A lightweight dual-representation cross-attention framework for urinary FTIR classification of lupus nephritis and...

LN subtype stratification is important for treatment and prognosis but relies on invasive renal biopsy, limiting repeated assessment. Urinary FTIR spectroscopy offers a label-free, repeatable alternative, yet remains insufficient for interpretable discrimination of clinically important subtypes, especially PLN and mixed LN. We therefore developed a compact, data-efficient, and interpretable urinary FTIR model for LN screening and PLN-mixed LN stratification.

First-morning urine spectra (500-4000 cm^-1) were collected and represented as synchronized raw and preprocessed signals. A lightweight Spectral Interaction Attention Former (SIA-Forme) was developed to encode patch-wise spectral information and fuse the two representations through bidirectional cross-attention. Under repeated stratified evaluation, the model achieved an ROC-AUC of 0.988 ± 0.013 for LN versus healthy controls (129 LN, 113 controls), and an accuracy of 86.0 ± 5.1% with an AUC of 0.875 ± 0.079 for PLN versus mixed LN discrimination (61 vs 48). The proposed method outperformed conventional chemometric models and several deep-learning baselines under the same protocol. Complementary interpretability analyses, including Welch's t-test with FDR correction, DeepSHAP, and spectral band masking, consistently highlighted the 1500-1700 cm^-1 and 3300-3500 cm^-1 regions as major contributors to subtype discrimination.

The results show that dual-representation fusion of urinary FTIR spectra can improve classification and interpretability in small-cohort LN analysis. The proposed framework provides a compact strategy for urinary spectral measurement and pattern analysis, with potential value for noninvasive LN screening and subtype-related assessment.