Danube Private University (DPU) is an accredited private university Danube Private University (DPU, Austria) is seeking to join Horizon Europe consortia as an execution-ready clinical living-lab and evidence partner for innovative health technologies—especially AI/imaging workflows and digital or sensor-enabled solutions. We participate strictly as DPU and provide a focused technical contribution; coordinators can complement us with additional competences as needed.
DPU is an accredited private university for human medicine and dentistry based in Krems an der Donau (Lower Austria). We combine academic agility with direct clinical access through DPU’s clinical infrastructure and cooperative university hospitals in Austria (Wiener Neustadt, Neunkirchen, Hochegg). This set-up supports realistic, multi-site clinical studies, access to care pathways and imaging data, and rapid iteration under real operational constraints.
What DPU can deliver (technical offering)
1) Clinical living-lab validation across real workflows (Krems + cooperative hospitals)
DPU designs and runs living-lab studies that translate prototypes into implementable solutions: workflow integration and process mapping, usability/human-factors testing, acceptability and adherence assessment, and pragmatic KPI frameworks (feasibility, safety, implementation outcomes). When a project needs broader clinical diversity or multi-site evidence, we can extend validation through the cooperative hospitals with harmonised protocols, shared data capture procedures, and cross-site comparability.
2) Evidence & validation backbone for innovative health tech (AI / digital / sensing)
We structure validation as an end-to-end evidence package: intended-use and context-of-use framing, endpoint and comparator strategy, acceptance criteria, and risk-proportionate evaluation depth. We also provide traceability from requirements → tests → results and audit-friendly reporting templates. For AI-enabled tools, we can operationalise cross-site generalisability plans, dataset-shift and drift monitoring concepts, uncertainty-aware reporting, and clinician-in-the-loop evaluation embedded in routine clinical workflows (including human oversight and auditability).
3) MIAAI: medical imaging AI and multimodal decision support
Through DPU’s Medical Image Analysis & Artificial Intelligence (MIAAI) activities, we contribute development and/or independent validation of imaging pipelines: segmentation and quantitative imaging biomarkers, structured feature extraction (including radiomics when justified), predictive modelling, explainability, and rigorous evaluation/reporting. Where relevant, we support “shadow-mode” clinical testing (decision support without clinical reliance) and produce transparent artefacts such as model cards, dataset statements, versioned evaluation scripts, and performance dashboards.
4) LiST / PI-SENS: intelligent sensing and non-invasive measurements—making them evidence-grade
For sensing and non-invasive measurement concepts, DPU focuses on the verification work that determines clinical usability: standardised sampling SOPs, calibration and repeatability/stability studies, drift analysis, confounder/interference matrices, signal processing and data-fusion concepts, and field-testing designs aligned to clinical endpoints and workflow constraints.
5) Adoption and co-creation grounded in DPU ecosystems (living-lab practice + Heracles–Hebe Foundation)
Beyond clinical testing, DPU can run structured stakeholder engagement that feeds directly back into technical work: co-creation workshops, clinician/patient feedback loops, and prevention- and youth-focused formats via the Heracles–Hebe Foundation. Outputs are actionable requirement updates, adoption barriers/enablers, and documented implementation conditions.
Concrete outputs DPU can commit to (proposal-ready deliverables)
• Clinical Living-Lab Validation Package: protocol set, workflow integration plan, usability/human-factors reports, implementation KPIs, and a multi-site deployment playbook.
• Evidence & Validation Blueprint: intended-use framing, claims-to-tests traceability, comparator/endpoint strategy, acceptance criteria, and audit-ready reporting templates.
• Reproducible Imaging-AI Evaluation Suite (MIAAI): evaluation scripts, cross-site reporting, uncertainty/drift monitoring plan, and transparency artefacts.
• Sensor Verification & Benchmarking Plan (LiST/PI-SENS): SOPs, stability/drift testing, confounder matrix, and field validation methodology.