A Machine Learning Explanation of the Pathogen-Immune Relationship of SARS-CoV-2 (COVID-19), and a Model to Predict Immunity and Therapeutic Opportunity: A Comparative Effectiveness Research Study (Preprint)

Abstract

BACKGROUND Approximately 80% of those infected with COVID-19 are immune. They are asymptomatic unknown carriers who still can infect those with whom they come into contact. Understanding what makes them immune could inform public health policies as to who needs to be protected and why, and possibly lead to novel therapeutics for those who cannot, or will not, be vaccinated once a vaccine is available. The clinical impacts of this study are it: (1) identified three immunological factors that differentiate asymptomatic, or resistant, COVID-19 patients; (2) identified the levels of those factors that can be used by clinicians to predict who is likely to be asymptomatic or symptomatic; (3) identified a novel COVID-19 therapeutic for further testing; and, (4) ordinally ranked 34 common immunological factors by their importance in predicting disease severity. OBJECTIVE The primary objectives of this study were to learn if machine learning could identify patterns in the pathogen-host immune relationship that differentiate or predict COVID-19 symptom immunity and, if so, which ones and at what levels. The secondary objective was to learn if machine learning could take such differentiators to build a model that could predict COVID-19 immunity with clinical accuracy. The tertiary objective was to learn about the relevance of other immune factors. Design: This was a comparative effectiveness research study on 53 common immunological factors using machine learning on clinical data from 74 similarly-grouped Chinese COVID-19-positive patients, 37 of whom were symptomatic and 37 asymptomatic. Setting: A single-center primary-care hospital in the Wanzhou District of China. Participants: Immunological factors were measured in patients who were diagnosed as SARS-CoV-2 positive by reverse transcriptase-polymerase chain reaction (RT-PCR) in the 14 days before the recordation of the observations. The median age of the 37 asymptomatic patients was 41 years (range 8-75 years), 22 were female, 15 were male. For comparison, 37 RT-PCR test-positive patients were selected and matched to the asymptomatic group by age, comorbidities, and sex. Main Outcome: The primary study outcome was that asymptomatic COVID-19 patients could be identified by three distinct immunological factors and level: stem-cell growth factor-beta (SCGF-) (> 127637), interleukin-16 (IL-16) (> 45), and macrophage colony-stimulating factor (M-CSF) (> 57). The secondary study outcome was the novel suggestion that stem-cell therapy with SCGF- may be a new valuable therapeutic for COVID-19. METHODS This was a comparative effectiveness research study on 53 common immunological factors using machine learning on clinical data from 74 similarly-grouped Chinese COVID-19-positive patients, 37 of whom were symptomatic and 37 asymptomatic. The setting was a single-center primary-care hospital in the Wanzhou District of China. Immunological factors were measured in patients who were diagnosed as SARS-CoV-2 positive by reverse transcriptase-polymerase chain reaction (RT-PCR) in the 14 days before the recordation of the observations. The median age of the 37 asymptomatic patients was 41 years (range 8-75 years), 22 were female, 15 were male. For comparison, 37 RT-PCR test-positive patients were selected and matched to the asymptomatic group by age, comorbidities, and sex. Machine learning models were trained and compared to understand the pathogen-immune relationship and predict who was immune to COVID-19 and why using the statistical programming language R. RESULTS When SCGF- was included in the machine-learning analysis, a decision-tree and extreme gradient boosting algorithms classified and predicted COVID-19 symptoms immunity with 100% accuracy. When SCGF- was excluded, a random-forest algorithm classified and predicted COVID-19 asymptomatic and symptomatic cases with 94.8% area under the ROC curve accuracy (95% CI 90.17% to 100%). Thirty-four (34) common immune factors have statistically significant (P-value < .05) associations with COVID-19 symptoms and 19 immune factors appear to have no statistically significant association. CONCLUSIONS People with an SCGF- level > 127637, or an IL-16 level > 45 and M-CSF level > 57, appear to be predictively immune to COVID-19, 100%, and 94.8% (ROC AUC) of the time, respectively. Testing levels of these three immunological factors may be a valuable tool at the point-of-care for managing and preventing outbreaks. Further, stem-cell therapy via SCGF- and/or M-CSF appear to be promising novel therapeutics for COVID-19.