The transformative potential of artificial intelligence (AI) and machine learning (ML) in healthcare has been increasingly recognized, particularly in medical image analysis and predictive modeling of patient outcomes. In this study, a novel convolutional neural network (CNN) architecture incorporating customized skip connections was introduced to enhance feature extraction and accelerate convergence during medical image classification. This model demonstrated superior performance compared with conventional architectures such as Residual Network with 50 layers (ResNet-50) and Visual Geometry Group with 16 layers (VGG16), achieving an accuracy of 96.5% along with improved precision, recall, and area under the receiver operating characteristic curve (AUC-ROC). In parallel, patient readmission risks were predicted using an optimized random forest algorithm, which, after hyperparameter tuning, attained a robust AUC-ROC value of 0.91, thereby underscoring its stability and predictive reliability. The integration of these approaches highlights the ability of AI and ML systems to deliver more accurate diagnoses, anticipate potential health risks, and recommend personalized treatment strategies, ultimately enabling faster and more precise clinical decision-making. Despite these advancements, challenges persist regarding data privacy, interpretability of AI-driven decisions, and the ethical use of patient information. Addressing these limitations will be critical for the broader adoption of AI-enabled healthcare systems. The findings of this study reinforce the role of advanced AI and ML frameworks in improving healthcare delivery, optimizing the use of limited resources, and reducing operational costs, thereby supporting more effective patient care.

Accurate evaluation of tibial mechanical properties is essential for the diagnosis of bone-related disorders, the monitoring of fracture healing, and the optimization of orthopedic rehabilitation outcomes. Conventional diagnostic approaches, including dual-energy X-ray absorptiometry (DXA) and other imaging-based methods, provide valuable information but are limited by radiation exposure, invasiveness, or insufficient sensitivity to early structural changes. To address these limitations, non-invasive vibration-based techniques have been developed as promising alternatives for quantitative, real-time, and radiation-free assessment of tibial biomechanics. Methods such as resonance frequency analysis (RFA), modal analysis, acoustic emission (AE), and laser doppler vibrometry (LDV) have been applied to estimate parameters including bone stiffness, bone mineral density (BMD), and healing dynamics. By introducing controlled vibrational input and recording the tibial response, structural integrity can be characterized, and early indicators of injury, degeneration, or impaired healing can be detected. Recent advances in high-resolution sensors, signal processing algorithms, and wearable technologies have enhanced the sensitivity and applicability of these techniques, while the integration of machine learning has enabled more robust interpretation of complex biomechanical signals. Despite these advances, significant challenges remain, including inter-patient variability, soft tissue damping effects, and the absence of standardized testing protocols. Furthermore, the clinical translation of vibration-based diagnostics requires validation against established imaging modalities and the development of predictive, individualized models of bone health that integrate artificial intelligence (AI) and multimodal data. Current evidence suggests that vibration analysis has the potential to offer a non-invasive and personalized approach to skeletal monitoring. Future research should focus on addressing methodological limitations, improving standardization, and advancing the integration of vibration assessment into routine orthopedic practice and precision medicine frameworks.

Diabetic foot ulcers (DFUs), often exacerbated by secondary bacterial infections, are a major complication of diabetes and a leading cause of morbidity. Understanding the spectrum of bacterial pathogens and their profiles of antibiotic resistance is essential for developing effective treatment strategies. This study aimed to identify bacterial isolates from the DFUs and evaluate their susceptibility to commonly used antibiotics. A total of 186 patients with the DFUs were examined at Hayatabad Medical Complex of Peshawar in Pakistan over a three-month period. Samples were collected from infected ulcer sites and cultured with standard microbiological techniques. Bacterial identification was performed with conventional methods, and antibiotic susceptibility testing was then conducted by using the Kirby-Bauer disk diffusion method. Gram-Negative bacteria were predominant, with Pseudomonas aeruginosa, Proteus mirabilis, Acinetobacter spp., Escherichia coli, Klebsiella spp., Enterobacter spp., and Streptococcus pyogenes being the most commonly isolated organisms. Gram-Positive isolates including Staphylococcus aureus and Staphylococcus epidermidis, P. aeruginosa, and Enterobacter spp. showed high sensitivity to Gentamicin, Meropenem, and Imipenem. In contrast, Acinetobacter spp. and Klebsiella spp. exhibited significant resistance, particularly to carbapenems. Staph. aureus was generally sensitive to first-line antibiotics, such as Vancomycin and Rifampicin whereas Staph. epidermidis demonstrated multidrug resistance including pan-drug resistance in some cases. These findings highlighted the complex and resistant microbial profiles of diabetic foot infections, thus emphasizing the importance of the culture-guided antibiotic therapy. The emergence of carbapenem-resistant strains underlined the requisites for continuous surveillance, judicious antibiotic use, and improved infection control strategies to aid the recovery of patients.

Diabetes mellitus (DM) is a major non-communicable metabolic disorder characterized by persistent hyperglycemia arising from impaired insulin secretion, insulin resistance, or a combination of both. As the global burden of DM continues to rise, understanding its prevalence and associated risk factors in specific populations is critical for the development of effective prevention and management strategies. A cross-sectional study was conducted among 150 residents (75 males and 75 females) attending a tertiary healthcare facility in Mardan, Pakistan. Sociodemographic characteristics, family history, body mass index (BMI), lifestyle behaviors, dietary patterns, psychological stress, and other potential risk factors were assessed using a structured questionnaire, while venous blood samples were collected to confirm the diagnosis of DM. Overall, the prevalence of DM was found to be 34.67% (n=52), with 29.33% (n=44) previously diagnosed and 5.33% (n=8) newly identified during the investigation. A significant sex-related disparity was observed, with prevalence rates of 26.67% (n=20) in males and 42.67% (n=32) in females. Rural residents exhibited a higher prevalence (42.86%, n=33) compared to urban residents (26.03%, n=19). Several risk factors demonstrated a notable association with DM, including advanced age (>60 years: 8.67%, n=13), obesity (12.67%, n=19), low physical activity (26.67%, n=40), smoking (11.33%, n=17), unhealthy dietary patterns (27.33%, n=41), high psychological stress (17.33%, n=26), hypertension (14%, n=21), and a positive family history (27.33%, n=41). The findings indicate an upward trend in the prevalence of DM in the Mardan region. Immediate implementation of targeted interventions, including public health education, lifestyle modification, dietary counseling, and risk factor management, is essential to mitigate the increasing burden of DM in this population.

Celiac disease (CD) is an autoimmune disorder triggered by gluten in genetically susceptible individuals, and viral infections have been proposed as potential cofactors in its pathogenesis. This study investigated the replication of SEN virus genotypes H and D in CD patients and their association with systemic cytokine levels. A total of 276 participants were enrolled, including 192 CD patients—115 on a gluten-containing diet (GCD) and 77 on a gluten-free diet (GFD)—alongside 84 healthy controls. SEN virus detection was performed using nested PCR, and serum cytokine levels (IL-1, IL-2, IL-4, IL-6, IL-8, IL-10, IFN-γ) were quantified via ELISA. SENV-H was detected in 71.4% of CD patients on a GCD, 66.7% of those on a GFD, and only 19.0% of healthy controls. In contrast, SENV-D was found exclusively in healthy individuals (23.8%) and not in CD patients. CD patients on a GCD exhibited markedly elevated cytokine levels, particularly IL-6 (76.2 ± 12.3 pg/mL), IL-8 (112.0 ± 40.2 pg/mL), and IFN-γ (50.2 ± 15.2 pg/mL), compared to GFD patients and healthy controls. Multivariate logistic regression identified IL-1, IL-2, IL-4, IL-6, IL-8, and IL-10 as significantly associated with active disease (ORs < 1, p < 0.05). Strong to very strong positive correlations were observed between SENV-H positivity and cytokine levels, with IL-6, IL-8, and IL-1 each showing correlation coefficients around 0.99. These results suggest that SENV-H may play a role in promoting or amplifying mucosal immune responses in active CD, whereas SENV-D appears unrelated. The findings highlight a potential interaction between viral replication and immune activation in celiac disease, meriting further mechanistic investigation.

Diabetic foot infection (DFI) represents a severe and potentially limb-threatening complication of long-standing and poorly controlled diabetes mellitus, a condition currently affecting over 422 million individuals globally and associated with more than 2 million annual deaths. This retrospective observational study was conducted at Hayatabad Medical Complex (HMC), Peshawar, with the objective of characterizing the clinical features, comorbidities, antibiotic regimens, and management outcomes of patients diagnosed with DFI. Clinical records of 341 patients admitted over a three-month period were reviewed. A male predominance was observed, with the highest prevalence noted among individuals aged 40–60 years. The majority of cases involved insulin-dependent diabetes mellitus, and an extended disease duration was identified as a major predisposing factor for DFI development. The mean hospitalization period was 25 days. Notably, complications such as peripheral neuropathy, diabetic nephropathy, and peripheral vasculopathy were more frequently documented in patients aged 65 years and older. Empirical treatment commonly involved poly-antibiotic regimens, which were administered in 64.81% of cases, underscoring the polymicrobial nature and severity of infections encountered. An amputation rate of 44.07% was recorded, which exceeds figures reported in comparable regional studies and is likely attributable to delayed clinical presentation and advanced stages of infection at the time of admission. The findings underscore the urgent need for enhanced early screening protocols, timely initiation of pathogen-targeted antimicrobial therapy, and multidisciplinary surgical intervention to reduce the risk of lower extremity amputation and the associated socio-economic burden.

Alzheimer’s disease (AD), a progressive neurodegenerative disorder characterized by severe cognitive decline, necessitates early and accurate diagnosis to improve patient outcomes. Recent advancements in deep learning (DL), particularly convolutional neural networks (CNNs), have demonstrated significant potential in medical image analysis (MIA). This study presents a robust CNN-based framework for the classification of AD using magnetic resonance imaging (MRI) data. The proposed methodology incorporates contrast stretching for image preprocessing, followed by principal component analysis (PCA) and recursive feature elimination (RFE) for feature selection, to enhance the discriminative power of the model. The framework is designed to classify MRI into four distinct categories: non-demented, very mildly demented, mildly demented, and moderately demented. Experimental validation on a comprehensive dataset reveals that the proposed approach achieves exceptional performance, with a validation accuracy of 97% and a training accuracy of 100%, alongside reduced loss and improved sensitivity. The integration of PCA and RFE is shown to effectively reduce dimensionality while retaining diagnostically critical features, thereby optimizing the model’s efficiency and interpretability. These findings underscore the potential of DL techniques to revolutionize the early detection and diagnosis of AD, offering a powerful tool for clinical decision-making and advancing the field of neuroimaging analysis. The proposed framework not only addresses the challenges of high-dimensional data but also provides a scalable and generalizable solution for the classification of neurodegenerative disorders.

Brain tumors represent a critical medical condition where early and accurate detection is paramount for effective treatment and improved patient outcomes. Traditional diagnostic methods relying on Magnetic Resonance Imaging (MRI) are often labor-intensive, time-consuming, and susceptible to human error, underscoring the need for more reliable and efficient approaches. In this study, a novel deep learning (DL) framework based on the Densely Connected Convolutional Network (DenseNet) architecture is proposed for the automated classification of brain tumors, aiming to enhance diagnostic precision and streamline medical image analysis. The framework incorporates adaptive filtering for noise reduction, Mask Region-based Convolutional Neural Network (Mask R-CNN) for precise tumor segmentation, and Gray Level Co-occurrence Matrix (GLCM) for robust feature extraction. The DenseNet architecture is employed to classify brain tumors into four categories: gliomas, meningiomas, pituitary tumors, and non-tumor cases. The model is trained and evaluated using the Kaggle MRI dataset, achieving a state-of-the-art classification accuracy of 96.96%. Comparative analyses demonstrate that the proposed framework outperforms traditional methods, including Back Propagation (BP), U-Net, and Recurrent Convolutional Neural Network (RCNN), in terms of sensitivity, specificity, and precision. The experimental results highlight the potential of integrating advanced DL techniques with medical image processing to significantly improve diagnostic accuracy and efficiency. This study not only provides a robust and reliable solution for brain tumor detection but also underscores the transformative impact of DL in medical imaging, offering radiologists a powerful tool for faster and more accurate diagnosis.

Diabetes is a chronic metabolic disorder that affects millions of people worldwide, making early detection crucial for effective management. This study assesses the effectiveness of three machine learning (ML) models, Logistic Regression (LR), Naïve Bayes (NB), and Decision Tree (DT), in predicting diabetes based on data from 392 individuals, including their demographic and clinical characteristics. The dataset underwent preprocessing to maintain data integrity, was standardized for model compatibility, and analyzed through feature correlation heatmaps, feature importance assessments, and statistical significance tests. The findings revealed that LR surpassed the other models, with the highest accuracy (78%), precision (73%), and F1-score (65%) for diabetic cases. NB showed moderate performance with 75% accuracy, while DT demonstrated the lowest accuracy (71%) due to overfitting. Receiver Operating Characteristic (ROC) analysis revealed strong discriminative power across all models, although perfect Area Under the Curve (AUC) scores indicate potential overfitting needing further validation. The study emphasizes the significance of key features like Glucose, Body Mass Index (BMI), and Age, which showed notable differences between diabetic and non-diabetic individuals. By enabling early detection and proactive management, these models can contribute to reducing diabetes-related complications, enhancing patient outcomes, and lessening the burden on healthcare systems. Future research should investigate ensemble learning, deep learning, and real-time data integration from Internet of Things (IoT) devices to improve predictive accuracy and scalability.

A bibliometric analysis was conducted to explore the research trends and emerging hotspots in the application of health monitoring technologies within nursing. Literature spanning from January 2021 to January 2025 was retrieved from the Web of Science Core Collection (WOSCC), and CiteSpace software was employed to analyze and visualize research outputs, institutional contributions, author collaborations, high-frequency keywords, and the evolution of keyword clusters over time. A total of 425 articles were identified, revealing a stable global publication output. The United States emerged as the leading contributor, with 138 articles, followed by China with 47. Prominent keywords such as "care," "management," and "remote patient monitoring (RPM)" were found to be indicative of current research foci. Analysis indicates a shift towards home-based care, smartphone integration, digital health solutions, and wearable devices, particularly in managing clinical conditions such as cardiovascular disease (CVD), cancer, and diabetes. The prevailing research trends highlight the importance of remote monitoring and nursing care within home settings, with an increasing emphasis on chronic diseases. Despite the growth in research activity, uneven international development and limited collaborative efforts, primarily within research teams, present challenges to the field’s progress. It is suggested that future research should focus on fostering international collaboration between academic, healthcare, and engineering sectors to ensure that monitoring technologies align with clinical needs. Moreover, the establishment of international regulations was recommended to standardize production processes, enhance product reliability, and facilitate the broader application of these technologies in nursing practice.

A two-month prospective study conducted at Hayatabad Medical Complex (HMC) Peshawar, Pakistan. In this study the pharmacotherapy patterns and drug-drug interaction (DDI) incidences were analyzed among 150 diabetic patients, of whom 50 presented with diabetic foot ulcer (DFU). Significant deviations from World Health Organization (WHO) core prescribing indicators were observed, particularly in the areas of polypharmacy and generic prescribing practices. The majority of DFU patients were from urban regions, with sedentary lifestyle factors identified as prominent contributors to DFU development. A higher incidence of DFU was noted among male patients with type 2 diabetes mellitus (T2DM) compared to female patients. Age distribution analysis revealed that patient ages ranged from 8 to 85 years, with 68% falling within the 41-60 age bracket, while only 2% were under 20 years of age. Among the all 391 pharmacotherapeutic agents prescribed, injectable medications constituted the majority (47.82%). Analysis of DDIs showed that 39.1% of prescribed medications were associated with drug interactions, with 72% of these classified as major interactions. The most frequently observed major DDIs involved combinations such as aspirin with Ramipril and Pregabalin with Losartan. These findings highlight the necessity for clinical pharmacists to review prescribing regimens to mitigate the risk of severe DDIs. The high prevalence of diabetes and DFU in this patient cohort is closely associated with lifestyle factors, insufficient health education, and lack of physical activity. These findings underline the urgent need for preventative strategies, including lifestyle modifications and public health education. Further investigation is recommended to enhance understanding of DFU risk factors and to develop improved prognostic and preventive frameworks.