RT journal article
T1 Cytokine Profiles as Predictive Biomarkers of Disease Severity and Progression in Engineered Stone Silicosis: A Machine Learning Approach
A1 Sánchez Morillo, Daniel
A1 Martín Carrillo, Ana
A1 Priego Torres, Blanca María
A1 Sopo Lambea, Iris
A1 Jiménez-Gómez, Gema
A1 León Jiménez, Antonio
A1 Campos Caro, Antonio
A2 BiomedicinaBiotecnología y Salud Pública
A2 Ingeniería en AutomáticaElectrónica, Arquitectura y Redes de Computadores
K1 engineered stone
K1 silicosis
K1 cytokines
K1 biomarkers
K1 machine learning
AB Background/Objectives: Silicosis caused by dust from engineered stone (ES) exposure is an emerging occupational lung disease that severely impacts respiratory health. This study aimed to analyze the association between cytokine profiles and disease severity and progression in patients with engineered stone silicosis (ESS) to assess their potential as biomarkers of progression and their usefulness to stratify risk. Methods: A longitudinal study was conducted with a seven-year follow-up (2017-2024) on 72 workers with simple silicosis (SS) or progressive massive fibrosis (PMF), all with a history of cutting, polishing, and finishing ES countertops. Data on lung function and levels of 27 cytokines were collected at four control points. Machine learning (ML) models were built to classify the disease stage and predict its progression. Results: 39% of patients with SS progressed to PMF. Significant differences in the expression of some cytokines were observed between ESS stages, suggesting a role in the evolution of the inflammatory process. Specifically, higher levels of IL-1RA, IL-8, IL-9, and IFN-γ were found at checkpoint 1 in patients with PMF compared to SS. The longitudinal analysis revealed a significant relationship between IL-1RA and MCP-1α and disease duration with MCP-1α also being associated with time and disease grade. Machine learning (ML) models were built using the cytokines selected through a sequential backward feature selection. The Support Vector Machine model achieved an accuracy of 83% in classifying disease stage (SS, PMF), and of 77% in predicting the disease progression. Conclusions: The findings suggest that cytokines can be used as dynamic biomarkers to reflect underlying inflammatory processes and monitor disease evolution. The performance of ML algorithms to predict diagnostic status based on cytokine profiles highlights their clinical value in supporting early diagnosis, monitoring disease progression, and guiding clinical decisions.
PB MDPI
SN 2075-4418
YR 2025
FD 2025
LK http://hdl.handle.net/10498/37486
UL http://hdl.handle.net/10498/37486
LA eng
DS Repositorio Institucional de la Universidad de Cádiz
RD 09-may-2026