Severity Predictors Using Immunology and Transcriptomics in Saliva Using Multi Neural Network Intelligence in SARS-CoV-2 Infection in Children (SPITS MISC)

Background: The purpose of this study was to develop a diagnostic modality to characterize disease severity and predict outcomes in children with SARS-CoV-2 infection, including those at risk for Multisystem Inflammatory Syndrome in Children (MIS-C). Although children were generally less affected by COVID-19 than adults, severe illnesses such as MIS-C and respiratory failure occurred in a subset of pediatric cases, with up to 80% of MIS-C patients requiring critical care and a 2 to 4% mortality rate. No existing tools could reliably distinguish which children exposed to SARS-CoV-2 would develop severe illnesses. The study hypothesized that integrating salivary microRNA (miRNA) biomarkers with social and clinical determinants of health could predict disease severity in children with SARS-CoV-2 infection.

Materials/Methods: This study was conducted in two phases and used an innovative combination of salivaomics, bioinformatics, and artificial intelligence (AI) analytics. During the first phase, researchers defined and compared the salivary molecular host response in children with severe and non-severe SARS-CoV-2 infection, and developed a model to predict disease severity based on these molecular signatures. In the second phase, the study focused on the development of a portable, rapid device to quantify salivary miRNAs with accuracy comparable to quantitative reverse-transcription polymerase chain reaction (qRT-PCR). Additionally, an AI-assisted cloud and mobile system was created to support early recognition of severe SARS-CoV-2 infection in pediatric populations.

Outcome/Impact: This study advanced understanding of the epigenetic regulation of the host immune response to SARS-CoV-2 and demonstrated the potential of saliva-based biomarkers for disease prediction. The resulting predictive model and rapid diagnostic device were expected to improve early identification of children at risk for severe COVID-19 or MIS-C, enabling timely intervention and resource allocation. The findings laid the groundwork for future personalized therapies and precision approaches to pediatric infectious diseases.