Covid severity prediction: Who cares about the data quality?

Teodora Nae, Johannes Krabbe, Faiza Allah Bukhsh, Jeewanie Jayasinghe Arachchige, Faizan Ahmed

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

44 Downloads (Pure)

Abstract

COVID-19 is an ongoing pandemic disrupting daily life and overwhelming the healthcare infrastructure. Since the outburst of the pandemic, researchers have used various techniques to predict many aspects of the disease, including mortality rate and severity. The reproducibility of this research is challenging due to varying methodologies used to collect data, data quality, vague description of methodological approach to training prediction models, over-relying on data imputation, and over-fitting. This paper focuses on these challenges and provides a short yet comprehensive review of research on COVID mortality and severity prediction. The emphasis is on the reproducibility of the results and data quality issues. To further elaborate on the issue, we report the development of severity prediction models using two data sets. CRISP-DM is used as a methodological approach. We analyze and criticize the quality of the used data sets and how they affect the performance and limitations of the trained models. We conclude this paper with comments on data quality issues, the importance of reproducibility, and suggestions to improve reproducibility.
Original languageEnglish
Title of host publicationCovid severity prediction: Who cares about the data quality?
Place of PublicationIslamabad, Pakistan
PublisherIEEE
Pages225-230
Number of pages6
ISBN (Electronic)979-8-3503-4593-3
ISBN (Print)979-8-3503-4594-0
DOIs
Publication statusPublished - 17 Feb 2023
Event19th International Conference on Frontiers of Information Technology, FIT 2022 - Islamabad, Pakistan
Duration: 12 Dec 202213 Dec 2022
Conference number: 19

Conference

Conference19th International Conference on Frontiers of Information Technology, FIT 2022
Abbreviated titleFIT 2022
Country/TerritoryPakistan
CityIslamabad
Period12/12/2213/12/22

Keywords

  • COVID-19
  • Training
  • Support vector machines
  • Pandemics
  • Data integrity
  • , Biological system modeling
  • Medical services
  • 2023 OA procedure

Fingerprint

Dive into the research topics of 'Covid severity prediction: Who cares about the data quality?'. Together they form a unique fingerprint.

Cite this