Обзорная статья

Explainable Artificial Intelligence Methods in Combating Pandemics: A Systematic Review

Felipe GiusteWallace H. Coulter School of Biomedical Engineering, Georgia Institute of Technology, Emory University, Atlanta, GA, USAWenqi ShiDepartment of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USAYuanda ZhuDepartment of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USATarun NarenDepartment of Nuclear and Radiological Engineering, Georgia Institute of Technology, Atlanta, GA, USAMonica IsgutSchool of Biology, Georgia Institute of Technology, Atlanta, GA, USAYing ShaWallace H. Coulter School of Biomedical Engineering, Georgia Institute of Technology, Emory University, Atlanta, GA, USATong LiWallace H. Coulter School of Biomedical Engineering, Georgia Institute of Technology, Emory University, Atlanta, GA, USAMitali GupteWallace H. Coulter School of Biomedical Engineering, Georgia Institute of Technology, Emory University, Atlanta, GA, USAMay D. WangWallace H. Coulter School of Biomedical Engineering, Georgia Institute of Technology, Emory University, Atlanta, GA, USA

2022en

ABI

Аннотация

Despite the myriad peer-reviewed papers demonstrating novel Artificial Intelligence (AI)-based solutions to COVID-19 challenges during the pandemic, few have made a significant clinical impact, especially in diagnosis and disease precision staging. One major cause for such low impact is the lack of model transparency, significantly limiting the AI adoption in real clinical practice. To solve this problem, AI models need to be explained to users. Thus, we have conducted a comprehensive study of Explainable Artificial Intelligence (XAI) using PRISMA technology. Our findings suggest that XAI can improve model performance, instill trust in the users, and assist users in decision-making. In this systematic review, we introduce common XAI techniques and their utility with specific examples of their application. We discuss the evaluation of XAI results because it is an important step for maximizing the value of AI-based clinical decision support systems. Additionally, we present the traditional, modern, and advanced XAI models to demonstrate the evolution of novel techniques. Finally, we provide a best practice guideline that developers can refer to during the model experimentation. We also offer potential solutions with specific examples for common challenges in AI model experimentation. This comprehensive review, hopefully, can promote AI adoption in biomedicine and healthcare.

Перевод пока недоступен

Идентификаторы

DOI: 10.1109/rbme.2022.3185953

Цитирования и источники

Цитирований: 2Использованных источников: 0

Показатели — AkademScholar