Artificial Intelligence Products Research Articles

Protocol for evaluating the fitness for purpose of an artificial intelligence product for radiology reporting in the BreastScreen New South Wales breast cancer screening programme

IntroductionRadiologist shortages threaten the sustainability of breast cancer screening programmes. Artificial intelligence (AI) products that can interpret mammograms could mitigate this risk. While previous studies have suggested this technology has...

Hybrid Method for User Review Sentiment Categorization in ChatGPT Application Using N-Gram and Word2Vec Features

The rapid development of Artificial Intelligence (AI) has significantly influenced nearly all aspects of life. One AI product widely used by people worldwide is the Chat Generative Pre-Training Transformer (ChatGPT), which can respond to questions conversationally. Although data indicates that the use of ChatGPT in Indonesia is less widespread than in other countries, a Populix survey reveals that half of the respondents have utilized ChatGPT, using AI more than once a month. This indicates its crucial role among the Indonesian population. ChatGPT is not limited to browsers; it is also available as a downloadable application on the Google Play Store. The ChatGPT application has garnered various user reviews, particularly those from Indonesia. Therefore, this research employs the Naïve Bayes Classifier and K-Means Clustering to classify sentiments and group user reviews of the ChatGPT application originating from Indonesia. The study utilizes TF-IDF and Word2Vec as feature extraction methods, combining various N-Gram in data preprocessing to consider the context of sequentially arranged words that may carry meaning. The best classification results are obtained from the trigram classification model, as indicated by precision, recall, and accuracy values of 0.99 each, along with an F1-score of 1. Clustering also yields positive results, with some overlapping, yet words within clusters exhibit high similarity. Categorization results suggest that user reviews of the ChatGPT application from Indonesia tend to be positive, expressing satisfaction impressions, providing feedback for feature development, and expressing hope for the continued availability of the accessible version of ChatGPT due to its remarkable benefits.

Big Data Analysis and Deep Learning Optimization in Artificial Intelligence Production of Information Enterprises

Intelligent manufacturing technology is required to upgrade existing enterprises' management and production operations. To construct a ground breaking fusion structure, this project unites the theoretical underpinnings, technical breakthroughs, and applications of data analytics, optimisation, and intelligent production engineering. It is driven by China's desire of cutting-edge commodities and efficient growth methods. This research establishes the broad framework for merging optimisation and data analytics. There is a list of data analytics and system optimisation technologies that can address important challenges with intelligent manufacturing. By integrating data analytics and optimisation, businesses may better forecasting and management of new terrain, as well as reveal hidden information to increase decision-making efficacy.

The advent of ChatGPT: Job Made Easy or Job Loss to Data Analysts

Artificial Intelligence (AI) has proven valuable in almost every field of endeavour, including education, sciences, engineering, technology, medical sciences, and numerous other areas of application. Despite its widespread usefulness, concerns have arisen about AI potentially displacing jobs due to its highly advanced capabilities, commonly called the "god-man effect." One remarkable AI product is ChatGPT, a Chatbot developed by an open AI company in the USA that is capable of engaging in conversations that resemble human interactions. This study explores the strengths and limitations of ChatGPT for data analysis, with the primary objective of assessing whether ChatGPT poses a threat to the job of data analysts. An econometric dataset with a sample size of thirty (30), which consists of one dependent variable and three independent variables, was simulated. The dataset was intentionally generated with issues like multicollinearity, outliers, and heteroscedasticity. Subsequently, multiple tests were conducted on the datasets to confirm the presence of these problems. The ChatGPT 3.5 and 4.0 versions were then used to analyse the data to examine this chatbot's prowess in performing data analysis. ChatGPT 3.5 and 4.0 accurately predicted the suitable statistical tool for analyzing the simulated datasets. Both versions of ChatGPT emphasized that the expertise of a professional data analyst would be necessary. While they could offer guidance on data analysis, they cannot perform the analysis themselves as they are solely AI models. ChatGPT can help with what to do next when a data analyst gets stuck. However, they should not be recognized as an authority in making statistical decisions. Therefore, ChatGPT may not replace data analysts but could make their job easier by serving as a helpful resource to turn to when they encounter challenges.

Human bias in evaluating AI product creativity

This study investigated the evaluation behavior of products generated by artificial intelligence (AI) by manipulating the creativity of rating stimuli according to their high and low novelty and usefulness. In addition, we analyzed the effect of perception of the generative AI on creativity ratings. We found a bias toward lower creativity ratings only for highly useful products when they were identified as AI-generated, and this bias was particularly strong for individuals with greater perceived threat from the generative AI. Our research highlights the importance of product attribute quality and producer identity in creativity ratings, and provides implications for the integration of AI into creative industries.

Considering the Secondary Use of Clinical and Educational Data to Facilitate the Development of Artificial Intelligence Models.

Medical training programs and health care systems collect ever-increasing amounts of educational and clinical data. These data are collected with the primary purpose of supporting either trainee learning or patient care. Well-established principles guide the secondary use of these data for program evaluation and quality improvement initiatives. More recently, however, these clinical and educational data are also increasingly being used to train artificial intelligence (AI) models. The implications of this relatively unique secondary use of data have not been well explored. These models can support the development of sophisticated AI products that can be commercialized. While these products have the potential to support and improve the educational system, there are challenges related to validity, patient and learner consent, and biased or discriminatory outputs. The authors consider the implications of developing AI models and products using educational and clinical data from learners, discuss the uses of these products within medical education, and outline considerations that should guide the appropriate use of data for this purpose. These issues are further explored by examining how they have been navigated in an educational collaborative.

Applications of Deep Learning in Trauma Radiology: A Narrative Review

Diagnostic imaging is essential in modern trauma care for initial evaluation and identifying injuries requiring intervention. Deep learning (DL) has become mainstream in medical image analysis and has shown promising efficacy for classification, segmentation, and lesion detection. This narrative review provides the fundamental concepts for developing DL algorithms in trauma imaging and presents an overview of current progress in each modality. DL has been applied to detect free fluid on Focused Assessment with Sonography for Trauma (FAST), traumatic findings on chest and pelvic X-rays, and computed tomography (CT) scans, identify intracranial hemorrhage on head CT, detect vertebral fractures, and identify injuries to organs like the spleen, liver, and lungs on abdominal and chest CT. Future directions involve expanding dataset size and diversity through federated learning, enhancing model explainability and transparency to build clinician trust, and integrating multimodal data to provide more meaningful insights into traumatic injuries. Though some commercial artificial intelligence products are Food and Drug Administration-approved for clinical use in the trauma field, adoption remains limited, highlighting the need for multi-disciplinary teams to engineer practical, real-world solutions. Overall, DL shows immense potential to improve the efficiency and accuracy of trauma imaging, but thoughtful development and validation are critical to ensure these technologies positively impact patient care.

Product information recognition in the retail domain as an MRC problem

This paper presents the task of recognizing product information (PI) (i.e., product names, prices, materials, etc.) mentioned in customer statements. This is one of the key components in developing artificial intelligence products to enable businesses to listen to their customers, adapt to market dynamics, continuously improve their products and services, and improve customer engagement by enhancing effectiveness of a chatbot. To this end, natural language processing (NLP) tools are commonly used to formulate the task as a traditional sequence labeling problem. However, in this paper, we bring the power of machine reading comprehension (MRC) tasks to propose another, alternative approach. In this setting, determining product information types is the same as asking “Which PI types are referenced in the statement?” For example, extracting product names (which corresponds to the label PRO_NAME) is cast as retrieving answer spans to the question “Which instances of product names are mentioned here?” We perform extensive experiments on a Vietnamese public dataset. The experimental results show the robustness of the proposed alternative method. It boosts the performance of the recognition model over the two robust baselines, giving a significant improvement. We achieved 92.87% in the F1 score on recognizing product descriptions at Level 1. At Level 2, the model yielded 93.34% in the F1 score on recognizing each product information type.

A comprehensive approach to safety for highly automated off-road machinery under Regulation 2023/1230

As of January 2027, Machine Safety Regulation 2023/1230 replaces Directive 2006/42/EC, and a proposal for the regulation of Artificial Intelligence (AI) systems is soon to be ratified by the European Council. These legislative changes address hazards from increased automation and AI integration. Original Equipment Manufacturers (OEMs) face compliance challenges due to a lack of standardized guidelines, especially for off-road machinery with level 4 ‘high automation’ capabilities.At level 4 ‘high automation’, the machine operator assumes a supervisory role, intervening only in situations beyond the designed operational domain. Relying solely on supervisor intervention at this level of automation is unreasonable. Within this context, legislative safety requirements to maintain safety advocate for robust risk management systems, including both a human-in-the-loop safety option and adequate safety-related decision-making by the level 4 ‘high automation’ off-road machine, i.e., the safe reasoning software becomes paramount.In this research, conducted through a systematic mapping study, we discuss emerging safety trends and integration for the safe reasoning software a level 4 off-road machine requires. Our analyses shows the necessity of safety constraint-based design procedures. These procedures involve constraining the AI system by embedding fault management, reasoning checks, and diagnostic monitoring together with safety-related decision-making, thereby enhancing functional reliability and reducing risks. We consider these trends and patterns through the lens of changing machine safety legislative requirements, and the proposal of the regulation of AI products. Illustrating their implications alongside a case study of a level 4 tree harvesting machine, for a tangible and to industry transferable perspective on our results.

Feedback Beamforming in the Time Domain.

Real-time source localization is crucial for high-end automation and artificial intelligence (AI) products. However, a low signal-to-noise ratio (SNR) and limited processing time can reduce localization accuracy. This work proposes a new architecture for a time-domain feedback-based beamformer that meets real-time processing demands. The main objective of this design is to locate reflective sources by estimating their direction of arrival (DOA) and signal range. Incorporating a feedback mechanism in this architecture refines localization precision, a unique aspect of this approach. We conducted an in-depth analysis to compare the effectiveness of time-domain feedback beamforming against conventional time-domain methods, highlighting their benefits and limitations. Our evaluation of the proposed architecture, based on critical performance indicators such as peak-to-sidelobe ratio, mainlobe width, and directivity factor, demonstrates its ability to improve beamformer effectiveness significantly.

Research on Machine Learning Copyright

A new round of scientific and technological revolution and industrial transformation led by artificial intelligence is on the rise. Driven by new theories and technologies, artificial intelligence presents new features such as deep learning, cross-border integration, human-machine collaboration, swarm intelligence openness, and autonomous control, and is having a significant and far-reaching impact on economic development, social progress, and global governance. Artificial intelligence technology has made a leap forward, and the ensuing legal issues have aroused discussions in the academic and practical circles, mainly focusing on the copyright law of artificial intelligence products, including the legal attribute of the generated results and its protection path, as well as exploring the new path of machine learning infringement risk and its compliance governance.

A multi-skilled staff scheduling and team configuration optimisation model for artificial intelligence project portfolio considering competence development and innovation-driven

This paper emphasises the pivotal role of enhancing research and development (R&D) staff competence and boosting team innovation efficiency in configuring R&D project teams for artificial intelligence (AI) product development. Diverging from traditional studies primarily focused on time, quality, and cost objectives, this study proposes prioritising the skill increments of staff and team diversity, aligning with the overarching goals of the R&D cycle. Targeting multi-skilled R&D personnel for scheduling and configuration, a three-objective tradeoff optimisation model is established. The nonlinear mixed-integer constrained programming model incorporates a learning effect for calculating employee skill value and employs a heterogeneity efficiency formula for assessing team diversity, particularly emphasising the diversity of R&D personnel research backgrounds. An algorithm based on Non-dominated Sorting Genetic Algorithm-II (NSGA-II) is designed to obtain the approximate Pareto optimal solution. Furthermore, it compares the algorithm with the multi-objective particle swarm optimisation (MOPSO), explores practical decision-making methods for Pareto solutions, and conducts sensitivity analyses on the learning rate and diversity level. Our research is relevant to enterprises seeking to enhance R&D capabilities with a certain degree of homogeneity among R&D employees. This paper exemplifies and validates the proposed model and solution approach using a new AI product from a healthcare company.

The impact of artificial intelligence technology innovation on economic development -- from the perspective of generative AI products

The new generation of artificial intelligence products, represented by ChatGPT and Wenyan Yixin, is rapidly and extensively integrating into human production and life at an unprecedented pace, breadth, and depth. Generative artificial intelligence possesses distinct characteristics and functionalities compared to rule-based artificial intelligence, exerting a more prominent dual impact on the high-quality development of China's economy. On the one hand, it can promote high-quality economic development through empowering effects such as innovation-driven effects, enhanced production efficiency, and industrial transformation and upgrading effects. On the other hand, it may give rise to deep-seated risks, including labor market disruptions, market monopolization issues, national security risks, and misinformation phenomena, which could hinder high-quality economic development. It is crucial to have a correct understanding and a scientific approach, leveraging its positive effects while proactively addressing negative impacts, guiding it to better serve the needs of China's high-quality economic development.

A typology of artificial intelligence data work

This article provides a new typology for understanding human labour integrated into the production of artificial intelligence systems through data preparation and model evaluation. We call these forms of labour ‘AI data work’ and show how they are an important and necessary element of the artificial intelligence production process. We draw on fieldwork with an artificial intelligence data business process outsourcing centre specialising in computer vision data, alongside a decade of fieldwork with microwork platforms, business process outsourcing, and artificial intelligence companies to help dispel confusion around the multiple concepts and frames that encompass artificial intelligence data work including ‘ghost work’, ‘microwork’, ‘crowdwork’ and ‘cloudwork’. We argue that these different frames of reference obscure important differences between how this labour is organised in different contexts. The article provides a conceptual division between the different types of artificial intelligence data work institutions and the different stages of what we call the artificial intelligence data pipeline. This article thus contributes to our understanding of how the practices of workers become a valuable commodity integrated into global artificial intelligence production networks.

Information communication technology, economic growth, natural resources, and renewable energy production: Evaluating the asymmetric and symmetric impacts of artificial intelligence in robotics and innovative economies

The ongoing integration of artificial intelligence (AI) into the fundamental fabric of society constitutes a transformative process, with the potential to exert profound influence on various facets of human existence including environmental quality. Our research investigates the interaction of AI and renewable energy production in 22 leading robotics and innovative countries, providing crucial insights into a previously underexplored domain. The study's novelty and originality are in demonstrating the precise impact of AI in enhancing and revolutionizing renewable energy production, consequently addressing, and filling a critical study gap. Our analysis comprises both asymmetric and symmetric assumptions to cover the positive and negative shocks of artificial intelligence on renewable energy from 1991 to 2020. The findings from the panel NARDL analysis provide substantial support for the profound impact of changes in artificial intelligence (AI) on the substantial stimulation of renewable energy in the long-run. Furthermore, AI plays a substantial role in enhancing long-term renewable energy production in the panel symmetric ARDL. In the country-specific investigation, it is found that Austria, Germany, and New Zealand are the nations where both affirmative and adverse changes in AI improve clean energy structure significantly in the short run. Natural resources, information communication technology (ICT), and economic growth also enhance renewable energy production. Finally, policies are directed to increase renewable energy production.

Coverage of Artificial Intelligence in Media

Artificial intelligence (AI) is an important catalyst that enables media associations to optimize and ameliorate their operations. The aim of the paper is to emphasize the significance and eventuality of AI during high- performance data analytics and media content generation. The focus is on responsible and ethically respectable use of AI, which imposes the need to continuously make trust, through multitudinous challenges, during the operation of implicit pitfalls. Standardization and obligatory publication of AI product data can pave the way for increased translucency and trust structure. Else, the power of AI, which has a huge eventuality to contribute to a better quality of life, could be converted into a suicide device.

Integrating Artificial Intelligence for Advancing Multiple-Cancer Early Detection via Serum Biomarkers: A Narrative Review.

The concept and policies of multicancer early detection (MCED) have gained significant attention from governments worldwide in recent years. In the era of burgeoning artificial intelligence (AI) technology, the integration of MCED with AI has become a prevailing trend, giving rise to a plethora of MCED AI products. However, due to the heterogeneity of both the detection targets and the AI technologies, the overall diversity of MCED AI products remains considerable. The types of detection targets encompass protein biomarkers, cell-free DNA, or combinations of these biomarkers. In the development of AI models, different model training approaches are employed, including datasets of case-control studies or real-world cancer screening datasets. Various validation techniques, such as cross-validation, location-wise validation, and time-wise validation, are used. All of the factors show significant impacts on the predictive efficacy of MCED AIs. After the completion of AI model development, deploying the MCED AIs in clinical practice presents numerous challenges, including presenting the predictive reports, identifying the potential locations and types of tumors, and addressing cancer-related information, such as clinical follow-up and treatment. This study reviews several mature MCED AI products currently available in the market, detecting their composing factors from serum biomarker detection, MCED AI training/validation, and the clinical application. This review illuminates the challenges encountered by existing MCED AI products across these stages, offering insights into the continued development and obstacles within the field of MCED AI.

A trustworthy AI reality-check: the lack of transparency of artificial intelligence products in healthcare.

Trustworthy medical AI requires transparency about the development and testing of underlying algorithms to identify biases and communicate potential risks of harm. Abundant guidance exists on how to achieve transparency for medical AI products, but it is unclear whether publicly available information adequately informs about their risks. To assess this, we retrieved public documentation on the 14 available CE-certified AI-based radiology products of the II b risk category in the EU from vendor websites, scientific publications, and the European EUDAMED database. Using a self-designed survey, we reported on their development, validation, ethical considerations, and deployment caveats, according to trustworthy AI guidelines. We scored each question with either 0, 0.5, or 1, to rate if the required information was "unavailable", "partially available," or "fully available." The transparency of each product was calculated relative to all 55 questions. Transparency scores ranged from 6.4% to 60.9%, with a median of 29.1%. Major transparency gaps included missing documentation on training data, ethical considerations, and limitations for deployment. Ethical aspects like consent, safety monitoring, and GDPR-compliance were rarely documented. Furthermore, deployment caveats for different demographics and medical settings were scarce. In conclusion, public documentation of authorized medical AI products in Europe lacks sufficient public transparency to inform about safety and risks. We call on lawmakers and regulators to establish legally mandated requirements for public and substantive transparency to fulfill the promise of trustworthy AI for health.

How AI should be used in radiology: assessing ambiguity and completeness of intended use statements of commercial AI products

BackgroundIntended use statements (IUSs) are mandatory to obtain regulatory clearance for artificial intelligence (AI)-based medical devices in the European Union. In order to guide the safe use of AI-based medical devices, IUSs need to contain comprehensive and understandable information. This study analyzes the IUSs of CE-marked AI products listed on AIforRadiology.com for ambiguity and completeness.MethodsWe retrieved 157 IUSs of CE-marked AI products listed on AIforRadiology.com in September 2022. Duplicate products (n = 1), discontinued products (n = 3), and duplicate statements (n = 14) were excluded. The resulting IUSs were assessed for the presence of 6 items: medical indication, part of the body, patient population, user profile, use environment, and operating principle. Disclaimers, defined as contra-indications or warnings in the IUS, were identified and compared with claims.ResultsOf 139 AI products, the majority (n = 78) of IUSs mentioned 3 or less items. IUSs of only 7 products mentioned all 6 items. The intended body part (n = 115) and the operating principle (n = 116) were the most frequently mentioned components, while the intended use environment (n = 24) and intended patient population (n = 29) were mentioned less frequently. Fifty-six statements contained disclaimers that conflicted with the claims in 13 cases.ConclusionThe majority of IUSs of CE-marked AI-based medical devices lack substantial information and, in few cases, contradict the claims of the product.Critical relevance statementTo ensure correct usage and to avoid off-label use or foreseeable misuse of AI-based medical devices in radiology, manufacturers are encouraged to provide more comprehensive and less ambiguous intended use statements.Key points• Radiologists must know AI products’ intended use to avoid off-label use or misuse.• Ninety-five percent (n = 132/139) of the intended use statements analyzed were incomplete.• Nine percent (n = 13) of the intended use statements held disclaimers contradicting the claim of the AI product.• Manufacturers and regulatory bodies must ensure that intended use statements are comprehensive.Graphical

Proceedings From the 2022 ACR-RSNA Workshop on Safety, Effectiveness, Reliability, and Transparency in AI

Despite the surge in artificial intelligence (AI) development for health care applications, particularly for medical imaging applications, there has been limited adoption of such AI tools into clinical practice. During a 1-day workshop in November 2022, co-organized by the ACR and the RSNA, participants outlined experiences and problems with implementing AI in clinical practice, defined the needs of various stakeholders in the AI ecosystem, and elicited potential solutions and strategies related to the safety, effectiveness, reliability, and transparency of AI algorithms. Participants included radiologists from academic and community radiology practices, informatics leaders responsible for AI implementation, regulatory agency employees, and specialty society representatives. The major themes that emerged fell into two categories: (1) AI product development and (2) implementation of AI-based applications in clinical practice. In particular, participants highlighted key aspects of AI product development to include clear clinical task definitions; well-curated data from diverse geographic, economic, and health care settings; standards and mechanisms to monitor model reliability; and transparency regarding model performance, both in controlled and real-world settings. For implementation, participants emphasized the need for strong institutional governance; systematic evaluation, selection, and validation methods conducted by local teams; seamless integration into the clinical workflow; performance monitoring and support by local teams; performance monitoring by external entities; and alignment of incentives through credentialing and reimbursement. Participants predicted that clinical implementation of AI in radiology will continue to be limited until the safety, effectiveness, reliability, and transparency of such tools are more fully addressed.