Urine SERS Spectra for Lupus Nephritis Diagnosis and Subtype Classification

A diagnostic accuracy of 93.55% was reported for distinguishing lupus nephritis from nephrotic syndrome using surface-enhanced Raman spectroscopy (SERS) and machine learning. The dataset, authored by Xue Xia and last updated in May 2026, contains SERS spectral data from urine samples to enable non-invasive diagnosis and pathological subtype classification. The data is shared under a CC-BY-4.0 license on figshare.

Use Cases

• Training machine learning models for lupus nephritis diagnosis based on urinary SERS spectral features.
• Developing classifiers to stratify lupus nephritis pathological subtypes using spectral molecular characteristics.
• Benchmarking liquid biopsy platforms against the reported 93.55% diagnostic accuracy.
• Exploring urinary biomarker discovery for autoimmune nephritis using spectral data analysis.

Strengths

• Reported diagnostic accuracy of 93.55% for distinguishing lupus nephritis from nephrotic syndrome.
• Data is shared under a permissive CC-BY-4.0 license.
• Methodology combines SERS with supervised machine learning (random forest algorithm).

Limitations

• Dataset is small, with a file size of 211.9 KB, indicating limited scope.
• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.

Provenance

Source

figshare, author Xue Xia.

Collection Method

Surface-enhanced Raman spectroscopy (SERS) of urine samples, analyzed with machine learning algorithms.

Freshness

Last updated 2026-05-05 05:23:54; freshness should be verified.