Fresenius Medical Care showcases leadership and innovation in kidney care disease at 61st European Renal Association (ERA) Congress 2024
Press release
- Enhancing kidney care through innovative approaches by data-driven insights and real-world evidence
- Company-wide experts highlight robust anonymized dialysis database
- CONVINCE study and the remarkable decrease of 23% in mortality rates for patients treated with high-volume hemodiafiltration will be presented
Bad Homburg (May 21, 2024) Fresenius Medical Care (FME), the world’s leading provider of products and services for individuals with renal diseases, today announced the presentation of nearly 40 company-affiliated research abstracts at the 61st European Renal Association (ERA) Congress, taking place May 23-26, 2024, in Stockholm, Sweden and virtually.
“Our mission to improve the lives of people living with kidney disease requires working continually to enhance the standard of kidney disease care, and research plays an important role in that advancement,” said Dr. Frank Maddux, Global Chief Medical Officer and Member of the Management Board for Fresenius Medical Care. “We’re proud to share some of our company’s latest research, delving into critical areas such as hemodiafiltration and hemodialysis therapies, using machine learning and artificial intelligence to drive insights, and advances in kidney care worldwide.”
A link to all Fresenius Medical Care-affiliated presentations can be found here 61st ERA Congress | Fresenius Medical Care. Highlights of this year’s posters for the congress include:
Comparison of Baseline Patient Characteristics of the CONVINCE Randomized Controlled Trial with Existing Trial and Registry Populations (May 24, Poster available from 16:45 CEST): A key to generalize the results of randomized trials in everyday clinical practice is how similar the study population is with the one we treat in real life. Comparison of key characteristics of the CONVINCE trial population with that of other randomized controlled trials and important dialysis registries from Europe, USA, and Australasia showed no major differences for age, sex, diabetes, cardiovascular disease, and prevalence of arteriovenous fistula.
Link
Validation of Artificial Intelligence Algorithm Classifying Arteriovenous Access Aneurysms in Hemodialysis: a Blinded Multicenter Prospective Study (May 23, Poster available from 00:11 CEST): Our AI-powered application demonstrated actionable accuracy in classifying arteriovenous access aneurysms within a demographically diverse HD population, enabling timely detection and interventions to prevent severe and potentially life-threatening outcomes such as sudden rupture.
Link
Use of Machine Learning Directed Interventions to Reduce Fluid Related Hospital Admissions in Hemodialysis Patients (May 24, Poster available from 15:15 CEST): The assessment of our machine learning model aimed at predicting hospitalization risk among hemodialysis patients due to fluid overload revealed encouraging findings. Notably, patients identified as high risk by the model who subsequently received intervention from nurses experienced substantial decrease in both fluid and all cause hospital admissions between baseline and follow-up period compared to those who did not receive any intervention.
Link
Application of ChatGPT to Support Nutritional Recommendations for Dialysis Patients (May 24, Poster available from 17:40 CEST): We explored the use of a Large Language Model (LLM), specifically, ChatGPT (GPT-4 model, openai.com), to support nutritional advice given to dialysis patients in a diverse population. The renal dietitian rated the recipes and cooking instructions as moderately satisfactory, but the nutritional analysis questionable. ChatGPT underestimated calories by 36%, protein by 28%, and fat, phosphorus, potassium, and sodium by around 50%. Our findings underscore the importance of a critical approach and the need to assess qualitatively and quantitatively the output created by LLMs.
Link
Quantitative Analysis of Dialytic Protein Loss with Medium Cut-Off and High-Flux Membranes (May 24, Poster available from 9 :10 CEST): We built an ex vivo system to test two dialyzers concurrently and implemented a robust proteomics workflow for a direct comparison of protein loss in the ultrafiltrate. Our data indicates, comprehensively and consistently, a greater extent of protein loss with Medium Cut-off membrane compared to High-Flux membranes, including the loss of salutary proteins.
Link
Dialysis Modality Patterns Across Six Continents in Apollo Dial DB (May 25, Poster available from 12:35 CEST) : Capturing data from over 40 countries, Apollo DB is an anonymized dialysis database that combines and harmonizes data from a global provider for research and quality improvement activities.
Link
link
