Software as a Medical Device in Diagnostic and Therapeutic Care: From Development to Real-World Implementation

Software as a Medical Device (SaMD) is reshaping diagnostic and therapeutic pathways, from AI-enabled interpretation of clinical data and images to software that guides treatment selection, monitoring, and the delivery of digital therapeutics. Yet translation into routine care remains uneven. Evidence generation is frequently disconnected from regulatory qualification and classification, quality management, cybersecurity, and lifecycle obligations. Implementation failures often reflect workflow misfit, usability constraints, limited clinician trust calibration, and insufficient monitoring of real-world performance, drift, and subgroup inequities. In parallel, the European MDR/IVDR transition and the emergence of the EU AI Act are creating new compliance interfaces that many developers and clinical teams struggle to operationalize. This Research Topic provides a practical forum that integrates regulatory science, clinical validation, and real-world implementation to support safe, effective, and equitable SaMD in diagnostic and therapeutic care across health systems. We focus on clinically anchored software, excluding administrative, billing, scheduling, or logistics tools.

This Research Topic aims to provide an evidence-based, practice-oriented reference for translating SaMD—particularly AI-enabled diagnostic tools and software supporting therapeutic decisions—into safe, effective, and equitable clinical use. We invite contributions that (i) clarify qualification and classification decisions (SaMD versus non-device software, MDR Rule 11 implications, and IVDR boundaries), (ii) strengthen clinical evaluation, including external validation, prospective studies where feasible, and principled use of real-world evidence (RWE), (iii) address workflow integration and human factors to reduce adoption failure and prevent unsafe use, and (iv) advance post-market surveillance and lifecycle management, including performance monitoring, drift detection, cybersecurity, and governance of updates.

Across themes, we prioritise reproducibility, clinically meaningful endpoints, transparent reporting of intended use and failure modes, and explicit assessment of bias and subgroup performance. We also welcome work on reimbursement and health technology assessment when linked to evidence and implementation. The collection will help align developers, regulators, clinicians, and health-system leaders around operational methods that protect patients while enabling accountable innovation. By bringing together validation studies, regulatory analyses, implementation case series, and methods papers, we aim to surface transferable lessons and practical checklists. Contributions should, where possible, quantify benefits, harms, and resource implications in real clinical settings for decision-makers.

We welcome manuscripts on SaMD used in diagnostic and therapeutic care, including AI-enabled clinical decision support and digital therapeutics, spanning development, clinical evaluation, implementation, and post-market learning. Submissions must state intended use, target population, clinical setting, decision point(s), and the comparator or standard of care. Where relevant, authors should position their work within regulatory expectations (EU MDR/IVDR, EU AI Act, FDA and IMDRF-aligned approaches) and describe quality management, data governance, and cybersecurity considerations. In-scope topics include but are not limited to the following:

• Qualification/classification
• Validation design
• Dataset representativeness
• Workflow integration (EHR/PACS/RIS)
• Usability/human factors
• Monitoring of performance drift
• Update governance
• Equity and access

We will accept Original Research, Systematic Reviews, Methods/Technology and Code, Study Protocols, Policy and Practice Reviews, and well-argued Perspectives grounded in evidence. We do not consider purely administrative or hospital management software. Authors are encouraged to share reporting checklists, de-identified code or models, and implementation materials for reuse.

Article types and fees

This Research Topic accepts the following article types, unless otherwise specified in the Research Topic description:

• Brief Research Report
• Case Report
• Classification
• Clinical Trial
• Data Report
• Editorial
• FAIR² Data
• General Commentary
• Hypothesis and Theory
• ... View all formats

Articles that are accepted for publication by our external editors following rigorous peer review incur a publishing fee charged to Authors, institutions, or funders.

Article types

This Research Topic accepts the following article types, unless otherwise specified in the Research Topic description:

• Brief Research Report
• Case Report
• Classification
• Clinical Trial
• Data Report
• Editorial
• FAIR² Data
• General Commentary
• Hypothesis and Theory
• Methods
• Mini Review
• Opinion
• Original Research
• Perspective
• Policy and Practice Reviews
• Policy Brief
• Review
• Study Protocol
• Systematic Review
• Technology and Code

Keywords: Software as a Medical Device (SaMD), AI as a Medical Device (AIaMD), MDR/IVDR, EU AI Act, Clinical validation, Real-world evidence, Post-market surveillance, Digital therapeutics

Important note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.