COVID-19 in Bangladesh: An Exploratory Data Analysis and Prediction of Neurological Syndrome Using Machine Learning Algorithms Based on Comorbidity
Lecture Notes on Data Engineering and Communications Technologies
; 132:595-608, 2022.
Article
in English
| Scopus | ID: covidwho-1990589
ABSTRACT
COVID-19 is caused by the SARS-CoV-2 virus, which has infected millions of people worldwide and claimed many lives. This highly contagious virus can infect people of all ages, but the symptoms and fatality are higher in elderly and comorbid patients. Many COVID-19 survivors have experienced a number of clinical consequences following their recovery. In order to have better knowledge about the long-COVID effects, we focused on the immediate and post-COVID-19 consequences in healthy and comorbid individuals and developed a statistical model based on comorbidity in Bangladesh. The dataset was gathered through a phone conversation with patients who had been infected with COVID-19 and had recovered. The results demonstrated that out of 705 patients, 66.3% were comorbid individuals prior to COVID-19 infection. Exploratory data analysis showed that the clinical complications are higher in the comorbid patients following COVID-19 recovery. Comorbidity-based analysis of long-COVID neurological consequences was investigated and risk of mental confusion was predicted using a variety of machine learning algorithms. On the basis of the accuracy evaluation metrics, decision trees provide the most accurate prediction. The findings of the study revealed that individuals with comorbidity have a greater likelihood of experiencing mental confusion after COVID-19 recovery. Furthermore, this study is likely to assist individuals dealing with immediate and post-COVID-19 complications and its management. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
Comorbidity; COVID-19; Exploratory data analysis; Long-COVID; Mental confusion; Data handling; Decision trees; Epidemiology; Learning algorithms; Machine learning; Neurology; Recovery; Risk assessment; Viruses; Bangladesh; Comorbidities; Data prediction; Machine learning algorithms; Model-based OPC; Phone conversations; Statistic modeling
Full text:
Available
Collection:
Databases of international organizations
Database:
Scopus
Type of study:
Prognostic study
Language:
English
Journal:
Lecture Notes on Data Engineering and Communications Technologies
Year:
2022
Document Type:
Article
Similar
MEDLINE
...
LILACS
LIS