Exploratory integration of near-infrared spectroscopy with clinical data: a machine learning approach for HCV detection in serum samples

BackgroundManaging chronic viral infections like Hepatitis C virus (HCV) often requires expensive healthcare resources and highly qualified personnel, making efficient diagnostic methods essential. Despite remarkable therapeutic advancements for the treatment of HCV, several challenges remain, such...

Full description

Saved in:
Bibliographic Details
Main Authors: Eloy Pérez-Gómez, José Gómez, Jennifer Gonzalo, Sergio Salgüero, Daniel Riado, María Luisa Casas, María Luisa Gutiérrez, Elena Jaime, Enrique Pérez-Martínez, Rafael García-Carretero, Javier Ramos, Conrado Fernández-Rodríguez, Myriam Catalá, Luca Martino, Óscar Barquero-Pérez
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-06-01
Series:Frontiers in Medicine
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fmed.2025.1596476/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850136012777324544
author Eloy Pérez-Gómez
José Gómez
José Gómez
Jennifer Gonzalo
Sergio Salgüero
Daniel Riado
María Luisa Casas
María Luisa Gutiérrez
Elena Jaime
Enrique Pérez-Martínez
Rafael García-Carretero
Javier Ramos
Conrado Fernández-Rodríguez
Conrado Fernández-Rodríguez
Myriam Catalá
Myriam Catalá
Luca Martino
Óscar Barquero-Pérez
author_facet Eloy Pérez-Gómez
José Gómez
José Gómez
Jennifer Gonzalo
Sergio Salgüero
Daniel Riado
María Luisa Casas
María Luisa Gutiérrez
Elena Jaime
Enrique Pérez-Martínez
Rafael García-Carretero
Javier Ramos
Conrado Fernández-Rodríguez
Conrado Fernández-Rodríguez
Myriam Catalá
Myriam Catalá
Luca Martino
Óscar Barquero-Pérez
author_sort Eloy Pérez-Gómez
collection DOAJ
description BackgroundManaging chronic viral infections like Hepatitis C virus (HCV) often requires expensive healthcare resources and highly qualified personnel, making efficient diagnostic methods essential. Despite remarkable therapeutic advancements for the treatment of HCV, several challenges remain, such as improved fast diagnostic procedures allowing universal screening.ObjectiveWe 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.MethodsNIRS 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 1,000–2,500 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.ResultsAfter preprocessing with Standard Normal Variate (SNV) correction and downsampling, the best-performing 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 1,150 nm, 1,410 nm, and 1,927 nm, associated with water molecular states and liver function biomarkers (GPT, GOT, GGT), reinforcing the biological relevance of this approach.ConclusionsThese 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.
format Article
id doaj-art-be9e6ec903a3472389a21d11e5a4fcae
institution OA Journals
issn 2296-858X
language English
publishDate 2025-06-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Medicine
spelling doaj-art-be9e6ec903a3472389a21d11e5a4fcae2025-08-20T02:31:13ZengFrontiers Media S.A.Frontiers in Medicine2296-858X2025-06-011210.3389/fmed.2025.15964761596476Exploratory integration of near-infrared spectroscopy with clinical data: a machine learning approach for HCV detection in serum samplesEloy Pérez-Gómez0José Gómez1José Gómez2Jennifer Gonzalo3Sergio Salgüero4Daniel Riado5María Luisa Casas6María Luisa Gutiérrez7Elena Jaime8Enrique Pérez-Martínez9Rafael García-Carretero10Javier Ramos11Conrado Fernández-Rodríguez12Conrado Fernández-Rodríguez13Myriam Catalá14Myriam Catalá15Luca Martino16Óscar Barquero-Pérez17Department of Signal Theory and Communications, EIF, University Rey Juan Carlos, Fuenlabrada, SpainDepartment of Biology and Geology, Physics and Inorganic Chemistry, ESCET, University Rey Juan Carlos, Móstoles, SpainInstituto de Investigación en Cambio Global (IICG-URJC), Universidad Rey Juan Carlos, Móstoles, SpainDepartment of Biology and Geology, Physics and Inorganic Chemistry, ESCET, University Rey Juan Carlos, Móstoles, SpainService of Clinical Biochemistry, Hospital Universitario Fundación Alcorcón, Alcorcón, SpainService of Gastroenterology, Hospital Universitario Rey Juan Carlos, Fuenlabrada, SpainService of Clinical Biochemistry, Hospital Universitario Fundación Alcorcón, Alcorcón, SpainService of Gastroenterology, Hospital Universitario Fundación Alcorcón, Alcorcón, SpainService of Clinical Biochemistry, Hospital Universitario Fundación Alcorcón, Alcorcón, SpainDepartment of Biology and Geology, Physics and Inorganic Chemistry, ESCET, University Rey Juan Carlos, Móstoles, SpainHospital Universitario Mostoles, Móstoles, SpainDepartment of Signal Theory and Communications, EIF, University Rey Juan Carlos, Fuenlabrada, SpainService of Gastroenterology, Hospital Universitario Fundación Alcorcón, Alcorcón, SpainDepartment of Medical Specialties and Public Health, University Rey Juan Carlos, Alcorcón, Madrid, SpainDepartment of Biology and Geology, Physics and Inorganic Chemistry, ESCET, University Rey Juan Carlos, Móstoles, SpainInstituto de Investigación en Cambio Global (IICG-URJC), Universidad Rey Juan Carlos, Móstoles, SpainDipartimento di Economia e Impresa, Universita di Catania, Catania, ItaliaDepartment of Signal Theory and Communications, EIF, University Rey Juan Carlos, Fuenlabrada, SpainBackgroundManaging chronic viral infections like Hepatitis C virus (HCV) often requires expensive healthcare resources and highly qualified personnel, making efficient diagnostic methods essential. Despite remarkable therapeutic advancements for the treatment of HCV, several challenges remain, such as improved fast diagnostic procedures allowing universal screening.ObjectiveWe 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.MethodsNIRS 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 1,000–2,500 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.ResultsAfter preprocessing with Standard Normal Variate (SNV) correction and downsampling, the best-performing 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 1,150 nm, 1,410 nm, and 1,927 nm, associated with water molecular states and liver function biomarkers (GPT, GOT, GGT), reinforcing the biological relevance of this approach.ConclusionsThese 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.https://www.frontiersin.org/articles/10.3389/fmed.2025.1596476/fullNIRSHCVHepatitis Cmachine learningpermutation feature importance
spellingShingle Eloy Pérez-Gómez
José Gómez
José Gómez
Jennifer Gonzalo
Sergio Salgüero
Daniel Riado
María Luisa Casas
María Luisa Gutiérrez
Elena Jaime
Enrique Pérez-Martínez
Rafael García-Carretero
Javier Ramos
Conrado Fernández-Rodríguez
Conrado Fernández-Rodríguez
Myriam Catalá
Myriam Catalá
Luca Martino
Óscar Barquero-Pérez
Exploratory integration of near-infrared spectroscopy with clinical data: a machine learning approach for HCV detection in serum samples
Frontiers in Medicine
NIRS
HCV
Hepatitis C
machine learning
permutation feature importance
title Exploratory integration of near-infrared spectroscopy with clinical data: a machine learning approach for HCV detection in serum samples
title_full Exploratory integration of near-infrared spectroscopy with clinical data: a machine learning approach for HCV detection in serum samples
title_fullStr Exploratory integration of near-infrared spectroscopy with clinical data: a machine learning approach for HCV detection in serum samples
title_full_unstemmed Exploratory integration of near-infrared spectroscopy with clinical data: a machine learning approach for HCV detection in serum samples
title_short Exploratory integration of near-infrared spectroscopy with clinical data: a machine learning approach for HCV detection in serum samples
title_sort exploratory integration of near infrared spectroscopy with clinical data a machine learning approach for hcv detection in serum samples
topic NIRS
HCV
Hepatitis C
machine learning
permutation feature importance
url https://www.frontiersin.org/articles/10.3389/fmed.2025.1596476/full
work_keys_str_mv AT eloyperezgomez exploratoryintegrationofnearinfraredspectroscopywithclinicaldataamachinelearningapproachforhcvdetectioninserumsamples
AT josegomez exploratoryintegrationofnearinfraredspectroscopywithclinicaldataamachinelearningapproachforhcvdetectioninserumsamples
AT josegomez exploratoryintegrationofnearinfraredspectroscopywithclinicaldataamachinelearningapproachforhcvdetectioninserumsamples
AT jennifergonzalo exploratoryintegrationofnearinfraredspectroscopywithclinicaldataamachinelearningapproachforhcvdetectioninserumsamples
AT sergiosalguero exploratoryintegrationofnearinfraredspectroscopywithclinicaldataamachinelearningapproachforhcvdetectioninserumsamples
AT danielriado exploratoryintegrationofnearinfraredspectroscopywithclinicaldataamachinelearningapproachforhcvdetectioninserumsamples
AT marialuisacasas exploratoryintegrationofnearinfraredspectroscopywithclinicaldataamachinelearningapproachforhcvdetectioninserumsamples
AT marialuisagutierrez exploratoryintegrationofnearinfraredspectroscopywithclinicaldataamachinelearningapproachforhcvdetectioninserumsamples
AT elenajaime exploratoryintegrationofnearinfraredspectroscopywithclinicaldataamachinelearningapproachforhcvdetectioninserumsamples
AT enriqueperezmartinez exploratoryintegrationofnearinfraredspectroscopywithclinicaldataamachinelearningapproachforhcvdetectioninserumsamples
AT rafaelgarciacarretero exploratoryintegrationofnearinfraredspectroscopywithclinicaldataamachinelearningapproachforhcvdetectioninserumsamples
AT javierramos exploratoryintegrationofnearinfraredspectroscopywithclinicaldataamachinelearningapproachforhcvdetectioninserumsamples
AT conradofernandezrodriguez exploratoryintegrationofnearinfraredspectroscopywithclinicaldataamachinelearningapproachforhcvdetectioninserumsamples
AT conradofernandezrodriguez exploratoryintegrationofnearinfraredspectroscopywithclinicaldataamachinelearningapproachforhcvdetectioninserumsamples
AT myriamcatala exploratoryintegrationofnearinfraredspectroscopywithclinicaldataamachinelearningapproachforhcvdetectioninserumsamples
AT myriamcatala exploratoryintegrationofnearinfraredspectroscopywithclinicaldataamachinelearningapproachforhcvdetectioninserumsamples
AT lucamartino exploratoryintegrationofnearinfraredspectroscopywithclinicaldataamachinelearningapproachforhcvdetectioninserumsamples
AT oscarbarqueroperez exploratoryintegrationofnearinfraredspectroscopywithclinicaldataamachinelearningapproachforhcvdetectioninserumsamples