Centro Singular de Investigación en Tecnoloxías Intelixentes (CiTIUS), Universidade de Santiago de Compostela, 15782, Santiago de Compostela, Spain.
Information Systems Department, Faculty of Computers and Artificial Intelligence, Benha University, Banha, 13518, Egypt.
Sci Rep. 2021 Jan 29;11(1):2660. doi: 10.1038/s41598-021-82098-3.
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.
阿尔茨海默病（AD）是最常见的痴呆类型。人们对其诊断和进展检测进行了深入研究。然而，研究结果对临床实践的影响往往很小，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分别进行研究；（3）目前的研究主要集中在优化复杂机器学习模型的性能，而忽略了其可解释性。因此，医生难以解释这些模型，并且感到难以信任它们。在本文中，我们精心开发了一种准确且可解释的 AD 诊断和进展检测模型。该模型为医生提供了准确的决策，并为每个决策提供了一组解释。具体来说，该模型整合了来自阿尔茨海默病神经影像学倡议（ADNI）真实世界数据集的 11 种模态，共 1048 个样本：294 名认知正常者、254 名稳定轻度认知障碍（MCI）患者、232 名进展性 MCI 患者和 268 名 AD 患者。它实际上是一个两层模型，随机森林（RF）作为分类器算法。在第一层，该模型对 AD 患者进行多类分类，以进行早期诊断。在第二层，该模型对从基线诊断开始三年内可能发生的 MCI 到 AD 的进展进行了二元分类。通过从大量生物和临床指标中选择关键标记物对模型性能进行了优化。关于可解释性，我们使用 SHapley Additive exPlanations (SHAP) 特征归因框架，为每一层的 RF 分类器提供了全局和实例级别的解释。此外，我们基于决策树和基于模糊规则的系统实现了 22 个解释器，为每一层的每个 RF 决策提供了补充依据。此外，这些解释以自然语言的形式呈现，以帮助医生理解预测。在第一层，该模型在交叉验证中的准确率达到 93.95%，F1 分数达到 93.94%；在第二层，该模型在交叉验证中的准确率达到 87.08%，F1 分数达到 87.09%。由于提供的解释与 AD 医学文献广泛一致，并且彼此之间也具有一致性，因此该设计的模型不仅准确，而且值得信赖、可解释和适用于医学领域。该系统通过深入了解不同模式对疾病风险的影响，为 AD 诊断和进展过程提供了详细的见解，从而有助于提高临床医生对 AD 诊断和进展过程的理解。
