Faculty of Computers and Artificial Intelligence, South Valley University, Hurghada, Egypt.
Communications and Information Technology, The Institute of Electronics, Queen's University of Belfast, Belfast, UK.
Sci Rep. 2023 Sep 28;13(1):16336. doi: 10.1038/s41598-023-42796-6.
Alzheimer's disease (AD) is the most common form of dementia. Early and accurate detection of AD is crucial to plan for disease modifying therapies that could prevent or delay the conversion to sever stages of the disease. As a chronic disease, patient's multivariate time series data including neuroimaging, genetics, cognitive scores, and neuropsychological battery provides a complete profile about patient's status. This data has been used to build machine learning and deep learning (DL) models for the early detection of the disease. However, these models still have limited performance and are not stable enough to be trusted in real medical settings. Literature shows that DL models outperform classical machine learning models, but ensemble learning has proven to achieve better results than standalone models. This study proposes a novel deep stacking framework which combines multiple DL models to accurately predict AD at an early stage. The study uses long short-term memory (LSTM) models as base models over patient's multivariate time series data to learn the deep longitudinal features. Each base LSTM classifier has been optimized using the Bayesian optimizer using different feature sets. As a result, the final optimized ensembled model employed heterogeneous base models that are trained on heterogeneous data. The performance of the resulting ensemble model has been explored using a cohort of 685 patients from the University of Washington's National Alzheimer's Coordinating Center dataset. Compared to the classical machine learning models and base LSTM classifiers, the proposed ensemble model achieves the highest testing results (i.e., 82.02, 82.25, 82.02, and 82.12 for accuracy, precision, recall, and F1-score, respectively). The resulting model enhances the performance of the state-of-the-art literature, and it could be used to build an accurate clinical decision support tool that can assist domain experts for AD progression detection.
阿尔茨海默病（AD）是最常见的痴呆症形式。早期、准确地发现 AD 对于计划进行疾病修饰治疗至关重要，这种治疗可以预防或延缓疾病向严重阶段的转化。作为一种慢性疾病，患者的多变量时间序列数据包括神经影像学、遗传学、认知评分和神经心理学测试，提供了关于患者状况的完整概况。这些数据已被用于构建机器学习和深度学习（DL）模型，以早期发现该疾病。然而，这些模型的性能仍然有限，在实际医疗环境中还不够稳定，无法被信任。文献表明，DL 模型的性能优于经典机器学习模型，但集成学习已被证明可以取得比独立模型更好的结果。本研究提出了一种新的深度堆叠框架，该框架结合了多个 DL 模型，以准确预测早期 AD。该研究使用长短期记忆（LSTM）模型作为基础模型，处理患者的多变量时间序列数据，以学习深度纵向特征。每个基础 LSTM 分类器都使用贝叶斯优化器使用不同的特征集进行优化。结果，最终优化的集成模型采用了在异构数据上训练的异构基础模型。使用来自华盛顿大学国家阿尔茨海默病协调中心数据集的 685 名患者队列，研究人员探索了所提出的集成模型的性能。与经典机器学习模型和基础 LSTM 分类器相比，所提出的集成模型的测试结果最高（即准确性、精确率、召回率和 F1 分数分别为 82.02、82.25、82.02 和 82.12）。所提出的模型提高了现有文献的性能，可用于构建一个精确的临床决策支持工具，帮助领域专家进行 AD 进展检测。
