Artificial Intelligence Systems Research Articles

Disruptor or enabler? AI and financial system stability

Purpose The advent of artificial intelligence (AI) tools signifies a major advancement in technology, poised to significantly influence the financial system. From a conceptual standpoint, AI introduces both advantages and challenges to the financial landscape. Thus, this study aims to examine the dynamics between AI and financial system stability through several distinct approaches. Initially, the authors investigate potential nonlinearities in this relationship to assess the asymmetric reactions of financial system stability to the application of AI, both positive and negative. Design/methodology/approach Subsequently, to address intra-country variations, the authors incorporate a heterogeneous effect within the cross-sections by using a nonlinear panel autoregressive distributed lag model, which serves as a panel data adaptation of the Shin et al. (2014) framework and is comparable to the nonstationary heterogeneous panel data model. Findings The findings indicate that final system stability exhibits asymmetric responses to AI, with the latter displaying a more pronounced reaction. The results remain consistent across various AI proxies. Ultimately, the findings emanating from the study carry significant implications for financial system regulators. Originality/value This paper addresses gaps in the AI–financial stability literature by empirically examining the relationship internationally, where existing studies are limited. While some prior research (e.g. Daud et al., 2022; Li, 2021; Khan et al., 2023a) explores this globally, they do not fully account for nonlinearities and heterogeneity effects. To the best of the authors’ knowledge, this study is the first to use panel data to incorporate both aspects, offering a more comprehensive understanding of AI’s impact on financial stability. Doing so advances empirical knowledge beyond the largely theoretical, country-specific focus of earlier work (e.g. Darangwa, 2021; Chen and Du, 2016).

THE URGENCY OF ARTIFICIAL INTELLIGENCE REGULATION FROM A JOINT AUTHORSHIP PERSPECTIVE ON COPYRIGHT INFRINGEMENT

This research, titled Urgency of Artificial Intelligence Regulation from the Perspective of Joint Authorship Against Copyright Infringement, aims to analyze the legal framework governing Artificial Intelligence (AI)-based creations in Indonesia and explore the application of the Joint Authorship perspective to AI-generated works. Using a normative legal methodology, the research focuses on library research involving laws, regulations, and related literature. The findings reveal that Indonesia's Copyright Law No. 28 of 2014 does not adequately address AI-based creations. Specifically, Articles 58 and 59, which reference the "death of the creator," imply that creators are human, creating ambiguity as AI lacks human cognitive abilities and cannot meet the necessary criteria for copyright protection. Additionally, the research suggests that applying the Joint Authorship perspective to AI-generated works could recognize them as collaborative efforts between humans and computer programs. This approach would benefit creators by ensuring shared copyright and acknowledging the contributions of both humans and AI systems in the creation process.

Conscious artificial intelligence and biological naturalism.

As artificial intelligence (AI) continues to advance, it is natural to ask whether AI systems can be not only intelligent, but also conscious. I consider why people might think AI could develop consciousness, identifying some biases that lead us astray. I ask what it would take for conscious AI to be a realistic prospect, challenging the assumption that computation provides a sufficient basis for consciousness. I'll instead make the case that consciousness depends on our nature as living organisms - a form of biological naturalism. I lay out a range of scenarios for conscious AI, concluding that real artificial consciousness is unlikely along current trajectories, but becomes more plausible as AI becomes more brain-like and/or life-like. I finish by exploring ethical considerations arising from AI that either is, or convincingly appears to be, conscious. If we sell our minds too cheaply to our machine creations, we not only overestimate them - we underestimate ourselves.

Abstract 7433: Predicting overall survival (OS) differences using longitudinal AI-driven imaging-based prognostication (IPRO) in patients with advanced non-small cell lung cancer (aNSCLC)

Abstract Background: Early prediction of overall survival benefit associated with cancer treatments remains a key challenge in clinical trials and patient care. Standardized measures such as the Response Evaluation Criteria in Solid Tumours (RECIST) v1.1 are used in clinical trials to define tumour response and progression, but are subject to inter- and intra-observer variability, and are infrequently used in day to day clinical practice. Imaging-based prognostication delta (IPRO-Δ) is an artificial intelligence system trained on longitudinal changes in rich features extracted from serial real-world imaging data, automatically predicting survival from pairs of baseline (BL) and follow up (FU) thoracic computed tomography (CT) scans. Methods: IPRO-Δ was evaluated in an external real-world dataset of 194 aNSCLC patients treated with first line systemic therapy at 17 cancer centers, with pretreatment BL and FU (8±4 weeks after treatment initiation) scans. IPRO-Δ generated survival predictions at week 8 for each patient. Kaplan-Meier analyses and hazard ratios (HR) evaluated the association of IPRO-Δ quartiles with OS, with the highest quartile representing progressive disease, the lowest treatment response, and the middle stable disease. Results: The cohort included 19 stage IIIB (9.8%) and 175 stage IV (90.2%) aNSCLC patients, with 94 females (48.5%) and a median age of 64 years. Most tumours were adenocarcinoma (n = 147, 75.8%), followed by squamous cell (n = 18, 9.3%), large cell (n = 5, 2.6%) and other histologies (n = 24, 12.4%). Table 1 shows survival stratification amongst IPRO-Δ quartiles for the overall population and the subgroup of EGFR+ patients. Conclusion: IPRO-Δ successfully predicted survival differences amongst aNSCLC patients using BL and week-8 CT scans. Future work will compare IPRO-Δ to RECIST v1.1, potentially leading to IPRO-Δ's use as a surrogate endpoint in aNSCLC trials. Citation Format: Mohammed A. Alvi, John Riskas, Shahid A. Haider, Vignesh Sivan, Oleksandra Samorodova, Jay Hennesy, Duoaud Shah, Felix Baldauf-Lenschen, Marina Salluzzi, Ronald Bridges, Omar F. Khan. Predicting overall survival (OS) differences using longitudinal AI-driven imaging-based prognostication (IPRO) in patients with advanced non-small cell lung cancer (aNSCLC) [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2025; Part 1 (Regular Abstracts); 2025 Apr 25-30; Chicago, IL. Philadelphia (PA): AACR; Cancer Res 2025;85(8_Suppl_1):Abstract nr 7433.

Abstract 1115: PM-AI agent: A conversational artificial intelligence system for precision medicine and advancing health equity through integrative clinical, genomic and social determinants of health data analysis

Abstract Introduction: The integration of clinical, genomic, and social determinants of health (SDoH) data is essential for advancing precision medicine. However, significant challenges remain due to the complexity of cancer research workflows, the technical expertise required, and the pressing need to address cancer health disparities. To overcome these barriers, we developed the Precision Medicine AI Agent (PM-AI)—an innovative conversational AI system that enables users to conduct integrative data analyses through natural language inquiries. Methods: PM-AI leverages large language models (LLMs) to convert user instructions into executable code and autonomously analyze local stored datasets. The system performs advanced tasks such as subset comparisons, clinical prevalence studies using odds ratio tests, and survival analyses that provide survival curves and hazard ratios. Additionally, PM-AI delivers detailed analytic reports with actionable insights to support decision-making. To validate its utility, PM-AI was applied to a case-control study using data from TCGA and cBioPortal (including the AACR GENIE dataset). The study examined RAS mutations and their impact on the response to FOLFOX (folinic acid, 5-fluorouracil, and oxaliplatin) in colorectal cancer patients. Notably, the analysis incorporated race, ethnicity, and SDoH data, adhering to NASEM recommendations for population descriptors in genomics research, ensuring equitable and representative insights. Results: PM-AI successfully compared FOLFOX-treated patients with or without RAS mutations and revealed a significant difference in progression-free survival. The result show that KRAS mutations predict a poorer response to FOLFOX and an increased risk of recurrence. These findings were consistent with those reported in the literature, validating PM-AI’s independent analytical capabilities. Conclusion: The development of PM-AI represents a transformative advancement in precision medicine research, addressing key challenges in the integration of clinical, genomic, population-specific variables (race, ethnicity, etc.), and SDoH, into analytical pipelines. By eliminating the need for programming, PM-AI bridges domain expertise with autonomous workflows, empowering researchers across disciplines. Its versatility in handling cross-domain datasets highlights its adaptability to diverse precision medicine applications. Overall, PM-AI ensures equitable and actionable insights, positioning this advance AI system as a scalable tool for advancing precision medicine and promoting health equity in cancer research. Citation Format: Enrique I. Velazquez-Villarreal, Ei-Wen Yang. PM-AI agent: A conversational artificial intelligence system for precision medicine and advancing health equity through integrative clinical, genomic and social determinants of health data analysis [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2025; Part 1 (Regular Abstracts); 2025 Apr 25-30; Chicago, IL. Philadelphia (PA): AACR; Cancer Res 2025;85(8_Suppl_1):Abstract nr 1115.

The Integration of Artificial Intelligence in In Vitro Fertilization: A Comprehensive Narrative Review

ABSTRACT Artificial Intelligence (AI) in Assisted Reproductive Technology (ART) is transforming key areas of fertility treatments such as sperm collection, analysis of ovum quality, selection of embryos, genetic tests, customized treatment plans, stimulation protocols, as well as monitoring of equipment. This review article aims to review how every one of these fields is advanced by AI and the contribution to the precision, speed, and outcomes of the patients. Sperm selection in ART is enhanced by AI capacity in identifying and characterizing sperm quality through morphology, motility, and deoxyribonucleic acid (DNA) integrity, eliminating chances of human errors. A range of AI systems involves the procedure of selection and sorting of sperm in order to maximize fertilization and minimize contamination. Likewise, AI optimizes the assessment of ova quality by bringing in morphological evaluations and time-lapse video imaging for continuous observation of ova maturation. Predictive analytics in AI deal with large patient data to tailor treatment options, modify stimulation schedules, and increase the likelihood of pregnancy. In embryo selection, AI assesses morphological characteristics and developmental trends obtained from time-lapse imaging to select embryos with the best implantation chances. Combining it with genetic screening technologies, AI can identify genetic disorders on time to guarantee that only healthy genetic material is transferred. Moreover, artificial intelligence equipment tracking systems track equipment status and prognosis thus improving laboratory productivity and compliance with the relevant laws. On the ethical front, AI enhances matters of ownership, data protection, and patient safety through all these processes. With the help of AI, ART clinics can increase effectiveness, enhance patients’ satisfaction, and develop the field of fertility treatments to make them more available and affordable.

Patient information needs for transparent and trustworthy cardiovascular artificial intelligence: A qualitative study

As health systems incorporate artificial intelligence (AI) into various aspects of patient care, there is growing interest in understanding how to ensure transparent and trustworthy implementation. However, little attention has been given to what information patients need about these technologies to promote transparency of their use. We conducted three asynchronous online focus groups with 42 patients across the United States discussing perspectives on their information needs for trust and uptake of AI, focusing on its use in cardiovascular care. Data were analyzed using a rapid content analysis approach. Our results suggest that patients have a set of core information needs, including specific information factors pertaining to the AI tool, oversight, and healthcare experience, that are relevant to calibrating trust as well as perspectives concerning information delivery, disclosure, consent, and physician AI use. Identifying patient information needs is a critical starting point for calibrating trust in healthcare AI systems and designing strategies for information delivery. These findings highlight the importance of patient-centered engagement when developing AI model documentation and communicating and provisioning information about these technologies in clinical encounters.

Impact of AI in Healthcare

Abstract: Artificial Intelligence in Healthcare Artificial Intelligence (AI) is revolutionizing the healthcare industry by enabling smarter diagnostics, personalized treatments, efficient workflows, and data-driven decision-making. Through technologies such as machine learning, natural language processing, and computer vision, AI systems can analyze vast volumes of medical data to identify patterns, predict outcomes, and assist clinicians in making accurate diagnoses.

Educating the Next Generation of Ethical AI Practitioners

Artificial intelligence (AI) technologies are rapidly advancing, increasing concerns about data privacy harms in AI models. We discuss how ethical AI can be incorporated into computer science curricula. This paper describes the design process for the first ‘AI Privacy Engineering’ course, to the best of our knowledge, taught in the United States. The course is designed for both undergraduate and graduate students at Georgia Tech. Throughout this course, students examine ethical implications of AI system design, development, deployment, and utilization, using the ACM’s General Ethical Principles as an ethical framework. Recognizing that data privacy represents only one possible form of harm, the course blends theoretical and conceptual lectures with hands-on projects that require students to address ethical issues, including bias, fairness, and accountability in AI systems. Herein, we discuss the course design process, including selecting the appropriate body of knowledge, establishing learning objectives, creating assignments, and considering pedagogical methodologies we employed. We explain the empirical methods used to inform our design, including a systematic review of courses teaching AI development at over 40 universities. Our structured curriculum can be used to effectively teach ethical and safe AI, and we propose how these topics may be incorporated more broadly into computer science courses. Finally, we discuss early successes and the challenges faced while teaching the course, particularly in maintaining relevance despite fast-paced changes in the field of AI, an evolving legislative landscape, accessing computational systems to run AI models, and varying levels of student preparedness.

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.

Cybersecurity Threats and Mitigation Strategies in AI Applications

The integration of artificial intelligence (AI) into daily life and critical infrastructure has elevated the importance of addressing cybersecurity concerns within AI applications. While AI systems offer numerous benefits, such as enhanced efficiency, automation, and decision-making, they also introduce novel vulnerabilities and threats. Ensuring the security and reliability of these systems is crucial. This paper investigates key cybersecurity challenges associated with AI, including data privacy, integrity, adversarial attacks, and the ethical implications of AI in security. Additionally, it examines the role of Shapley Additive explainable AI in promoting transparency, allowing for greater interpretability of AI models and insights into decision-making processes.

Utilizing Machine Learning Techniques to Predict University Students' Digital Competence

Given the importance of possessing the digital competence (DC) required by the technological age, whether for teachers or students and even communities and governments, educational institutions in most countries have sought to benefit from modern technologies brought about by the technological revolution in developing learning and teaching and using modern technologies in providing educational services to learners. Since university students will have the doors to work opened in all fields, the research aims to know their level of DC in artificial intelligence (AI) applications and systems utilizing machine learning (ML) techniques. The descriptive approach was used, as the research community consisted of students from the University of Baghdad in its colleges with scientific and human specializations. To measure the level of DC, a questionnaire was applied as a data collection tool to a sample of 400 male and female students, distributed based on gender and academic specialization. The results showed that the sample students did not have high DC. Their possession of DC related to AI applications and systems was to a moderate degree. The results indicated that there were differences in the responses of the study sample members due to the gender variable and the specialization variable, in favor of the female students with scientific specialization.

The legitimacy of modern data processing in the workplace

The use of modern data processing in the workplace, such as algorithms, big data and artificial intelligence (AI) raises numerous legal questions, particularly in relation to labour law, non-discrimination law, and data protection regulations. A key issue is whether, and under what conditions, algorithms and AI systems can be lawfully employed in compliance with data protection laws. This article aims to delve deeper into the issue by outlining the legal framework, exploring current legal challenges through two recent examples, and offering further considerations based on these findings.

Advancements in IoT-Based Data Logging for Crop Evapotranspiration Monitoring: Trends and Challenges: A Review

The Internet of Things (IoT) integration with agriculture has brought revolutionary changes to the field of data collection and analysis through agricultural evapotranspiration (ET) monitoring. IoT data logging systems integrate advanced sensors with wireless networks and cloud computing which enable real-time monitoring of soil moisture as well as soil temperature and humidity and atmospheric environmental conditions. Through innovative technological developments farmers can establish precise irrigation systems that enhance water resources and yield production and respond effectively to environmental changes. The Internet of Things delivers essential functions for precise agriculture by enabling automatic data acquisition and distant system monitoring basics for better decision-making. Current advancements in ET technologies involve the manufacturing of advanced sensors which combine high accuracy capabilities with low power consumption while using advanced communication systems with extensive range capabilities and artificial intelligence systems for forecasting ET estimations. The slow adoption rate of IoT in agriculture is affected by several barriers including the high costs of implementation as well as rural area network connectivity problems and security risks related to data protection. Better future research will concentrate on sensor price reduction along with better network infrastructure and AI algorithms for optimizing ET prediction accuracy. Increasing reliability along with efficiency in IoT agricultural systems requires tackling these specific issues. The potential of monitoring ET rates through IoT technology shows great promise to transform how farmers manage their water supply. Global food security becomes more sustainable through IoT enabled data-driven irrigation which reduces water wastage and enables superior crop production.

Aptamer-functionalized graphene quantum dots combined with artificial intelligence detect bacteria for urinary tract infections

ObjectivesUrinary tract infection is one of the most prevalent forms of bacterial infection, and prompt and efficient identification of pathogenic bacteria plays a pivotal role in the management of urinary tract infections. In this study, we propose a novel approach utilizing aptamer-functionalized graphene quantum dots integrated with an artificial intelligence detection system (AG-AI detection system) for rapid and highly sensitive detection of Escherichia coli (E. coli).MethodsFirstly, graphene quantum dots were modified with the aptamer that can specifically recognize and bind to E. coli. Therefore, the fluorescence intensity of graphene quantum dots was positively correlated with the concentration of E. coli. Finally, the fluorescence images were processed by artificial intelligence system to obtain the result of bacterial concentration.ResultsThe AG-AI detection system, with wide linearity (103-109 CFU/mL) and a low detection limit (3.38×102 CFU/mL), can effectively differentiate between E. coli and other urinary tract infection bacteria. And the result of detection system is in good agreement with MALDI-TOF MS.ConclusionsThe detection system is an accurate and effective way to detect bacteria in urinary tract infections.

Unveiling the Potential of Large Language Models in Transforming Chronic Disease Management: Mixed Methods Systematic Review.

Chronic diseases are a major global health burden, accounting for nearly three-quarters of the deaths worldwide. Large language models (LLMs) are advanced artificial intelligence systems with transformative potential to optimize chronic disease management; however, robust evidence is lacking. This review aims to synthesize evidence on the feasibility, opportunities, and challenges of LLMs across the disease management spectrum, from prevention to screening, diagnosis, treatment, and long-term care. Following the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analysis) guidelines, 11 databases (Cochrane Central Register of Controlled Trials, CINAHL, Embase, IEEE Xplore, MEDLINE via Ovid, ProQuest Health & Medicine Collection, ScienceDirect, Scopus, Web of Science Core Collection, China National Knowledge Internet, and SinoMed) were searched on April 17, 2024. Intervention and simulation studies that examined LLMs in the management of chronic diseases were included. The methodological quality of the included studies was evaluated using a rating rubric designed for simulation-based research and the risk of bias in nonrandomized studies of interventions tool for quasi-experimental studies. Narrative analysis with descriptive figures was used to synthesize the study findings. Random-effects meta-analyses were conducted to assess the pooled effect estimates of the feasibility of LLMs in chronic disease management. A total of 20 studies examined general-purpose (n=17) and retrieval-augmented generation-enhanced LLMs (n=3) for the management of chronic diseases, including cancer, cardiovascular diseases, and metabolic disorders. LLMs demonstrated feasibility across the chronic disease management spectrum by generating relevant, comprehensible, and accurate health recommendations (pooled accurate rate 71%, 95% CI 0.59-0.83; I2=88.32%) with retrieval-augmented generation-enhanced LLMs having higher accuracy rates compared to general-purpose LLMs (odds ratio 2.89, 95% CI 1.83-4.58; I2=54.45%). LLMs facilitated equitable information access; increased patient awareness regarding ailments, preventive measures, and treatment options; and promoted self-management behaviors in lifestyle modification and symptom coping. Additionally, LLMs facilitate compassionate emotional support, social connections, and health care resources to improve the health outcomes of chronic diseases. However, LLMs face challenges in addressing privacy, language, and cultural issues; undertaking advanced tasks, including diagnosis, medication, and comorbidity management; and generating personalized regimens with real-time adjustments and multiple modalities. LLMs have demonstrated the potential to transform chronic disease management at the individual, social, and health care levels; however, their direct application in clinical settings is still in its infancy. A multifaceted approach that incorporates robust data security, domain-specific model fine-tuning, multimodal data integration, and wearables is crucial for the evolution of LLMs into invaluable adjuncts for health care professionals to transform chronic disease management. PROSPERO CRD42024545412; https://www.crd.york.ac.uk/PROSPERO/view/CRD42024545412.

The imperative of diversity and equity for the adoption of responsible AI in healthcare

Artificial Intelligence (AI) in healthcare holds transformative potential but faces critical challenges in ethical accountability and systemic inequities. Biases in AI models, such as lower diagnosis rates for Black women or gender stereotyping in Large Language Models, highlight the urgent need to address historical and structural inequalities in data and development processes. Disparities in clinical trials and datasets, often skewed toward high-income, English-speaking regions, amplify these issues. Moreover, the underrepresentation of marginalized groups among AI developers and researchers exacerbates these challenges. To ensure equitable AI, diverse data collection, federated data-sharing frameworks, and bias-correction techniques are essential. Structural initiatives, such as fairness audits, transparent AI model development processes, and early registration of clinical AI models, alongside inclusive global collaborations like TRAIN-Europe and CHAI, can drive responsible AI adoption. Prioritizing diversity in datasets and among developers and researchers, as well as implementing transparent governance will foster AI systems that uphold ethical principles and deliver equitable healthcare outcomes globally.

AI and Social Interactions: How Artificial Intelligence is Shaping Human Psychology and Social Dynamics

People's socializing tendencies have been profoundly changed by the use and acceptance of AI equipment. With an emphasis on motivated involvement and interaction actions, this research looks at how artificial intelligence (AI) affects people psychologically. The goal of the project is to provide a conceptual structure for understanding how innovations and advancements in AI technology affect the request, conduct, and intellect of individuals. Surveys and qualitative methods were used to test the study concepts. The results demonstrated a good correlation between empathy and artificial intelligence (AI), as well as a positive relationship between cognitive integration and each person's awareness level. The invention is encouraged by the psychological association between considerable data proficiency and the intermediate level of mental drive. To support personal growth, the research aims to shine a light on how AI technology influences unique creative attitudes and explain the conduct, drive, and cognitive aspects of AI systems from the social-psychological standpoint.

Detection of diabetic macular oedema patterns with fine-grained image categorisation on optical coherence tomography

PurposeTo develop an artificial intelligence (AI) system for detecting pathological patterns of diabetic macular oedema (DME) with fine-grained image categorisation using optical coherence tomography (OCT) images.MethodsThe development of the AI...

Artificial intelligence-assisted esophagogastroduodenoscopy improves procedure quality for endoscopists in early stages of training

AbstractCompleteness of esophagagogastroduodenoscopy (EGD) varies among endoscopists, leading to a high miss rate for gastric neoplasms. This study aimed to determine the effect of the Cerebro real-time artificial intelligence (AI) system on completeness of EGD for endoscopists in early stages of training.The AI system was built with CNN and Motion Adaptive Temporal Feature Aggregation (MA-TFA). A prospective sequential cohort study was conducted. Endoscopists were taught about the standardized EGD protocol to examine 27 sites. Then, each subject performed diagnostic EGDs per protocol (control arm). After completion of the required sample size, subjects performed diagnostic EGDs with assistance of the AI (study arm). The primary outcome was the rate of completeness of EGD. Secondary outcomes included overall inspection time, individual site inspection time, completeness of photodocumentation, and rate of positive pathologies.A total of 466 EGDs were performed with 233 in each group. Use of AI significantly improved completeness of EGD [mean (SD) (92.6% (6.2%) vs 71.2% (16.8%)]; P <0.001 (95% confidence interval 19.2%–23.8%, SD 0.012). There was no difference in overall mean (SD) inspection time [765.5 (338.4) seconds vs 740.4 (266.2); P=0.374]. Mean (SD) number of photos for photo-documentation significantly increased in the AI group [26.9 (0.4) vs 10.3 (4.4); P <0.001]. There was no difference in detection rates for pathologies in the two groups [8/233 (3.43%) vs 5/233 (2.16%), P=0.399].Completeness of EGD examination and photodocumentation by endoscopists in early stages of are improved by the AI-assisted software Cerebro.