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.
Intradialytic hypotension (IDH) affects roughly one-quarter of hemodialysis sessions and contributes to organ injury, treatment intolerance, and reduced patient survival. Despite its frequency, predicting which patients will develop hypotension during a given session remains challenging. We hypothesized that dialysis machine-derived circuit parameters, particularly transmembrane pressure measured at treatment initiation, might identify patients at risk before blood pressure drops occur.
We prospectively enrolled 25 adults receiving maintenance hemodialysis at Ngoerah Hospital Dialysis center (19 male and 6 female patients wih average age 46.7±8.3 years, vintage >48 months) were studied. Vascular access included 15 fistulae and 10 catheters. Etiologies were diabetic nephropathy (n=9), hypertensive nephrosclerosis (n=7), glomerulonephritis (n=5), nephrolithiasis (n=3), and unknown (n=1). Machine logs captured transmembrane pressure (TMP), arterial/venous pressures, blood flow, dialysate flow (QD), and ultrafiltration parameters at 20-30 minute intervals. We derived 25 circuit features including means, maximum points, and slopes. IDH was defined as systolic blood pressure fall ≥20 mmHg or nadir <90 mmHg. Mann-Whitney tests assessed univariate associations; logistic regression and Random Forest models evaluated predictive performance
IDH occurred in 7 patients (28%). Five circuit parameters were significant: minimum QD (0 vs 486 mL/min, p=0.005), mean QD (475 vs 499 mL/min, p=0.017), maximum TMP (10.1 vs 16.7 mmHg, p=0.020), mean TMP (4.2 vs 10.9 mmHg, p=0.040), and minimum blood flow (241 vs 154 mL/min, p=0.049). Lower TMP paradoxically associated with IDH. Logistic regression achieved excellent discrimination (AUC 0.897, accuracy 84%, specificity 100%, sensitivity 43%). Random Forest demonstrated perfect performance (AUC 1.000, accuracy 100%). Feature importance: maximum TMP (29.1%), mean QD (25.6%), mean TMP (18.7%)
Machine-derived circuit signatures, particularly TMP and dialysate flow patterns, robustly predict IDH (AUC 0.897-1.000), representing early hemodynamic instability markers. These findings support automated real-time warning system development. This is a novel study despite small sample limitations, consistent results suggest genuine predictive utility requiring multicenter validation.
