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.
To evaluate the efficacy of an artificial intelligence (AI)-powered dietary self-assessment system in improving nutritional status and biochemical parameters among maintenance hemodialysis (MHD) patients.
A prospective randomized controlled trial was conducted, enrolling 160 MHD patients from a tertiary hospital between January 2024 and June 2025. Participants were randomized into an AI intervention group (*n*=80) and a conventional control group (*n*=80). The control group received standard dietitian guidance, while the intervention group used a proprietary AI dietary management system integrating image recognition, personalized recommendations, and real-time feedback. The system, aligned with Chinese CKD nutrition guidelines, analyzed daily uploaded food images to estimate sodium, phosphorus, potassium, and protein intake, generating a dynamic nutrition score (0–100). Over 3 months, primary outcomes included serum phosphorus, potassium, and albumin levels; secondary outcomes comprised MNA-SF nutritional scores, KDQOL-36 quality of life scales, and dietary adherence rates.
The AI group showed a 23.5±6.2-point improvement in dietary scores (vs. 8.1±4.7 in controls, P<0.001), with 68.4% achieving target scores (≥80) (vs. 31.6%, P=0.002). Biochemically, the AI group reduced serum phosphorus from 2.21±0.43 mmol/L to 1.76±0.38 mmol/L (vs. 2.19±0.41→1.98±0.39 mmol/L in controls, between-group P=0.013), with a 62% lower hyperkalemia incidence (6.3% vs. 16.9%, P=0.041). Nutritional status improved significantly: MNA-SF scores increased by 4.2±1.1 points (vs. 1.8±0.9, P<0.001), and hypoalbuminemia (<35g/L) decreased from 28.9% to 12.5% (vs. 27.5%→23.8%). Patients used the AI system 2.3±0.8 times daily, with 87% endorsing recipe accuracy. Multivariate analysis revealed each 10-point dietary score increase reduced hyperphosphatemia risk by 34% (OR=0.66, 95%CI 0.52–0.83).
The AI-driven dietary self-assessment system significantly enhanced dietary adherence and metabolic control (e.g., hyperphosphatemia) in MHD patients. Its image recognition and personalized feedback offer a scalable solution for chronic disease nutrition management.
