CAM) visualization also confirms the efficacy of the proposed model for detecting B‐ALL, T‐ALL, and normal cells. The comparative studies establish the superiority of the proposed scheme over other state‐of‐the‐art approaches. These findings indicate that MHAOSL‐Net offers a promising and efficient solution for reliable ALL subtype detection in clinical settings.
Advanced Health Science and Technology Journal · مجلد 1 (2) · 92-99
Abstract Background: Epilepsy remains one of the most prevalent neurological disorders worldwide, characterized by recurrent seizures resulting from abnormal electrical brain activity. Traditional diagnostic methods, such as electroencephalography (EEG) and magnetic resonance imaging (MRI), although widely used, often fail to provide sufficient accuracy when applied in isolation due to their inherent limitations in temporal or spatial resolution. These challenges highlight the need for integrated analytical approaches capable of leveraging complementary modalities for improved diagnostic precision. Objectives: This study aims to address the limitations of single-modality diagnostic techniques by proposing a multimodal deep learning framework that integrates EEG and MRI data to enhance the accuracy of epilepsy detection. The objectives include preprocessing EEG signals to remove artifacts, segmenting MRI scans for structural feature extraction, employing CNNs to model EEG spatio-temporal dependencies, using ViTs to capture hierarchical MRI features, and integrating these representations through a cross-attention fusion mechanism for effective supervised classification. Method: The methodology involves preprocessing EEG signals to eliminate artifacts and ensure clean temporal representation, along with MRI scan segmentation to extract structural information. Convolutional neural networks (CNNs) were used to model spatio-temporal patterns within EEG signals, while vision transformers (ViTs) extracted spatially hierarchical features from MRI data. A cross-attention fusion mechanism was designed to integrate these complementary modalities, and a supervised classifier performed the final prediction. Model training and evaluation were carried out using a high-performance computing setup with GPU acceleration to efficiently handle multimodal data. Results: Experimental results demonstrated that the proposed multimodal deep learning model significantly outperformed state-of-the-art pretrained CNN and ViT baselines across major evaluation metrics, including accuracy, precision, recall, F1-score, and Matthews correlation coefficient. The confusion matrix further confirmed robust differentiation between normal and epileptic classes, emphasizing the reliability of the proposed framework for accurate clinical decision-making. Conclusion: The findings of this study indicate that integrating EEG and MRI data through a multimodal fusion framework provides a substantial improvement in epilepsy detection compared to single-modality approaches. The results highlight the importance of combining complementary temporal and structural information to achieve reliable diagnostic performance. This work contributes to advancing early detection, reducing diagnostic errors, and supporting timely treatment strategies, reinforcing the value of multimodal deep learning approaches in personalized healthcare.
Fox-Fordyce disease (FFD) is a rare, chronic skin disorder affecting apocrine sweat glands, predominantly in women. It manifests as pruritic, dome-shaped papules in areas such as the axillae and pubic region. Treatment remains challenging, with limited success from conventional therapies. We report two cases of Saudi women aged 27 and 28 years presenting with hyperpigmented axillary papules and mild pruritus, consistent with FFD. One patient had no comorbidities, while the other had a known history of sickle cell anemia. Both cases were managed with laser therapy (erbium:yttrium aluminum garnet (YAG) in case 1 and ablative CO₂ in case 2) using precise protocols and follow-up plans. Clinical images demonstrated visual improvement post treatment. Adjunctive topical therapy was administered to manage inflammation and prevent hyperpigmentation. The cases underscore the typical presentation of FFD and the potential efficacy of laser-based interventions, even in patients with complex medical histories. Notably, the presence of sickle cell anemia did not exacerbate FFD manifestations, supporting the current treatment modalities. While hormonal therapy was not employed, its relevance remains a subject for future exploration. Laser therapy offers a promising approach for managing refractory FFD. Further studies are warranted to evaluate long-term outcomes and explore hormone-modulating strategies tailored to FFD's pathophysiology.
Saudi Medical Horizons Journal · مجلد 5 (1) · 42-49
The main objective of this study was to evaluate and summarize the available clinical evidence on the efficacy and safety of tofacitinib for the treatment of vitiligo. A thorough search across four databases identified 416 relevant publications. After removing duplicates using Rayyan QCRI and assessing their relevance, 204 full-text articles were reviewed, and ultimately, five studies met the criteria for inclusion were included. A total of 121 vitiligo patients were included; less than half of them 52 (43%) were males. Findings indicate that while tofacitinib alone has limited effectiveness, its combination with narrowband-ultraviolet B (NBUVB) phototherapy significantly enhances repigmentation, particularly in refractory cases, including acral lesions. Micro-focused UVB phototherapy also demonstrates high efficacy, with further improvements observed when paired with tofacitinib. However, a 16-week treatment duration may be insufficient for patients with inadequate responses to prior therapies, suggesting the need for higher doses or extended treatment periods. This makes a combination of tofacitinib and phototherapy promising as a therapeutic strategy against vitiligo, with cases resistant to all the modalities of standard therapy. As promising as these results read with significant repigmentation, full optimization of treatment duration and dosage will be imperative. These findings need to be further confirmed in future large, randomized controlled trials and long-term outcomes evaluated to definitely establish a standardized protocol for vitiligo management. These efforts will be essential to fully realize the potential of Janus kinase (JAK) inhibitors as part of a comprehensive, targeted approach to the management of vitiligo.