Jul 2026· Information Hiding· pp. 1-4· 0 citations· 18 references
Computer Science
TL;DR
This project aims to establish robust methodologies for evaluating transparency and trust, integrating human factors and clinical performance into a multidimensional validation pipeline, ensuring that AI-enabled health solutions are clinically reliable, transparent, and compliant.
Abstract
Artificial Intelligence-Enabled Medical Devices (AIeMD) promise to revolutionize healthcare, yet their safe adoption relies on effective Human-AI Interaction (HAAI) design and validation. Established usability engineering standards and guidances, including IEC 62366-1 and FDA frameworks, fail to address the novel sociotechnical risks of "black-box" systems, including automation bias and the misalignment of clinician mental models. This doctoral project directly addresses this gap, with the primary goal of developing a tailored human factor/usability engineering framework specifically for AIeMD. The project aims to establish robust methodologies for evaluating transparency and trust, integrating human factors and clinical performance into a multidimensional validation pipeline. Ultimately, this work will provide the evaluative tools necessary to move from subjective satisfaction to safety-critical, risk-based validation, ensuring that AI-enabled health solutions are clinically reliable, transparent, and compliant
Results identify a "symmetry of modality": qualitative interviews correlate with written text explanations, while Think-Aloud protocols better assess cognitively demanding tools like SHAP values.
M. A. D. De Oliveira, Constança Roquette, Nuno Matela et al.· Proceedings of the Internati...· 0 citations
Against the ongoing intelligent transformation of global healthcare, human factors engineering (HFE) is essential to the safe deployment of intelligent medical devices. Yet existing reviews largely offer chronological summaries and fragmented, scenario-specific analyses, leaving the field’s paradigm evolution and cross-scenario human–AI challenges under-synthesized. Following the PRISMA-ScR guideline, this scoping review synthesizes the literature to construct a four-stage developmental framework for medical HFE, delineate four interconnected core human–machine collaboration challenges, and clarify the prevailing theoretical, methodological, and translational constraints. It further identifies future directions—human–AI collaborative reliability evaluation, data-driven usability testing, and digital-twin-supported full-lifecycle validation. By integrating paradigm evolution, core challenges, and regulatory translation into a single analytical framework, this work provides a structured foundation for subsequent research, human-centered design, and regulatory evaluation of intelligent medical devices.
Hui-Ling Hu, Ran Li, Yong Yin et al.· Frontiers in Industrial Engi...· 0 citations
Background/Objectives: The increasing integration of artificial intelligence (AI) into assistive technologies challenges evaluation models traditionally centred on usability, satisfaction and device-related outcomes. Because AI-enabled systems are probabilistic, data-dependent and adaptive, their evaluation must also address algorithmic behaviour, user agency and consequences in everyday life. This critical review aimed to identify and compare standardised instruments, frameworks and structured procedures for evaluating AI-enabled assistive technologies and to determine the extent to which they connect AI-specific properties with the goals of persons with disabilities, activities, participation and environmental conditions. Methods: MEDLINE/PubMed, Scopus and IEEE Xplore were searched without publication-date restrictions, with final searches completed on 30 June 2026 and complemented by backward and forward citation searching. Data were extracted on approach type, purpose, stage of application, target populations and technologies, methodological evidence, evaluated dimensions and outcomes. Evidence was classified as documented, partially documented, not documented or not applicable, while dimensional coverage was coded as explicit, partial or absent. Results: Of the 2299 records screened by title and abstract, 478 publications underwent full-text assessment and 45 were retained in the documentary corpus. These publications supported 16 evaluation approaches: four frameworks, three structured procedures and nine measurement instruments published between 2001 and 2026. The person-related dimension was explicitly operationalised in 15 approaches and activity in nine, whereas participation was explicit in only one and environmental factors in six. AI-specific properties were explicitly evaluated in three approaches, and everyday-life outcomes over time in two. Among the approaches included in this review, none combined comprehensive coverage of person, activity, participation and environment with AI-specific evaluation and longitudinal monitoring. Conclusions: Evaluation remains fragmented across assistive technology, human–computer interaction, human–robot interaction and AI assessment traditions. The review proposes assistive validity as a higher-order criterion linking technical performance, agency and meaningful outcomes for persons with disabilities. It also identifies a modular and longitudinal evaluation architecture as a priority for future empirical development and validation.
It is argued that usability engineering should be a formative, safety-critical discipline integrated throughout the product lifecycle, including aftermarket deployment, and not merely a compliance task.
Preetha Moorthy, T. Nagel, Eva Hornecker· i-com· 0 citations
This mixed-methods evaluation suggests that a deliberately constrained, language-focused AI system can improve the accessibility of medical notes while preserving clinical accuracy and safety while extending into clinical interpretation.
Nicholas Lamb· Frontiers in Digital Health· 0 citations
Artificial intelligence (AI) is widely regarded as one of the most promising innovations in healthcare, yet its adoption in routine clinical practice remains limited. Only a small proportion of AI applications developed in research settings are successfully integrated into healthcare delivery. Major barriers include poor interoperability with existing health information systems, complex regulatory requirements, limited scientific evidence, and the lack of clear clinical guidelines. Many AI tools have been evaluated through methodologically weak studies, often retrospective and lacking external validation, contributing to skepticism among healthcare professionals. Additional challenges involve healthcare professionals' education and training, algorithm transparency, and the ability of healthcare organizations to effectively incorporate these technologies into clinical workflows. To promote the safe and effective adoption of AI, stronger clinical evidence, structured training programs, and organizational models capable of supporting its implementation are required. Addressing these issues is essential to ensure that AI can deliver meaningful benefits for patients, healthcare professionals, and healthcare systems.
Eugenio Santoro· Recenti progressi in medicin...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
