Identifying sepsis susceptibility genes in post-surgical patients using an artificial intelligence approach

FERNANDO VAQUERIZO-VILLAR^1,2,3*Tamara Hernández Beeftink^4*María Heredia- Rodríguez^5,6,7Esther Gómez-Sánchez^3,5,6,7Mario Lorenzo-López^3,5,6,7Rocío López-Herrero^3,5,6,7Miguel Bardaji-Carrillo^3,6,7Alvaro Tamayo-Velasco^3,5,7Marta Martín-Fernández^5,6,7Laura Sánchez-de Prada⁷Julián Álvarez-Escudero⁸Sonia Veiras^8,9Aurora Baluja^10,9Hugo Gonzalo-Benito^3,5,7Pedro Martínez-Paz^11,5,7Adrián García-Concejo^5,7Amanda Fernández-Rodríguez^12,5,7María Angeles Jiménez-Sousa^12,5,7Salvador Resino^12,5,7Laura Martínez-Campelo^13,14Eva Suárez-Pajés¹⁵Inés Quintela^13,14,9RAQUEL CRUZ GUERRERO^13,14Angel Carracedo^10,13,14Jesús Villar^16,17,18Carlos Flores^15,17,19,20Roberto Hornero^2,6Eduardo Tamayo^3,5,6,7

• ¹University of Valladolid, Valladolid, Spain
• ²Centro de Investigacion Biomedica en red en Bioingenieria Biomateriales y Nanomedicina, Zaragoza, Spain
• ³Hospital Clinico Universitario de Valladolid, Valladolid, Spain
• ⁴University of Leicester, Leicester, United Kingdom
• ⁵Centro de Investigacion Biomedica en Red Enfermedades Infecciosas, Madrid, Spain
• ⁶Universidad de Valladolid, Valladolid, Spain
• ⁷Biocritic, Group for Biomedical Research in Critical Care Medicine, Valladolid, Spain
• ⁸Complejo Hospitalario Universitario de Santiago de Compostela, Santiago de Compostela, Spain
• ⁹Instituto de Investigacion Sanitaria de Santiago de Compostela, Santiago de Compostela, Spain
• ¹⁰Hospital Virxe da Xunqueira, Cee, Spain
• ¹¹Queen Mary University of London William Harvey Research Institute, London, United Kingdom
• ¹²Centro Nacional de Microbiologia, Majadahonda, Spain
• ¹³Fundacion Publica Galega de Medicina Xenomica, Santiago de Compostela, Spain
• ¹⁴Centro de Investigacion Biomedica en Red de Enfermedades Raras, Valencia, Spain
• ¹⁵Hospital Universitario Nuestra Senora de la Candelaria, Santa Cruz de Tenerife, Spain
• ¹⁶Hospital Universitario de Gran Canaria Dr Negrin, Las Palmas de Gran Canaria, Spain
• ¹⁷Centro de Investigacion Biomedica en Red Enfermedades Respiratorias, Madrid, Spain
• ¹⁸St Michael's Hospital Li Ka Shing Knowledge Institute, Toronto, Canada
• ¹⁹Instituto Tecnologico y de Energias Renovables SA, Santa Cruz de Tenerife, Spain
• ²⁰Universidad Fernando Pessoa Canarias, Las Palmas de Gran Canaria, Spain

Abstract Background: Early detection of sepsis is essential for its successful management. Although genome-wide association studies (GWAS) have shown potential in identifying sepsis-related genetic variants, they often involve heterogeneous patient groups and use single-locus analysis methods. Here, we aim to identify new sepsis susceptibility loci in post-surgical patients using an explainable artificial intelligence (XAI) approach applied to GWAS data. Methods: GWAS was performed in 750 post-operative patients with sepsis and 3,500 population controls. We applied a novel XAI-based methodology to GWAS-derived single nucleotide polymorphisms (SNPs) to predict sepsis and prioritise new genetic variants associated with postoperative sepsis susceptibility. We also assessed functional and enrichment effects using empirical data from integrated software tools and datasets, with the top-ranked variants and associated genes. Results: Our XAI-GWAS approach showed a notable performance in predicting post-surgical sepsis and prioritized SNPs (such as rs17653532, rs1575081785, and rs74707084) with higher contribution to post-operative sepsis prediction and facilitated the discovery of post-operative sepsis risk loci with important functional implications related to gene expression regulation, DNA replication, cyclic nucleotide signalling, cell proliferation, and cardiac dysfunction. Conclusions: The combination of GWAS and XAI prioritized loci associated with post-operative sepsis susceptibility. The determination of key genes, such as PRIM2, SYNPR, and RBSN, through preoperative blood tests could enhance risk stratification, enable early detection of post-operative sepsis, and guide targeted interventions to improve patient outcomes. Further research with additional and ethnically diverse cohorts comprising sepsis and non-sepsis patients undergoing major surgery is needed to validate these exploratory findings.