Machine learning in the diagnosis of asthma phenotypes during coronavirus disease 2019 pandemic.

Background: During the coronavirus disease 2019 (COVID-19) pandemic, it has become a pressing need to be able to diagnose aspirin hypersensitivity in patients with asthma without the need to use oral aspirin challenge (OAC) testing. OAC is time consuming and is associated with the risk of severe hypersensitive reactions. In this study, we sought to investigate whether machine learning (ML) based on some clinical and laboratory procedures performed during the pandemic might be used for discriminating between patients with aspirin hypersensitivity and those with aspirin-tolerant asthma. Methods: We used a prospective database of 135 patients with non-steroidal anti-inflammatory drug (NSAID)-exacerbated respiratory disease (NERD) and 81 NSAID-tolerant (NTA) patients with asthma who underwent OAC. Clinical characteristics, inflammatory phenotypes based on sputum cells, as well as eicosanoid levels in induced sputum supernatant and urine were extracted for the purpose of applying ML techniques. Results: The overall best ML model, neural network (NN), trained on a set of best features, achieved a sensitivity of 95% and a specificity of 76% for diagnosing NERD. The 3 promising models (i.e., multiple logistic regression, support vector machine, and NN) trained on a set of easy-to-obtain features including only clinical characteristics and laboratory data achieved a sensitivity of 97% and a specificity of 67%. Conclusions: ML techniques are becoming a promising tool for discriminating between patients with NERD and NTA. The models are easy to use, safe, and achieve very good results, which is particularly important during the COVID-19 pandemic.

A simple method to describe the COVID-19 trajectory and dynamics in any country based on Johnson cumulative density function fitting.

A simple method is utilised to study and compare COVID-19 infection dynamics between countries based on curve fitting to publicly shared data of confirmed COVID-19 infections. The method was tested using data from 80 countries from 6 continents. We found that Johnson cumulative density functions (CDFs) were extremely well fitted to the data (R2 > 0.99) and that Johnson CDFs were much better fitted to the tails of the data than either the commonly used normal or lognormal CDFs. Fitted Johnson CDFs can be used to obtain basic parameters of the infection wave, such as the percentage of the population infected during an infection wave, the days of the start, peak and end of the infection wave, and the duration of the wave's increase and decrease. These parameters can be easily interpreted biologically and used both for describing infection wave dynamics and in further statistical analysis. The usefulness of the parameters obtained was analysed with respect to the relation between the gross domestic product (GDP) per capita, the population density, the percentage of the population infected during an infection wave, the starting day and the duration of the infection wave in the 80 countries. We found that all the above parameters were significantly associated with GDP per capita, but only the percentage of the population infected was significantly associated with population density. If used with caution, this method has a limited ability to predict the future trajectory and parameters of an ongoing infection wave.