Artificial Intelligence Research Articles

Can AI help emerging economy hidden champions climb upstream in GVCs? Evidence from Chinese listed hidden champions

Purpose Hidden champions are key actors in leading emerging economy firms to break free from the low-end lock-in problem within global value chains (GVCs). This study aims to analyse how hidden champions leverage artificial intelligence (AI) to achieve leapfrog upgrading in GVCs. Design/methodology/approach This study designs a two-way fixed effects model to examine how AI technology adoption affects the GVC upgrading of hidden champions by using a data set of 8,689 firm–year observations from 1,204 Chinese A-share listed hidden champions between 2013 and 2023. The sample data are derived from the annual financial data of firms and the text mining analysis of annual reports. Findings Results indicate that AI adoption enhances the positions of hidden champions in GVCs. In particular, this enhancement is mediated through the increasing specialisation and production efficiency of hidden champions and their domestic industry peers. Moreover, the effect of AI adoption on GVC upgrading is more pronounced for hidden champions with higher levels of automation. Hidden champions in labour-intensive and technology-intensive industries gain greater benefits from AI adoption in terms of GVC upgrading. The positive effect is particularly salient for hidden champions located in cities with high computing power capacity. Originality/value This study proposes a novel concept of domestic GVC leadership capability and extends discussions on the breakthroughs of emerging economy firms from low value-added activities by examining how Chinese hidden champions leverage AI to integrate accessible domestic supply chain resources for leapfrog GVC upgrading. The findings guide emerging economy firms in approaching the GVC upgrading ceiling to successfully climb the global GVC upgrading ladder. The discoveries also provide insights into how AI can enhance GVC resilience.

SMOTE-Enhanced Explainable AI Model for Predicting Visual Field Progression in Myopic Normal-Tension Glaucoma.

The AI model, enhanced by SMOTE to balance data classes, accurately predicted visual field deterioration in patients with myopic normal-tension glaucoma. Using SHAP analysis, the key variables driving disease progression were identified. To develop and validate a Synthetic Minority Over-sampling Technique (SMOTE)-enhanced artificial intelligence (AI) model for predicting visual field progression in myopic normal-tension glaucoma (NTG) patients. This retrospective cohort study included 100 eyes from myopic NTG patients with a mean follow-up of 10.3±3.2 years. Baseline parameters included intraocular pressure (IOP), central corneal thickness, axial length, and visual field metrics. A SMOTE-enhanced AI model was created to address class imbalance in progression events. Model performance was evaluated using receiver operating characteristic (ROC) analysis, cross-validation, and calibration plots. Predictive factor importance was evaluated through SHapley Additive exPlanations (SHAP) analysis. Visual field progression was observed in 28% of patients, with a median progression time of 3.2 years. The AI model achieved an area under the ROC curve (AUC) of 0.83 (95% CI, 0.75-0.91), with promising sensitivity (0.81) and specificity (0.77). SHAP analysis identified baseline mean deviation (MD), age, axial length, baseline IOP, and visual field index (VFI) as key predictors. When patients were stratified based on model-predicted risk scores, those with scores above 0.8 had significantly higher observed progression rates (82.6%) compared to those with lower risk scores. Subgroup analysis revealed strong correlations between progression risks and older age, greater axial length, and worse baseline MD. The SMOTE-enhanced AI model shows reasonable predictive performance and potential clinical utility for identifying visual field progression in myopic NTG patients, though further validation in larger cohorts is needed. By addressing class imbalance and myopia-specific challenges, this approach enables personalized risk stratification and early intervention.

Evaluation of error detection and treatment recommendations in nucleic acid test reports using ChatGPT models.

Accurate medical laboratory reports are essential for delivering high-quality healthcare. Recently, advanced artificial intelligence models, such as those in the ChatGPT series, have shown considerable promise in this domain. This study assessed the performance of specific GPT models-namely, 4o, o1, and o1mini-in identifying errors within medical laboratory reports and in providing treatment recommendations. In this retrospective study, 86 medical laboratory reports of Nucleic acid test report for the seven upper respiratory tract pathogens were compiled. There were 285 errors from four common error categories intentionally and randomly introduced into reports and generated 86 incorrected reports. GPT models were tasked with detecting these errors, using three senior medical laboratory scientists (SMLS) and three medical laboratory interns (MLI) as control groups. Additionally, GPT models were tasked with generating accurate and reliable treatment recommendations following positive test outcomes based on 86 corrected reports. χ2 tests, Kruskal-Wallis tests, and Wilcoxon tests were used for statistical analysis where appropriate. In comparison with SMLS or MLI, GPT models accurately detected three error types, and the average detection rates of the three GPT models were 88.9 %(omission), 91.6 % (time sequence), and 91.7 % (the same individual acted both as the inspector and the reviewer). However, the average detection rate for errors in the result input format by the three GPT models was only 51.9 %, indicating a relatively poor performance in this aspect. GPT models exhibited substantial to almost perfect agreement with SMLS in detecting total errors (kappa [min, max]: 0.778, 0.837). However, the agreement between GPT models and MLI was moderately lower (kappa [min, max]: 0.632, 0.696). When it comes to reading all 86 reports, GPT models showed obviously reduced reading time compared with SMLS or MLI (all p<0.001). Notably, our study also found the GPT-o1 mini model had better consistency of error identification than the GPT-o1 model, which was better than that of the GPT-4o model. The pairwise comparisons of the same GPT model's outputs across three repeated runs showed almost perfect agreement (kappa [min, max]: 0.912, 0.996). GPT-o1 mini showed obviously reduced reading time compared with GPT-4o or GPT-o1(all p<0.001). Additionally, GPT-o1 significantly outperformed GPT-4o or o1mini in providing accurate and reliable treatment recommendations (all p<0.0001). The detection capability of some of medical laboratory report errors and the accuracy and reliability of treatment recommendations of GPT models was competent, especially, potentially reducing work hours and enhancing clinical decision-making.

Artificial intelligence Integration for Financial Inclusion: a Study in pakistan

Artificial Intelligence (AI) integration into financial systems has been given important attention due to its potential to enhance financial inclusion, particularly in developing economies like Pakistan. This research examines the potential of AI integration for financial inclusion through mediating variables. The primary aim of this study is to uncover AI solution benefits that improve financial inclusion when these important factors interact. This quantitative study aims to look into the role of AI integration in Pakistan's financial inclusion. Data was collected from 200 financial services users in Pakistan. Data is analyzed using statistical techniques such as PLS-SEM. PLS-SEM modeling was implied to examine the research framework of the study. The study confirms that AI integration has a positive role in mediating variables. The study has implications, that can be recognized and used by policymakers to shape targeted interventions, and policies, which improve financial access by enhancing user knowledge about financial matters and promoting the acceptance of AI system utilization. Findings enable practitioners to create better financial education programs and inclusive financial service delivery so that people can easily understand and access desired outcomes. This study enhanced the academic knowledge of the utilization of AI technology to promote economic growth in developing economies. Keywords: Artificial Intelligence, Financial Inclusion, Financial Literacy, User adoption, Finance.

Challenges of using artificial intelligence in social work education

ABSTRACT The difficulties of using artificial intelligence (AI) in social work education at Palestinian institutions are covered in the study. The authors discuss the numerous advantages that artificial intelligence can provide, they touch on the moral concerns raised about using AI in social work education, and the paper concludes by outlining suggested future steps to advance AI’s use in social work education. The paper used a case study approach with a qualitative research methodology to investigate the difficulties of using AI in social work education. In-depth interviews with 12 instructors who work in social work departments at four Palestinian colleges were used to provide complexity and depth, the interviews used a structured style with open-ended questions. Using the MAXQDA 2020 application, inductive thematic latent content analysis was used to examine the data. The results showed that the most important challenges of using AI in social work education in Palestinian universities are the lack of experience and skills necessary to use AI, and the weak capabilities of universities in providing computer laboratories, the study revealed the proposed future steps to enhance the use of AI in social work education in Palestinian universities from the perspective of teachers.

Utilizing artificial intelligence to predict and analyze socioeconomic, environmental, and healthcare factors driving tuberculosis globally

Tuberculosis (TB) is a major global health issue, contributing significantly to mortality and morbidity rates worldwide. Socioeconomic, environmental, and healthcare factors significantly impact TB trends. Therefore, we aimed to predict TB and identify the determinants of the disease using advanced artificial intelligence (AI). This study employed the advanced machine learning (ML) model, XGBoost (eXtreme gradient boosting), combined with XAI (eXplainable artificial intelligence) and spatial analysis to describe global TB incidence and mortality rates across 194 countries from 2000 to 2022. Spatial autocorrelation analysis utilizing Moran’s I revealed geographical clusters and significant determinants affecting TB incidence. Treatment success rates and MDR-TB treatment initiation were identified as pivotal determinants of TB incidence. The correlation study revealed a substantial positive relationship between TB incidence in HIV-positive patients and overall TB incidence (r = 0.83). Confirmed cases of MDR-TB had the most significant impact on TB incidence (SHAP = 0.874). Additionally, air pollution had a notable impact on TB incidence (SHAP = 1.36). The XGBoost model demonstrated the best predictive performance for TB incidence and mortality, exhibiting the lowest RMSE (0.88), the highest R2 (0.67), and Adjusted R2 (0.65). This study highlights the potential of integrating XGBoost and XAI methodologies as a holistic framework for effectively tackling global tuberculosis incidence and mortality rates, as well as for the proficient application of advanced analytical techniques in public health.

Automated assessment of simulated laparoscopic surgical skill performance using deep learning

Artificial intelligence (AI) has the potential to improve healthcare and patient safety and is currently being adopted across various fields of medicine and healthcare. AI and in particular computer vision (CV) are well suited to the analysis of minimally invasive surgical simulation videos for training and performance improvement. CV techniques have rapidly improved in recent years from accurately recognizing objects, instruments, and gestures to phases of surgery and more recently to remembering past surgical steps. Lack of labeled data is a particular problem in surgery considering its complexity, as human annotation and manual assessment are both expensive in time and cost, and in most cases rely on direct intervention of clinical expertise. In this study, we introduce a newly collected simulated Laparoscopic Surgical Performance Dataset (LSPD) specifically designed to address these challenges. Unlike existing datasets that focus on instrument tracking or anatomical structure recognition, the LSPD is tailored for evaluating simulated laparoscopic surgical skill performance at various expertise levels. We provide detailed statistical analyses to identify and compare poorly performed and well-executed operations across different skill levels (novice, trainee, expert) for three specific skills: stack, bands, and tower. We employ a 3-dimensional convolutional neural network (3DCNN) with a weakly-supervised approach to classify the experience levels of surgeons. Our results show that the 3DCNN effectively distinguishes between novices, trainees, and experts, achieving an F1 score of 0.91 and an AUC of 0.92. This study highlights the value of the LSPD dataset and demonstrates the potential of leveraging 3DCNN-based and weakly-supervised approaches to automate the evaluation of surgical performance, reducing reliance on manual expert annotation and assessments. These advancements contribute to improving surgical training and performance analysis.

Study of an effective machine learning-integrated science curriculum for high school youth in an informal learning setting

PurposeThis study evaluates the effectiveness of a machine learning (ML) integrated science curriculum implemented within the Science Research Mentorship Program (SRMP) for high school youth at the American Museum of Natural History (AMNH) over 2 years. The 4-week curriculum focused on ML knowledge gain, skill development, and self-efficacy, particularly for under-represented youth in STEM.BackgroundML is increasingly prevalent in STEM fields, making early exposure to ML methods and artificial intelligence (AI) literacy crucial for youth pursuing STEM careers. However, STEM fields, particularly those focused on AI research and development, suffer from a lack of diversity. Learning experiences that support the participation of under-represented groups in STEM and ML are essential to addressing this gap.ResultsParticipant learning was assessed through pre- and post-surveys measuring ML knowledge, skills, and self-efficacy. Results from the implementation of the curriculum show that participants gained understanding of ML knowledge and skills (p < 0.001, d = 1.083) and self-efficacy in learning ML concepts (p = 0.004, d = 0.676). On average, participants who identified as female and non-white showed greater learning gains than their white male peers (ML knowledge: p < 0.001, d = 1.191; self-efficacy: p = 0.006, d = 0.631), decreasing gaps in ML knowledge, skills, and self-efficacy identified in pre-survey scores.ConclusionsThe ML-integrated curriculum effectively enhances students’ understanding and confidence in ML concepts, especially for under-represented groups in STEM, and provides a model for future ML education initiatives in informal science settings. We suggest that policy makers and school leaders take into account that high school age youth can learn ML concepts through integrated curricula while maintaining an awareness that curriculum effectiveness varies across demographic groups.

Artificial intelligence in language learning: biometric feedback and adaptive reading for improved comprehension and reduced anxiety

This study investigates the efficacy of an AI-enhanced reading platform in enhancing reading comprehension and influencing psychological variables such as motivation, anxiety, and cognitive load among second language (L2) learners. A mixed-methods approach was employed, combining quantitative analyses of reading comprehension scores and psychological measures with qualitative exploration through focus group discussions. A total of 300 participants were randomly assigned to either the experimental group, which used the AI platform, or the control group, which used traditional digital resources. Quantitative results revealed significant improvements in reading comprehension, motivation, anxiety reduction, and cognitive load management among participants using the AI platform compared to the control group. Effect sizes indicated large to moderate impacts of the intervention across all measured variables. Biometric data analysis, including heart rate variability (HRV) and eye-tracking metrics, provided objective evidence supporting the platform’s efficacy in reducing stress levels and promoting more efficient reading behaviors. Qualitative findings illuminated participants’ experiences, highlighting enhanced engagement, reduced anxiety, development of improved reading strategies, and appreciation for the user-friendly platform design. The study underscores the potential of AI-driven educational technologies to optimize language learning outcomes by providing personalized, adaptive, and supportive learning environments.

Artificial Intelligence in Online Journalism: A New Paradigm of Communication

Artificial Intelligence in Online Journalism: A New Paradigm of Communication

Machine Learning and Artificial Intelligence for Research on Hypertension.

Hypertension continues to be the leading modifiable risk factor for mortality globally, contributing significantly to cardiovascular disease. According to the World Health Organization, hypertension affects an estimated 1.28 billion adults globally, yet nearly half of these individuals are unaware of their condition, and many remain untreated or inadequately managed1. The American Heart Association (AHA) 2017 Hypertension Guidelines define hypertension as blood pressure (BP) ≥130/80 mmHg and recommend a target BP of <130-140/80 mmHg for most adults. Effective management of hypertension is crucial in reducing morbidity and mortality, and current clinical guidelines emphasize the importance of early detection, lifestyle modifications, and pharmacological treatment to mitigate long-term health risks. With the recent development and advancement of artificial intelligence (AI) and machine learning (ML), the landscape for hypertension care and research is evolving at an accelerating pace to improve health outcomes worldwide.

Identifying Risks and Ethical Considerations of AI in Gambling: A Scoping Review

ABSTRACT Artificial intelligence (AI) is experiencing widespread adoption in the gambling sector. This scoping review aimed to identify and summarize the current literature on the risks and ethical considerations of AI applications in gambling. Following PRISMA-ScR guidelines, we conducted electronic searches across 30 databases. Reflecting the infancy of this field of inquiry, 16 studies met our predefined eligibility criteria. The literature converged around six themes: Explainability, Exploitation, Algorithmic Flaws, Consumer Rights, Accountability, and Human-in-the-Loop. As a globally reaching product, gambling regulators and operators need to be cognizant not just of philosophical principles but also of the rich tapestry of global ethical traditions.

Uncharted Territory: Gen Z’s Unethical AI Use and Organizational Cybersecurity

ABSTRACT The purpose of this study is to examine the unethical use of Artificial Intelligence by Generation Z, encompassing behaviors such as improper use of ChatGPT in educational settings, the creation of misleading social media content, and online manipulation. Despite the substantial body of research on unethical practices in information technology, there exists a noticeable gap in the investigation of unethical generative AI use. We utilize a scenario-based research design involving Generation Z participants and employing a blend of linear and nonlinear quantitative Structured Equation Modeling as well as a qualitative post-hoc analysis. Our study illuminates the nuanced dimensions of artificial intelligence exploitation by Generation Z. We find that Generation Z individuals’ ideological stance toward unethical generative AI use have minimal influence, instead the perceived overall gain of such use acts a major driving force. Moreover, we observed through our qualitative post-hoc analysis that Generation Z is pragmatic, digitally proficient and possesses a willingness to question societal norms that appear as the driving force behind their use of generative AI. Our work is the first of its kind to explore the unethical use of gAI specifically in the context of Generation Z individuals and explore its implications for businesses as they begin to populate the workforce. With the dramatic increase in gAI integration by businesses, these “native” gAI users will play a pivotal role in the success or failure of such adoption, especially in terms of its ethical or unethical application in business.

A large dataset covering the Chinese national sign language for dual-view isolated sign language recognition

Isolated Sign Language Recognition (ISLR), which seeks to automatically align sign videos with corresponding glosses, has recently gained considerable attention from the artificial intelligence community. This technology has the potential to bridge the communication gap between hearing people and the deaf community. However, the development of ISLR is hindered by the scarcity of sign language datasets. Moreover, existing ISLR datasets are limited by their provision of a single perspective, which makes hand gesture occlusion difficult to handle. In addition, existing Chinese ISLR datasets, such as DEVISIGN and NMFs-CSL, fail to cover the entire vocabulary of Chinese National Sign Language (CNSL). This greatly obstructs the application of ISLR in the real world. To address these challenges, we introduce a novel word-level sign language dataset for ISLR that encompasses the entire CNSL vocabulary, comprising 6,707 unique signs. Moreover, it provides two perspectives of signers: the front side and the left side. There are ten signers involved in sign video recording, and the processes of sign video recording, annotation and quality assurance were rigorously controlled. To the best of our knowledge, this dataset is the first dual-view Chinese sign language dataset for ISLR that covers all the sign words in CNSL.

Data-driven discovery of Pt single atom embedded germanosilicate MFI zeolite catalysts for propane dehydrogenation

Zeolite-confined metal is an important class of heterogeneous catalysts, demonstrating exceptional catalytic performance in many reactions, but the identification of a stable metal-zeolite combination with a simple synthetic method remains a top challenge. Here artificial intelligence methods, particularly global neural network potential based large-scale atomic simulation, are utilized to design Pt-containing zeolite frameworks for propane-to-propene conversion. We show that out of the zeolite database (>220 structure framework) and more than 100,000 Pt/Ge differently distributed configurations, there are only three Ge-containing zeolites, germanosilicate (MFI, IWW and SAO) that are predicted to be capable of stabilizing Pt single atom embedded in zeolite skeleton and at the meantime allowing propane fast diffusion. Among, the Pt1@Ge-MFI catalyst is successfully synthesized via a simple one-pot synthesis without a lengthy post-treatment procedure, and characterized by high-resolution experimental techniques. We demonstrate that the catalyst features an in-situ formed [GePtO3H2] active site under the reductive reaction condition that can achieve long-term (>750 h) high activity and selectivity (98%) for propane dehydrogenation. Our simple catalyst synthesis holds promise for scale-up industrial applications that can now be rooted in first principles via data-driven catalyst design.

Updates on novel and traditional OCT and OCTA biomarkers in nAMD.

Predictivity of optical coherence tomography (OCT) examination for the development of neovascular age-related macular degeneration (nAMD) was demonstrated to be superior compared to other methods, suggesting it as an elective method for screening purposes. Moreover, OCT and OCT angiography (OCTA) have enabled us to provide accurate prognostic information to nAMD patients. Along with well-known prognostic biomarkers, such as the presence of reticular pseudodrusen, the volume of the pigment epithelial detachment (PED), subretinal fluid (SRF), intraretinal fluid (IRF) and hyperreflective foci (HRF), emerging parameters show promising results and may allow a further refinement of prediction and customization of treatment and follow up strategies. This review of the literature discusses the main OCT and OCTA biomarkers reported in literature for nAMD, with a special focus on recent updates on the subject. Future perspectives of clinical applications include the development of artificial intelligence models considering all the described biomarkers to allow automatic and detailed characterization of each lesion based on imaging information.

Effect of Uncertainty-Aware AI Models on Pharmacists' Reaction Time and Decision-Making in a Web-Based Mock Medication Verification Task: Randomized Controlled Trial.

Artificial intelligence (AI)-based clinical decision support systems are increasingly used in health care. Uncertainty-aware AI presents the model's confidence in its decision alongside its prediction, whereas black-box AI only provides a prediction. Little is known about how this type of AI affects health care providers' work performance and reaction time. This study aimed to determine the effects of black-box and uncertainty-aware AI advice on pharmacist decision-making and reaction time. Recruitment emails were sent to pharmacists through professional listservs describing a web-based, crossover, randomized controlled trial. Participants were randomized to the black-box AI or uncertainty-aware AI condition in a 1:1 manner. Participants completed 100 mock verification tasks with AI help and 100 without AI help. The order of no help and AI help was randomized. Participants were exposed to correct and incorrect prescription fills, where the correct decision was to "accept" or "reject," respectively. AI help provided correct (79%) or incorrect (21%) advice. Reaction times, participant decisions, AI advice, and AI help type were recorded for each verification. Likelihood ratio tests compared means across the three categories of AI type for each level of AI correctness. A total of 30 participants provided complete datasets. An equal number of participants were in each AI condition. Participants' decision-making performance and reaction times differed across the 3 conditions. Accurate AI recommendations resulted in the rejection of the incorrect drug 96.1% and 91.8% of the time for uncertainty-aware AI and black-box AI respectively, compared with 81.2% without AI help. Correctly dispensed medications were accepted at rates of 99.2% with black-box help, 94.1% with uncertainty-aware AI help, and 94.6% without AI help. Uncertainty-aware AI protected against bad AI advice to approve an incorrectly filled medication compared with black-box AI (83.3% vs 76.7%). When the AI recommended rejecting a correctly filled medication, pharmacists without AI help had a higher rate of correctly accepting the medication (94.6%) compared with uncertainty-aware AI help (86.2%) and black-box AI help (81.2%). Uncertainty-aware AI resulted in shorter reaction times than black-box AI and no AI help except in the scenario where "AI rejects the correct drug." Black-box AI did not lead to reduced reaction times compared with pharmacists acting alone. Pharmacists' performance and reaction times varied by AI type and AI accuracy. Overall, uncertainty-aware AI resulted in faster decision-making and acted as a safeguard against bad AI advice to approve a misfilled medication. Conversely, black-box AI had the longest reaction times, and user performance degraded in the presence of bad AI advice. However, uncertainty-aware AI could result in unnecessary double-checks, but it is preferred over false negative advice, where patients receive the wrong medication. These results highlight the importance of well-designed AI that addresses users' needs, enhances performance, and avoids overreliance on AI.

Artificial intelligence (AI) in restorative dentistry: current trends and future prospects

BackgroundArtificial intelligence (AI) holds immense potential in revolutionizing restorative dentistry, offering transformative solutions for diagnostic, prognostic, and treatment planning tasks. Traditional restorative dentistry faces challenges such as clinical variability, resource limitations, and the need for data-driven diagnostic accuracy. AI’s ability to address these issues by providing consistent, precise, and data-driven solutions is gaining significant attention. This comprehensive literature review explores AI applications in caries detection, endodontics, dental restorations, tooth surface loss, tooth shade determination, and regenerative dentistry. While this review focuses on restorative dentistry, AI’s transformative impact extends to orthodontics, prosthodontics, implantology, and dental biomaterials, showcasing its versatility across various dental specialties. Emerging trends such as AI-powered robotic systems, virtual assistants, and multi-modal data integration are paving the way for groundbreaking innovations in restorative dentistry.MethodsMethodologically, a systematic approach was employed, focusing on English-language studies published between 2020–2025(January), resulting in 63 peer-reviewed publications for analysis. Studies in caries detection, pedodontics, dental restorations, endodontics, tooth surface loss, and tooth shade determination highlighted AI trends and advancements. Inclusion criteria focused on AI applications in restorative dentistry, and publication timeframe. PRISMA guidelines were followed to ensure transparency in study selection, emphasizing on accuracy metrics and clinical relevance. The study selection process was carefully documented, and a flowchart of the stages, including identification, screening, eligibility, and inclusion, is shown in Fig. 1 to provide further clarity and reproducibility in the selection process.ResultsThe review identified significant advancements in AI-driven solutions across multiple domains of restorative dentistry. Notable studies demonstrated AI’s ability to achieve high diagnostic accuracy, such as up to 95% accuracy in caries detection, and its capacity to improve treatment planning efficiency, thus reducing patient chair time. Predictive analytics for personalized treatments was another area where AI has shown substantial promise.ConclusionThe review discussed trends, challenges, and future research directions in AI-driven dentistry, highlighting the transformative potential of AI in optimizing dental care. Key challenges include data privacy concerns, algorithmic bias, interpretability of AI decision-making processes, and the need for standardized AI training programs in dental education. Further research should focus on integrating AI with emerging technologies like 3D printing for personalized restorations, and developing AI training programs for dental professionals.Clinical SignificanceThe integration of AI into restorative dentistry offers precision-driven solutions for improved patient outcomes. By enabling faster diagnostics, personalized treatment approaches, and preventive care strategies, AI can significantly enhance patient-centered care and clinical efficiency. This review contributes to advancing the understanding and implementation of AI in dental practice by synthesizing key findings, identifying trends, and addressing challenges.

Mammographic classification of interval breast cancers and artificial intelligence performance.

European studies suggest artificial intelligence (AI) can reduce interval breast cancers (IBCs). However, research on IBC classification and AI's effectiveness in the U.S., particularly using digital breast tomosynthesis (DBT) and annual screening, is limited. We aimed to mammographically classify IBCs and assess AI performance using a 12-month screening interval. From digital mammography (DM) and DBT screening mammograms acquired 2010-2019 at a U.S. tertiary care academic center, we identified IBCs diagnosed <12 months after a negative mammogram. At least three breast radiologists retrospectively classified IBCs as missed-reading error, minimal signs-actionable, minimal signs-non-actionable, true interval, occult, or missed-technical error. A deep-learning AI tool assigned risk scores (1-10) to the negative index screening mammograms, with scores ≥8 considered "flagged." Statistical analysis evaluated associations among IBC types and AI exam scores, AI markings, and patient/tumor characteristics. From 184,935 screening mammograms (65% DM, 35% DBT), we identified 148 IBCs in 148 women (mean age, 61±12 years). Of these, 26% were minimal signs-actionable; 24% occult; 22% minimal signs-non-actionable; 17% missed-reading error; 6% true interval; and 5% missed-technical error (p<.001). AI scored 131 mammograms (17 errors excluded). AI most frequently flagged exams with missed-reading errors (90%), minimal signs-actionable (89%) and minimal signs-non-actionable (72%) (p=.02). AI localized mammographically-visible types more accurately (35-68%) than non-visible types (0-50%, p=.02). AI more frequently flagged and accurately localized IBC types that were mammographically visible at screening (missed or minimal signs), as compared to true interval or occult cancers.

Accuracy of artificial intelligence in prediction of osteoporotic fractures in comparison with dual-energy X-ray absorptiometry and the Fracture Risk Assessment Tool: A systematic review

BACKGROUND Osteoporotic fractures, whether due to postmenopausal or senile causes, impose a significant financial burden on developing countries and diminish quality of life. Recent advancements in artificial intelligence (AI) algorithms have demonstrated immense potential in predicting osteoporotic fractures. AIM To assess and compare the efficacy of AI models against dual-energy X-ray absorptiometry (DXA) and the Fracture Risk Assessment Tool (FRAX) in predicting fragility fractures. METHODS We conducted a literature search in English using electronic databases, including PubMed, Web of Science, and Scopus, for studies published until May 2024. The keywords employed were fragility fractures, osteoporosis, AI, deep learning, machine learning, and convolutional neural network. The inclusion criteria for selecting publications were based on studies involving patients with proximal femur and vertebral column fractures due to osteoporosis, utilizing AI algorithms, and analyzing the site of fracture and accuracy for predicting fracture risk using SPSS version 29 (Chicago, IL, United States). RESULTS We identified 156 publications for analysis. After applying our inclusion criteria, 24489 patients were analyzed from 13 studies. The mean area under the receiver operating characteristic curve was 0.925 ± 0.69. The mean sensitivity was 68.3% ± 15.3%, specificity was 85.5% ± 13.4%, and positive predictive value was 86.5% ± 6.3%. DXA showed a sensitivity of 37.0% and 74.0%, while FRAX demonstrated a sensitivity of 45.7% and 84.7%. The P value for sensitivity between DXA and AI was &lt; 0.0001, while for FRAX it was &lt; 0.0001 and 0.2. CONCLUSION This review found that AI is a valuable tool to analyze and identify patients who will suffer from fragility fractures before they occur, demonstrating superiority over DXA and FRAX. Further studies are necessary to be conducted across various centers with diverse population groups, larger datasets, and a longer duration of follow-up to enhance the predictive performance of the AI models before their universal application.