XGBoost-SHAP-based interpretable diagnostic framework for alzheimer's disease.
XGBoost-SHAP-based interpretable diagnostic framework for alzheimer's disease.
复制标题
DOI：
10.1186/s12911-023-02238-9
复制
发表时间：
2023-07-25
影响因子：
3.5
通讯作者：
Yu, Hongmei
中科院分区：
文献类型：
--
作者：
Yi, Fuliang;Yang, Hui;Chen, Durong;Qin, Yao;Han, Hongjuan;Cui, Jing;Bai, Wenlin;Ma, Yifei;Zhang, Rong;Yu, Hongmei
关键词：
由于阿尔茨海默病（AD）从正常认知（NC）发展到轻度认知障碍（MCI）时所面临的类别不平衡问题，目前的临床实践遇到了关于使用机器学习（ML）辅助诊断AD的挑战。这导致低诊断性能。我们的目的是构建一个可解释的框架，极端梯度提升-Shapley加性解释（XGBoost-SHAP），以处理不同AD进展状态之间的不平衡在算法层面。我们还试图实现NC，MCI和AD的多重分类。我们从阿尔茨海默病神经影像学倡议（ADNI）数据库中获得了患者数据，包括临床信息，神经心理学测试结果，神经影像学衍生的生物标志物和APOE-ε4基因状态。首先，应用三种特征选择算法，然后将它们包含在XGBoost算法中。由于三类之间的不平衡，我们改变了样本权重分布，以实现NC，MCI和AD的多分类。然后，SHAP方法连接到XGBoost，形成一个可解释的框架。该框架利用归因思想，将模型预测的影响量化为数值，并根据其方向和大小进行分析。随后，使用前10个特征（最佳子集）来简化临床决策过程，并将其性能与随机森林（RF），Bagging，AdaBoost和朴素贝叶斯（NB）分类器进行比较。最后，国家阿尔茨海默氏症协调中心（NACC）数据集被用来评估最佳子集内的功能的影响路径的一致性。与RF，Bagging，AdaBoost，NB和XGBoost（未加权）相比，可解释框架具有更高的分类性能，准确率分别提高了0.74%，0.74%，1.46%，13.18%和0.83%。该框架实现了高灵敏度（81.21%/74.85%），特异性（92.18%/89.86%），准确度（87.57%/80.52%），受试者工作特征曲线下面积（AUC）ADNI和NACC数据集上的阳性临床效用指数（0.91/0.88）、阳性临床效用指数（0.71/0.56）和阴性临床效用指数（0.75/0.68）。在ADNI数据集中，根据SHAP值，发现前10个特征与AD发病风险有不同的相关性。具体而言，CDRSB、ADAS 13、ADAS 11、心室容积、ADASQ 4和FAQ的SHAP值越高，AD发病风险越高。相反，LDELTOTAL、mPACCdigit、RAVLT_immediate和MMSE的SHAP值越高，AD发病风险越低。NACC数据集也发现了类似的结果。提出的可解释框架有助于在不平衡的AD多分类任务中实现优异的性能，并为临床决策提供科学指导（最佳子集），从而促进疾病管理，并为优化AD预防和治疗方案提供新的研究思路。在线版本包含补充材料，可通过10.1186/s12911-023-02238-9获得。
Due to the class imbalance issue faced when Alzheimer’s disease (AD) develops from normal cognition (NC) to mild cognitive impairment (MCI), present clinical practice is met with challenges regarding the auxiliary diagnosis of AD using machine learning (ML). This leads to low diagnosis performance. We aimed to construct an interpretable framework, extreme gradient boosting-Shapley additive explanations (XGBoost-SHAP), to handle the imbalance among different AD progression statuses at the algorithmic level. We also sought to achieve multiclassification of NC, MCI, and AD. We obtained patient data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database, including clinical information, neuropsychological test results, neuroimaging-derived biomarkers, and APOE-ε4 gene statuses. First, three feature selection algorithms were applied, and they were then included in the XGBoost algorithm. Due to the imbalance among the three classes, we changed the sample weight distribution to achieve multiclassification of NC, MCI, and AD. Then, the SHAP method was linked to XGBoost to form an interpretable framework. This framework utilized attribution ideas that quantified the impacts of model predictions into numerical values and analysed them based on their directions and sizes. Subsequently, the top 10 features (optimal subset) were used to simplify the clinical decision-making process, and their performance was compared with that of a random forest (RF), Bagging, AdaBoost, and a naive Bayes (NB) classifier. Finally, the National Alzheimer’s Coordinating Center (NACC) dataset was employed to assess the impact path consistency of the features within the optimal subset. Compared to the RF, Bagging, AdaBoost, NB and XGBoost (unweighted), the interpretable framework had higher classification performance with accuracy improvements of 0.74%, 0.74%, 1.46%, 13.18%, and 0.83%, respectively. The framework achieved high sensitivity (81.21%/74.85%), specificity (92.18%/89.86%), accuracy (87.57%/80.52%), area under the receiver operating characteristic curve (AUC) (0.91/0.88), positive clinical utility index (0.71/0.56), and negative clinical utility index (0.75/0.68) on the ADNI and NACC datasets, respectively. In the ADNI dataset, the top 10 features were found to have varying associations with the risk of AD onset based on their SHAP values. Specifically, the higher SHAP values of CDRSB, ADAS13, ADAS11, ventricle volume, ADASQ4, and FAQ were associated with higher risks of AD onset. Conversely, the higher SHAP values of LDELTOTAL, mPACCdigit, RAVLT_immediate, and MMSE were associated with lower risks of AD onset. Similar results were found for the NACC dataset. The proposed interpretable framework contributes to achieving excellent performance in imbalanced AD multiclassification tasks and provides scientific guidance (optimal subset) for clinical decision-making, thereby facilitating disease management and offering new research ideas for optimizing AD prevention and treatment programs. The online version contains supplementary material available at 10.1186/s12911-023-02238-9.
登录
查看更多内容
影响因子：
5.7
作者：
Dubey R;Zhou J;Wang Y;Thompson PM;Ye J;Alzheimer's Disease Neuroimaging Initiative
通讯作者：
Alzheimer's Disease Neuroimaging Initiative
影响因子：
2.2
作者：
Bruno D;Mueller KD;Betthauser T;Chin N;Engelman CD;Christian B;Koscik RL;Johnson SC
通讯作者：
Johnson SC
影响因子：
4.4
作者：
Bin Tufail, Ahsan;Ma, Yong-Kui;Zhang, Qiu-Na
通讯作者：
Zhang, Qiu-Na
影响因子：
7.7
作者：
Ebrahimi, Amir;Luo, Suhuai;Chiong, Raymond
通讯作者：
Chiong, Raymond
使用多模态数据的线性判别分析评分对阿尔茨海默病的各个阶段进行多类诊断
影响因子：
7.7
作者：
Lin, Weiming;Gao, Qinquan;Tong, Tong
通讯作者：
Tong, Tong