Back
For best output, select "Paper Size" as "A4" and "Margin" as "0" or "None".
To save or print to PDF, please select Print Destination > Save as PDF, enable Background Graphics under "More Settings", then click "Save".
During the congress, E-Posters will be accessible to all participants on the congress website 24/7, as well as in the E-poster stations in the congress center.
Preparing your E-Poster
Please review the E-Poster format requirements carefully when preparing your E-Poster. Should your E-Poster not meet the mentioned requirements, it may not be displayed as described above.
E-Poster Submission Deadline
Please prepare and upload your E-Poster no later than March 14, 2026 11.59PM CET. After this date, you will no longer be able to prepare and upload your E-poster and it will not be displayed and accessible on the congress website.
Please follow the instructions below to input your abstract title.
Abstract titles should be brief and reflect the content of the abstract.
Artificial intelligence (AI) is increasingly used to support rehabilitation planning for chronic kidney disease (CKD). Yet AI outputs can vary by language: models trained predominantly on English sources may produce more detailed, clinically aligned recommendations than those prompted in other languages. This discrepancy can affect personalization, safety, and equitable access to high‑quality rehabilitation guidance.
We conducted a comparative assessment of AI‑generated rehabilitation programs for CKD, issuing matched queries in Ukrainian and English to three systems (Gemini, ChatGPT, Copilot). Programs were appraised for: alignment with international guidance (KDIGO/ERA), clarity of progression (frequency, duration, intensity), safety provisions (monitoring, access protection), and adaptability (balance work, fatigue management, home‑based options). We then synthesized an integrated protocol combining the strongest elements across systems.
Ukrainian‑language prompts predominantly returned wellness‑oriented content (breathing, relaxation, low‑impact aerobic and basic strength) with limited progression parameters and sparse monitoring instructions. English‑language prompts more consistently produced structured protocols: graded aerobic targets, resistance dosed by repetitions/sets, balance training, explicit intensity guidance (e.g., Borg RPE 11–13), and adaptations for post‑session recovery and symptom monitoring. Across systems, convergence was highest for core components (aerobic, resistance, flexibility), but specificity and clinical granularity were greater in English outputs. The integrated protocol improved clarity on progression, safety checkpoints, and team‑based implementation, while remaining feasible for home and outpatient rehabilitation.
Practical significance
For national nephrology associations and clinical teams, adopting a standardized, AI‑assisted rehabilitation pathway can:
Improve consistency: shared templates with graded targets and safety flags.
Support scalability: patient‑facing materials and clinician checklists for primary, dialysis, and rehabilitation settings.
Enhance equity: bilingual delivery and culturally adapted examples to widen access.
Integration proposal
Bilingual prompt library: vetted English and Ukrainian prompts mapped to guideline‑based outputs.
Implementation bundle: one‑page clinician algorithm (screening, RPE targets, access protection), patient handouts, and progress logs.
Training modules: short courses for physiotherapists and nurses on AI‑assisted personalization and monitoring.
Additional contribution
We propose a lightweight “AI robustness checklist” (language, safety, progression, adaptability) for local validation of AI‑generated programs, enabling associations to endorse tools that meet minimum clinical standards and reduce language‑driven disparities.
AI can support safe and effective rehabilitation in CKD, but the language of interaction significantly influences the quality of recommendations. English queries currently provide more clinically robust outputs. Development of multilingual AI corpora is essential to ensure equitable access to AI‑assisted rehabilitation worldwide.
