Data Mining in the COVID-19: Application of Association Rules to Analyze Epidemiological Data of Patients in Mexico

Abstract

This research uses data mining methodology to extract information from a large database containing 1,048,576 records of COVID-19 patients in Mexico during 2023. The Apriori algorithm is used to find the association rules and analyze the clinical and demographic variables. The target is to find out the chance of intubation by the factor interaction. After preprocessing the data, the Apriori algorithm employs a minimum support of 21.6% and a minimum confidence of 60% to meet the market basket needs. In all, 833 association rules are produced, which establish connections between variables like lab findings, intensive care unit admission, chronic obstructive pulmonary disease or asthma diagnosis, and intubation requirements. Certain rules show very dependable correlations with confidence levels of 99%. The results enable proactive medical interventions and resource management by offering crucial information for the early identification of high-risk individuals. The study demonstrates how data mining techniques may be used to retrieve important information from huge epidemiological databases. To find hidden relationships in a large database of COVID-19 patients in Mexico, this work effectively uses the Apriori algorithm, producing vital data for public health decision-making.

Received: 25 December 2024 | Revised: 24 June 2025 | Accepted: 31 August 2025

Conflicts of Interest

The authors declare that they have no conflicts of interest to this work.

Data Availability Statement

The epidemiological dataset that supports the findings of this study is openly available at the Mexican Government’s DGE repository: https://datos.covid-19.conacyt.mx/.

Author Contribution Statement

Bogart Yail Marquez: Conceptualization, Software, Validation, Investigation, Resources, Data curation, Writing – original draft, Writing – review & editing, Visualization, Supervision, Project administration, Funding acquisition. Raul Barutch Pimienta-Gallardo: Validation, Formal analysis, Resources, Writing – review & editing, Visualization, Funding acquisition. Arturo Realyvásquez-Vargas: Methodology, Validation, Investigation, Resources, Writing – original draft, Visualization.