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.
Early diagnosis of CKD is critical to prevent progression, but in many settings invasive or expensive diagnostics limit access. We evaluated the use of multispectral autofluorescence imaging of urinary exfoliated proximal tubule cells (PTCs), combined with machine learning analysis, as a non-invasive diagnostic approach to distinguish people with reduced renal function from normal.
Adults (≥18 years) were recruited and provided spot urine samples. Exfoliated PTCs were isolated via immunomagnetic separation using anti-CD13 and anti-SGLT2 antibodies. Using a customized multispectral fluorescence microscope with 34 excitation-emission combinations, cellular autofluorescence spectra were acquired. Preprocessing of spectral data was followed by feature extraction; classification was performed using linear Support Vector Machine in the SMIAL MATLAB GUI (version 1.00) with 5-fold cross validation. Comparative analyses included three discrimination tasks: (1) eGFR ≥ 60 vs eGFR < 60, (2) eGFR ≥ 90 vs eGFR 60–90, and (3) eGFR 60–90 vs eGFR < 60
Sixty individuals were included: 40 had eGFR ≥ 60 and 20 had eGFR < 60.
For distinguishing eGFR ≥ 60 vs < 60, the classifier achieved AUC 0.81 ± 0.04. storage.unitedwebnetwork.com+1
In subgroup analysis between eGFR ≥ 90 vs 60–90, AUC was 0.74 ± 0.05. storage.unitedwebnetwork.com
Between eGFR 60–90 vs < 60, AUC was 0.80 ± 0.08. storage.unitedwebnetwork.com
These results indicate moderate discrimination capacity using autofluorescence features of urinary PTCs. Qualitative observations indicated distinct spectral shifts associated with declining kidney function, consistent with cellular changes from metabolic and oxidative stress
Multispectral autofluorescence imaging of urinary exfoliated PTCs, coupled with machine learning spectral analysis, shows promise as a non-invasive diagnostic tool to differentiate among levels of kidney function. While performance is not yet at clinical diagnostic thresholds, further refinement of spectral feature engineering, larger cohorts, and more sophisticated classifiers may improve accuracy. This approach could eventually provide a low-cost, urine-based screening tool for CKD in low-resource settings.
