The Regulation of Artificial Intelligence in Digital Radiology in the Scientific Literature: A Narrative Review of Reviews

Artificial Intelligence-Based Software as a Medical Device (AI-SaMD): A Systematic Review

Background/Objectives: Artificial intelligence-based software as a medical device (AI-SaMD) refers to AI-powered software used for medical purposes without being embedded in physical devices. Despite increasing approvals over the past decade, research in this domain-spanning technology, healthcare, and national security-remains limited. This research aims to bridge the existing research gap in AI-SaMD by systematically reviewing the literature from the past decade, with the aim of classifying key findings, identifying critical challenges, and synthesizing insights related to technological, clinical, and regulatory aspects of AI-SaMD. Methods: A systematic literature review based on the PRISMA framework was performed to select the relevant AI-SaMD studies published between 2015 and 2024 in order to uncover key themes such as publication venues, geographical trends, key challenges, and research gaps. Results: Most studies focus on specialized clinical settings like radiology and ophthalmology rather than general clinical practice. Key challenges to implement AI-SaMD include regulatory issues (e.g., regulatory frameworks), AI malpractice (e.g., explainability and expert oversight), and data governance (e.g., privacy and data sharing). Existing research emphasizes the importance of (1) addressing the regulatory problems through the specific duties of regulatory authorities, (2) interdisciplinary collaboration, (3) clinician training, (4) the seamless integration of AI-SaMD with healthcare software systems (e.g., electronic health records), and (5) the rigorous validation of AI-SaMD models to ensure effective implementation. Conclusions: This study offers valuable insights for diverse stakeholders, emphasizing the need to move beyond theoretical analyses and prioritize practical, experimental research to advance the real-world application of AI-SaMDs. This study concludes by outlining future research directions and emphasizing the limitations of the predominantly theoretical approaches currently available.

Advancements in Digital Cytopathology Since COVID-19: Insights from a Narrative Review of Review Articles

Background/Objectives: The integration of digitalization in cytopathology is an emerging field with transformative potential, aiming to enhance diagnostic precision and operational efficiency. This narrative review of reviews (NRR) seeks to identify prevailing themes, opportunities, challenges, and recommendations related to the process of digitalization in cytopathology. Methods: Utilizing a standardized checklist and quality control procedures, this review examines recent advancements and future implications in this domain. Twenty-one review studies were selected through a systematic process. Results: The results highlight key emerging trends, themes, opportunities, challenges, and recommendations in digital cytopathology. First, the study identifies pivotal themes that reflect the ongoing technological transformation, guiding future focus areas in the field. A major trend is the integration of artificial intelligence (AI), which is increasingly critical in improving diagnostic accuracy, streamlining workflows, and assisting decision making. Notably, emerging AI technologies like large language models (LLMs) and chatbots are expected to provide real-time support and automate tasks, though concerns around ethics and privacy must be addressed. The reviews also emphasize the need for standardized protocols, comprehensive training, and rigorous validation to ensure AI tools are reliable and effective across clinical settings. Lastly, digital cytopathology holds significant potential to improve healthcare accessibility, especially in remote areas, by enabling faster, more efficient diagnoses and fostering global collaboration through telepathology. Conclusions: Overall, this study highlights the transformative impact of digitalization in cytopathology, improving diagnostic accuracy, efficiency, and global accessibility through tools like whole-slide imaging and telepathology. While artificial intelligence plays a significant role, the broader focus is on integrating digital solutions to enhance workflows and collaboration. Addressing challenges such as standardization, training, and ethical considerations is crucial to fully realize the potential of these advancements.

Integrating AI and Assistive Technologies in Healthcare: Insights from a Narrative Review of Reviews

The integration of artificial intelligence (AI) into assistive technologies is an emerging field with transformative potential, aimed at enhancing autonomy and quality of life for individuals with disabilities and aging populations. This overview of reviews, utilizing a standardized checklist and quality control procedures, examines recent advancements and future implications in this domain. The search for articles for the review was finalized by 15 December 2024. Nineteen review studies were selected through a systematic process identifying prevailing themes, opportunities, challenges, and recommendations regarding the integration of AI in assistive technologies. First, AI is increasingly central to improving mobility, healthcare diagnostics, and cognitive support, enabling personalized and adaptive solutions for users. The integration of AI into traditional assistive technologies, such as smart wheelchairs and exoskeletons, enhances their performance, creating more intuitive and responsive devices. Additionally, AI is improving the inclusion of children with autism spectrum disorders, promoting social interaction and cognitive development through innovative devices. The review also identifies significant opportunities and challenges. AI-powered assistive technologies offer enormous potential to increase independence, reduce reliance on external support, and improve communication for individuals with cognitive disorders. However, challenges such as personalization, digital literacy among the elderly, and privacy concerns in healthcare contexts need to be addressed. Notably, AI itself is expanding the concept of assistive technology, shifting from traditional tools to intelligent systems capable of learning and adapting to individual needs. This evolution represents a fundamental change in assistive technology, emphasizing dynamic, adaptive systems over static solutions. Finally, the study emphasizes the growing economic investment in this sector, forecasting significant market growth, with AI-driven assistive devices poised to transform the landscape. Despite challenges such as high development costs and regulatory hurdles, opportunities for innovation and affordability remain. This review underscores the importance of addressing challenges related to standardization, accessibility, and ethical considerations to ensure the successful integration of AI into assistive technologies, fostering greater inclusivity and improved quality of life for users globally.

The use of predetermined change control plans to enable the release of new versions of software as a medical device

OBJECTIVES

This study investigates how Predetermined Change Control Plans (PCCPs) can support the Software Development Life Cycle (SDLC) of certain Software as a Medical Device (SaMD).

METHODS

Targeted surveys collected qualitative and quantitative data on the current regulatory change process for SaMD; the use of PCCPs; the potential parameters of PCCPs in terms of technical, clinical, usability, and administrative changes to SaMD; and whether PCCPs could be used more broadly for all SaMDs.

RESULTS

Results indicate that the current regulatory approach is not fit for purpose, specifically regarding fast-moving SaMD or continuous-learning AI SaMD. There was strong support for PCCPs to cover device technology, usability, and administrative changes, while clinical changes had limited support and required further investigation. The EU lags behind the US and now the UK in addressing these challenges and should look to legislate and implement PCCPs to ensure ongoing innovation and investment in digital health technologies.

CONCLUSION

This work is novel in the gathering of meaningful input from experts, practitioners, and regulatory professionals within the SaMD industry located in the EU, UK, and US on the value and need for PCCPs. This study has implications for practice and policy as it can inform SaMD guidance and legislation.

Integrating Ethical Principles Into the Regulation of AI-Driven Medical Software

In recent years, a sharp increase in artificial intelligence (AI)-based software as medical devices has been seen in the United States and the European Union. Despite the huge potential of these devices in alleviating suffering through rapid identification and early intervention, their adoption in clinical practice has remained relatively slow due to ethical questions surrounding their usage. Even though there is no universal framework for the approval of these devices, the guiding principles behind individual regulatory bodies almost stay the same, with some more focused on the technical aspect while others involving the ethical aspects as well. The International Medical Device Regulators Forum devised a SaMD Working Group to outline the essential controls guiding the approval of these devices, but there is a lack of a structured approach for the regulatory approval process. This article outlines the principles of medical ethics, such as autonomy, beneficence, and fair distribution of healthcare sources, and how they relate to the use of AI-based devices. The core regulatory guidelines are then viewed in light of these ethical principles. We recommend that a comprehensive regulatory framework with integration of principles of medical ethics be made public. Though no universally accepted framework is available, regulating quality management, risk assessment, and data privacy would help build trust to promote the adoption of AI in healthcare.

Computational Nuclear Oncology Toward Precision Radiopharmaceutical Therapies: Ethical, Regulatory, and Socioeconomic Dimensions of Theranostic Digital Twins

Computational nuclear oncology for precision radiopharmaceutical therapy (RPT) is a new frontier for theranostic treatment personalization. A key strategy relies on the possibility to incorporate clinical, biomarker, image-based, and dosimetric information in theranostic digital twins (TDTs) of patients to move beyond a one-size-fits-all approach. The TDT framework enables treatment optimization by real-time monitoring of the real-world system, simulation of different treatment scenarios, and prediction of resulting treatment outcomes, as well as facilitating collaboration and knowledge sharing among health care professionals adopting a harmonized TDT. To this aim, the major social, ethical, and regulatory challenges related to TDT implementation and adoption have been analyzed. Methods: The artificial intelligence-dosimetry working group of the Society of Nuclear Medicine and Molecular Imaging is actively proposing, motivating, and developing the field of computational nuclear oncology, a unified set of scientific principles and mathematic models that describe the hierarchy of etiologic mechanisms involved in RPT dose response. The major social, ethical, and regulatory challenges to realize TDTs have been highlighted from the literature and discussed within the working group, and possible solutions have been identified. Results: This technology demands the implementation of advanced computational tools, harmonized and standardized collection of large real-time data, and modeling protocols to enable interoperability across institutions. However, current legislations limit data sharing despite TDTs' benefiting from such data. Although anonymizing data is often sufficient, ethical concerns may prevent sharing without patient consent. Approaches such as seeking ethical approval, adopting federated learning, and following guidelines can address this issue. Accurate and updated data input is crucial for reliable TDT output. Lack of reimbursement for data processing in treatment planning and verification poses an economic barrier. Ownership of TDTs, especially in interconnected systems, requires clear contracts to allocate liability. Complex contracts may hinder TDT implementation. Robust security measures are necessary to protect against data breaches. Cross-border data sharing complicates risk management without a global framework. Conclusion: A mechanism-based TDT framework can guide the community toward personalized dosimetry-driven RPT by facilitating the information exchange necessary to identify robust prognostic or predictive dosimetry and biomarkers. Although the future is bright, we caution that care must be taken to ensure that TDT technology is implemented in a socially responsible manner.

Developing technologies to assess vascular ageing: a roadmap from VascAgeNet

Vascular ageing (vascular ageing) is the deterioration of arterial structure and function which occurs naturally with age, and which can be accelerated with disease. Measurements of vascular ageing are emerging as markers of cardiovascular risk, with potential applications in disease diagnosis and prognosis, and for guiding treatments. However, vascular ageing is not yet routinely assessed in clinical practice. A key step towards this is the development of technologies to assess vascular ageing. In this Roadmap, experts discuss several aspects of this process, including: measurement technologies; the development pipeline; clinical applications; and future research directions. The Roadmap summarises the state of the art, outlines the major challenges to overcome, and identifies potential future research directions to address these challenges.

Precision Metrics: A Narrative Review on Unlocking the Power of KPIs in Radiology for Enhanced Precision Medicine

(Background) Over the years, there has been increasing interest in adopting a quality approach in radiology, leading to the strategic pursuit of specific and key performance indicators (KPIs). These indicators in radiology can have significant impacts ranging from radiation protection to integration into digital healthcare. (Purpose) This study aimed to conduct a narrative review on the integration of key performance indicators (KPIs) in radiology with specific key questions. (Methods) This review utilized a standardized checklist for narrative reviews, including the ANDJ Narrative Checklist, to ensure thoroughness and consistency. Searches were performed on PubMed, Scopus, and Google Scholar using a combination of keywords related to radiology and KPIs, with Boolean logic to refine results. From an initial yield of 211 studies, 127 were excluded due to a lack of focus on KPIs. The remaining 84 studies were assessed for clarity, design, and methodology, with 26 ultimately selected for detailed review. The evaluation process involved multiple assessors to minimize bias and ensure a rigorous analysis. (Results and Discussion) This overview highlights the following: KPIs are crucial for advancing radiology by supporting the evolution of imaging technologies (e.g., CT, MRI) and integrating emerging technologies like AI and AR/VR. They ensure high standards in diagnostic accuracy, image quality, and operational efficiency, enhancing diagnostic capabilities and streamlining workflows. KPIs are vital for radiological safety, measuring adherence to protocols that minimize radiation exposure and protect patients. The effective integration of KPIs into healthcare systems requires systematic development, validation, and standardization, supported by national and international initiatives. Addressing challenges like CAD-CAM technology and home-based radiology is essential. Developing specialized KPIs for new technologies will be key to continuous improvement in patient care and radiological practices. (Conclusions) In conclusion, KPIs are essential for advancing radiology, while future research should focus on improving data access and developing specialized KPIs to address emerging challenges. Future research should focus on expanding documentation sources, improving web search methods, and establishing direct connections with scientific associations.

Expanding role and scope of artificial intelligence in the field of gastrointestinal pathology

Digital pathology (DP) and its subsidiaries including artificial intelligence (AI) are rapidly making inroads into the area of diagnostic anatomic pathology (AP) including gastrointestinal (GI) pathology. It is poised to revolutionize the field of diagnostic AP. Historically, AP has been slow to adopt digital technology, but this is changing rapidly, with many centers worldwide transitioning to DP. Coupled with advanced techniques of AI such as deep learning and machine learning, DP is likely to transform histopathology from a subjective field to an objective, efficient, and transparent discipline. AI is increasingly integrated into GI pathology, offering numerous advancements and improvements in overall diagnostic accuracy, efficiency, and patient care. Specifically, AI in GI pathology enhances diagnostic accuracy, streamlines workflows, provides predictive insights, integrates multimodal data, supports research, and aids in education and training, ultimately improving patient care and outcomes. This review summarized the latest developments in the role and scope of AI in AP with a focus on GI pathology. The main aim was to provide updates and create awareness among the pathology community.

The Integration of Deep Learning in Radiotherapy: Exploring Challenges, Opportunities, and Future Directions through an Umbrella Review

This study investigates, through a narrative review, the transformative impact of deep learning (DL) in the field of radiotherapy, particularly in light of the accelerated developments prompted by the COVID-19 pandemic. The proposed approach was based on an umbrella review following a standard narrative checklist and a qualification process. The selection process identified 19 systematic review studies. Through an analysis of current research, the study highlights the revolutionary potential of DL algorithms in optimizing treatment planning, image analysis, and patient outcome prediction in radiotherapy. It underscores the necessity of further exploration into specific research areas to unlock the full capabilities of DL technology. Moreover, the study emphasizes the intricate interplay between digital radiology and radiotherapy, revealing how advancements in one field can significantly influence the other. This interdependence is crucial for addressing complex challenges and advancing the integration of cutting-edge technologies into clinical practice. Collaborative efforts among researchers, clinicians, and regulatory bodies are deemed essential to effectively navigate the evolving landscape of DL in radiotherapy. By fostering interdisciplinary collaborations and conducting thorough investigations, stakeholders can fully leverage the transformative power of DL to enhance patient care and refine therapeutic strategies. Ultimately, this promises to usher in a new era of personalized and optimized radiotherapy treatment for improved patient outcomes.

The unintended consequences of artificial intelligence in paediatric radiology

Over the past decade, there has been a dramatic rise in the interest relating to the application of artificial intelligence (AI) in radiology. Originally only 'narrow' AI tasks were possible; however, with increasing availability of data, teamed with ease of access to powerful computer processing capabilities, we are becoming more able to generate complex and nuanced prediction models and elaborate solutions for healthcare. Nevertheless, these AI models are not without their failings, and sometimes the intended use for these solutions may not lead to predictable impacts for patients, society or those working within the healthcare profession. In this article, we provide an overview of the latest opinions regarding AI ethics, bias, limitations, challenges and considerations that we should all contemplate in this exciting and expanding field, with a special attention to how this applies to the unique aspects of a paediatric population. By embracing AI technology and fostering a multidisciplinary approach, it is hoped that we can harness the power AI brings whilst minimising harm and ensuring a beneficial impact on radiology practice.

Breaking Barriers-The Intersection of AI and Assistive Technology in Autism Care: A Narrative Review

(Background) Autism increasingly requires a multidisciplinary approach that can effectively harmonize the realms of diagnosis and therapy, tailoring both to the individual. Assistive technologies (ATs) play an important role in this context and hold significant potential when integrated with artificial intelligence (AI). (Objective) The objective of this study is to analyze the state of integration of AI with ATs in autism through a review. (Methods) A review was conducted on PubMed and Scopus, applying a standard checklist and a qualification process. The outcome reported 22 studies, including 7 reviews. (Key Content and Findings) The results reveal an early yet promising interest in integrating AI into autism assistive technologies. Exciting developments are currently underway at the intersection of AI and robotics, as well as in the creation of wearable automated devices like smart glasses. These innovations offer substantial potential for enhancing communication, interaction, and social engagement for individuals with autism. Presently, researchers are prioritizing innovation over establishing a solid presence within the healthcare domain, where issues such as regulation and acceptance demand increased attention. (Conclusions) As the field continues to evolve, it becomes increasingly clear that AI will play a pivotal role in bridging various domains, and integrated ATs with AI are positioned to act as crucial connectors.

An Umbrella Review of the Fusion of fMRI and AI in Autism

The role of functional magnetic resonance imaging (fMRI) is assuming an increasingly central role in autism diagnosis. The integration of Artificial Intelligence (AI) into the realm of applications further contributes to its development. This study's objective is to analyze emerging themes in this domain through an umbrella review, encompassing systematic reviews. The research methodology was based on a structured process for conducting a literature narrative review, using an umbrella review in PubMed and Scopus. Rigorous criteria, a standard checklist, and a qualification process were meticulously applied. The findings include 20 systematic reviews that underscore key themes in autism research, particularly emphasizing the significance of technological integration, including the pivotal roles of fMRI and AI. This study also highlights the enigmatic role of oxytocin. While acknowledging the immense potential in this field, the outcome does not evade acknowledging the significant challenges and limitations. Intriguingly, there is a growing emphasis on research and innovation in AI, whereas aspects related to the integration of healthcare processes, such as regulation, acceptance, informed consent, and data security, receive comparatively less attention. Additionally, the integration of these findings into Personalized Medicine (PM) represents a promising yet relatively unexplored area within autism research. This study concludes by encouraging scholars to focus on the critical themes of health domain integration, vital for the routine implementation of these applications.

Promoting Universal Equitable Accessibility: An Overview on the Impact of Assistive Technology in the UN, UNICEF, and WHO Web Portals

The number of people with disabilities and frailties who need support and assistance is increasing. Assistive technologies (ATs) are increasingly playing a central role in supporting people with disabilities and frailties. The study investigated the impact of the ATs on the websites of the UN, UNICEF, and WHO in terms of proposed activities and actions. The methodology proposed was based on two points of view: (1) A formal process to directly select elements in the institutional webs of the UN, UNICEF, and WHO. (2) A formal process for a complementary literature narrative review based on an umbrella review of Pubmed and Scopus. A standard checklist and a qualification process were applied. The outcome reported 35 documents from the direct search on the web and 19 systematic reviews for the complimentary literature overview. The direct search returned documents related to initiatives focused on the following: The tailoring of the ATs to a person based on international guidelines and specific monitoring initiatives of the AT introduction/access based on surveys both at the population and system/government level with the publication of the data/metadata in an observatory. Dissemination initiatives of both the culture of ATs (e.g., catalog, guidelines, reports, congresses) and of recommendations. The literature overview contributed more specifically to the use and effectiveness of categories of ATs. Both direct research and the literature overview have shown a consistent growth in interest in ATs. The initiatives of the UN, UNICEF, and WHO have been consistent with the institutional role and aimed at improving the diffusion of ATs through capillary monitoring, which is not free from obstacles, and a diffusion of the culture and rational use of ATs. The narrative review shows also the important role of research in monitoring the development, use, and effectiveness of devices, strategies, and support of international institutional initiatives. Important initiatives have been launched internationally on AT in terms of monitoring, dissemination, and improvement in access. However, it is necessary to consider and face the obstacles that limit these initiatives.

Bridging the Gap: Exploring Opportunities, Challenges, and Problems in Integrating Assistive Technologies, Robotics, and Automated Machines into the Health Domain

The field of healthcare is continually evolving and advancing due to new technologies and innovations [...].

The Artificial Intelligence in Teledermatology: A Narrative Review on Opportunities, Perspectives, and Bottlenecks

Artificial intelligence (AI) is recently seeing significant advances in teledermatology (TD), also thanks to the developments that have taken place during the COVID-19 pandemic. In the last two years, there was an important development of studies that focused on opportunities, perspectives, and problems in this field. The topic is very important because the telemedicine and AI applied to dermatology have the opportunity to improve both the quality of healthcare for citizens and the workflow of healthcare professionals. This study conducted an overview on the opportunities, the perspectives, and the problems related to the integration of TD with AI. The methodology of this review, following a standardized checklist, was based on: (I) a search of PubMed and Scopus and (II) an eligibility assessment, using parameters with five levels of score. The outcome highlighted that applications of this integration have been identified in various skin pathologies and in quality control, both in eHealth and mHealth. Many of these applications are based on Apps used by citizens in mHealth for self-care with new opportunities but also open questions. A generalized enthusiasm has been registered regarding the opportunities and general perspectives on improving the quality of care, optimizing the healthcare processes, minimizing costs, reducing the stress in the healthcare facilities, and in making citizens, now at the center, more satisfied. However, critical issues have emerged related to: (a) the need to improve the process of diffusion of the Apps in the hands of citizens, with better design, validation, standardization, and cybersecurity; (b) the need for better attention paid to medico-legal and ethical issues; and (c) the need for the stabilization of international and national regulations. Targeted agreement initiatives, such as position statements, guidelines, and/or consensus initiatives, are needed to ensure a better result for all, along with the design of both specific plans and shared workflows.

Ten Years of TeleHealth and Digital Healthcare: Where Are We?

Due to the development of the technological innovation of devices, availability of increasingly performing networks, improvement of the digitization processes, and the push to greater diffusion determined by the COVID-19 pandemic, Digital Healthcare (DH), also referred to as Digital Health [...]

Artificial Intelligence Systems Assisting in the Assessment of the Course and Retention of Orthodontic Treatment

This scoping review examines the contemporary applications of advanced artificial intelligence (AI) software in orthodontics, focusing on its potential to improve daily working protocols, but also highlighting its limitations. The aim of the review was to evaluate the accuracy and efficiency of current AI-based systems compared to conventional methods in diagnosing, assessing the progress of patients' treatment and follow-up stability. The researchers used various online databases and identified diagnostic software and dental monitoring software as the most studied software in contemporary orthodontics. The former can accurately identify anatomical landmarks used for cephalometric analysis, while the latter enables orthodontists to thoroughly monitor each patient, determine specific desired outcomes, track progress, and warn of potential changes in pre-existing pathology. However, there is limited evidence to assess the stability of treatment outcomes and relapse detection. The study concludes that AI is an effective tool for managing orthodontic treatment from diagnosis to retention, benefiting both patients and clinicians. Patients find the software easy to use and feel better cared for, while clinicians can make diagnoses more easily and assess compliance and damage to braces or aligners more quickly and frequently.

Assistive Technologies and Quadriplegia: A Map Point on the Development and Spread of the Tongue Barbell Piercing

The barbell piercing can be used as an assistive device that allows people with severe disabilities, such as tetraplegia, to control their environments using the movement of the tongue. The human tongue can move rapidly and accurately, such that the tip can touch every tooth. Lingual control systems allow people with disabilities to take advantage of their residual skills for easier communication and to improve the control of mobility and the surrounding environment. The aim of this study was to conduct a narrative review of the development and dissemination of the assistive technologies based on tongue control by means of the barbell piercing. The design of the study was based on: (I) an overview of Pubmed complemented with other databases and Web searches (also institutional); (II) an organization according to a standardized checklist for narrative reviews; (III) an arrangement with four different perspectives: the trends in the scientific literature, technological evolution and categorization, dominant approaches, issues of incorporation into the health domain-such as acceptance, safety, and regulations. The results have highlighted: (1) that the volume of scientific productions, which started in this sector before the smartphone expansion, has not increased; (2) that it is possible to make a map point of the technological evolution and categorization; (3) that these assistive technologies have a high degree of acceptance and performance, especially when integrated with aid tools with mechatronics; (4) and the complexity of the regulatory framework in this area. The study, from a general point of view, highlighted the high potential of these systems and we suggest investing the energy into agreement tools for assistive technologies (AT)s, such as health technology assessment studies, comparative assessment analysis, or consensus conferences that could allow a better diffusion and use of ATs, including these systems.