Explainable Artificial Intelligence Methods in Combating Pandemics: A Systematic Review

Abstract

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 decisionmaking. 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.

Explainable artificial intelligence incorporated with domain knowledge diagnosing early gastric neoplasms under white light endoscopy

“…Conversely, an explainable AI may increase the trust and acceptance of physicians and patients towards AI, reduce risks in healthcare, and is regulatory compliance of healthcare providers 14,15 . To achieve AI explainability in the medical field, many previous studies used a novel technique named LIME (Linear Interpretable Model-Agnostic Explanations) 16,17 .…”

A Review of the Role of Artificial Intelligence in Healthcare

“…In healthcare, doctors and patients can realize the reasons behind diagnosis using XAI, since it can explain diagnostic decisions made by AI [142]. A recent study found that XAI establishes trust in AI by giving visual feedback to the user regarding significant metrics that are used to obtain the model prediction [144]. Another study observed that XAI methods are required to improve radiologists' trust in classification predictions of CT images with the acquisition of numerous visual insights into the automatic workflow [145].…”

Explainable AI for unveiling deep learning pollen classification model based on fusion of scattered light patterns and fluorescence spectroscopy

“…Explainable AI (xAI) solutions for biomedical domain are attracting increasing scientific interest 36 . Emerging applications include drug discoveries 37 , cancer diagnosis 38 , microbiome studies 39 and clinical decision support systems in pandemics 40 . We believe that research community working on automatic pollen classification would highly benefit as well from xAI solutions providing insights into how classifiers make decisions.…”