SERS analysis: A novel approach for detecting non-alcoholic steatohepatitis

CHINA: According to a study published in the journal Hepatology International, fully connected neural network-based serum surface-enhanced Raman spectroscopy (SERS) analysis provides an efficient and practical method for the non-invasive detection of non-alcoholic steatohepatitis (NASH).

A third of adults worldwide are thought to be affected by non-alcoholic fatty liver disease (NAFLD), which is a concern to public health. The inflammatory and progressing variant of NAFLD is non-alcoholic steatohepatitis (NASH).

The "gold standard" for diagnosing NASH as of this date is liver biopsy (LB), yet this is an intrusive diagnostic process with complications.

Therefore, a low-risk, non-invasive diagnostic technique that can successfully identify NASH at an early stage is considered necessary.

According to Zu-Fang Huang and colleagues, "in our exploratory work, a surface-enhanced Raman spectroscopy (SERS) approach for serum biochemical analysis was created with the sole goal of establishing a simple blood test for the non-invasive detection of NASH".

Using data from a liver biopsy, the researchers looked into developing and validating a new diagnostic model for non-invasively diagnosing NASH by merging SERS and neural network techniques.

For this purpose, between November 2016 and September 2019 at the First Affiliated Hospital of Wenzhou Medical University in Wenzhou (China), 261 Chinese patients with biopsy-proven NAFLD were enrolled. Based on SERS spectra and neural network techniques, a prediction model for NASH was developed. As an independent validation cohort, a second sample of 52 NAFLD patients who underwent liver biopsy between April 2019 and September 2019 was employed. To improve the Raman scattering signals, blood serum was combined with silver nanoparticles that were the SERS-active nanostructures. A neural network with a fully connected residual module at its core trained the NASH classification model using the spectral data set.

Conclusive points of the study:

• In the validation set, the model produced an AUROC of 0.83 (95% confidence interval [CI] 0.70-0.92), which was higher than the AUROCs of serum CK-18-M30 levels (AUROC 0.63, 95% CI 0.48-0.76, p = 0.044) and the HAIR score (AUROC 0.65, 95% CI 0.51-0.77, p = 0.040).
• Subgroup analysis revealed that the model was effective across a range of patient categories.

In conclusion, the findings of this investigation indicate that the SERS blood serum analysis offers a quick, easy, and accurate method for determining the existence of NASH.

"Future research in various ethnic cohorts of NAFLD patients is required to confirm the clinical use of the SERS analysis and to determine whether this technology may also be used to non-invasively track therapeutic responses to novel pharmacotherapies for NASH," the researchers wrote.

Reference

Gao, F., Lu, DC., Zheng, TL. et al. Fully connected neural network-based serum surface-enhanced Raman spectroscopy accurately identifies non-alcoholic steatohepatitis. Hepatol Int (2022). https://doi.org/10.1007/s12072-022-10444-2