A multilayer multimodal detection and prediction model based on explainable artificial intelligence for Alzheimer's disease.
A multilayer multimodal detection and prediction model based on explainable artificial intelligence for Alzheimer's disease.
复制标题
基于可解释人工智能的多层多模态阿尔茨海默病检测与预测模型。
DOI：
10.1038/s41598-021-82098-3
复制
发表时间：
2021-01-29
影响因子：
4.6
通讯作者：
Kwak KS
中科院分区：
文献类型：
--
作者：
El-Sappagh S;Alonso JM;Islam SMR;Sultan AM;Kwak KS
阿尔茨海默病（AD）是最常见的痴呆类型。其诊断和进展检测已被深入研究。然而，研究通常对临床实践影响不大，主要原因如下：（1）大多数研究主要依赖于单一模式，特别是神经影像学;（2）诊断和进展检测通常作为两个独立的问题单独研究;（3）当前的研究主要集中在优化复杂机器学习模型的性能，而忽略了它们的可解释性。因此，医生们很难解释这些模型，也很难相信它们。在本文中，我们仔细开发了一个准确和可解释的AD诊断和进展检测模型。该模型为医生提供了准确的决策沿着，并为每个决策提供了一组解释。具体而言，该模型整合了来自阿尔茨海默病神经成像倡议（ADNI）真实世界数据集的1048名受试者的11种模式：294名认知正常，254名稳定的轻度认知障碍（MCI），232名进行性MCI和268名AD。它实际上是一个两层模型，使用随机森林（RF）作为分类器算法。在第一层中，该模型对AD患者的早期诊断进行了多类分类。在第二层中，该模型应用二元分类来检测从基线诊断起三年内可能的MCI到AD的进展。该模型的性能通过从大量生物学和临床测量中选择的关键标志物进行优化。关于可解释性，我们提供，为每一层，全球和基于实例的解释RF分类器使用SHapley加法解释（SHAP）的特征属性框架。此外，我们实现了22个基于决策树和模糊规则系统的解释器，为每一层的每一个RF决策提供互补的理由。此外，这些解释以自然语言形式表示，以帮助医生理解预测。所设计的模型在第一层中实现了93.95%的交叉验证准确率和93.94%的F1分数，而在第二层中实现了87.08%的交叉验证准确率和87.09%的F1分数。由此产生的系统不仅准确，而且值得信赖，负责，医学上适用，这要归功于所提供的解释，这些解释彼此之间以及与AD医学文献大致一致。拟议的系统可以帮助提高AD的诊断和进展过程的临床理解，提供详细的见解，不同的方式对疾病风险的影响。
Alzheimer’s disease (AD) is the most common type of dementia. Its diagnosis and progression detection have been intensively studied. Nevertheless, research studies often have little effect on clinical practice mainly due to the following reasons: (1) Most studies depend mainly on a single modality, especially neuroimaging; (2) diagnosis and progression detection are usually studied separately as two independent problems; and (3) current studies concentrate mainly on optimizing the performance of complex machine learning models, while disregarding their explainability. As a result, physicians struggle to interpret these models, and feel it is hard to trust them. In this paper, we carefully develop an accurate and interpretable AD diagnosis and progression detection model. This model provides physicians with accurate decisions along with a set of explanations for every decision. Specifically, the model integrates 11 modalities of 1048 subjects from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) real-world dataset: 294 cognitively normal, 254 stable mild cognitive impairment (MCI), 232 progressive MCI, and 268 AD. It is actually a two-layer model with random forest (RF) as classifier algorithm. In the first layer, the model carries out a multi-class classification for the early diagnosis of AD patients. In the second layer, the model applies binary classification to detect possible MCI-to-AD progression within three years from a baseline diagnosis. The performance of the model is optimized with key markers selected from a large set of biological and clinical measures. Regarding explainability, we provide, for each layer, global and instance-based explanations of the RF classifier by using the SHapley Additive exPlanations (SHAP) feature attribution framework. In addition, we implement 22 explainers based on decision trees and fuzzy rule-based systems to provide complementary justifications for every RF decision in each layer. Furthermore, these explanations are represented in natural language form to help physicians understand the predictions. The designed model achieves a cross-validation accuracy of 93.95% and an F1-score of 93.94% in the first layer, while it achieves a cross-validation accuracy of 87.08% and an F1-Score of 87.09% in the second layer. The resulting system is not only accurate, but also trustworthy, accountable, and medically applicable, thanks to the provided explanations which are broadly consistent with each other and with the AD medical literature. The proposed system can help to enhance the clinical understanding of AD diagnosis and progression processes by providing detailed insights into the effect of different modalities on the disease risk.
登录
查看更多内容
毕竟有希望：量化神经网络中的意见和可信度。
影响因子：
4
作者：
Cheng M;Nazarian S;Bogdan P
通讯作者：
Bogdan P
DOI：
10.1109/tbme.2015.2404809
发表时间：
2015-07
期刊：
IEEE transactions on bio-medical engineering
影响因子：
--
作者：
Cheng B;Liu M;Zhang D;Munsell BC;Shen D
通讯作者：
Shen D
影响因子：
4.6
作者：
Ding X;Bucholc M;Wang H;Glass DH;Wang H;Clarke DH;Bjourson AJ;Dowey LRC;O'Kane M;Prasad G;Maguire L;Wong-Lin K
通讯作者：
Wong-Lin K
影响因子：
3.9
作者：
El-Sappagh, Shaker;Alonso, Jose M.;Kwak, Kyung-Sup
通讯作者：
Kwak, Kyung-Sup
影响因子：
3.9
作者：
Adadi, Amina;Berrada, Mohammed
通讯作者：
Berrada, Mohammed