Genetic justification of COVID-19 patient outcomes using DERGA, a novel data ensemble refinement greedy algorithm
Panagiotis G Asteris1, Amir H Gandomi2,3, Danial J Armaghani4
1Computational Mechanics Laboratory, School of Pedagogical and Technological Education, Athens, Greece.
Insights
Predicting COVID-19 severity is crucial. This study identified key complement genetic variants using AI, achieving 97% accuracy in predicting patient outcomes and hospital admission needs.
Area of Science:
- Immunology
- Genetics
- Computational Biology
Background:
- Complement inhibition shows therapeutic potential in diseases like COVID-19.
- Accurate prediction of disease severity is essential for patient management.
- Identifying genetic factors influencing complement activity is critical for personalized medicine.
Purpose of the Study:
- To identify key complement genetic variants associated with COVID-19 outcomes.
- To develop an AI-based prediction tool for disease severity.
- To determine an optimal pattern of genetic variants for accurate outcome prediction.
Main Methods:
- Analysis of genetic data from 204 hospitalized COVID-19 patients.
- Utilized an artificial intelligence (AI)-based algorithm for outcome prediction (ICU vs. non-ICU admission).
- Employed the alpha-index to identify predictive genetic variants and the DERGA algorithm for pattern determination.
Main Results:
- Identified 30 highly predictive complement genetic variants using the alpha-index.
- The DERGA algorithm achieved 97% accuracy in predicting COVID-19 disease outcome.
- Detected a total of 977 variants, with individual variations ranging from 40 to 161 per patient.
Conclusions:
- The alpha-index is effective for ranking numerous genetic variants.
- AI-driven analysis of complement genetic variants enables highly accurate prediction of disease outcomes.
- This approach facilitates the development of predictive tools for personalized COVID-19 management.
Abstract:
Complement inhibition has shown promise in various disorders, including COVID-19. A prediction tool including complement genetic variants is vital. This study aims to identify crucial complement-related variants and determine an optimal pattern for accurate disease outcome prediction. Genetic data from 204 COVID-19 patients hospitalized between April 2020 and April 2021 at three referral centres were analysed using an artificial intelligence-based algorithm to predict disease outcome (ICU vs. non-ICU admission). A recently introduced alpha-index identified the 30 most predictive genetic variants. DERGA algorithm, which employs multiple classification algorithms, determined the optimal pattern of these key variants, resulting in 97% accuracy for predicting disease outcome. Individual variations ranged from 40 to 161 variants per patient, with 977 total variants detected. This study demonstrates the utility of alpha-index in ranking a substantial number of genetic variants. This approach enables the implementation of well-established classification algorithms that effectively determine the relevance of genetic variants in predicting outcomes with high accuracy.
More Related Videos
Related Concept Videos
Single Nucleotide Polymorphisms-SNPs
Human Genetics
The complex relationship between genetics and psychology is observable through common biological components such...
Genome-wide Association Studies-GWAS
GWAS does not require the identification of the target gene involved in...
Exon Recombination
Exon shuffling follows “splice frame rules.” Each exon...
Incomplete Dominance
What is Genetic Engineering?


