Genetic prediction of ICU hospitalization and mortality in COVID-19 patients using artificial neural networks
Panagiotis G Asteris1, Eleni Gavriilaki2, Tasoula Touloumenidou2
1Computational Mechanics Laboratory, School of Pedagogical and Technological Education, Athens, Greece.
Insights
This study identifies critical complement gene variants and develops an artificial neural network (ANN) to predict severe Coronavirus disease-19 (COVID-19) outcomes. The findings link genetic variations to impaired complement function, improving early risk assessment for COVID-19 patients.
Area of Science:
- Immunogenetics
- Computational Biology
- Infectious Diseases
Background:
- An early prediction model for Coronavirus disease-19 (COVID-19) morbidity and mortality is needed.
- The complement system plays a role in immune response and may influence COVID-19 severity.
- Genetic variations within complement pathway genes could impact clinical outcomes.
Purpose of the Study:
- To identify complement-related genetic variants associated with COVID-19 ICU hospitalization and death.
- To develop an artificial neural network (ANN) for predicting these severe outcomes.
- To validate the association between identified variants and impaired complement phenotypes.
Main Methods:
- Prospective recruitment of adult Caucasian patients hospitalized with COVID-19.
- Targeted next-generation sequencing to identify variants in complement and related genes.
- Development and validation of an ANN using patient age, gender, and identified genetic variants.
Main Results:
- Identified 5 critical variants (in C3, THBD, CFH, CFHR1) associated with severe COVID-19 among 381 variants.
- Developed an ANN that predicted morbidity and mortality with 89.47% accuracy.
- Observed significantly increased THBD and C3a levels in severe COVID-19 patients with relevant variants, indicating impaired complement function.
Conclusions:
- An ANN model accurately predicts ICU hospitalization and death in COVID-19 patients using complement gene variants, age, and gender.
- Genetic dysregulation in complement pathway genes is linked to impaired complement phenotype in severe COVID-19.
- This study provides a novel tool for early risk stratification of COVID-19 patients.
Abstract:
There is an unmet need of models for early prediction of morbidity and mortality of Coronavirus disease-19 (COVID-19). We aimed to a) identify complement-related genetic variants associated with the clinical outcomes of ICU hospitalization and death, b) develop an artificial neural network (ANN) predicting these outcomes and c) validate whether complement-related variants are associated with an impaired complement phenotype. We prospectively recruited consecutive adult patients of Caucasian origin, hospitalized due to COVID-19. Through targeted next-generation sequencing, we identified variants in complement factor H/CFH, CFB, CFH-related, CFD, CD55, C3, C5, CFI, CD46, thrombomodulin/THBD, and A Disintegrin and Metalloproteinase with Thrombospondin motifs (ADAMTS13). Among 381 variants in 133 patients, we identified 5 critical variants associated with severe COVID-19: rs2547438 (C3), rs2250656 (C3), rs1042580 (THBD), rs800292 (CFH) and rs414628 (CFHR1). Using age, gender and presence or absence of each variant, we developed an ANN predicting morbidity and mortality in 89.47% of the examined population. Furthermore, THBD and C3a levels were significantly increased in severe COVID-19 patients and those harbouring relevant variants. Thus, we reveal for the first time an ANN accurately predicting ICU hospitalization and death in COVID-19 patients, based on genetic variants in complement genes, age and gender. Importantly, we confirm that genetic dysregulation is associated with impaired complement phenotype.
