1. Introduction
Since December 2019, a cohort of patients in Wuhan, Hubei Province,
China, has suffered from unknown etiology acute respiratory disease. The
first cases showed a connection to the Huanan wholesale market for
seafood. The Chinese Centre for Disease Control and Prevention (CDC)
found a new coronavirus, previously referred to by the International
Committee on Taxonomy of Viruses (ICTV) as severe acute respiratory
syndrome coronavirus 2 (SARS-CoV-2, formerly referred to as 2019-nCoV),
by analyzing the patient’s throat swab sample. Human
angiotensin-converting enzyme 2 (ACE2) molecules strongly interact with
the SARS-CoV-2 Spike protein’s receptor-binding domain (RBD). This gives
human respiratory epithelial cells a high infectious proficiency of the
virus. The virus induces exhaustion, fever, cough, and serious or
moderate breathing impediments. SARS-CoV-2 is referred to as Coronavirus
Disease 2019 (COVID-19), which showed moderate symptoms in the majority
of patients (1). Early disease detection helps to provide necessary,
appropriate care for clinicians. The clinical and epidemiological
features of coronavirus were examined by Zheng et al. (2). Treatment,
radiological, laboratory, clinical, demographic, and epidemiological
data were used for 99 confirmed patients in China with COVID-19. As
typical symptoms, they reported fever, tiredness, and dry cough. The
median age of patients registered is 49 years, 41 percent had the
underlying disorder, 49 percent had near interaction with patients
affected by COVID19, and 42 percent had resided or traveled to Wuhan.
Lower counts of CD8 and CD4, lower white blood cells, lymphocytes, and
neutrophils; higher levels of natriuretic peptides in the brain; higher
myocardial damage levels, and higher C-reactive proteins can be used for
early detection of disease in seriously ill patients. (1).
The severity of the COVID-19 pandemic is associated with the survival of
individuals, and evaluating the level of severity, especially in
individuals with chronic diseases, improves the quality of life and can
reduce the mortality rates caused by this virus. The severity of the
COVID-19 disease was divided into four stages, i.e., mild, moderate,
extreme, and serious, in accordance with the Guidelines provided by the
Ministry of Health, Labor and Welfare, Japan, on the Diagnosis and
Treatment of Novel Coronavirus. In short, the mild disease was
characterized as a lack of respiratory symptoms, no radiological
pulmonary manifestations, and levels of oxygen saturation (SpO2) of
about 96 percent. The moderate disease was defined as mild respiratory
symptoms, 93 percent < SpO2 < 96 percent, and
radiological evidence of pneumonia. Severe cases were described as
oxygen support requiring SpO2 93 percent. Critical was described as
requiring support for acute respiratory distress syndrome (ARDS) by the
heart-lung machine or extracorporeal membrane oxygenation (ECMO) (3).
Medical signs, personal traits, and demographic characteristics were
strongly associated with COVID-19 infection in various research studies.
Other clinical characteristics, specifically obesity, cardiovascular
disease, and hypertension, have also been reported in studies as
important factors influencing the rate of COVID19 infection. On the
other hand, studies discuss the demographic characteristics strongly
associated with COVID-19 disease worldwide, such as a country’s gross
domestic product ratio, smoking prevalence, a country’s average annual
temperature, etc. (4).
Understanding clinical/demographic features, progression, and prognosis
of the COVID-19 disease may help recognize critically ill patients,
provide appropriate care, and avoid mortality (5). In light of this
important data, this research aims to design an intelligent model that
predicts the disease severity level by modeling the relationships
between the severity of COVID-19 infection and the various
demographic/clinical characteristics of individuals.