[Paper Review] Association Learning Between the COVID-19 Infections and Global Demographic Characteristics Using the Class Rule Mining and Pattern Matching

Wasiq Khan, Abrar Hussain+3 more|arXiv (Cornell University)|Sep 27, 2020

COVID-19 epidemiological studies32 references4 citations

TL;DR

This study proposes an intelligent model combining class rule mining and pattern matching to uncover multi-dimensional associations between global demographic attributes and COVID-19 severity levels. Using self-organizing maps, class association rules, and statistical analysis on data up to 20 August 2020, it identifies strong links—particularly involving female smokers—suggesting demographic distributions significantly influence disease progression and severity across regions.

ABSTRACT

Over 26 million cases have been confirmed worldwide (by 20 August 2020) since the Coronavirus disease (COIVD_19) outbreak in December 2019. Research studies have been addressing diverse aspects in relation to COVID_19 including potential symptoms, predictive tools and specifically, correlations with various demographic attributes. However, very limited work is performed towards the modelling of complex associations between the combined demographic attributes and varying nature of the COVID_19 infections across the globe. Investigating the underlying disease associations with the combined demographical characteristics might help in comprehensive analysis this devastating disease as well as contribute to its effective management. In this study, we present an intelligent model to investigate the multi-dimensional associations between the potentially relevant demographic attributes and the COVID_19 severity levels across the globe. We gather multiple demographic attributes and COVID_19 infection data (by 20 August 2020) from various reliable sources, which is then fed-into pattern matching algorithms that include self-organizing maps, class association rules and statistical approaches, to identify the significant associations within the processed dataset. Statistical results and the experts report indicate strong associations between the COVID_19 severity levels and measures of certain demographic attributes such as female smokers, when combined together with other attributes. These results strongly suggest that the mechanism underlying COVID_19 infection severity is associated to distribution of the certain demographic attributes within different regions of the world. The outcomes will aid the understanding of the dynamics of disease spread and its progression that might in turn help the policy makers and the society, in better understanding and management of the disease.

Motivation & Objective

• To model complex associations between combined demographic attributes and COVID-19 infection severity across global regions.
• To address the limited research on multi-dimensional demographic influences on disease progression and severity.
• To support public health policy by identifying high-risk demographic clusters linked to severe outcomes.
• To integrate pattern matching techniques with statistical validation for robust association discovery.

Proposed method

• Gathered global demographic and COVID-19 infection data from reliable sources up to 20 August 2020.
• Applied self-organizing maps to detect underlying patterns in high-dimensional demographic and infection data.
• Employed class association rule mining to extract significant relationships between demographic features and COVID-19 severity levels.
• Integrated statistical analysis to validate the significance of discovered associations.
• Combined results with expert reports to assess clinical and epidemiological plausibility of findings.

Experimental results

Research questions

• RQ1 Which combinations of demographic attributes show strong associations with higher COVID-19 severity levels globally?
• RQ2 How do demographic distributions across regions correlate with variations in disease progression and severity?
• RQ3 What specific demographic groupings, such as female smokers, demonstrate significant predictive power for severe outcomes?
• RQ4 To what extent do pattern matching and rule mining techniques reveal non-obvious associations in multi-dimensional health data?

Key findings

• A strong association was identified between female smokers and increased COVID-19 severity, suggesting a significant demographic risk factor.
• The integration of self-organizing maps and class association rules revealed complex, non-linear relationships between demographic clusters and disease outcomes.
• Statistical validation and expert review confirmed the significance and plausibility of the identified associations.
• The model demonstrated that demographic distributions across regions are strongly linked to variations in disease severity patterns.
• The findings indicate that demographic attributes such as gender, smoking behavior, and regional distribution collectively influence the dynamics of disease spread and severity.