BACKGROUND: Whole-slide imaging (WSI) has shifted pathology toward digital workflows, creating the foundation for applying artificial intelligence (AI) to diagnostic tasks. This review summarises validated AI applications in diagnostic pathology, with an emphasis on clinical performance, regulatory developments and the practical barriers that affect implementation. METHODS: A structured search of PubMed, Scopus and Google Scholar identified English-language, peer-reviewed studies from January 2020 to May 2025. Eligible studies applied AI to diagnostic, grading or prognostic tasks in human tissue, used a pathologist-confirmed reference standard and included external or multi-centre validation. RESULTS: More than 150,000 digital slides were represented across the included studies. Reported performance metrics demonstrated strong diagnostic accuracy across several validated applications. Large meta-analyses and externally validated studies reported sensitivity values exceeding 96% and specificity above 93% for selected cancer-detection tasks, while other studies demonstrated high agreement for Gleason grading (QWK up to 0.862) and biomarker quantification (Ki-67 ICC 0.98). CONCLUSION: AI has the capacity to strengthen diagnostic pathology by improving consistency, measurement and efficiency. Moving from experimental use to routine reporting will require broad validation across centres, enhanced model transparency, strong quality-assurance systems and close cooperation between developers and pathologists.
Background: Chemical peels are widely used for mild-to-moderate acne vulgaris, but comparative evidence is dispersed across small trials and multiple active formulations. This review synthesized the supplied randomized evidence and compared efficacy and tolerability across peel types using network meta-analysis. Methods: PubMed, the Cochrane Library, Scopus, and Web of Science were searched for randomized active-comparator trials of chemical peels for acne vulgaris up to June 2026. Random-effects network meta-analyses used standardized mean differences (SMDs) for continuous outcomes and risk ratios (RRs) for categorical and safety outcomes, each with 95% confidence intervals (CIs). Salicylic acid was the reference treatment, and treatments were ranked using surface under the cumulative ranking curve (SUCRA) values. Results: Twenty-three randomized trials with reported enrollment totaling 1,170 participants were included. Most continuous efficacy comparisons were not statistically significant. Relative to salicylic acid, Jessner's solution was associated with a smaller reduction in papule count (SMD 2.49, 95% CI 1.28 to 3.70) and a smaller reduction in Michaelsson acne score (SMD 1.78, 95% CI 0.41 to 3.16). Salicylic plus mandelic acid ranked highest for good improvement (SUCRA 91.9%), but its RR versus salicylic acid was imprecise (RR 1.96, 95% CI 0.75 to 5.13). Trichloroacetic acid was associated with more erythema than salicylic acid (RR 2.74, 95% CI 1.10 to 6.78). Heterogeneity was substantial for non-inflammatory lesion count, papule count, pustule count, and Michaelsson acne score. Treatment-label fragmentation and undocumented handling of split-face correlations limited confidence in rankings. Conclusion: Our analysis does not establish broad superiority of one chemical peel for acne vulgaris. Salicylic acid performed favorably against Jessner's solution for selected efficacy outcomes and had a lower erythema risk than trichloroacetic acid, but most estimates were imprecise and several networks were heterogeneous. Treatment choice should remain individualized, and the findings require confirmation in rigorously reported head-to-head trials with standardized outcomes.
chemical peelsacnesalicylic acidJessner's solution
BACKGROUND: Neonatal nurses in high-risk Neonatal Intensive Care Units (NICUs) navigate complex, time-sensitive clinical decisions where accuracy and judgment are critical. Generative artificial intelligence (AI) has emerged as a supportive tool, yet its integration raises concerns about its impact on nurses' decision-making, professional autonomy, and organizational workflows. AIM: This study explored how neonatal nurses experience and integrate generative AI in clinical decision-making, examining its influence on nursing practice, organizational dynamics, and cultural adaptation in Saudi Arabian NICUs. METHODS: An interpretive phenomenological approach, guided by Complexity Science, Normalization Process Theory, and Tanner's Clinical Judgment Model, was employed. A purposive sample of 33 neonatal nurses participated in semi-structured interviews and focus groups. Thematic analysis was used to code and interpret data, supported by an inter-rater reliability of 0.88. Simple frequency counts were included to illustrate the prevalence of themes but were not used as quantitative measures. Trustworthiness was ensured through reflexive journaling, peer debriefing, and member checking. RESULTS: Five themes emerged: (1) Clinical Decision-Making, where 93.9% of nurses reported that AI-enhanced judgment but required human validation; (2) Professional Practice Transformation, with 84.8% noting evolving role boundaries and workflow changes; (3) Organizational Factors, as 97.0% emphasized the necessity of infrastructure, training, and policy integration; (4) Cultural Influences, with 87.9% highlighting AI's alignment with family-centered care; and (5) Implementation Challenges, where 90.9% identified technical barriers and adaptation strategies. CONCLUSIONS: Generative AI can support neonatal nurses in clinical decision-making, but its effectiveness depends on structured training, reliable infrastructure, and culturally sensitive implementation. These findings provide evidence-based insights for policymakers and healthcare leaders to ensure AI integration enhances nursing expertise while maintaining safe, patient-centered care.
Diabetes, a chronic condition affecting millions worldwide, necessitates early intervention to prevent severe complications. While accurately predicting diabetes onset or progression remains challenging due to complex and imbalanced datasets, recent advancements in machine learning offer potential solutions. Traditional prediction models, often limited by default parameters, have been superseded by more sophisticated approaches. Leveraging Bayesian optimization to fine-tune XGBoost, researchers can harness the power of complex data analysis to improve predictive accuracy. By identifying key factors influencing diabetes risk, personalized prevention strategies can be developed, ultimately enhancing patient outcomes. Successful implementation requires meticulous data management, stringent ethical considerations, and seamless integration into healthcare systems. This study focused on optimizing the hyperparameters of an XGBoost ensemble machine learning model using Bayesian optimization. Compared to grid search XGBoost (accuracy: 97.24%, F1-score: 95.72%, MCC: 81.02%), the XGBoost with Bayesian optimization achieved slightly improved performance (accuracy: 97.26%, F1-score: 95.72%, MCC:81.18%). Although the improvements observed in this study are modest, the optimized XGBoost model with Bayesian optimization represents a promising step towards revolutionizing diabetes prevention and treatment. This approach holds significant potential to improve outcomes for individuals at risk of developing diabetes.
The continuous progression of cancerous severity due to the interaction of physical (ultraviolet radiation), chemical (smoking, mycotoxins, and heavy metals), and biological (microbial populations) carcinogens inspired scientists to develop a correlation between active therapeutic agents and cancer proliferation. This review highlights the molecular mechanism by which lycopene imparts its anticancerous role, focusing on clinical and animal trials to validate its effectiveness. The antioxidant profile of lycopene promotes anticancerous properties that reduce cancer prevalence by activating cell signaling pathways and gene expression (involved in cancer cell proliferation). Lycopene's anti-inflammatory properties suppresses the tumor growth and development-promoting pathways, such as the PI3K/Akt/mTOR pathway. The anticancer property of lycopene is also evidenced by its inhibitory potential of the Wnt/β-catenin signaling pathway that is involved in cancer cell modulation and propagation. Lycopene also suppresses and neutralizes oxidative stress and reactive oxygen species (ROS)-induced DNA damage, preventing gene mutation. Inflammation-induced cell death is mitigated by lycopene's anti-inflammatory potential that lowers the expression of interleukin 6 (IL-6) and tumor necrosis factor-alpha (TNF-α). Several clinical and randomized control trials have revealed the effect of lycopene supplementation in the management of cancer, including breast cancer, pancreatic cancer, prostate cancer, colon cancer, ovarian cancer, skin cancer, oral cancer, liver cancer, gastric cancer, and kidney cancer, by lessening prostate-specific antigen (PSA) levels. These studies also accentuate certain limitations that need further trials to evaluate the long-term consequences of lycopene supplementations and their specific effective dose.
BACKGROUND: Nurses in neonatal intensive care units face critical challenges in managing emergencies where timely, accurate interventions are essential for survival. Traditional nursing education often lacks the hands-on, immersive training required to build complex emergency skills, contributing to persistent neonatal mortality globally. Virtual reality (VR) simulation, grounded in Kolb's Experiential Learning Theory, offers a promising solution by replicating realistic and repeatable clinical scenarios. While VR has shown potential in nursing education, its specific impact on high-risk neonatal emergencies remains underexplored. AIM: To evaluate the effectiveness of a VR simulation program in enhancing nurse competency and improving neonatal outcomes during emergency care, grounded in Kolb's Experiential Learning Theory. METHODS: A concurrent triangulation mixed-methods design was implemented over two weeks across four pediatric hospitals. Through stratified random sampling, 128 NICU nurses were allocated to VR simulation (n = 64) or traditional training (n = 64) groups. Quantitative data were collected using validated instruments (OSCE: CVI = 0.92, MCQ: α = 0.86) measuring clinical skills, knowledge retention, and decision-making accuracy. Qualitative data were gathered through semi-structured interviews (n = 24) exploring experiential aspects. RESULTS: The VR group showed significant improvements in clinical skills (OSCE: +16.1 points, p < 0.001, d = 1.58), decision-making accuracy (+ 16.7%, p < 0.001), and reduced stabilization times (-6.2 min, p < 0.001). Patient safety events decreased by 52% (p < 0.001). Thematic analysis revealed enhanced professional competence (83%), reduced clinical anxiety (75%), and positive learning experiences (88%), despite minor technical challenges. CONCLUSION: VR simulation demonstrates superior effectiveness for neonatal emergency training, significantly improving both nurse competency and patient outcomes. While geographic specificity and brief follow-up duration limit generalizability, findings support VR's potential for enhancing emergency preparedness. Future research should address longitudinal outcomes and implementation across diverse healthcare settings. CLINICAL TRIAL NUMBER: Not applicable.
virtual reality simulationneonatal intensive care unitnursing competenciesKolb's experiential learning theory
The healthcare industry, aided by technology, leverages the Internet of Things (IoT) paradigm to offer patient/user-related services that are ubiquitous and personalized. The authorized repository stores ubiquitous data for which access-level securities are granted. These security measures ensure that only authorized entities can access patient/user health information, preventing unauthorized entries and data downloads. However, recent sophisticated security and privacy attacks such as data breaches, data integrity issues, and data collusion have raised concerns in the healthcare industry. As healthcare data grows, conventional solutions often fail due to scalability concerns, causing inefficiencies and delays. This is especially true for multi-key authentication. Dependence on conventional access control systems leads to security flaws and authorization errors caused by static user behaviour models. This article introduces an Opportunistic Access Control Scheme (OACS) for leveraging access-level security. This approach is a defendable access control scheme in which the user permissions are based on their requirement and data. After accessing the healthcare record, a centralized IoT security augmentation and assessment is provided. The blockchain records determine and revoke the access grant based on previous access and delegation sequences. This scheme analyses the possible delegation methods for providing precise users with interrupt-free healthcare record access. The blockchain recommendations are analyzed using a trained learning paradigm to provide further access and denials. The proposed method reduces false rates by 11.74%, increases access rates by 13.1%, speeds up access and processing by 12.36% and 13.23%, respectively, and reduces failure rates by 9.94%. The OACS decreases false rates by 10.64%, processing time by 15.62%, and failure rates by 10.95%.
Internet of Thingshealthcare data securityblockchainmachine learning
In the present scenario, cancerous tumours are common in humans due to major changes in nearby environments. Skin cancer is a considerable disease detected among people. This cancer is the uncontrolled evolution of atypical skin cells. It occurs when DNA injury to skin cells, or a genetic defect, leads to an increase quickly and establishes malignant tumors. However, in rare instances, many types of skin cancer occur from DNA changes tempted by infrared light affecting skin cells. This disease is a worldwide health problem, so an accurate and appropriate diagnosis is needed for efficient treatment. Current developments in medical technology, like smart recognition and analysis utilizing machine learning (ML) and deep learning (DL) techniques, have transformed the analysis and treatment of these conditions. These approaches will be highly effective for the recognition of skin cancer utilizing biomedical imaging. This study develops a Multi-scale Feature Fusion of Deep Convolutional Neural Networks on Cancerous Tumor Detection and Classification (MFFDCNN-CTDC) model. The main aim of the MFFDCNN-CTDC model is to detect and classify cancerous tumours using biomedical imaging. To eliminate unwanted noise, the MFFDCNN-CTDC method initially utilizes a sobel filter (SF) for the image preprocessing stage. For the segmentation process, Unet3+ is employed, providing precise localization of tumour regions. Next, the MFFDCNN-CTDC model incorporates multi-scale feature fusion by combining ResNet50 and EfficientNet architectures, capitalizing on their complementary strengths in feature extraction from varying depths and scales of the input images. The convolutional autoencoder (CAE) model is utilized for the classification method. Finally, the parameter tuning process is performed through a hybrid fireworks whale optimization algorithm (FWWOA) to enhance the classification performance of the CAE model. A wide range of experiments is performed to authorize the performance of the MFFDCNN-CTDC approach. The experimental validation of the MFFDCNN-CTDC approach exhibited a superior accuracy value of 98.78% and 99.02% over existing techniques under ISIC 2017 and HAM10000 datasets.
skin cancer detectionskin lesion classificationmulti-scale feature fusionconvolutional neural networks
The recent approval of the nasal spray combination of mometasone (MOM) and olopatadine (OLO) presents a significant analytical challenge, as only a single reported method exists for its determination, deviating from eco-friendly practices. This study addresses this critical gap by pioneering the application of machine learning techniques to develop robust UV spectrophotometric approach for the simultaneous quantification of MOM and OLO, along with two genotoxic impurities: 4-dimethylamino pyridine (DAP) and methyl para-toluene sulfonate (MTS). By simultaneously determining these highly concerning genotoxic impurities and active pharmaceutical ingredients, this method underscores its paramount significance in upholding rigorous pharmaceutical quality standards and safeguarding patient safety. Applying the multilevel-multifactor experimental design, the calibration set was meticulously chosen at five different concentrations, yielding 25 calibration mixtures with central levels of 4, 46.5, 2.5, and 3 µg/mL for MOM, OLA, MTS, and DAP, respectively. The key innovation lies in the strategic implementation of the Kennard-Stone Clustering Algorithm to create a robust validation set of thirteen mixtures, resolving the limitations of reported chemometric methods' random data splitting. This approach ensures unbiased evaluation across the full concentration space, improving the method's reliability and sustainability. The robustness of this approach was rigorously tested using five distinct chemometric models: principal component regression, classical least squares, partial least squares, genetic algorithm-partial least squares, and multivariate curve resolution-alternating least squares, demonstrating its broad applicability across diverse modeling techniques. All models successfully determined all components with excellent recovery, low bias-corrected prediction, and adequate limits of detection. The Greenness Index Spider Charts and the Green Solvents Selection Tool were used to choose environmentally conscious solvents. A comprehensive sustainability assessment employed six state-of-the-art tools, including the national environmental method index, complementary green analytical procedure index, analytical greenness metric, blue applicability grade index, carbon footprint analysis, and the red-green-blue 12 metrics. Favorable results across all metrics affirmed the method's eco-friendliness, real-world applicability, and cost-effectiveness, supporting sustainable development goals in pharmaceutical quality control processes.
The rising demand for skin-lightening products has brought glutathione, a tripeptide with antioxidant properties and melanogenesis-regulating effects, into focus as a potentially safer alternative to conventional agents. This narrative review aims to evaluate the efficacy and safety of oral, topical, and intravenous glutathione in skin-lightening therapies. Oral administration shows significant but variable decreases in melanin levels with limited side effects. Topical formulations provide good-level melanin reduction and skin texture improvement but with varying sustainability. Intravenous glutathione, although having rapid action, is associated with serious safety concerns like anaphylaxis and hepatotoxicity, further aggravated by a lack of standardized dosing protocols. Current evidence supports glutathione's potential as a depigmenting agent but underscores the need for rigorous, large-scale clinical trials to establish long-term safety, optimal dosing, and standardized applications. Until such data are available, clinicians and consumers should exercise caution to ensure safe and effective dermatological practices, particularly with intravenous use.
Congenital heart disease (CHD), impacting around 1 % of infants worldwide, constitutes a significant healthcare challenge. Early detection is crucial, however constrained by the intricacies of conventional diagnostic techniques such as auscultation and echocardiography. This research presents a tailored one-dimensional convolutional neural network (1D-CNN) for the classification of phonocardiogram (PCG) signals into normal or abnormal categories, providing an automated and efficient solution for congenital heart disease (CHD) diagnosis. The model was trained on a composite dataset consisting of local pediatric PCG signals and publicly accessible dataset. Preprocessing methods, such as low- and high-pass filtering (60-650 Hz), resampling, and noise reduction, were utilized to enhance signal quality. Data augmentation techniques, including chunking, padding, and pitch-shifting, were employed to rectify dataset imbalances and improve model efficacy. Experimental results indicate substantial enhancements, attaining an accuracy of 98.56 %, precision of 98.56 %, F1 score of 98.55 %, sensitivity of 0.98, and specificity of 0.99. The comparative analysis demonstrates the proposed approach's superiority over current methods regarding accuracy and reliability. The research highlights the promise of combining modern signal processing with deep learning for efficient CHD screening. The suggested model exhibits outstanding performance yet, issues like dataset variability and noise persist. Future endeavors involve extending to multiclass categorization and assessing performance across a wider range of medical problems. This study represents a significant advancement in accessible, automated CHD diagnoses, enhancing clinical competence to elevate pediatric treatment.
AIM: To evaluate the efficacy and outcomes of integrative technologies employed in nursing-led interventions for the management of diabetes. BACKGROUND: With the global rise in diabetes prevalence, there is growing interest in digital health solutions to improve disease self-management. Nurses are increasingly leveraging technologies, such as mobile applications, wearable devices, and telehealth platforms, to support individuals with diabetes. However, the effectiveness and implementation outcomes of such nursing-led digital interventions remain variably reported in the literature. METHODS: A systematic review was conducted following PRISMA 2020 guidelines. Comprehensive five database searches (PubMed, CINAHL, Scopus, Web of Science, and Embase) identified randomized controlled trials (RCTs) from 2013 to 2024. Studies were included if they involved nurse-led interventions incorporating digital technologies for diabetes management. Data were synthesized using narrative and thematic analysis. Risk of bias was assessed using the RoB 2 tool. RESULTS: Thirteen RCTs involving diverse technologies demonstrated improvements in glycemic control (HbA1c reduction), self-management behaviors, and quality of life. Interventions incorporating personalized coaching, regular follow-up, and patient-centered feedback were particularly effective. Most studies were rated as low risk of bias, though some showed concerns regarding reporting practices and intervention fidelity. CONCLUSION: Nursing-led digital health interventions can significantly enhance diabetes care outcomes. Their success is contingent upon sustained patient engagement, nurse training, and organizational support. Broader implementation requires addressing digital literacy and system-level integration challenges. IMPLICATIONS FOR PRACTICE: Nurse-led technologies should be embedded in care models to support scalable, personalized, and effective diabetes self-management across diverse settings. CLINICAL TRIAL NUMBER: Not applicable.
diabetes managementnurse-led interventiondigital health technologiesmobile health apps
Telehealth adoption gained popularity during the coronavirus disease 2019 (COVID-19) pandemic and had substantial and various impacts on patient outcomes depending on the specific environment, healthcare system, and quality of telehealth services supplied. Hence, this systematic review explored those impacts and their sustainability post-pandemic. To conduct this systematic review, a thorough literature search was undertaken in electronic databases such as PubMed, Medline, Web of Science, Google Scholar, databases, Embase, and PsycINFO using relevant keywords. We included articles written in English and published in the last 10 years that reported on the impact of telehealth adoption on various patient outcomes and the impact of sustainability post-pandemic. The findings of this systematic review highlight the remarkable impact of telehealth adoption on patient outcomes and the sustainability of these initiatives post-pandemic. Telehealth has proven to enhance various aspects of healthcare, spanning from prevention to follow-up. Another effect of telehealth adoption is the significant reduction in hospitalizations. Furthermore, telehealth profoundly impacts hospital stays, leading to a decrease in all-cause hospital days per patient by 1.07 (95% confidence interval (CI): 1.76 to 0.39) days and a shorter mean hospital stay for condition-related hospitalizations by 89% (95% CI 1.42 to 0.36), providing evidence of efficient healthcare delivery. There was also a reduction in mortality rates for patients receiving telemedicine interventions. Telehealth is also cost-effective while remaining highly effective. Patient satisfaction is another key outcome of telehealth adoption observed. The convenience and reduced expenses of telehealth have garnered positive feedback from patients, reinforcing the desirability of telehealth as a viable alternative to in-person visits. Despite these numerous benefits, barriers and disparities in telehealth adoption and utilization persist, especially in rural hospitals that face challenges, including a lack of Health Information Exchange (HIE) capacity, limited patient engagement capabilities, and the absence of financial reimbursement. This systematic review underscores the remarkable impact of telehealth adoption on patient outcomes and its sustainability post-pandemic. However, barriers and disparities still exist, requiring attention to ensure equitable access to telehealth services. The evidence supports the continued development and implementation of telehealth initiatives to improve healthcare delivery and patient outcomes post-pandemic.
ABSTRACT The growing environmental concerns associated with petrochemical‐based plastics, including their persistence, contribution to climate change, and adverse effects on ecosystems and human health, have accelerated the search for sustainable alternatives. Starch‐based bioplastics have emerged as a promising solution due to their biodegradability, renewability, and compatibility with existing food packaging technologies. This review comprehensively examines production mechanisms of starch‐based bioplastics, focusing on their formulation, structural modifications, and industrial applications. The role of plasticizers in improving flexibility and reducing brittleness is discussed. Their natural decomposition into environmentally benign byproducts supports a circular economy and aligns with global sustainability goals. However, the downside of using bioplastic is that the raw material used for its fabrication is also used for sustenance, and so a trade‐off between growing feedstock crops and food production is inevitable. The higher manufacturing costs of bioplastics as compared to conventional plastics are also a limiting factor. Hence, bioplastics do not completely serve as a long‐term panacea for problems associated with plastic pollution. This review therefore attempts to (i) enumerate the benefits of starch in food packaging, (ii) delineate the physical and chemical treatments that enhance hydrophobicity, mechanical strength, and thermal stability, (iii) suggest the proper disposal procedures to ward off health issues and to conserve the environment, and (iv) advocate the implementation of stringent recycling measures and emphasize on the policies and legislation for green transition. Future research should focus on optimizing polymer blends, reinforcing compatibility with synthetic and natural polymers, and advancing manufacturing techniques to enable widespread adoption in food packaging applications.