|
|
基于脑结构特征和认知行为特征的阿尔茨海默症分类诊断
|
Abstract:
阿尔茨海默症是一种多发于老年人的神经退行性疾病，由于病程不可逆且无法治愈，因而及时发现该病早期阶段并采取针对性的治疗措施具有重要意义。本文基于脑结构特征和认知行为特征，辅以人口统计学特征和生物标志物，对阿尔茨海默症进行三分类和五分类诊断。将数据进行预处理后，采用随机森林对特征重要性进行排序，依据排序结果和各特征组合在机器学习模型中的表现，分别选取出15个、21个特征，用于训练随机森林、梯度提升树、CatBoost、LightGBM、XGBoost等机器学习模型。结果显示，LightGBM和XGBoost分别在阿尔茨海默症的三分类和五分类诊断中表现出优异性能，分类准确率分别为99.25%和95.94%，F1-分数分别为99.25%和95.92%。经过五折交叉验证可知，上述模型的性能和稳定性都比较出色。最后，对比两次诊断选取出的特征，为今后阿尔茨海默症的诊断提出部分建议。
Alzheimer’s disease is a kind of neurodegenerative disease which mainly occurs in the elderly. Because the course of the disease is irreversible and incurable, it is of great significance to find the early stage of the disease and take targeted treatment measures. In this paper, the three-classifi- cation and five-classification diagnosis of Alzheimer’s disease are performed based on brain structural characteristics and cognitive behavioral characteristics, supplemented by demographic characteristics and biomarkers. After the data is pre-processed, Random Forest is used to sort the importance of features. According to the sorting results and the performance of each feature combination in the machine learning models, 15 and 21 features are selected respectively for training machine learning models such as Random Forest, GBDT, CatBoost, LightGBM and XGBoost. The results show that LightGBM and XGBoost have excellent performance in the three-classification and five-classification diagnosis of Alzheimer's disease, with classification accuracy of 99.25% and 95.94%, and F1-score of 99.25% and 95.92%, respectively. After the five-fold cross validation, the performance and stability of the above models are excellent. Finally, the characteristics selected from the two diagnoses are compared, and some suggestions are put forward for the future diagnosis of Alzheimer’s disease.
| [1] | Hahn, K., Myers, N., Prigarin, S., Rodenacker, K., Kurz, A., F？rstl, H., et al. (2013) Selectively and Progressively Disrupted Structural Connectivity of Functional Brain Networks in Alzheimer’s Disease—Revealed by a Novel Framework to Analyze Edge Distributions of Networks Detecting Disruptions with Strong Statistical Evidence. NeuroImage, 81, 96-109. https://doi.org/10.1016/j.neuroimage.2013.05.011 |
| [2] | Thies, W. and Bleiler, L. (2012) 2012 Alzheimer’s Disease Facts and Figures Alzheimer’s Association. Alzheimer’s & Dementia, 8, 131-168. https://doi.org/10.1016/j.jalz.2012.02.001 |
| [3] | Mitchell, A.J. and Shiri‐Feshki, M. (2009) Rate of Progression of Mild Cognitive Impairment to Dementia—Meta‐ analysis of 41 Robust Inception Cohort Studies. Acta Psychiatrica Scandinavica, 119, 252-265. https://doi.org/10.1111/j.1600-0447.2008.01326.x |
| [4] | Kloppel, S., Stonnington, C.M., Chu, C., Draganski, B., Scahill, R.I., Rohrer, J.D., et al. (2008) Automatic Classification of MR Scans in Alzheimer’s Disease. Brain, 131, 681-689. https://doi.org/10.1093/brain/awm319 |
| [5] | Li, S., Yuan, X., Pu, F., Li, D., Fan, Y., Wu, L., et al. (2014) Abnormal Changes of Multidimensional Surface Features Using Multivariate Pattern Classification in Amnestic Mild Cognitive Impairment Patients. Journal of Neuroscience, 34, 10541-10553. https://doi.org/10.1523/jneurosci.4356-13.2014 |
| [6] | Silveira, M. and Marques, J. (2010) Boosting Alzheimer Disease Diagnosis Using PET Images. 2010 20th International Conference on Pattern Recognition, Istanbul, 23-26 August 2010, 2556-2559. https://doi.org/10.1109/icpr.2010.626 |
| [7] | Wang, Z., Zheng, Y., Zhu, D.C., Bozoki, A.C. and Li, T. (2018) Classification of Alzheimer’s Disease, Mild Cognitive Impairment and Normal Control Subjects Using Resting-State Fmri Based Network Connectivity Analysis. IEEE Journal of Translational Engineering in Health and Medicine, 6, 1-9. https://doi.org/10.1109/jtehm.2018.2874887 |
| [8] | 刘茜, 王瑜, 付常洋, 等. 基于特征选择的阿尔茨海默症辅助诊断[J]. 中国医学物理学杂志, 2020, 37(5): 656-660. |
| [9] | 杨邦坤, 汪乐生, 聂颖, 等. 基于机器学习的阿尔兹海默症初期行为辨识方法[J]. 生物医学工程研究, 2021, 40(2): 121-125. |
| [10] | 李彩, 范炤. 基于机器学习的阿尔兹海默症分类预测[J]. 中国医学物理学杂志, 2020, 37(3): 379-384. |
| [11] | 刘德华, 殷国盛, 范炤. 基于特征选择下机器学习对阿尔茨海默病的分类[J]. 中国医学影像学杂志, 2023, 31(2): 167-174. |
| [12] | 方匡南, 吴见彬, 朱建平, 等. 随机森林方法研究综述[J]. 统计与信息论坛, 2011, 26(3): 32-38. |
| [13] | Friedman, J.H. (2001) Greedy Function Approximation: A Gradient Boosting Machine. The Annals of Statistics, 29, 1189-1232. https://doi.org/10.1214/aos/1013203451 |
| [14] | Chen, T. and Guestrin, C. (2016). XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, 13-17 August 2016, 785-794. https://doi.org/10.1145/2939672.2939785 |
| [15] | Ke, G., Meng, Q., Finley, T., et al. (2017) LightGBM: A Highly Efficient Gradient Boosting Decision Tree. Proceedings of the 31st International Conference on Neural Information Processing Systems, Long Beach, 4-9 December 2017, 3149-3157. |
| [16] | Prokhorenkova, L., Gusev, G., Vorobev, A., et al. (2018) CatBoost: Unbiased Boosting with Categorical Features. 32nd Conference on Neural Information Processing Systems, Montréal, 3-8 December 2018, 6639-6649. |
| [17] | Rodriguez, J.D., Perez, A. and Lozano, J.A. (2010) Sensitivity Analysis of K-Fold Cross Validation in Prediction Error Estimation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 32, 569-575. https://doi.org/10.1109/tpami.2009.187 |
| [18] | Citron, M. (2002) Alzheimer’s Disease: Treatments in Discovery and Development. Nature Neuroscience, 5, 1055-1057. https://doi.org/10.1038/nn940 |
