A4 Article in conference proceedings
Requirement analysis for an artificial intelligence model for the diagnosis of the COVID-19 from chest X-ray data (2021)

Kalliokoski, T. (2021). Requirement analysis for an artificial intelligence model for the diagnosis of the COVID-19 from chest X-ray data. In Y. Huang, L. Kurgan, F. Luo, X. Hu, Y. Chen, E. Dougherty, A. Kloczkowski, & Y. Li (Eds.), IEEE BIBM 2021 : Proceedings of the 2021 IEEE International Conference on Bioinformatics and Biomedicine, December 9-12, 2021, Virtual Event (pp. 3157-3164). IEEE. https://doi.org/10.1109/bibm52615.2021.9669525

JYU authors or editors

Publication details

All authors or editors: Kalliokoski, Tuomo

Parent publication: IEEE BIBM 2021 : Proceedings of the 2021 IEEE International Conference on Bioinformatics and Biomedicine, December 9-12, 2021, Virtual Event

Parent publication editors: Huang, Yufei; Kurgan, Lukasz; Luo, Feng; Hu, Xiaohua; Chen, Yidong; Dougherty, Edward; Kloczkowski, Andrzej; Li, Yaohang

Place and date of conference: Virtual event, 9.-12.12.2021

ISBN: 978-1-6654-0126-5

eISBN: 978-1-6654-2982-5

Publication year: 2021

Publication date: 09/12/2021

Pages range: 3157-3164

Publisher: IEEE

Publication country: United States

Publication language: English

DOI: https://doi.org/10.1109/bibm52615.2021.9669525

Publication open access: Not open

Publication channel open access: Channel is not openly available

Publication is parallel published (JYX): https://jyx.jyu.fi/handle/123456789/79514

Publication is parallel published: https://arxiv.org/abs/2110.12464

Web address of parallel published publication (pre-print): https://jyx.jyu.fi/handle/123456789/79514

Abstract

There are multiple papers published about different AI models for the COVID-19 diagnosis with promising results. Unfortunately according to the reviews many of the papers do not reach the level of sophistication needed for a clinically usable model. In this paper I go through multiple review papers, guidelines, and other relevant material in order to generate more comprehensive requirements for the future papers proposing a AI based diagnosis of the COVID-19 from chest X-ray data (CXR). Main findings are that a clinically usable AI needs to have an extremely good documentation, comprehensive statistical analysis of the possible biases and performance, and an explainability module.

Keywords: COVID-19; statistical models; statistical methods; artificial intelligence; diagnostics; forecasts; data systems; data models; medicine (science)

Free keywords: COVID-19; statistical analysis; data models; clinical diagnosis; artificial intelligence

Contributing organizations

Ministry reporting: Yes

Reporting Year: 2021

JUFO rating: 1