Background　Sarcopenia　associated　with　systemic　sclerosis　(SSc)　significantly　compromises　patient　prognosis　and　quality　of　life.　However,　reliable　diagnostic　biomarkers　remain　lacking.　This　study　aimed　to　identify　molecular　markers　for　early　detection　using　integrative　computational　approaches.Methods　An　integrated　analysis　based　on　the　Gene　Expression　Omnibus　(GEO)　database　was　performed.　Crosstalk　genes　(CGs)　were　identified　using　least　absolute　shrinkage　and　selection　operator　(LASSO)　regularization,　ensemble　decision　trees,　and　support　vector　machine-based　feature　selection.　Machine　learning　algorithms　were　employed　to　construct　a　predictive　scoring　model　and　to　assess　the　diagnostic　value　of　key　biomarkers.　Hub　mRNAs　were　validated　using　quantitative　polymerase　chain　reaction　(qPCR).　Immune　cell　infiltration　profiles　and　functional　correlations　were　also　examined.Results　Five　key　CGs-NOX4,　STC2,　NEK6,　IGSF10,　and　EMX2-were　identified　as　molecular　links　between　SSc　and　sarcopenia.　A　predictive　model　incorporating　NOX4　and　NEK6　was　developed,　and　a　diagnostic　threshold　was　established.　PCR　validation　confirmed　the　differential　expression　of　NOX4　and　NEK6　in　both　SSc　and　SSc-associated　sarcopenia,　demonstrating　high　predictive　accuracy.　Furthermore,　the　combined　NOX4-NEK6　model　exhibited　a　superior　area　under　the　curve　(AUC)　compared　to　either　gene　alone.　Immune　infiltration　analysis　revealed　significant　correlations　between　CGs　and　multiple　immune　cell　populations.Conclusion　This　study　proposes　NOX4　and　NEK6　as　novel　biomarkers,　offering　a　non-invasive　strategy　for　the　early　detection　of　SSc-associated　sarcopenia.　This　study　also　reveals　a　shared　immune-dysregulation　node　linking　SSc　and　sarcopenia,　positions　these　crosstalk　genes　as　multi-disease　prevention　targets,　and　paves　the　way　for　personalized　immunotherapy　and　rapid　bench-to-bedside　translation.