IEEE Open Journal of the Communications Society · مجلد 6 · 881-925
The advent of Fifth-Generation (5G) networks has introduced significant security challenges due to increased complexity and diverse use cases. Conventional threat models may fall short of addressing these emerging threats effectively. This paper presents a new security mitigation model using artificial neural network (ANN) with interpretive structure modeling (ISM) to improve the 5G network security system. The main goal of this study is to develop a 5G network security mitigation model (5GN-SMM) that leverages the predictive capabilities of ANN and the analysis of ISM to identify and mitigate security threats by providing practices in 5G networks. This model aims to improve the accuracy and effectiveness of security measures by integrating advanced computational practices with systematic modeling. Initially, a systematic evaluation of existing 5G network security threats was conducted to identify gaps and incorporate best practices into the proposed model. In the second phase, an empirical survey was conducted to identify and validate the systematic literature review (SLR) findings. In the third phase, we employed a hybrid approach integrating ANN for real-time threat detection and risk assessment and utilizing ISM to analyze the relationships between security threats and vulnerabilities, creating a structured framework for understanding their interdependencies. A case study was conducted in the last stage to test and evaluate 5GN-SMM. The given article illustrates that the proposed hybrid model of ANN-ISM shows a better understanding and management of the security threats than the conventional techniques. The component of the ANN then comes up with the potential of the security breach with improved accuracy, and the ISM framework helps in understanding the relationship and the priorities of the threats. We identified 15 security threats and 144 practices in 5G networks through SLR and empirical surveys. The identified security threats were then analyzed and categorized into 15 process areas and five levels of 5GN-SMM. The proposed model includes state-of-the-art machine learning with traditional information security paradigms to offer an integrated solution to the emerging complex security issues related to 5G. This approach enhances the capacity to detect threats and contributes to good policy enforcement and other risk-related activities to enhance safer 5G networks.
The incidence of suicide, self-harm, and mental crises among teenagers is rising, presenting significant global public health issues. Conventional clinical risk evaluations have inadequate predictive accuracy, often overlooking high-risk adolescents. Machine learning models employing electronic health records provide an innovative method for predicting mental health crises through the integration of intricate clinical data patterns. Hence, this review aims to comprehensively examine and synthesize information about machine learning models created using electronic health record data for predicting suicide attempts, self-harm, or mental hospitalization in teenagers. Adhering to Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA) principles, we executed an exhaustive search across six databases (2000-2025) for peer-reviewed research utilizing machine learning algorithms on electronic health record data to predict adolescent mental health crises. The inclusion criteria emphasized structured or unstructured electronic health record inputs, teenage cohorts (ages 10-20), and performance indicators like area under the curve (AUC), sensitivity, or specificity. The Prediction Model Risk of Bias Assessment Tool (PROBAST) was utilized to evaluate the risk of bias. Our search yielded five studies (2019-2024) that satisfied the inclusion criteria. All studies were retrospective cohorts conducted in high-income nations. Structured electronic health record data (e.g., diagnoses, prescriptions) were frequently utilized; two studies included natural language processing. Machine learning models demonstrated moderate to high discrimination (AUC 0.68-0.88), exhibiting optimal performance in short-term suicide prediction with hybrid data inputs. All investigations, however, exhibited a significant risk of bias in the analysis domain owing to insufficient external validation and absent calibration data. The positive predictive values consistently remained modest across all models. Overall, machine learning models demonstrate potential for enhancing adolescent suicide risk classification utilizing electronic health record data, surpassing numerous traditional instruments. Nonetheless, issues of generalizability, ethical constraints, and implementation obstacles remain. Thorough validation, calibration, and equity assessments are necessary prior to incorporation into clinical practice.
adolescent mental healthsuicide risk predictionself-harmelectronic health records
Sepsis is a life-threatening condition, and early recognition in the emergency department (ED) is crucial for reducing mortality. However, traditional ED sepsis screening tools (e.g., Systemic Inflammatory Response Syndrome (SIRS) and quick Sequential Organ Failure Assessment (qSOFA)) often lack sensitivity for early detection. Machine learning (ML)-based early warning systems have been proposed to address this gap by analyzing complex clinical data in real time. To address this, we systematically reviewed studies (2015-2025) assessing ML-based sepsis warning systems in adult EDs. Databases searched included PubMed, Embase, Scopus, and Web of Science. Included studies reported diagnostic performance and/or clinical outcomes. Overall, a total of 11 studies (primarily retrospective, with a few prospective) were included. ML models using vital signs, laboratory results, and electronic health record (EHR) data demonstrated high discrimination for sepsis, with area under the receiver operating characteristic curve (AUROC) values often exceeding 0.80, and outperformed traditional scoring tools. Many provided earlier warnings, often two to four hours before sepsis was clinically recognized. Implementation studies showed that ML-based alerts expedited treatment; one multi-center system reduced time to antibiotics by ~1.8 hours when alerts were promptly addressed. Some reports noted reduced organ failure and mortality. However, evidence of improved patient outcomes remains inconsistent, likely due to study heterogeneity and limited prospective validation. ML-based early warning systems show strong potential for improving sepsis recognition and treatment in EDs. Further multi-center trials are needed to confirm their impact on outcomes and guide safe implementation.
sepsisearly warning systemsmachine learningemergency department
Journal of Advanced Trends in Medical Research · مجلد 2 (3) · 596-601
Background: Non-alcoholic fatty liver disease (NAFLD) is one of the causes of chronic liver diseases. Inconsistency in the microbiome population of individual guts and host–microbial interactions leads to low response in dietary and pharmacological-based treatments. This study aimed to develop and evaluate a metagenomic-guided, culturally adapted dietary and probiotic intervention to reduce hepatic fat and improve metabolic outcomes in obese Saudi adults with NAFLD. Materials and Methods: We combined gut metagenomic analysis, machine learning-based diet modelling and tailored probiotic supplementation to create an intervention platform. Probiotic specificity depends on functional deficits in bacteria participating in specific metabolic pathways, particularly bile acid metabolism. This technique supplements medication with microbiome-based drug processing. Results: At week 24, magnetic resonance imaging–proton density fat fraction (MRI-PDFF) decreased by −3.4 ± 2.2% (control), −8.9 ± 3.1% (diet) and −12.3 ± 3.8% (diet + probiotics); liver fat reduction was significant (analysis of variance (ANOVA) P = 0.0004). In the combined intervention, Faecalibacterium prausnitzii increased 2.3-fold (P = 0.003), faecal butyrate rose from 28.7 ± 4.1 to 45.2 ± 5.6 μmol/g (P = 0.002), faecal deoxycholic acid (fDCA) fell 34% (P = 0.010) with a rise in ursodeoxycholic acid (UDCA) (P = 0.015) and high-sensitivity C-reactive protein declined 42% (6.4 ± 1.7 to 3.7 ± 1.3 mg/L) versus 18% in controls (between-group P = 0.0008). Conclusion: Our precision-guided approach is a novel, scalable solution to managing NAFLD, leveraging the alignment of interactions between hosts, the microbiome and diet within a cultural context. The framework has the potential to optimise therapeutic response in high-risk Saudi communities, and the individual modulation of microbiomes on metabolic diseases is highlighted.
Plastic and reconstructive surgery increasingly depends on data-driven instruments to improve clinical decision-making. Machine learning (ML), through its capacity to analyze intricate, high-dimensional data, presents novel prospects for forecasting surgical outcomes with enhanced accuracy compared to traditional statistical models. This systematic study evaluates the extent, efficacy, and methodological rigor of ML applications in plastic and reconstructive surgery, encompassing burn treatment, microsurgical reconstruction, and breast surgery. Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) 2020 standards, we searched four main databases for research published between January 2015 and March 2025. Eligible papers used ML models to predict clinical outcomes in plastic or reconstructive surgery and provided quantifiable performance indicators. Data were retrieved using the Checklist for Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modelling Studies (CHARMS) and Prediction Model Risk of Bias Assessment Tool (PROBAST) frameworks, then synthesized narratively. We included eleven studies that had more than 34,000 patients. Random forests, neural networks, and gradient boosting have emerged as the most prevalent and highest-performing models, with several attaining AUCs exceeding 0.90. Notwithstanding encouraging outcomes, the majority of research depended on internal validation, with only one performing external validation. Calibration reporting and data transparency were constrained. The majority of studies exhibited a high or moderate risk of bias. In summary, ML models provide significant prediction accuracy in plastic surgery; yet, they are limited by methodological deficiencies that impede clinical implementation. Future initiatives must prioritize external validation, repeatability, and ethical execution to facilitate the safe and successful incorporation into surgical practice.
Down syndrome (DS) is a genetic condition characterized by distinct facial features and developmental challenges, making early and accurate detection crucial for timely intervention and support. Traditional diagnostic methods often require specialized expertise, which can be resource intensive and inaccessible in many settings. In this study, we propose a novel artificial intelligence (AI)-driven approach to detecting DS using facial images, leveraging advancements in deep learning and machine learning for accurate and scalable diagnostics. A dataset of 168 facial images was curated from publicly accessible platforms, comprising 95 images of individuals without DS and 73 with the condition. The model was implemented using TensorFlow/PyTorch and employs RegNet X and Shifted Window Transformer (SWIN Transformer) for feature extraction, capturing both local and global facial features. To enhance feature representation, an attention-based fusion mechanism was applied, prioritizing the most discriminative patterns while filtering redundant information. For classification, an Extremely Randomized Tree (ExtraTrees) model was employed, known for its ability to efficiently handle high-dimensional data with strong generalization capabilities. The model was fine-tuned using Bayesian Optimization and Hyperband (BOHB), which optimized hyperparameters by balancing exploration and exploitation, thereby improving predictive performance. The final classification achieved a 99.2% accuracy with an area under the curve (AUC) of 1.00, demonstrating exceptional reliability in distinguishing DS from normal cases. By combining advanced feature extraction, fusion, and classification techniques, this study highlights the potential of AI to revolutionize DS diagnostics, offering a non-invasive, efficient, and scalable solution for early detection.
Down syndromeface classificationearly diagnosismodel interpretability
Journal of Advanced Trends in Medical Research · مجلد 2 (3) · 523-528
Background: Diabetic neuropathy is a common and disabling complication of type 2 diabetes (T2D), often linked to Vitamin B12 deficiency. Despite observed B12 malabsorption in T2D patients, the role of gut microbiota in this process is poorly understood. Methods: We established a novel fecal microbiota transplantation (FMT) model using samples from T2D patients stratified by B12 status and neuropathy severity, transplanted into germ-free mice. We assessed ileal expression of B12 transporters, serum B12 levels and cobalamin-related metabolites. Neuropathy progression was evaluated through nerve conduction studies and histopathological analysis. Microbial composition was analysed through 16S rRNA sequencing, and metabolomic data were obtained using ion mobility-enhanced liquid chromatography-mass spectrometry. Machine learning algorithms integrated microbial and host data to identify predictive patterns and therapeutic targets. Results: FMT from T2D donors with B12 deficiency led to decreased expression of B12 absorption markers and reduced serum B12 levels in recipient mice. These mice showed early signs of neuropathy, confirmed by slowed nerve conduction and structural nerve damage. Specific microbial taxa were significantly associated with altered B12 metabolism and indicators of neuropathy. Multiomics and machine learning analyses revealed key microbial signatures and metabolic pathways involved in B12 dysregulation. Conclusion: Gut microbiota plays a mechanistic role in Vitamin B12 malabsorption and the progression of diabetic neuropathy. This model provides a platform for microbiota-informed diagnostics and targeted interventions in T2D complications.
Autism spectrum disorder (ASD) is a diverse neurodevelopmental condition with a significant genetic basis. Machine learning (ML) and deep learning (DL) models are emerging as powerful tools for identifying potential ASD risk genes and biomarkers to improve diagnostic accuracy. This narrative systematic review synthesizes evidence on the use of ML and DL models for ASD prediction and diagnosis, focusing on studies that utilized genetic variants and biomarkers. We conducted a systematic search across six databases [Web of Science, PubMed, Science Direct, Semantic Scholar, Institute of Electrical and Electronics Engineers (IEEE Xplore), and Association for Computing Machinery Digital Library (ACM-DL)] for articles published between 2009 and 2024, yielding 483 initial records. Multiple inclusion criteria were applied, and only peer-reviewed articles that used artificial intelligence, ML, or DL to predict ASD based on genetic biomarkers were included. After deduplication and applying inclusion and exclusion criteria, 14 studies were included in this review. These studies focused on genetic variants based on whole-genome sequencing, whole-exome sequencing, RNA sequencing, single-nucleus RNA sequencing, mRNA expression, long non-coding RNA, or single nucleotide polymorphism data. Our findings indicate that various ML models achieved robust performance, while DL architectures such as DeepASDPred outperformed ML models, with an accuracy of 93.8%. Most of the studies used datasets such as the Simons Foundation Autism Research Initiative (SFARI), the Simons Simplex Collection (SSC), the Autism Genetic Resource Exchange (AGRE), Atlas of the Developing Human Brain (BrainSpan), and the Simons Foundation Powering Autism Research for Knowledge (SPARK). The reviewed studies demonstrate that ML can help identify genetic risk factors and biomarkers that contribute to ASD. However, challenges remain, including data heterogeneity, small sample sizes, and the need for greater model interpretability. Addressing these challenges is crucial for translating ML models into clinically useful tools. In conclusion, DL substantially enhances ASD prediction, leveraging genetic data to identify novel candidate genes and support biological discovery of cell type-specific gene expression and roles of non-coding mutations in ASD.
Hematological biomarkers have emerged as powerful tools in diagnosing Acute Heart Failure (AHF). This study introduces a novel diagnostic framework that integrates Explainable Artificial Intelligence (XAI) with Morris Sensitivity Analysis (MSA) to enhance both the interpretability and performance of machine learning models in AHF detection. A dataset consisting of 425 AHF patients and 430 controls was analyzed using eight machine learning models, including XGBoost, Histogram-based Gradient Boosting (histGB), Explainable Boosting Machine (EBM), and Random Forest. Model performance was evaluated through metrics such as AUC, accuracy, precision, recall, and Brier score. Hyperparameters were optimized via Bayesian optimization. Feature importance was assessed using MSA to identify variables with the highest predictive influence. The histGB model achieved the highest performance with an AUC of 87.93%. Both MSA and EBM consistently identified PDW, RDW-CV, NEU, NEU/LY ratio, age, and WBC as top predictive features across multiple models. These hematological markers demonstrated strong potential for early diagnosis and risk stratification in AHF patients. This study presents a clinically relevant, interpretable, and cost-effective diagnostic strategy that combines XAI with MSA for AHF prediction. The framework enhances clinical trust and provides a pathway toward personalized treatment by identifying accessible hematological biomarkers. The integration of explainability into AI models improves their transparency and applicability in real-world clinical settings.
KSII Transactions on Internet and Information Systems · مجلد 19 (10)
Human-Computer Interaction for autonomous communication systems is traditionally developed through the stages of the usability engineering paradigm.However, a major challenge within this paradigm is synchronizing evolving user needs with the dynamic interaction environment.To address this gap, this article proposes the Relativity Turner Training Algorithm (RTTA).The algorithm estimates the relativity measure between the user's interaction context and the actual requirements, allowing the system to adapt more effectively over time.Unlike rule-based techniques, the RTTA leverages machine learning to identify contextual adjustment trends and optimize requirement matching, drawing on past interaction data.The relativity factor is derived from users' previous interaction responses.When relativity is low, the algorithm anticipates potential context changes.The "Turner" component then evaluates whether these changes can yield higher relativity-that is, a closer alignment between the new context and the user's requirements.If such alignment is achieved, interaction quality improves, and the need for further adjustments decreases.In this way, the algorithm dynamically balances relativity (measuring context-requirement alignment) and Asma Aledrees et al.: Enhancing Human-Computer Interaction Context Awareness through the Relativity Turner Training Algorithm Turner (guiding beneficial context shifts) across both short-and long-term interaction intervals.To advance research in adaptive HCI systems, the proposed RTTA framework provides a robust foundation by enabling the seamless integration of advanced machine learning techniques with multimodal interaction methods.
Journal of Advanced Trends in Medical Research · مجلد 2 (3) · 620-628
Background: Precision oncology in advanced urologic malignancies frequently uses genomic markers, which are insufficient to fully represent tumour metabolic heterogeneity. This study investigated if integrative lipidomics – metabolomics profiling by surface-assisted laser desorption/ionisation mass spectrometry (SALDI-MS) and a supervised machine-learning pipeline could be leveraged to enable informed decision-making for targeted therapy selection. Methods: SALDI-MS was completed on resected or biopsy tumour material with concomitant Liquid Chromatography-mass spectrometry (MS)/MS-based annotations of lipids/metabolites. Features were harmonised and modelled with a hybrid graph neural network – Transformer classifier, using nested cross-validation as well as Delong tests for area under the curve comparison. A blinded retrospective cohort with matched clinical treatment decisions was used for evaluations. Results: Compared with matrix-assisted laser desorption/ionisation MS, nanostructured Si@Au SALDI-MS substrates enhanced the number of detected lipid/metabolite features by 47% from tissue sections. The integrative model found 37 high-parameter lipid – metabolite features, and enhanced discrimination compared with single dimensional models by 11%–18% ( P < 0.001). In a blinded cohort of 87 patients, the therapy-selection model performed with 79% accuracy compared with 48% for programmed death-ligand 1 immunohistochemistry alone; the mean area under the receiver operating characteristic in the ablation analyses was 0.91 ± 0.03. Conclusions: Integrative SALDI-MS lipidomics – metabolomics, together with machine learning, demonstrated promise to inform targeted therapy decisions in advanced urologic cancers, and deserves prospective validation.
Human Behavior and Emerging Technologies · مجلد 2025 (1)
ASD (autism spectrum disorder) is a neurodevelopmental disorder affecting people’s social interaction, learning, and communication skills worldwide. It is a behaviorally distinct syndrome that is combined with several unknown and known disorders. The symptoms include sleep disorders, seizures, gastrointestinal tract symptoms, anxiety, wandering, hyperactivity/attention‐deficit disorder, and obesity. Hence, early detection of ASD is significant. However, clinically standardized screening tests are considered a prolonged diagnostic time, which is prone to errors and also leads to a rise in medical costs. Therefore, to decrease the time required for diagnosis and improve the precision of the model, AI (artificial intelligence) (machine learning (ML)) techniques are used to complement other traditional methods. Hence, this study has proposed a modified deep dynamic Levenberg–Marquardt (DDLM) optimized approach, which enhances the accuracy and classifier’s precision for implementing binary classification of children with ASD and children without ASD and tackles the issues in early detection. The process starts by preprocessing the data using label encoding and feature scaling techniques for eradicating irrelevant and noisy data, and then classification proceeds by utilizing the modified DDLM model. The dataset used in the proposed model is an amalgamation of datasets, which are ASD meta‐abundance and GSE113690_Autism_16S_rRNA. Additionally, a comparison of classifiers with three ML‐based algorithms, namely, MLP (multilayer perceptron), NB (naïve Bayes), and XGBoost (extreme gradient boost), is performed to analyze the effectiveness of the proposed system in the binary classification of ASD. The efficacy of the proposed system is evaluated using performance factors such as specificity, precision, F 1‐score, accuracy, and recall.
Abstract Land use and land cover (LULC) analysis is crucial for understanding societal development and assessing changes during the Anthropocene era. Conventional LULC mapping faces challenges in capturing changes under cloud cover and limited ground truth data. To enhance the accuracy and comprehensiveness of the descriptions of LULC changes, this investigation employed a combination of advanced techniques. Specifically, multitemporal 30 m resolution Landsat-8 satellite imagery was utilized, in addition to the cloud computing capabilities of the Google Earth Engine (GEE) platform. Additionally, the study incorporated the random forest (RF) algorithm. This study aimed to generate continuous LULC maps for 2014 and 2020 for the Shrirampur area of Maharashtra, India. A novel multiple composite RF approach based on LULC classification was utilized to generate the final LULC classification maps utilizing the RF-50 and RF-100 tree models. Both RF models utilized seven input bands (B1 to B7) as the dataset for LULC classification. By incorporating these bands, the models were able to influence the spectral information captured by each band to classify the LULC categories accurately. The inclusion of multiple bands enhanced the discrimination capabilities of the classifiers, increasing the comprehensiveness of the assessment of the LULC classes. The analysis indicated that RF-100 exhibited higher training and validation/testing accuracy for 2014 and 2020 (0.99 and 0.79/0.80, respectively). The study further revealed that agricultural land, built-up land, and water bodies have changed adequately and have undergone substantial variation among the LULC classes in the study area. Overall, this research provides novel insights into the application of machine learning (ML) models for LULC mapping and emphasizes the importance of selecting the optimal tree combination for enhancing the accuracy and reliability of LULC maps based on the GEE and different RF tree models. The present investigation further enabled the interpretation of pixel-level LULC interactions while improving image classification accuracy and suggested the best models for the classification of LULC maps through the identification of changes in LULC classes.
land use and land cover changerandom forestLandsat 8Google Earth Engine
To identify patterns in big medical datasets and use Deep Learning and Machine Learning (ML) to reliably diagnose Cardio Vascular Disease (CVD), researchers are currently delving deeply into these fields. Training on large datasets and producing highly accurate validation results is exceedingly difficult. Furthermore, early and precise diagnosis is necessary due to the increased global prevalence of cardiovascular disease (CVD). However, the increasing complexity of healthcare datasets makes it challenging to detect feature connections and produce precise predictions. To address these issues, the Intelligent Cardiovascular Disease Diagnosis based on Ant Colony Optimisation with Enhanced Deep Learning (ICVD-ACOEDL) model was developed. This model employs feature selection (FS) and hyperparameter optimization to diagnose CVD. Applying a min-max scaler, medical data is first consistently prepared. The key feature that sets ICVD-ACOEDL apart is the use of Ant Colony Optimisation (ACO) to select an optimal feature subset, which in turn helps to upgrade the performance of the ensuring deep learning enhanced neural network (DLENN) classifier. The model reforms the hyperparameters of DLENN for CVD classification using Bayesian optimization. Comprehensive evaluations on benchmark medical datasets show that ICVD-ACOEDL exceeds existing techniques, indicating that it could have a significant impact on CVD diagnosis. The model furnishes a workable way to increase CVD classification efficiency and accuracy in real-world medical situations by incorporating ACO for feature selection, min-max scaling for data pre-processing, and Bayesian optimization for hyperparameter tweaking.
This study highlights drought forecasting for understanding the semi-arid area in India, where drought phenomena play vital role in the irrigation, drinking water supplies, and sustaining the ecological with economic balance for every nation. Therefore, drought forecasting is important for the future drought planning based on the machine learning (ML) models. Hence, The Standardized Precipitation Index (SPI) at 3- and 6-month periods have been selected and used for future drought forecasting scenarios in area. The combinations of ten inputs SPI-1- and SPI-10 were used for predicting modeling for SPI-3 and SPI-6 timescales, that modeling developed based on the historical SPI datasets from 1989 to 2019 years. The SPI-3 and SPI-6 maximum and minimum values are shown SPI-3 (2.03 and -5.522) and SPI-6 (1.94 and -6.93). The SPI is a popular method for estimating the drought analysis and has been used everywhere at global level. The developed models have been compared with each other, with the best combination of input variables selected using subset regression models and sensitivity studies. After that, the active input parameters were used for forecasting of SPI-3 and SPI-6 values to understanding of drought in semi-arid area. The finest input variables combination have been used in the Ml models and established the novel five models such as robust linear regression, bagged trees, boosted trees, support vector regression (SVM-Linear), and Matern Gaussian Process Regression (Matern GPR) models. Such kind of models first time has been applied for the forecasting of future drought conditions. Whole models were fine and improved modeling by using hyperparameters tuning, bagging, and boosting models. Entire ML models’ accuracy was compared using different statistical metrics. Compared with five ML models accuracy, we have found that the Matern GPR model better accuracy than other ML models. The best model accuracy is R2 = 0.95 and 0.93, RMSE, MSE, MAE, MARE, and NSE values, respectively, for predicting SPI-3 and SPI-6 values in the area. Therefore, the Matern GPR model was identified as the finest ML algorithm for predicting SPI-3 and SPI-6 associated with other algorithms. This research demonstrates the Matern GPR model's efficacy in predicting multiscale SPI-3 and SPI-6 under climate variations. It can be helpful in soil and water resource conservation planning and management and understanding droughts in the entire basin areas of the country India.