Al Rasheed University College

Big data and its distributed approach to data management have evolved significantly in recent years, giving rise to a huge volume of data generated from new services, devices (e.g. IoT), and applications. Recently, federated learning (FL) has been proposed for training deep learning models on distributed data in order to address significant challenges previously described in the literature, e.g., those concerns considering privacy, security, computational overhead, and legal restrictions. Nevertheless, while FL adequately addresses the above-mentioned limitations, there are still lingering drawbacks regarding privacy, security, scalability, single point of failure, and conflicting security policies. Specifically, the handling of sensitive data complicates the sharing and utilisation of data without breaching confidentiality. In this work, we propose a novel learning approach, named the AI-To-Data (ATD) learning method, to deal with the previous drawbacks. In particular, ATD proposes a more robust decentralised approach in which AI models are transferred to the data for training rather than centrally aggregating the model’s parameters. Each ATD node operates as both a local and a global entity, i.e. training on local data while synthesising models from other nodes. This new approach preserves data locality while enabling collaborative model training, thus fostering a more secure and integrated learning environment. Additionally, Eye on ATD, a blockchain-based security mechanism, is proposed to be incorporated into ATD to address potential security and privacy vulnerabilities, e.g. malicious participants or tampered updates. Our approach based on the combination of ATD and Eye on ATD has been extensively evaluated using three distinct datasets across multiple nodes considering multi-scenarios of abnormal behaviour detection tasks, including violence. The empirical results demonstrated that our proposal outperforms the state-of-the-art by obtaining an average accuracy of 92.1%. It has been carried out an independent test in order to validate the generalisation of ATD, achieving an accuracy of 89.2%. In addition, the scalability of the ATD has been tested by adding a fourth node with different behaviours, including shoplifting. In the last scenario, ATD achieved an accuracy of 93.3% when considering the four nodes without any negative impact on the performance of the entire system. Finally, it is worth highlighting how ATD ensures compliance with various regulatory frameworks due to ATD facilitates seamless node scalability and supports customisable data governance policies. The code of the proposed framework, both ATD and Eye on ATD, is available at https://github.com/LaithAlzubaidi/ATD/tree/main.

Background: Risk-Assessment Models may not accurately predict Venous Thromboembolism (VTE). This study prospectively assessed the use and decision-making accuracy of the Caprini and Padua risk-assessment models for antithrombotic prophylaxis in predicting VTE. Methods: Prospective study was conducted on 1075 Baghdad Teaching Hospital patients from December 1, 2022, until January 1, 2024. All patients and the subgroup examined for RAM discrimination using baseline medical and demographic data. Assessing Caprini and Padua scores' sensitivity and specificity. We analyze each score using the ROC curve and AUC. Results: The study observed 37 VTE cases. Individuals with VTE events had a significantly higher mean age (±SD) of 60.62 (15.8), p = 0.001. VTE occurs in 54% of acutely infected and/or rheumatologic patients P 0.002. Survival time and event-free period mean was 83.099 days (95% CI: 81.877-84.322) for patients without thromboprophylaxis and 74.085 days for those utilizing it. The Caprini RAM predicted VTE with 0.652 AUC, lower than Padua's 0.724. The Caprini RAM had 54.1% sensitivity and 61.7% specificity, whereas the Padua prediction score had 97.3% and 36.0%. Conclusion: The Caprini scores and Padua Prediction Score may improve hospital patients' thromboembolic risk classification compared to current practice.

The article examines the role of sustainable development in advancing political development from a contemporary Islamic perspective, focusing on how the principles of human rights align with the functions of civil state institutions. The research explores how sustainable development initiatives, as outlined in the 2030 Agenda, resonate with Islamic values of justice, equity, and societal well-being. Employing a qualitative approach, this analysis draws on Islamic jurisprudential sources and international frameworks, such as the UN Sustainable Development Goals (SDGs) and the Universal Declaration of Human Rights, to highlight areas of alignment and divergence. Findings reveal that sustainable development can be a foundation for political development within a contemporary Islamic framework by supporting governance structures rooted in justice, accountability, and community welfare. Political development within an Islamic context refers to the evolution of governance structures that integrate justice ('Adl), equity (Qist), and accountability (Mas'uliyyah) as foundational principles. This aligns with the Islamic legal tradition, where governance is rooted in Sharia-based ethical and moral obligations. Governance models in Islamic societies incorporate participatory decision-making through institutions such as Shura (consultative councils) and Hisbah (public oversight mechanisms), ensuring justice and accountability in policy implementation. Moreover, the study identifies two primary viewpoints: one that views sustainable development as inherently conducive to political development and another that sees political frameworks, especially democratic participation, as essential for sustainable outcomes. This article underscores that contemporary Islamic principles can complement sustainable development efforts, reinforcing political stability, social justice, and institutional integrity within civil state structures.

Background: Increasing polypharmacy and complicated prescription regimens raise the likelihood of CYP-mediated drug-drug interactions (DDIs) in older people. Objective: To assess the incidence of CYP-mediated DDIs in older people with polypharmacy and examine the correlation between medication dispensation and the likelihood of these interactions in this high-risk group. Methods: A cross-sectional 17-week analysis was performed, including consecutive new patients aged 65 years and over who were undergoing polypharmacy (defined as the use of more than five medications) at a community pharmacy. The medication profiles of these individuals were evaluated using SuperCYPsPred software and UpToDate® Lexidrug. The frequency of possible CYP-mediated interactions was evaluated. The pharmacists' judgments to suggest prescription adjustments based on the likelihood of CYP-mediated interactions were documented. Results: The prevalence of possible CYP-mediated drug-drug interactions identified among 220 older persons with polypharmacy was 84.5%. Moderate severity DDIs were the predominant and significant kind of interaction (2.70±3.157). A linear regression analysis was performed to predict the frequency of drug interactions based on the number of drugs. A significant association has been identified (F(1,14)= 67.789, p<0.001). The predominant CYP isoenzyme was CYP3A4 at 34.6%, followed by CYP2C9 at 21.4% and CYP2D6 at 15.7%, with no notable gender differences. Conclusion: The older patients have at least one DDI. Elderly adults taking five or more medicines require frequent care owing to a fourfold greater chance of drug interactions.

Background: Treatment with melatonin as anti-oxidant's supplements may has a role in psoriasis with diminished anti-oxidant system function. This medical trial targets the efficiency of melatonin as an adjunctive management with etanercept in mitigating the severity of chronic plaque psoriasis. Material & Methods: A double-blind prospective randomized clinical trial study conducted over a three-month period from 1stJanuary 2022 to 30th March 2022 at Department of Dermatology at Merjan Teaching Hospital in Babylon City/Iraq to assess the efficiency of melatonin as adjuvant therapy with etanercept in the management of psoriasis. Sixty adult patients (18 female, 42 males; age range 17-60 years) with psoriasis were selected through convenience sampling & distributed randomly into (2) groups. The group (A, n=30) received etanercept and placebo, whilst Group (B, n=30) received etanercept plus melatonin, orally, once daily. Psoriasis Area and Severity Index scores as a severity measuring index and blood levels of malondialdehyde and superoxide dismutase were assessed at baseline and at the completion of the intervention. Results: A significantly improvement in the PASI score and oxidative indicators (MDA and SOD) were observed following both biological therapy and adjunctive melatonin treatment; For group A representing a 69.14% improvement. While for group D, PASI score, MDA and SOD representing an 81.87% improvement. Conclusion: The daily administration adjuvant therapy 5 mg melatonin supplementation with etanercept to patients with psoriasis for 3months had reduce the severity of disease in a short period time.