Search Results (7,503)

The secondary use of electronic health records is essential for developing artificial intelligence-based clinical decision support systems. However, even after direct identifiers are removed, de-identified electronic health records remain vulnerable to re-identification, membership inference attacks, and model extraction attacks. This study examined the balance between privacy protection and model utility by evaluating de-identification strategies and differentially private learning in large-scale electronic health records. De-identified records from a tertiary medical center were analyzed and compared with three strategies—baseline generalization, enhanced generalization, and enhanced generalization with suppression—together with differentially private stochastic gradient descent. Privacy risks were assessed through k-anonymity distributions, membership inference attacks, and model extraction attacks. Model performance was evaluated using standard predictive metrics, and privacy budgets were estimated for differentially private stochastic gradient descent. Enhanced generalization with suppression consistently improved k-anonymity distributions by reducing small, high-risk classes. Membership inference attacks remained at the chance level under all conditions, indicating that patient participation could not be inferred. Model extraction attacks closely replicated victim model outputs under baseline training but were substantially curtailed once differentially private stochastic gradient descent was applied. Notably, privacy-preserving learning maintained clinically relevant performance while mitigating privacy risks. Combining suppression with differentially private stochastic gradient descent reduced re-identification risk and markedly limited model extraction while sustaining predictive accuracy. These findings provide empirical evidence that a privacy–utility balance is achievable in clinical applications. Full article

Background: Papilledema, an ophthalmic finding associated with increased intracranial pressure, is often induced by dermatological medications, including corticosteroids, isotretinoin, and tetracyclines. Early detection is crucial for preventing irreversible optic nerve damage, but access to ophthalmologic expertise is often limited in rural settings. Artificial intelligence (AI) may enable the automated and accurate detection of papilledema from fundus images, thereby supporting timely diagnosis and management. Objective: The primary objective of this study was to explore the diagnostic capability of ChatGPT-4o, a general large language model with multimodal input, in identifying papilledema from fundus photographs. For context, its performance was compared with a ResNet-based convolutional neural network (CNN) specifically fine-tuned for ophthalmic imaging, as well as with the assessments of two human ophthalmologists. The focus was on applications relevant to dermatological care in resource-limited environments. Methods: A dataset of 1094 fundus images (295 papilledema, 799 normal) was preprocessed and partitioned into a training set and a test set. The ResNet model was fine-tuned using discriminative learning rates and a one-cycle learning rate policy. GPT-4o and two human evaluators (a senior ophthalmologist and an ophthalmology resident) independently assessed the test images. Diagnostic metrics including sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), accuracy, and Cohen’s Kappa, were calculated for each evaluator. Results: GPT-4o, when applied to papilledema detection, achieved an overall accuracy of 85.9% with substantial agreement beyond chance (Cohen’s Kappa = 0.72), but lower specificity (78.9%) and positive predictive value (73.7%) compared to benchmark models. For context, the ResNet model, fine-tuned for ophthalmic imaging, reached near-perfect accuracy (99.5%, Kappa = 0.99), while two human ophthalmologists achieved accuracies of 96.0% (Kappa ≈ 0.92). Conclusions: This study explored the capability of GPT-4o, a large language model with multimodal input, for detecting papilledema from fundus photographs. GPT-4o achieved moderate diagnostic accuracy and substantial agreement with the ground truth, but it underperformed compared to both a domain-specific ResNet model and human ophthalmologists. These findings underscore the distinction between generalist large language models and specialized diagnostic AI: while GPT-4o is not optimized for ophthalmic imaging, its accessibility, adaptability, and rapid evolution highlight its potential as a future adjunct in clinical screening, particularly in underserved settings. These findings also underscore the need for validation on external datasets and real-world clinical environments before such tools can be broadly implemented. Full article

In this paper, the authors analyze the applicability of artificial intelligence algorithms for classifying file encryption methods based on statistical features extracted from the binary content of files. The prepared datasets included both unencrypted files and files encrypted using selected cryptographic algorithms in Electronic Codebook (ECB) and Cipher Block Chaining (CBC) modes. These datasets were further diversified by varying the number of encryption keys and the sample sizes. Feature extraction focused solely on basic statistical parameters, excluding an analysis of file headers, keys, or internal structures. The study evaluated the performance of several models, including Random Forest, Bagging, Support Vector Machine, Naive Bayes, K-Nearest Neighbors, and AdaBoost. Among these, Random Forest and Bagging achieved the highest accuracy and demonstrated the most stable results. The classification performance was notably better in ECB mode, where no random initialization vector was used. In contrast, the increased randomness of data in CBC mode resulted in lower classification effectiveness, particularly as the number of encryption keys increased. This paper provides a comprehensive analysis of the classifiers’ performance across various encryption configurations and suggests potential directions for further experiments. Full article

This article presents an innovative approach to optimizing the seismic modeling and analysis of high-rise buildings by automating the process with Python 3.13 and the ETABS 22.1.0 API. The process begins with the collection of information on the base building, a structure of seventeen regular levels, which includes data from structural elements, material properties, geometric configuration, and seismic and gravitational loads. These data are organized in an Excel file for further processing. From this information, a code is developed in Python that automates the structural modeling in ETABS through its API. This code defines the sections, materials, edge conditions, and loads and models the elements according to their coordinates. The resulting base model is used as a starting point to generate an optimal solution using a genetic algorithm. The genetic algorithm adjusts column and beam sections using an approach that includes crossover and controlled mutation operations. Each solution is evaluated by the maximum displacement of the structure, calculating the fitness as the inverse of this displacement, favoring solutions with less deformation. The process is repeated across generations, selecting and crossing the best solutions. Finally, the model that generates the smallest displacement is saved as the optimal solution. Once the optimal solution has been obtained, it is implemented a second code in Python is implemented to perform static and dynamic seismic analysis. The key results, such as displacements, drifts, internal and basal shear forces, are processed and verified in accordance with the Peruvian Technical Standard E.030. The automated model with API shows a significant improvement in accuracy and efficiency compared to traditional methods, highlighting an R² = 0.995 in the static analysis, indicating an almost perfect fit, and an RMSE = 1.93261 × 10⁻⁵, reflecting a near-zero error. In the dynamic drift analysis, the automated model reaches an R² = 0.9385 and an RMSE = 5.21742 × 10⁻⁵, demonstrating its high precision. As for the lead time, the model automated completed the process in 13.2 min, which means a 99.5% reduction in comparison with the traditional method, which takes 3 h. On the other hand, the genetic algorithm had a run time of 191 min due to its stochastic nature and iterative process. The performance of the genetic algorithm shows that although the improvement is significant between Generation 1 and Generation 2, is stabilized in the following generations, with a slight decrease in Generation 5, suggesting that the algorithm has reached its level has reached a point of convergence. Full article

The integration of artificial intelligence plays a critical role in human resource management in local governments by ensuring smooth, essential HR operations, including recruitment, performance management, and workforce planning. The current study is a systematic review focused on determining the performance management factors that should be considered when using artificial intelligence in the local government sector. Although artificial intelligence (AI) is becoming increasingly integrated into the governance and administrative systems of local governments around the world, this study raises critical questions about how performance should be managed, measured, and improved. Articles were screened based on their title, abstract, and keywords, following which the inclusion and exclusion criteria were applied. A comprehensive search was conducted in the EBSCOhost, Emerald Insight, Taylor & Francis, Scopus, and SpringerLink databases. These databases were chosen because they are prominent sources that publish various materials related to the social sciences. This scoping review followed the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews) guidelines and included 22 peer-reviewed empirical studies published between 2015 and 2025. Analysis of the identified 22 peer-reviewed articles revealed that the successful application of AI in local government performance management depends on six critical performance management factors: data quality and accessibility; strategic alignment with performance goals; evaluation criteria and metrics; ethical and legal oversight; institutional capacity and leadership; and change management and stakeholder engagement. These factors are interdependent and represent both technical and organisational dimensions of public administration. This study highlights that AI entails more than innovation; it reshapes the foundations of performance governance, requiring new capabilities, values, and institutional practices. Full article

Bias in artificial intelligence is a critical issue because these technologies increasingly influence decision-making in a wide range of areas. The recommender system field is one of them, where biases can lead to unfair or skewed outcomes. The origin usually lies in data biases coming from historical inequalities or irregular sampling. Recommendation algorithms using such data contribute to a greater or lesser extent to amplify and perpetuate those imbalances. On the other hand, different types of biases can be found in the outputs of recommender systems, and they can be evaluated by a variety of metrics specific to each of them. However, biases should not be treated independently, as they are interrelated and can potentiate or mask each other. Properly assessing the biases is crucial for ensuring fair and equitable recommendations. This work focuses on analyzing the interrelationship between different types of biases and proposes metrics designed to jointly evaluate multiple interrelated biases, with particular emphasis on those biases that tend to mask or obscure discriminatory treatment against minority or protected demographic groups, evaluated in terms of disparities in recommendation quality outcomes. This approach enables a more comprehensive assessment of algorithmic performance in terms of both fairness and predictive accuracy. Special attention is given to Graph Neural Network-based recommender systems, due to their strong performance in this application domain. Full article

Traditional police interrogation processes remain largely time-consuming and reliant on substantial human effort for both analysis and documentation. Intuition Artificial Intelligence (INTU-AI) is a Windows application designed to digitalize the administrative workflow associated with police interrogations, while enhancing procedural efficiency through the integration of AI-driven emotion recognition models. The system employs a multimodal approach that captures and analyzes emotional states using three primary vectors: Facial Expression Recognition (FER), Speech Emotion Recognition (SER), and Text-based Emotion Analysis (TEA). This triangulated methodology aims to identify emotional inconsistencies and detect potential suppression or concealment of affective responses by interviewees. INTU-AI serves as a decision-support tool rather than a replacement for human judgment. By automating bureaucratic tasks, it allows investigators to focus on critical aspects of the interrogation process. The system was validated in practical training sessions with inspectors and with a 12-question questionnaire. The results indicate a strong acceptance of the system in terms of its usability, existing functionalities, practical utility of the program, user experience, and open-ended qualitative responses. Full article

We investigate the applicability of visual foundation models, a recent advancement in artificial intelligence, for archaeological remote sensing. In contrast to earlier approaches, we employ a strictly zero-shot methodology, testing the hypothesis that such models can perform archaeological feature detection without any fine-tuning or other adaptation for the remote sensing domain. Across five experiments using satellite imagery, aerial LiDAR, and drone video data, we assess the models’ ability to detect archaeological features. Our results demonstrate that such foundation models can achieve detection performance comparable to that of human experts and established automated methods. A key advantage lies in the substantial reduction of required human effort and the elimination of the need for training data. To support reproducibility and future experimentation, we provide open-source scripts and datasets and suggest a novel workflow for remote sensing projects. If current trends persist, foundation models may offer a scalable and accessible alternative to conventional archaeological prospection. Full article

Recent advancements in the Internet of Things (IoT) and artificial intelligence (AI) are unlocking transformative opportunities across society. One of the most critical challenges addressed by these technologies is the ageing population, which presents mounting concerns for healthcare systems and quality of life worldwide. By supporting continuous monitoring, personal care, and data-driven decision-making, IoT and AI are shifting healthcare delivery from a reactive approach to a proactive one. This paper presents a comprehensive overview of IoT-based systems with a particular focus on the Internet of Healthcare Things (IoHT) and their integration with AI, referred to as the Artificial Intelligence of Things (AIoT). We illustrate the operating procedures of IoHT systems in detail. We highlight their applications in disease management, health promotion, and active ageing. Key enabling technologies, including cloud computing, edge computing architectures, machine learning, and smart sensors, are examined in relation to continuous health monitoring, personalized interventions, and predictive decision support. This paper also indicates potential challenges that IoHT systems face, including data privacy, ethical concerns, and technology transition and aversion, and it reviews corresponding defense mechanisms from perception, policy, and technology levels. Future research directions are discussed, including explainable AI, digital twins, metaverse applications, and multimodal sensor fusion. By integrating IoT and AI, these systems offer the potential to support more adaptive and human-centered healthcare delivery, ultimately improving treatment outcomes and supporting healthy ageing. Full article

Echocardiography is a first-line, non-invasive imaging modality widely used to assess cardiac structure and function; however, its interpretation remains highly operator dependent and subject to variability. The integration of artificial intelligence (AI) into echocardiographic practice holds the potential to transform workflows, enhance efficiency, and improve the consistency of assessments across diverse clinical settings. Interest in the application of AI to echocardiography has grown significantly since the early 2000s with AI models that assist with image acquisition, disease detection, measurement automation, and prognostic stratification for various cardiac conditions. Despite this momentum, the safe and effective deployment of AI models relies on rigorous development and validation practices, yet these are infrequently described in the literature. This narrative review aims to provide a comprehensive overview of the essential steps in the development and validation of AI models for echocardiography. Additionally, it explores current challenges and outlines future directions for the integration of AI within echocardiography. Full article

Background/Objectives: Accurate identification of vulvar high-grade squamous intraepithelial lesions (HSIL) is essential for preventing progression to invasive squamous cell carcinoma. This study addresses the gap in artificial intelligence (AI) applications for vulvar lesion diagnosis by developing and validating the first convolutional neural network (CNN) model to automatically detect and classify HPV-related vulvar lesions—specifically HSIL and low-grade squamous intraepithelial lesions (LSIL)—based on vulvoscopy images. Methods: This bicentric study included data from 28 vulvoscopies, comprising a total of 9857 annotated frames, categorized using histopathological reports (HSIL or LSIL). The dataset was divided into training, validation, and testing sets for development and assessment of a YOLOv11-based object detection model. Results: The CNN demonstrated a recall (sensitivity) of 99.7% and a precision (positive predictive value) of 99.1% for lesion detection and classification. Conclusions: This is the first AI model developed for detecting and classifying HPV-related vulvar lesions. The integration of such models into vulvoscopy could significantly improve diagnostic accuracy and positively impact women’s health by reducing the need for potentially invasive and anatomy-altering procedures. Full article

Stricter requirements on nutrient removal in wastewater treatment are being imposed by rapid urbanization and tightening water-quality standards. Despite their excellent solid–liquid separation and effective biological treatment, MBRs in conventional operation remain hindered by membrane fouling, limited robustness to influent variability, and elevated energy consumption. In recent years, precise process control and resource-oriented operation have been enabled by the integration of artificial intelligence (AI) with MBRs. Advances in four areas are synthesized in this review: optimization of MBR control architectures, intelligent adaptation to multi-source wastewater, regulation of membrane operating parameters, and enhancement of nitrogen and phosphorus removal. According to reported studies, increases in total nitrogen and total phosphorus removal have been achieved by AI-driven strategies while energy use and operating costs have been reduced; under heterogeneous influent and dynamic operating conditions, stronger generalization and more effective real-time regulation have been demonstrated relative to traditional approaches. For large-scale deployment, key challenges are identified as improvements in model interpretability and applicability, the overcoming of data silos, and the realization of multi-objective collaborative optimization. Addressing these challenges is regarded as central to the realization of robust, scalable, and low-carbon intelligent wastewater treatment. Full article

The Internet of Things (IoT) revolutionizes connectivity, enabling innovative applications across healthcare, industry, and smart cities but also introducing significant cybersecurity challenges due to its expanded attack surface. Intrusion Detection Systems (IDSs) play a pivotal role in addressing these challenges, offering tailored solutions to detect and mitigate threats in dynamic and resource-constrained IoT environments. Through a rigorous analysis, this study classifies IDS research based on methodologies, performance metrics, and application domains, providing a comprehensive synthesis of the field. Key findings reveal a paradigm shift towards integrating artificial intelligence (AI) and hybrid approaches, surpassing the limitations of traditional, static methods. These advancements highlight the potential for IDSs to enhance scalability, adaptability, and detection accuracy. However, unresolved challenges, such as resource efficiency and real-world applicability, underline the need for further research. By contextualizing these findings within the broader landscape of IoT security, this work emphasizes the critical importance of developing IDS solutions that ensure the reliability, privacy, and security of interconnected systems, contributing to the sustainable evolution of IoT ecosystems. Full article

This study examines the ethical problems of using artificial intelligence (AI) applications in higher education, focusing on activities performed by university educators. Drawing on Slovak legislation that defines educators’ responsibilities, the study classifies their activities into three categories: teaching, scientific research, and other (academic management and self-directed professional development). From standpoint of methodology, a thematic review of 42 open-access, peer-reviewed articles published between 2022 and 2025 was conducted across the Web of Science and Scopus databases. Relevant AI applications and their associated ethical issues were identified and thematically categorized. Results of this study show that AI applications are extensively used across all analysed areas of university educators’ activities. Most notably used are applications that are generative language models, editing and paraphrasing tools, learning and assessment software, management and search tools, visualizing and design tools, and analysis and management systems. Their adoption raises ethical concerns which can be thematically grouped into six categories: privacy and data protection, bias and fairness, transparency and accountability, autonomy and oversight, governance gaps, and integrity and plagiarism. The results provide universities with a structured analytical framework to assess and address ethical risks related to AI use in specific academic activities. Although the study is limited to open-access literature, it offers a conceptual foundation for future empirical research and the development of ethical, institutionally grounded AI policies in higher education. Full article

Due to their unique advantages—such as small size, easy integration, flexible wearability, low power consumption, high sensitivity, and material designability—organic field-effect transistor (OFET) gas sensors have significant application potential in fields such as environmental detection, smart healthcare, robotics, and artificial intelligence. Benzothiadiazole fused tetrathiafulvalenes (TTF) are promising organic semiconductor candidates due to their abundant S atoms and planar π-π conjugation skeletons. We designed a series of derivatives by side-chain modification, and conducted systematic computations on TTF derivatives, including reported and newly designed materials, to analyze how geometric factors affect the charge transport properties of materials at the PBE0/6-311G(d,p) level. The frontier molecular orbitals (FMOs) and reorganization energy indicate that the designed derivatives are promising candidates for organic semiconductor sensing materials. Furthermore, theoretical calculations reveal that the designed TTF derivatives are sensitive to gases like NH₃, H₂S, and SO₂, indicating organic field-effect transistors (OFETs) with gas-sensing functions. Full article