Frontiers in Artificial Intelligence最新文献

{"title":"The role of AI for MRI-analysis in multiple sclerosis-A brief overview.","authors":"Jean-Pierre R Falet, Steven Nobile, Aliya Szpindel, Berardino Barile, Amar Kumar, Joshua Durso-Finley, Tal Arbel, Douglas L Arnold","doi":"10.3389/frai.2025.1478068","DOIUrl":"https://doi.org/10.3389/frai.2025.1478068","url":null,"abstract":"<p><p>Magnetic resonance imaging (MRI) has played a crucial role in the diagnosis, monitoring and treatment optimization of multiple sclerosis (MS). It is an essential component of current diagnostic criteria for its ability to non-invasively visualize both lesional and non-lesional pathology. Nevertheless, modern day usage of MRI in the clinic is limited by lengthy protocols, error-prone procedures for identifying disease markers (e.g., lesions), and the limited predictive value of existing imaging biomarkers for key disability outcomes. Recent advances in artificial intelligence (AI) have underscored the potential for AI to not only improve, but also transform how MRI is being used in MS. In this short review, we explore the role of AI in MS applications that span the entire life-cycle of an MRI image, from data collection, to lesion segmentation, detection, and volumetry, and finally to downstream clinical and scientific tasks. We conclude with a discussion on promising future directions.</p>","PeriodicalId":33315,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"8 ","pages":"1478068"},"PeriodicalIF":3.0,"publicationDate":"2025-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12011719/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144031572","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Legal regulation of AI-assisted academic writing: challenges, frameworks, and pathways.","authors":"Runyang Gao, Danghui Yu, Biao Gao, Heng Hua, Zhaoyang Hui, Jingquan Gao, Cha Yin","doi":"10.3389/frai.2025.1546064","DOIUrl":"https://doi.org/10.3389/frai.2025.1546064","url":null,"abstract":"<p><strong>Introduction: </strong>The widespread application of artificial intelligence in academic writing has triggered a series of pressing legal challenges.</p><p><strong>Methods: </strong>This study systematically examines critical issues, including copyright protection, academic integrity, and comparative research methods. We establishes a risk assessment matrix to quantitatively analyze various risks in AI-assisted academic writing from three dimensions: impact, probability, and mitigation cost, thereby identifying high-risk factors.</p><p><strong>Results: </strong>The findings reveal that AI-assisted writing challenges fundamental principles of traditional copyright law, with judicial practice tending to position AI as a creative tool while emphasizing human agency. Regarding academic integrity, new risks, such as \"credibility illusion\" and \"implicit plagiarism,\" have become prominent in AI-generated content, necessitating adaptive regulatory mechanisms. Research data protection and personal information security face dual challenges in data security that require technological and institutional innovations.</p><p><strong>Discussion: </strong>Based on these findings, we propose a three-dimensional regulatory framework of \"transparency, accountability, technical support\" and present systematic policy recommendations from institutional design, organizational structure, and international cooperation perspectives. The research results deepen understanding of legal attributes of AI creation, promote theoretical innovation in digital era copyright and academic ethics, and provide practical guidance for academic institutions in formulating AI usage policies.</p>","PeriodicalId":33315,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"8 ","pages":"1546064"},"PeriodicalIF":3.0,"publicationDate":"2025-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12009830/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143999432","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Emotional prompting amplifies disinformation generation in AI large language models.","authors":"Rasita Vinay, Giovanni Spitale, Nikola Biller-Andorno, Federico Germani","doi":"10.3389/frai.2025.1543603","DOIUrl":"https://doi.org/10.3389/frai.2025.1543603","url":null,"abstract":"<p><strong>Introduction: </strong>The emergence of artificial intelligence (AI) large language models (LLMs), which can produce text that closely resembles human-written content, presents both opportunities and risks. While these developments offer significant opportunities for improving communication, such as in health-related crisis communication, they also pose substantial risks by facilitating the creation of convincing fake news and disinformation. The widespread dissemination of AI-generated disinformation adds complexity to the existing challenges of the ongoing infodemic, significantly affecting public health and the stability of democratic institutions.</p><p><strong>Rationale: </strong>Prompt engineering is a technique that involves the creation of specific queries given to LLMs. It has emerged as a strategy to guide LLMs in generating the desired outputs. Recent research shows that the output of LLMs depends on emotional framing within prompts, suggesting that incorporating emotional cues into prompts could influence their response behavior. In this study, we investigated how the politeness or impoliteness of prompts affects the frequency of disinformation generation by various LLMs.</p><p><strong>Results: </strong>We generated and evaluated a corpus of 19,800 social media posts on public health topics to assess the disinformation generation capabilities of OpenAI's LLMs, including davinci-002, davinci-003, gpt-3.5-turbo, and gpt-4. Our findings revealed that all LLMs efficiently generated disinformation (davinci-002, 67%; davinci-003, 86%; gpt-3.5-turbo, 77%; and gpt-4, 99%). Introducing polite language to prompt requests yielded significantly higher success rates for disinformation (davinci-002, 79%; davinci-003, 90%; gpt-3.5-turbo, 94%; and gpt-4, 100%). Impolite prompting resulted in a significant decrease in disinformation production across all models (davinci-002, 59%; davinci-003, 44%; and gpt-3.5-turbo, 28%) and a slight reduction for gpt-4 (94%).</p><p><strong>Conclusion: </strong>Our study reveals that all tested LLMs effectively generate disinformation. Notably, emotional prompting had a significant impact on disinformation production rates, with models showing higher success rates when prompted with polite language compared to neutral or impolite requests. Our investigation highlights that LLMs can be exploited to create disinformation and emphasizes the critical need for ethics-by-design approaches in developing AI technologies. We maintain that identifying ways to mitigate the exploitation of LLMs through emotional prompting is crucial to prevent their misuse for purposes detrimental to public health and society.</p>","PeriodicalId":33315,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"8 ","pages":"1543603"},"PeriodicalIF":3.0,"publicationDate":"2025-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12009909/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144002012","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Community-engaged artificial intelligence: an upstream, participatory design, development, testing, validation, use and monitoring framework for artificial intelligence and machine learning models in the Alaska Tribal Health System.","authors":"Brian Travis Rice, Stacy Rasmus, Robert Onders, Timothy Thomas, Gretchen Day, Jeremy Wood, Carla Britton, Tina Hernandez-Boussard, Vanessa Hiratsuka","doi":"10.3389/frai.2025.1568886","DOIUrl":"https://doi.org/10.3389/frai.2025.1568886","url":null,"abstract":"<p><p>American Indian and Alaska Native (AI/AN) communities are at a critical juncture in health research, where combining participatory methods with advancements in artificial intelligence and machine learning (AI/ML) can promote equity. Community-based participatory research methods which emerged to help Alaska Native communities navigate the complicated legacy of historical research abuses provide a framework to allow emerging AI/ML technologies to align with their unique world views, community strengths, and healthcare goals. A consortium of researchers (including Alaska Native Tribal Health Consortium, the Center for Alaska Native Health Research at University of Alaska, Fairbanks, Stanford University, Southcentral Foundation, and Maniilaq Association) is using community-engaged AI/ML methods to address air medical ambulance (medevac) utilization in rural communities within the Alaska Tribal Health System (ATHS). This mixed-methods convergent triangulation study uses qualitative and quantitative analyses to develop AI/ML models tailored to community needs, provider concerns, and cultural contexts. Early successes have led to a second funded project to expand community perspectives, pilot models, and address issues of governance and ethics. Using the Ethical, Legal, and Social Implications of Research framework to address implementation of AI/ML in AI/AN communities, this second grant expands community engagement, technical capacity, and creates a body within the ATHS able to provide recommendations about AI/ML security, privacy, governance and policy. These two projects have the potential to provide equitable AI/ML implementation in Alaska Native healthcare and provide a roadmap for researchers and policy makers looking to effect similar change in other AI/AN and marginalized communities.</p>","PeriodicalId":33315,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"8 ","pages":"1568886"},"PeriodicalIF":3.0,"publicationDate":"2025-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12009764/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144037486","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The current state, challenges, and future directions of artificial intelligence in healthcare in Saudi Arabia: systematic review.","authors":"Najla M Aljehani, Fatima E Al Nawees","doi":"10.3389/frai.2025.1518440","DOIUrl":"https://doi.org/10.3389/frai.2025.1518440","url":null,"abstract":"<p><strong>Background: </strong>The use of artificial intelligence has been part of the healthcare technologies used in managing various aspects of healthcare processes. In Saudi Arabia, the use of artificial intelligence for managing healthcare has been influenced by the increasing use of healthcare technologies within the healthcare system. The aim of this study is to systematically review the current state, challenges, and future directions of artificial intelligence in healthcare in Saudi Arabia.</p><p><strong>Methods: </strong>The study used a systematic review methodology, which used the critical appraisal of articles on the use of artificial intelligence in healthcare. The critical appraisal used the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) and Joanna Briggs Institute (JBI) to implement the inclusion and exclusion criteria. The initial search for articles led to 88 articles, which were screened to 13, based on the inclusion and exclusion criteria.</p><p><strong>Results: </strong>The current state of the use of artificial intelligence in Saudi's healthcare system has been slowed down by the gradual uptake of healthcare technologies and the investments required. The main challenges identified included lack of policies to support artificial intelligence, lack of adequate capital for infrastructure and human resources and lack of cultures to accommodate the artificial intelligence in Saudi Arabia. With the current privatization and increased use of the artificial intelligence, the future of artificial intelligence in Saudi's healthcare system would see an increase in their utilization. Specific findings indicate the potential of artificial intelligence in improving clinical practice through blockchain, and that investments in artificial intelligence have encompasses various applications, including radiology. Skills gaps expected among healthcare professionals and the adoption of new technology are difficulties impacting the utilization of artificial intelligence in the healthcare sector.</p><p><strong>Conclusion: </strong>The use of artificial intelligence in Saudi's healthcare system requires the investments into infrastructure, human resource development and gradual commitments towards the healthcare technologies. The use of artificial intelligence would have benefits such as effectiveness in access to care and ability to meet the healthcare outcomes.</p>","PeriodicalId":33315,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"8 ","pages":"1518440"},"PeriodicalIF":3.0,"publicationDate":"2025-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12019849/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144001185","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Mortality prediction of heart transplantation using machine learning models: a systematic review and meta-analysis.","authors":"Ida Mohammadi, Setayesh Farahani, Asal Karimi, Saina Jahanian, Shahryar Rajai Firouzabadi, Mohammadreza Alinejadfard, Alireza Fatemi, Bardia Hajikarimloo, Mohammadhosein Akhlaghpasand","doi":"10.3389/frai.2025.1551959","DOIUrl":"https://doi.org/10.3389/frai.2025.1551959","url":null,"abstract":"<p><strong>Introduction: </strong>Machine learning (ML) models have been increasingly applied to predict post-heart transplantation (HT) mortality, aiming to improve decision-making and optimize outcomes. This systematic review and meta-analysis evaluates the performance of ML algorithms in predicting mortality and explores factors contributing to model accuracy.</p><p><strong>Method: </strong>A systematic search of PubMed, Scopus, Web of Science, and Embase identified relevant studies, with 17 studies included in the review and 12 in the meta-analysis. The algorithms assessed included random forests, CatBoost, neural networks, and others. Model performance was evaluated using pooled area under the curve (AUC) values, with subgroup analyses for algorithm type, validation methods, and prediction timeframes. The risk of bias was assessed using the QUADAS-2 tool.</p><p><strong>Results: </strong>The pooled AUC of all ML algorithms was 0.65 (95% CI: 0.64, 0.67), with no significant difference between machine learning and deep learning models (<i>p</i> = 0.67). Among the algorithms, CatBoost demonstrated the highest accuracy (AUC 0.80, 95% CI: 0.74, 0.86), while K-nearest neighbor had the lowest accuracy (AUC 0.53, 95% CI: 0.50, 0.55). A meta-regression indicated improved model performance with longer post-transplant periods (<i>p</i> = 0.008). When pooling only the best-performing models, the AUC improved to 0.73 (95% CI: 0.68, 0.78). The risk of bias was high in eight studies, with the flow and timing domains most commonly contributing to bias.</p><p><strong>Conclusion: </strong>ML models demonstrate moderate accuracy in predicting post-HT mortality, with CatBoost achieving the best performance. While ML shows potential for improving predictive precision, significant heterogeneity and biases highlight the need for standardized methods and further external validations to enhance clinical applicability.</p><p><strong>Systematic review registration: </strong>https://www.crd.york.ac.uk/PROSPERO/view/CRD42024509630, CRD42024509630.</p>","PeriodicalId":33315,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"8 ","pages":"1551959"},"PeriodicalIF":3.0,"publicationDate":"2025-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12006172/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144054225","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Detection and classification of ChatGPT-generated content using deep transformer models.","authors":"Mahdi Maktabdar Oghaz, Lakshmi Babu Saheer, Kshipra Dhame, Gayathri Singaram","doi":"10.3389/frai.2025.1458707","DOIUrl":"https://doi.org/10.3389/frai.2025.1458707","url":null,"abstract":"<p><strong>Introduction: </strong>The rapid advancement of AI, particularly artificial neural networks, has led to revolutionary breakthroughs and applications, such as text-generating tools and chatbots. However, this potent technology also introduces potential misuse and societal implications, including privacy violations, misinformation, and challenges to integrity and originality in academia. Several studies have attempted to distinguish and classify AI-generated textual content from human-authored work, but their performance remains questionable, particularly for AI models utilizing large language models like ChatGPT.</p><p><strong>Methods: </strong>To address this issue, we compiled a dataset consisting of both human-written and AI-generated (ChatGPT) content. This dataset was then used to train and evaluate a range of machine learning and deep learning models under various training conditions. We assessed the efficacy of different models in detecting and classifying AI-generated content, with a particular focus on transformer-based architectures.</p><p><strong>Results: </strong>Experimental results demonstrate that the proposed RoBERTa-based custom deep learning model achieved an F1-score of 0.992 and an accuracy of 0.991, followed by DistilBERT, which yielded an F1-score of 0.988 and an accuracy of 0.988. These results indicate exceptional performance in detecting and classifying AI-generated content.</p><p><strong>Discussion: </strong>Our findings establish a robust baseline for the detection and classification of AI-generated textual content. This work marks a significant step toward mitigating the potential misuse of AI-powered text generation tools by providing a reliable approach for distinguishing between human and AI-generated text. Future research could explore the generalizability of these models across different AI-generated content sources and address evolving challenges in AI text detection.</p>","PeriodicalId":33315,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"8 ","pages":"1458707"},"PeriodicalIF":3.0,"publicationDate":"2025-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12006062/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143999418","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Optimized design and performance evaluation of long-pressure-short-extraction ventilation and dust removal system based on the Coanda effect.","authors":"Xinguo Wang, Jinbo Zhao, Yufu Li, Zhibin Li","doi":"10.3389/frai.2025.1565889","DOIUrl":"https://doi.org/10.3389/frai.2025.1565889","url":null,"abstract":"<p><p>Mine ventilation and dust control systems are crucial for ensuring occupational safety and health during underground mining operations. Traditional long-pressure short-suction systems face challenges such as inefficient airflow organization, formation of vortex dead zones, high energy consumption, and inadequate adaptability to dynamic conditions in mining faces. This study addresses these limitations by proposing an optimized long-pressure short-suction ventilation and dust control system leveraging the Coandă effect. Through numerical simulations, experimental validation, and machine learning techniques, the study develops a comprehensive system to enhance dust control performance. The Coandă effect was employed to optimize the structural design of ventilation ducts, ensuring airflow attachment to tunnel surfaces, reducing dust dispersion, and achieving high-efficiency airflow with lower power consumption. The key parameters optimized include the spacing between the air supply and exhaust ducts, the pressure-to-suction ratio, and the height of the ventilation duct. The optimal pressure-to-suction ratio was found to be 2:3, which minimizes dust concentration at both the mining machine and downstream locations. Numerical simulations and experimental results demonstrated that the optimized system achieved dust concentration reductions of up to 84.12% in high initial dust conditions (800 mg/m³). These findings provide a solid foundation for intelligent and energy-efficient ventilation and dust control in mining operations, ensuring both safety and energy savings.</p>","PeriodicalId":33315,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"8 ","pages":"1565889"},"PeriodicalIF":3.0,"publicationDate":"2025-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12004412/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144041876","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Handling missing data of using the XGBoost-based multiple imputation by chained equations regression method.","authors":"Zhao Jinbo, Li Yufu, Mo Haitao","doi":"10.3389/frai.2025.1553220","DOIUrl":"https://doi.org/10.3389/frai.2025.1553220","url":null,"abstract":"<p><p>This study introduces an XGBoost-MICE (Multiple Imputation by Chained Equations) method for addressing missing data in mine ventilation parameters. Using historical ventilation system data from Shangwan Coal Mine, scenarios with different missing rates (5, 10, and 15%) and iteration numbers (30 and 50) were simulated to validate the accuracy and effectiveness of the approach. The results demonstrate that as the missing rate increased from 5 to 15%, the Mean Squared Error (MSE) rose from 0.0445 to 0.3254, while the Explained Variance decreased from 0.988309 to 0.943267. Additionally, the Mean Absolute Error (MAE) increased by 0.29. Iteration experiments on the \"frictional resistance per 100 meters\" attribute showed convergence of MSE and MAE after six iterations. Overall, the XGBoost-MICE method exhibited high imputation accuracy and stable convergence across various missing data scenarios, providing robust technical support for optimizing intelligent mine ventilation systems.</p>","PeriodicalId":33315,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"8 ","pages":"1553220"},"PeriodicalIF":3.0,"publicationDate":"2025-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12003350/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144031457","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Structural studies of Parvoviridae capsid assembly and evolution: implications for novel AAV vector design.","authors":"Heather A Noriega, Qizhao Wang, Daozhan Yu, Xiang Simon Wang","doi":"10.3389/frai.2025.1559461","DOIUrl":"https://doi.org/10.3389/frai.2025.1559461","url":null,"abstract":"<p><p>Adeno-associated virus (AAV) vectors have emerged as powerful tools in gene therapy, potentially treating various genetic disorders. Engineering the AAV capsids through computational methods enables the customization of these vectors to enhance their effectiveness and safety. This engineering allows for the development of gene therapies that are not only more efficient but also personalized to unique genetic profiles. When developing, it is essential to understand the structural biology and the vast techniques used to guide vector designs. This review covers the fundamental biology of the Parvoviridae capsids, focusing on modern structural study techniques, including (a) Cryo-electron microscopy and X-ray Crystallography studies and (b) Comparative analysis of capsid structures across different Parvoviridae species. Along with the structure and evolution of the Parvoviridae capsids, computational methods have provided significant insights into the design of novel AAV vector techniques, which include (a) Structure-guided design of AAV capsids with improved properties, (b) Directed Evolution of AAV capsids for specific applications, and (c) Computational prediction of AAV capsid-receptor interactions. Further discussion addressed the ongoing challenges in the AAV vector design and proposed future directions for exploring enhanced computational tools, such as artificial intelligence/machine learning and deep learning.</p>","PeriodicalId":33315,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"8 ","pages":"1559461"},"PeriodicalIF":3.0,"publicationDate":"2025-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12000042/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144017258","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}