Document Type

Journal Article

Publication Title

Scientific Reports

Volume

14

Issue

1

PubMed ID

38688931

Publisher

Nature

School

School of Science

Comments

Islam, M. N., Islam, M. S., Shourav, N. H., Rahman, I., Faisal, F. A., Islam, M. M., & Sarker, I. H. (2024). Exploring post-COVID-19 health effects and features with advanced machine learning techniques. Scientific Reports, 14, article 9884. https://doi.org/10.1038/s41598-024-60504-w

Abstract

COVID-19 is an infectious respiratory disease that has had a significant impact, resulting in a range of outcomes including recovery, continued health issues, and the loss of life. Among those who have recovered, many experience negative health effects, particularly influenced by demographic factors such as gender and age, as well as physiological and neurological factors like sleep patterns, emotional states, anxiety, and memory. This research aims to explore various health factors affecting different demographic profiles and establish significant correlations among physiological and neurological factors in the post-COVID-19 state. To achieve these objectives, we have identified the post-COVID-19 health factors and based on these factors survey data were collected from COVID-recovered patients in Bangladesh. Employing diverse machine learning algorithms, we utilised the best prediction model for post-COVID-19 factors. Initial findings from statistical analysis were further validated using Chi-square to demonstrate significant relationships among these elements. Additionally, Pearson’s coefficient was utilized to indicate positive or negative associations among various physiological and neurological factors in the post-COVID-19 state. Finally, we determined the most effective machine learning model and identified key features using analytical methods such as the Gini Index, Feature Coefficients, Information Gain, and SHAP Value Assessment. And found that the Decision Tree model excelled in identifying crucial features while predicting the extent of post-COVID-19 impact.

DOI

10.1038/s41598-024-60504-w

Creative Commons License

Creative Commons Attribution 4.0 License
This work is licensed under a Creative Commons Attribution 4.0 License.

Share

 
COinS