Evaluating the impact of an explainable machine learning system on the interobserver agreement in chest radiograph interpretation

Hieu H. Pham; Ha Q. Nguyen; Hieu T. Nguyen; Linh T. Le; Khanh Lam

Evaluating the impact of an explainable machine learning system on the interobserver agreement in chest radiograph interpretation

Image and Video Processing 2023-04-05 v1 Computer Vision and Pattern Recognition

Authors: Hieu H. Pham , Ha Q. Nguyen , Hieu T. Nguyen , Linh T. Le , Khanh Lam

Abstract

We conducted a prospective study to measure the clinical impact of an explainable machine learning system on interobserver agreement in chest radiograph interpretation. The AI system, which we call as it VinDr-CXR when used as a diagnosis-supporting tool, significantly improved the agreement between six radiologists with an increase of 1.5% in mean Fleiss' Kappa. In addition, we also observed that, after the radiologists consulted AI's suggestions, the agreement between each radiologist and the system was remarkably increased by 3.3% in mean Cohen's Kappa. This work has been accepted for publication in IEEE Access and this paper is our short version submitted to the Midwest Machine Learning Symposium (MMLS 2023), Chicago, IL, USA.

Keywords

explainable machine learning chest radiograph interobserver agreement vinDr-cxr fleiss' kappa cohen's kappa prospective study

Cite

@article{arxiv.2304.01220,
  title  = {Evaluating the impact of an explainable machine learning system on the interobserver agreement in chest radiograph interpretation},
  author = {Hieu H. Pham and Ha Q. Nguyen and Hieu T. Nguyen and Linh T. Le and Khanh Lam},
  journal= {arXiv preprint arXiv:2304.01220},
  year   = {2023}
}

Comments

This work has been accepted for publication in IEEE Access. This is a short version submitted to the Midwest Machine Learning Symposium (MMLS 2023), Chicago, IL, USA

Evaluating the impact of an explainable machine learning system on the interobserver agreement in chest radiograph interpretation

Abstract

Keywords

Cite

Comments

Related papers