
Early detection of chronic diseases is essential for reducing long-term health complications and improving patient survival outcomes. Traditional diagnostic systems rely heavily on single-modality data, such as medical imaging or clinical records, which often fail to capture the multidimensional nature of chronic disease progression. This research presents a multimodal deep learning framework that integrates medical images with Electronic Health Records (EHR) to enhance early disease prediction. The proposed system utilizes a Convolutional Neural Network (CNN) for extracting structural and morphological patterns from imaging modalities such as MRI, CT, X-ray, and retinal fundus images. In parallel, an LSTM/Transformer-based encoder processes EHR variables, including laboratory values, comorbidities, vitals, and demographic information. The latent representations from both modalities are fused using an intermediate multimodal fusion strategy to generate a unified patient-level diagnostic prediction. Experimental results show that the proposed multimodal model significantly outperforms image-only and EHR-only models, achieving an overall accuracy of 92.8%, an F1-score of 91.0%, and an AUC of 0.96. Per-class analysis demonstrates substantial improvement in detecting early-stage conditions such as diabetic retinopathy, chronic kidney disease, cardiovascular diseases, and COPD. The inclusion of Grad-CAM and SHAP-based interpretability analyses further enhances the clinical reliability of the model. Overall, the findings confirm that integrating imaging and EHR data through multimodal deep learning provides a more comprehensive and accurate approach for early chronic disease detection and has strong potential for real clinical implementation.
Transdermal drug delivery systems have gained increasing attention as an effective strategy for sustaining drug release and enhancing therapeutic performance, particularly in the management of fungal infections that demand prolonged treatment. The present study focuses on the formulation and evaluation of antifungal transdermal patches containing luliconazole and posaconazole, two potent azole-class antifungal agents. The primary objective was to assess the skin permeation behavior, release kinetics, and antifungal efficacy of the optimized formulations. In vitro skin permeation studies were conducted using Franz diffusion cells, and the cumulative drug release profiles indicated a controlled and sustained release pattern over an extended period. Data obtained from permeation was fitted to various kinetic models—zero-order, first-order, Higuchi, and Korsmeyer-Peppas—to determine the underlying drug release mechanism. The optimized formulations predominantly followed Higuchi kinetics, suggesting diffusion-controlled release, supported by non-Fickian transport behavior in Peppas analysis. Antifungal activity of the drug-loaded patches was assessed through Minimum Inhibitory Concentration (MIC) and zone of inhibition studies against pathogenic fungal strains, including Candida albicans, Trichophyton rubrum and Aspergillus niger. The patches exhibited significant inhibitory activity, with the luliconazole–posaconazole combination demonstrating enhanced antifungal efficacy compared to single-drug formulations. The improved permeation and potent antifungal action indicate effective drug delivery to deeper skin layers where fungal pathogens commonly persist.
Background: Recurrent venous hypertension due to central venous stenosis or occlusion is a common complication in hemodialysis patients, often resulting from previous central venous catheterization. Endovascular treatments like balloon angioplasty and stenting offer initial relief but suffer from high recurrence rates, while surgical interventions provide alternative solutions when endovascular therapy fails. Objective: to compare short-term outcomes between venoplasty with stenting and surgical management in recurrent venous hypertension secondary to central venous occlusion among hemodialysis patients. Patients and Methods: This prospective randomized trial was conducted on 40 patients with recurrent venous hypertension, assigned to receive either endovascular stenting or surgical bypass. Clinical and imaging assessments were performed, with patency and symptom resolution evaluated at 1, 3 and 6 months. Results: Postoperative arm circumference showed a significantly greater reduction in the surgical group (P=0.003), with both groups having significant within-group decreases (P<0.001) and no baseline differences (P=0.390). Similarly, forearm circumference reduction was significantly greater in the surgical group (P<0.001), with significant decreases in both groups post-intervention (P<0.001) and comparable preoperative measurements (P=0.201). Intraoperative venography findings differed significantly between groups (P=0.004), indicating more severe lesions in the surgical group, Procedure duration was significantly longer in the surgical group (P<0.001). Conclusion: Surgical venous drainage provided superior primary patency and more effective early resolution of limb swelling compared to venoplas ty with stenting, despite longer operative time. Both interventions are effective in maintaining dialysis access, however venoplasty is safer compared to surgical venous drainage which is associated with higher 30-days mortality rate.
Background: Colorectal cancer ranks as the third most prevalent cancer globally and the second leading cause of cancer-related deaths. Obstruction, a common complication in advanced cases, often necessitates emergency surgical intervention. Traditional multi-stage procedures such as Hartmann’s operation are widely used but carry significant morbidity and impact on quality of life. Objective: to assess the results of primary anastomosis after left colectomy for obstructing mass in emergency cases regarding early post operative complications like surgical site infection, ileus, incidence of leakage, restoration of bowel movement, hospital stay and rate of readmission within one month from the time of intervention. Patients and Methods: This one-arm clinical trial was conducted at Ain Shams University Hospitals over 12 months, involving 37 patients with obstructing left colon masses. All underwent left colectomy with primary hand-sewn anastomosis. Patients were carefully selected based on intraoperative findings (good vascularity, absence of sepsis or perforation). Data were collected on postoperative recovery, complications, and hospital stay. Results: Anastomotic leakage occurred in 3 patients (8.1%), surgical site infections in 7 patients (18.9%), ileus in 5 patients (13.5%), and readmissions in 3 patients (8.1%). Bowel movement was restored in 86.5% of patients within three days. Mean hospital stay was 7.2 ± 1.2 days. No perioperative mortality was recorded. Conclusion: Primary anastomosis after emergency left colectomy is a safe and viable option in selected patients. When performed by experienced surgeons and guided by strict intraoperative criteria, it offers favorable short-term outcomes and avoids the need for stoma formation.
The use of chimney technique in endovascular repair of abdominal aortic aneurysms (ChEVAR) has had a secondary role. Although it was first developed in an emergent/urgent setting, the publication of various important studies has helped overcome scepticism towards this technique in elective procedures. This paper reviews current evidence about ChEVAR, focusing on clinical results, technical notes and comparisons with other techniques. The new ChEVAR findings show favourable mid- and long-term clinical outcomes, even in elective patients. These results, comparable to those related to fenestrated endografts, have been achieved through standardisation in planning and materials. An adequate endograft oversizing associated to the right aortic neck length is fundamental to avoid ChEVAR-related complications, such as type 1a endoleaks. These data indicate that ChEVAR, compared to other complex endovascular treatments, has comparable outcomes along with features that could make it an essential option in every clinical setting.