Exploratory Integration of Near-Infrared Spectroscopy with Clinical Data: A Machine Learning Approach for HCV Detection in Serum Samples

Eloy Pérez Gómez¹José Gómez¹Jennifer Gonzalo¹Sergio Salgüero²Daniel Riado³María Luisa Casas⁴María Luisa Gutiérrez⁴Elena Jaime⁴Enrique Pérez-Martínez¹Rafael García-Carretero⁵Javier Ramos¹Conrado Fernández-Rodríguez⁴Myriam Catalá¹Luca Martino⁶Óscar Barquero-Pérez^1*

• ¹Rey Juan Carlos University, Móstoles, Madrid, Spain
• ²El Escorial Hospital, San Lorenzo de El Escorial, Madrid, Spain
• ³Hospital Universitario Rey Juan Carlos, Madrid, Madrid, Spain
• ⁴Hospital Universitario Fundación Alcorcón, Alcorcón, Madrid, Spain
• ⁵Hospital Universitario de Móstoles, Móstoles, Madrid, Spain
• ⁶University of Catania, Catania, Sicily, Italy

In this study, we propose a novel approach that combines Near-Infrared Spectroscopy (NIRS) and clinical data with machine learning (ML) to improve Hepatitis C Virus (HCV) detection in serum samples. NIRS offers a fast, non-destructive, and residue-free alternative to traditional diagnostic methods, while ML models enable feature selection and predictive analysis. We applied L1-regularized Logistic Regression (L1-LR) to identify the most informative wavelengths for HCV detection within the 1000-2500 nm range, and then integrated these spectral features with routine clinical markers using a Random Forest (RF) model. Our dataset comprised 137 serum samples from 38 patients, each represented by a NIRS spectrum and clinical data from blood tests. After preprocessing with Standard Normal Variate (SNV) correction and downsampling, the bestperforming RF model, which combined NIRS features and clinical data, achieved an accuracy of 72.2% and an AUC-ROC of 0.850, outperforming models using only clinical or spectral data.Feature importance analysis highlighted specific wavelengths near 1150 nm, 1410 nm, and 1927 nm, associated with water molecular states and liver function biomarkers (GPT, GOT, GGT), reinforcing the biological relevance of this approach. These findings suggest that integrating NIRS and clinical data through machine learning enhances HCV diagnostic capabilities, offering a scalable and non-invasive alternative for early detection and risk assessment.