@inproceedings{f73a913efbd04fc6b0a81a471000ac6d,
title = "Utilizing Brain Region Volume Estimations to Enhance Interpretability of Decision Trees for Alzheimer's Disease Classification",
abstract = "While numerous artificial intelligence (AI) models based on deep learning have been proposed for diagnosing Alzheimer's disease from MRI images, their lack of explainability remains a challenge. In this study, we introduce an alternative transparent model using decision trees and propose a novel method for producing explainable predictions. Our approach involves processing MRI data by considering the percentage of brain regions as input to the decision tree, rather than traditional volumetric data. The resulting self-explanatory decision tree model transforms its binary tree graph into a rule-path shape, facilitating easy tracing of the generated tree's path. Our study demonstrates that the accuracy of decision trees can reach 97% using a region-percentage approach, which is an increase from the 71% accuracy obtained with the conventional volumetric approach.",
keywords = "Alzheimer's disease, brain volume region, decision tree, self-explanatory",
author = "Le Sang and Isack Farady and Kuo, {Chia Chen} and Lin, {Po Chiang} and Lin, {Chih Yang}",
note = "Publisher Copyright: {\textcopyright} 2024 IEEE.; 11th IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2024 ; Conference date: 09-07-2024 Through 11-07-2024",
year = "2024",
doi = "10.1109/ICCE-Taiwan62264.2024.10674181",
language = "???core.languages.en_GB???",
series = "11th IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2024",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "311--312",
booktitle = "11th IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2024",
}