Using Data Mining Techniques to Diagnosis of the Covid-19 Effects on the Hospital Readmission

Zakur, Yahya and Mirashrafi, Seyed Bagher and Flaih, Laith (2023) Using Data Mining Techniques to Diagnosis of the Covid-19 Effects on the Hospital Readmission. In: The third affiliation address has been corrected from “Cihan University” to “Cihan University-Erbil”, on June 7, 2024, August8-9\2023, Indonesia.

[thumbnail of Conference paper] Text (Conference paper)
Article_EWC_17-11-2023.pdf - Published Version
Available under License Creative Commons Attribution Non-commercial No Derivatives.

Download (2MB)

Abstract

The COVID-19 pandemic led to a substantial increase in the volume, diversity, and output pace of healthcare data. Countries depended on traditional methods to monitor diseases and public health to manage the epidemic, while advanced technology such as artificial intelligence and computation enabled efficient data processing. That datasets are usually enormous, growing exponentially, and comprise a collection of complicated item sets. To extract big, complicated itemsets, robust, straightforward, and computationally efficient techniques are crucial. Based on concepts from computer science, machine learning, and data mining, the Apriori method is a viable approach for supporting the values of database items in this study. There are two distinct implementation methods for Apiori: low confidence and support (Apiori algorithm) and the Apriori property algorithm. In conclusion, the performance of the Apriori property algorithm was superior to that of the traditional Apriori algorithm.

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: Data Mining, Covid-19, Hospital Readmission, Diagnosis, Healthcare Analytics.
Subjects: Q Science > Q Science (General)
T Technology > T Technology (General)
Divisions: Department of Computer Science > Research papers
Depositing User: ePrints Depositor
Date Deposited: 20 Nov 2024 15:26
Last Modified: 20 Nov 2024 15:26
URI: https://eprints.cihanuniversity.edu.iq/id/eprint/2856

Actions (login required)

View Item
View Item