Influenza and anosmia: Important prediction factors for severity and death of COVID-19

Abstract

Objectives: To investigate the factors related to the severity and mo rtality of COVID-19 using big data-machine learning techniques. Methods: This study included 8070 patients in South Korea diagnosed with COVID-19 between January and July 2020, and whose data were available from the National-Health-Insurance-Service. Results: Machine-learning algorithms were performed to evaluate the effects of comorbidities on severity and mortality of COVID-19. The most common comorbidities of COVID-19 were pulmonary inflammation followed by hypertension. The model that best predicted severity was a neural network (AUC: 85.06%). The most important variable for predicting severity in the neural network model was a history of influenza (relative importance: 0.083). The model that best predicted mortality was the logistic regression elastic net (EN) model (AUC: 93.86%). The most important variables for mortality in the EN model were age (coefficient: 2.136) and anosmia (coefficient: –1.438). Conclusions: In COVID-19 patients, influenza was found to be a major adverse factor in addition to old age and male. In addition, anosmia was found to be a major factor associated with lower severity and mortality. Therefore, in the current situation where there is no adequate COVID-19 treatment at present, examining the patient's history of influenza vaccination and anosmia in addition to age and sex will be an important indicator for predicting the severity and mortality of COVID-19 patients.

COPD is a risk factor for COVID-19, but does not confer increased severity of the disease

“…among all patients who underwent SARS-CoV-2 testing, and the "secondary outcome" was severe disease or mortality of patients who tested positive for SARS-CoV-2. The definition of severe disease included: 1) requirement for oxygen supplementation, 2) intensive care unit (ICU) admission, 3) intubation with mechanical ventilation, or 4) application of extracorporeal membrane oxygenation (ECMO) [8,9]. We performed two rounds of propensity score (PS) matching to balance the baseline characteristics and reduce potential confounders.…”

Detection of COVID-19 and age-dependent dysosmia with paired crushable odorant ampules

“…The mean age of the patients seen in the clinic was 54.3 years, standard deviation 16.2. The median age of the respiratory clinic patients was 55 years; although olfactory dysfunction normally increases with age, in COVID-19 patients increasing age is correlated with lower prevalence of olfactory dysfunction (2), and lack of anosmia is associated with higher risk of severe illness and death in hospitalized patients(3, 14, 15). Uninfected patients in the current sample of patients over the age of 40 had 1.65 higher than expected incidence of anosmia; SARS-CoV-2 infection was associated with anosmia incidence ∼3.9 times higher than expected from the NHANES study (Table 2).…”

“…The risk of anosmia was 2.40 times greater if a patient displayed SARS-CoV-2 positivity (p= 0.0016, two tailed; Table 1). (2), and lack of anosmia is associated with higher risk of severe illness and death in hospitalized patients (3,14,15).…”

“…Olfactory dysfunction is a well-documented early sign of SARS-CoV-2 infection. Advancing age is correlated with olfactory dysfunction (1); but older COVID-19 patients have a lower prevalence of olfactory dysfunction (2), and the best predictors of death in hospitalized patients are age and a lack of anosmia (3). Conversely, COVID-19 patients with dysosmia have less severe symptoms (4, 5), are younger (6, 7), and have a better prognosis (3, 8-15); however, this may not hold for cases with prolonged anosmia (16-18).…”

“…Conversely, COVID-19 patients with dysosmia have less severe symptoms (4,5), are younger (6,7), and have a better prognosis (3,(8)(9)(10)(11)(12)(13)(14)(15); however, this may not hold for cases with prolonged anosmia (16)(17)(18).…”