Chronic　kidney　disease　(CKD),　characterized　by　structural　or　functional　renal　abnormalities,　poses　substantial　health　risks.　With　a　global　prevalence　nearing　13　%,　fewer　than　10　%　of　affected　individuals　are　aware　of　their　condition.　Early-stage　CKD　frequently　goes　undetected　due　to　the　lack　of　specific　symptoms　and　the　high　costs　and　logistical　challenges　associated　with　traditional　blood　testing.　This　study　introduces　an　anionic,　ultrasensitive　aerogel　SERS　platform　(CS-Ag@4-mbn),　constructed　from　sodium　alginate　and　carboxymethyl　cellulose,　optimized　for　efficient　biomarker　capture　and　rapid　urinary　analysis.　The　CS-Ag@4-mbn　platform　demonstrates　an　exceptional　R6G　adsorption　capacity　of　2.67　×　10−6　mol/g　and　a　detection　limit　of　8.81　×　10−11　M,　underscoring　its　advanced　SERS　recognition　performance.　Furthermore,　the　integration　of　an　internal　standard　signal　within　the　CS-Ag@4-mbn　system　reduces　potential　errors　and　facilitates　dataset　correction.　To　interpret　the　acquired　SERS　data,　five　machine　learning　algorithms—PCA,　SVM,　DT,　KNN,　and　RF—were　employed,　successfully　constructing　models　to　differentiate　CKD　stages　(healthy　and　stages　I[sbnd]V).　These　models　achieved　accuracy　rates　of　up　to　100　%　in　training　and　97.58　%　in　testing,　even　without　urine　pre-processing,　highlighting　the　platform＇s　potential　for　non-invasive,　early-stage　CKD　screening　and　diagnosis.　©　2025　Elsevier　B.V.