Requirement analysis for an artificial intelligence model for the diagnosis of the COVID-19 from chest X-ray data

  title={Requirement analysis for an artificial intelligence model for the diagnosis of the COVID-19 from chest X-ray data},
  author={Tuomo Kalliokoski},
  journal={2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)},
  • T. Kalliokoski
  • Published 24 October 2021
  • Medicine
  • 2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)
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… 

Figures and Tables from this paper


Common pitfalls and recommendations for using machine learning to detect and prognosticate for COVID-19 using chest radiographs and CT scans
It is found that none of the models identified are of potential clinical use due to methodological flaws and/or underlying biases, which is a major weakness, given the urgency with which validated COVID-19 models are needed.
Curbing the AI-induced enthusiasm in diagnosing COVID-19 on chest X-Rays: the present and the near-future
The authors intended to create and validate an ML software solution able to discriminate on the basis of the CXR between SARS-CoV-2-induced bronchopneumonia and other bronchipneumonia etiologies, and raise public awareness about the quality of AI protocols and algorithms and to encourage public sharing of as many CxR images with common quality standards.
AI for radiographic COVID-19 detection selects shortcuts over signal
It is demonstrated that recent deep learning systems to detect COVID-19 from chest radiographs rely on confounding factors rather than medical pathology, creating an alarming situation in which the systems appear accurate, but fail when tested in new hospitals.
How far have we come? Artificial intelligence for chest radiograph interpretation.
Discovery of a Generalization Gap of Convolutional Neural Networks on COVID-19 X-Rays Classification
It is shown that good generalization to unseen sources has not been achieved and deep learned models may leverage source specific confounders to differentiate COVID-19 from pneumonia preventing generalizing to new data sources (i.e. external sites).
ML4H Auditing: From Paper to Practice
This work targets the paper-to-practice gap by applying an ML4H audit framework proposed by the ITU/WHO Focus Group on Artificial Intelligence for Health (FG-AI4H) to three use cases: diagnostic prediction of diabetic retinopathy, diagnostic predictions of Alzheimer’s disease, and cytomorphologic classification for leukemia diagnostics.
Opening the black box of AI‐Medicine
In order to implement AI medicine successfully, interpretability of ML algorithm needs to improve and opening the black box in AI medicine needs to take a stepwise approach.
An adversarial approach for the robust classification of pneumonia from chest radiographs
Improved out-of-hospital generalization performance of a pneumonia classifier is demonstrated by training a model that is invariant to the view position of chest radiographs (anterior-posterior vs. posterior-anterior).