An Explainable AI Framework for Artificial Intelligence of Medical Things

TL;DR

This paper presents an explainable AI framework for medical applications, integrating multiple XAI techniques and ensemble deep learning to improve transparency and accuracy in brain tumor diagnosis within AIoMT systems.

Contribution

It introduces a novel XAI framework tailored for AIoMT, combining LIME, SHAP, Grad-Cam, and ensemble CNNs for transparent and accurate medical diagnosis.

Findings

Achieved 99% training accuracy and 98% validation accuracy.

Demonstrated high precision, recall, and F1 scores in brain tumor detection.

Enhanced trust and interpretability in AI-driven healthcare systems.

Abstract

The healthcare industry has been revolutionized by the convergence of Artificial Intelligence of Medical Things (AIoMT), allowing advanced data-driven solutions to improve healthcare systems. With the increasing complexity of Artificial Intelligence (AI) models, the need for Explainable Artificial Intelligence (XAI) techniques become paramount, particularly in the medical domain, where transparent and interpretable decision-making becomes crucial. Therefore, in this work, we leverage a custom XAI framework, incorporating techniques such as Local Interpretable Model-Agnostic Explanations (LIME), SHapley Additive exPlanations (SHAP), and Gradient-weighted Class Activation Mapping (Grad-Cam), explicitly designed for the domain of AIoMT. The proposed framework enhances the effectiveness of strategic healthcare methods and aims to instill trust and promote understanding in AI-driven medical applications. Moreover, we utilize a majority voting technique that aggregates predictions from multiple convolutional neural networks (CNNs) and leverages their collective intelligence to make robust and accurate decisions in the healthcare system. Building upon this decision-making process, we apply the XAI framework to brain tumor detection as a use case demonstrating accurate and transparent diagnosis. Evaluation results underscore the exceptional performance of the XAI framework, achieving high precision, recall, and F1 scores with a training accuracy of 99% and a validation accuracy of 98%. Combining advanced XAI techniques with ensemble-based deep-learning (DL) methodologies allows for precise and reliable brain tumor diagnoses as an application of AIoMT.