A multilayer multimodal detection and prediction model based on explainable artificial intelligence for Alzheimer's disease.
Journal
Scientific reports
ISSN: 2045-2322
Titre abrégé: Sci Rep
Pays: England
ID NLM: 101563288
Informations de publication
Date de publication:
29 01 2021
29 01 2021
Historique:
received:
21
10
2019
accepted:
29
12
2020
entrez:
30
1
2021
pubmed:
31
1
2021
medline:
16
11
2021
Statut:
epublish
Résumé
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.
Identifiants
pubmed: 33514817
doi: 10.1038/s41598-021-82098-3
pii: 10.1038/s41598-021-82098-3
pmc: PMC7846613
doi:
Types de publication
Journal Article
Multicenter Study
Randomized Controlled Trial
Research Support, N.I.H., Extramural
Research Support, Non-U.S. Gov't
Research Support, U.S. Gov't, Non-P.H.S.
Langues
eng
Sous-ensembles de citation
IM
Pagination
2660Subventions
Organisme : NIA NIH HHS
ID : U01 AG024904
Pays : United States
Références
Alberdi, A., Aztiria, A. & Basarab, A. On the early diagnosis of Alzheimer’s disease from multimodal signals: a survey. Artif. Intell. Med. 71, 1–29 (2016).
pubmed: 27506128
doi: 10.1016/j.artmed.2016.06.003
Masters, C. L. & Beyreuther, K. Alzheimer’s centennial legacy: prospects for rational therapeutic intervention targeting the Aβ amyloid pathway. Brain 129, 2823–2839 (2006).
pubmed: 17012295
doi: 10.1093/brain/awl251
Zamrini, E., De Santi, S. & Tolar, M. Imaging is superior to cognitive testing for early diagnosis of Alzheimer’s disease. Neurobiol. Aging 25, 685–691 (2004).
pubmed: 15172748
doi: 10.1016/j.neurobiolaging.2004.02.009
Liu, M., Zhang, J., Adeli, E. & Shen, D. Joint classification and regression via deep multi-task multi-channel learning for Alzheimer’s disease diagnosis. IEEE Trans. Biomed. Eng. 1 (2018).
Lee, G. et al. Predicting Alzheimer’s disease progression using multi-modal deep learning approach. Sci. Rep. 9, 1–12 (2019).
Nie, L. et al. Modeling disease progression via multisource multitask learners: a case study with Alzheimer’s disease. IEEE Trans. Neural Netw. Learn. Syst. 28, 1508–1519 (2017).
pubmed: 26929064
doi: 10.1109/TNNLS.2016.2520964
Wee, C. Y., Yap, P. T. & Shen, D. Prediction of Alzheimer’s disease and mild cognitive impairment using cortical morphological patterns. Hum. Brain Mapp. 34, 3411–3425 (2013).
pubmed: 22927119
doi: 10.1002/hbm.22156
Liao, Q. et al. Multi-task deep convolutional neural network for cancer diagnosis. Neurocomputing https://doi.org/10.1016/j.neucom.2018.06.084 (2018).
doi: 10.1016/j.neucom.2018.06.084
Lu, D., Popuri, K., Ding, W., Balachandar, R. & Beg, M. F. Multimodal and multiscale deep neural networks for the early diagnosis of Alzheimer’s disease using structural MR and FDG-PET images. Sci. Rep. 8, 5697 (2018).
pubmed: 29632364
pmcid: 5890270
doi: 10.1038/s41598-018-22871-z
Liu, M., Cheng, D., Wang, K. & Wang, Y. Multi-modality cascaded convolutional neural networks for Alzheimer’s disease diagnosis. Neuroinformatics 16, 295–308 (2018).
pubmed: 29572601
doi: 10.1007/s12021-018-9370-4
Qiu, S. et al. Fusion of deep learning models of MRI scans, mini-mental state examination, and logical memory test enhances diagnosis of mild cognitive impairment. Alzheimer’s Dement. Diagnosis Assess. Dis. Monit. 10, 737–749 (2018).
Kim-Han, T., Pew-Thian, Y. & Dinggang, S. Multi-stage diagnosis of Alzheimer’s Disease with incomplete multimodal data via multi-task deep learning. In Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support 160–168 (Springer, Cham, 2017).
Hinrichs, C., Singh, V., Xu, G. & Johnson, S. C. Predictive markers for AD in a multi-modality framework: an analysis of MCI progression in the ADNI population. Neuroimage 55, 574–589 (2011).
pubmed: 21146621
doi: 10.1016/j.neuroimage.2010.10.081
Zhou, J., Liu, J., Narayan, V. A. & Ye, J. Modeling disease progression via multi-task learning. Neuroimage 78, 233–248 (2013).
pubmed: 23583359
doi: 10.1016/j.neuroimage.2013.03.073
Wang, T., Qiu, R. G. & Yu, M. Predictive modeling of the progression of Alzheimer’ s disease with recurrent neural networks. Sci. Rep. https://doi.org/10.1038/s41598-018-27337-w (2018).
doi: 10.1038/s41598-018-27337-w
pubmed: 30591712
pmcid: 6308232
Ding, X. et al. A hybrid computational approach for efficient Alzheimer’s disease classification based on heterogeneous data. Sci. Rep. 8, 1–10 (2018).
doi: 10.1038/s41598-018-27997-8
Gray, K. R., Aljabar, P., Heckemann, R. A. & Hammers, A. Random forest-based similarity measures for multi-modal classification of Alzheimer’ s disease. Neuroimage 65, 167–175 (2013).
pubmed: 23041336
doi: 10.1016/j.neuroimage.2012.09.065
Das, D., Ito, J., Kadowaki, T. & Tsuda, K. An interpretable machine learning model for diagnosis of Alzheimer’s disease. PeerJ 7, e6543 (2019).
pubmed: 30842909
pmcid: 6398390
doi: 10.7717/peerj.6543
Mattila, J. et al. A disease state fingerprint for evaluation of Alzheimer’s disease. J. Alzheimer’s Dis. 27, 163–176 (2011).
doi: 10.3233/JAD-2011-110365
Bucholc, M. et al. A practical computerized decision support system for predicting the severity of Alzheimer’s disease of an individual. Expert Syst. Appl. 130, 157–171 (2019).
pubmed: 31402810
pmcid: 6688646
doi: 10.1016/j.eswa.2019.04.022
Travers, C. et al. Opportunities and obstacles for deep learning in biology and medicine. bioRxiv https://doi.org/10.1101/142760 (2017).
doi: 10.1101/142760
Choi, H. & Jin, K. H. Predicting cognitive decline with deep learning of brain metabolism and amyloid imaging. Behav. Brain Res. 344, 103–109 (2018).
pubmed: 29454006
doi: 10.1016/j.bbr.2018.02.017
Spasov, S., Passamonti, L., Duggento, A., Lio, P. & Toschi, N. A parameter-efficient deep learning approach to predict conversion from mild cognitive impairment to Alzheimer’s disease. Neuroimage 189, 276–287 (2019).
pubmed: 30654174
doi: 10.1016/j.neuroimage.2019.01.031
Zhang, D. & Shen, D. Multi-modal multi-task learning for joint prediction of multiple regression and classification variables in Alzheimer’s disease. Neuroimage 59, 895–907 (2012).
pubmed: 21992749
doi: 10.1016/j.neuroimage.2011.09.069
Cheng, B., Liu, M., Zhang, D., Munsell, B. C. & Shen, D. Domain transfer learning for MCI conversion prediction. IEEE Trans. Biomed. Eng. 62, 1805–1817 (2015).
pubmed: 25751861
pmcid: 4474791
doi: 10.1109/TBME.2015.2404809
Moore, P. J., Lyons, T. J. & Gallacher, J. Random forest prediction of Alzheimer’s disease using pairwise selection from time series data. PLoS ONE 14, 1–14 (2019).
doi: 10.1371/journal.pone.0211558
Moradi, E., Pepe, A., Gaser, C., Huttunen, H. & Tohka, J. Machine learning framework for early MRI-based Alzheimer’s conversion prediction in MCI subjects. Neuroimage 104, 398–412 (2015).
pubmed: 25312773
doi: 10.1016/j.neuroimage.2014.10.002
Fisher, C. K., Smith, A. M. & Walsh, J. R. Machine learning for comprehensive forecasting of Alzheimer’s disease progression. Sci. Rep. 9, 1–14 (2019).
doi: 10.1038/s41598-019-49656-2
Oxtoby, N. P. & Alexander, D. C. Imaging plus X: Multimodal models of neurodegenerative disease. Curr. Opin. Neurol. 30, 371–379 (2017).
pubmed: 28520598
pmcid: 5491241
doi: 10.1097/WCO.0000000000000460
Burrell, J. How the machine ‘Thinks:’ understanding opacity in machine learning algorithms. Ssrn https://doi.org/10.2139/ssrn.2660674 (2015).
doi: 10.2139/ssrn.2660674
Adadi, A. & Berrada, M. Peeking Inside the black-box: a survey on explainable artificial intelligence (XAI). IEEE Access 6, 52138–52160 (2018).
doi: 10.1109/ACCESS.2018.2870052
Lundberg, S. M. et al. Explainable machine-learning predictions for the prevention of hypoxaemia during surgery. Nat. Biomed. Eng. 2, 749–760 (2018).
pubmed: 31001455
pmcid: 6467492
doi: 10.1038/s41551-018-0304-0
Guidotti, R. et al. A survey of methods for explaining black box models. ACM Comput. Surv. 51, 93:1-93:42 (2018).
Quinlan, J. R. C4.5: Programs for Machine Learning (Morgan Kaufmann Publishers, San Mateo, 1993).
El-Sappagh, S. et al. An ontology-based interpretable fuzzy decision support system for diabetes diagnosis. IEEE Access 6, 37371–37394 (2018).
doi: 10.1109/ACCESS.2018.2852004
Trillas, E. & Eciolaza, L. Fuzzy Logic: An Introductory Course for Engineering Students (Springer, New York, 2015).
doi: 10.1007/978-3-319-14203-6
Huysmans, J., Dejaeger, K., Mues, C., Vanthienen, J. & Baesens, B. An empirical evaluation of the comprehensibility of decision table, tree and rule based predictive models. Decis. Support Syst. 51, 141–154 (2011).
doi: 10.1016/j.dss.2010.12.003
Alonso, J. M., Castiello, C., Lucarelli, M. & Mencar, C. Modeling interpretable fuzzy rule-based classifiers for medical decision support. In Medical Applications of Intelligent Data Analysis: Research Advancements. 1064–1081 (Hershey, PA, USA: IGI Global, 2013).
Alonso, J. M., Castiello, C. & Mencar, C. Interpretability of fuzzy systems: current research trends and prospects. In Springer Handbook of Computational Intelligence 219–237 (Springer, Berlin, 2015).
Fernandez-Delgado, M., Cernadas, E., Barro, S. & Amorim, D. Do we need hundreds of classifiers to solve real world classification problems. J. Mach. Learn. Res. 15, 3133–3181 (2014).
Alonso, J. M., Ramos-Soto, A., Castiello, C. & Mencar, C. Hybrid data-expert explainable beer style classifier. In IJCAI/ECAI Workshop on Explainable Artificial Intelligence 1–5 (2018).
Ribeiro, M. T., Singh, S. & Guestrin, C. ‘Why Should I Trust You?’: Explaining the Predictions of Any Classifier (2016).
Zhou, Z.-H., Jiang, Y. & Chen, S.-F. Extracting symbolic rules from trained neural network ensembles. AI Commun. 16, 3–15 (2003).
Breiman, L. Statistical modeling: the two cultures. Stat. Sci. 16, 199–231 (2001).
doi: 10.1214/ss/1009213726
Zhao, X., Wu, Y., Lee, D. L. & Cui, W. IForest: interpreting random forests via visual analytics. IEEE Trans. Vis. Comput. Graph. 25, 407–416 (2019).
doi: 10.1109/TVCG.2018.2864475
Matthews, K. Tau protein abnormalities correlate with the severity of dementia in Alzheimer’s disease. Nat. Clin. Pract. Neurol. 2, 178 (2006).
doi: 10.1038/ncpneuro0139
Murphy, M. P. & Levine, H. Alzheimer’s disease and the amyloid-β peptide. J. Alzheimer’s Dis. 19, 311–323 (2010).
doi: 10.3233/JAD-2010-1221
Sadigh-Eteghad, S. et al. Amyloid-beta: a crucial factor in Alzheimer’s disease. Med. Princ. Pract. 24, 1–10 (2015).
pubmed: 25471398
doi: 10.1159/000369101
Verdile, G. et al. The role of beta amyloid in Alzheimer’ s disease: still a cause of everything or the only one who got caught?. Pharmacol. Res. 50, 397–409 (2004).
pubmed: 15304237
doi: 10.1016/j.phrs.2003.12.028
Thaweepoksomboon, J. et al. Assessment of cerebrospinal fluid (CSF) beta-amyloid (1–42), phosphorylated tau (ptau-181) and total Tau protein in patients with Alzheimer’s disease (AD) and other dementia at Siriraj Hospital Thailand. J. Med. Assoc. Thai. 94(Suppl 1), S77-83 (2011).
pubmed: 21721431
Zetterberg, H. Biomarkers for Alzheimer’ s disease: current status and prospects for the future. J. Intern. Med. 6, 643–663 (2018).
Weiner, M. W. et al. Recent publications from the Alzheimer’s disease neuroimaging initiative: reviewing progress toward improved AD clinical trials. Alzheimer’s Dement. 13, e1–e85 (2017).
Tong, T. et al. A novel grading biomarker for the prediction of conversion from mild cognitive impairment to Alzheimer’s disease. IEEE Trans. Biomed. Eng. 64, 155–165 (2017).
pubmed: 27046891
doi: 10.1109/TBME.2016.2549363
Li, K., O’Brien, R., Lutz, M. & Luo, S. A prognostic model of Alzheimer’s disease relying on multiple longitudinal measures and time-to-event data. Alzheimer’s Dement. 14, 644–651 (2018).
doi: 10.1016/j.jalz.2017.11.004
Jin, Y., Su, Y., Zhou, X. H. & Huang, S. Heterogeneous multimodal biomarkers analysis for Alzheimer’s disease via Bayesian network. Eurasip J. Bioinform. Syst. Biol. 2016, 4–11 (2016).
doi: 10.1186/s13637-016-0046-9
Breiman, L. E. O. Random forests. Mach. Learn. 45, 5–32 (2001).
doi: 10.1023/A:1010933404324
Lebedev, A. V. et al. Random forest ensembles for detection and prediction of Alzheimer’s disease with a good between-cohort robustness. NeuroImage Clin. 6, 115–125 (2014).
pubmed: 25379423
pmcid: 4215532
doi: 10.1016/j.nicl.2014.08.023
Ramírez, J. et al. Ensemble of random forests one vs. rest classifiers for MCI and AD prediction using ANOVA cortical and subcortical feature selection and partial least squares. J. Neurosci. Methods 302, 47–57 (2018).
pubmed: 29242123
doi: 10.1016/j.jneumeth.2017.12.005
Cheng, M., Nazarian, S. & Bogdan, P. There is hope after all: quantifying opinion and trustworthiness in neural networks. Front. Artif. Intell. 3 (2020).
Dodd, E., Cheston, R. & Ivanecka, A. The assessment of dementia in primary care. J. Psychiatr. Ment. Health Nurs. 22, 731–737 (2015).
pubmed: 26459923
doi: 10.1111/jpm.12250
Onoda, K. & Yamaguchi, S. Revision of the cognitive assessment for dementia, iPad version (CADi2). PLoS One 9 (2014).
El-Sappagh, S., Abuhmed, T., Riazul Islam, S. M. & Kwak, K. S. Multimodal multitask deep learning model for Alzheimer’s disease progression detection based on time series data. Neurocomputing 412, 197–215 (2020).
doi: 10.1016/j.neucom.2020.05.087
El-Sappagh, S. et al. Alzheimer’s disease progression detection model based on an early fusion of cost-effective multimodal data. Futur. Gener. Comput. Syst. 115 (2021).
Chen, G. et al. Classification of Alzheimer disease, mild cognitive impairment, and normal cognitive status with large-scale network analysis based on resting-state functional MR imaging. Radiology 259, 213–221 (2011).
pubmed: 21248238
pmcid: 3064820
doi: 10.1148/radiol.10100734
Wang, P. et al. Aberrant intra-and inter-network connectivity architectures in Alzheimer’s disease and mild cognitive impairment. Sci. Rep. 5, 1–12 (2015).
Yang, R. & Bogdan, P. Controlling the multifractal generating measures of complex networks. Sci. Rep. 10, 1–13 (2020).
Zhang, Y., Zhang, H., Chen, X., Lee, S. W. & Shen, D. Hybrid high-order functional connectivity networks using resting-state functional MRI for mild cognitive impairment diagnosis. Sci. Rep. 7, 1–15 (2017).
McKhann, G. et al. Clinical diagnosis of Alzheimer’s disease: report of the NINCDS-ADRDA Work Group under the auspices of Department of Health and Human Services Task Force on Alzheimer’s Disease. Neurology 34, 939–939 (2012).
doi: 10.1212/WNL.34.7.939
Jagust, W. J. et al. The Alzheimer’s disease neuroimaging initiative 2 PET core: 2015. Alzheimer’s Dement. 11, 757–771 (2015).
doi: 10.1016/j.jalz.2015.05.001
Desikan, R. S. et al. An automated labeling system for subdividing the human cerebral cortex on MRI scans into gyral based regions of interest. Neuroimage 31, 968–980 (2006).
pubmed: 16530430
doi: 10.1016/j.neuroimage.2006.01.021
Chawla, N. V., Bowyer, K. W., Hall, L. O. & Kegelmeyer, W. P. SMOTE: Synthetic minority over-sampling technique. J. Artif. Intell. Res. 16, 321–357 (2002).
doi: 10.1613/jair.953
Elisseeff, A. & Pontil, M. Leave-one-out error and stability of learning algorithms with applications. In NATO science series sub series iii computer and systems sciences 111–130 (ISO Press, 2003).
Krstajic, D., Buturovic, L. J., Leahy, D. E. & Thomas, S. Cross-validation pitfalls when selecting and assessing regression and classification models. J. Cheminform. 6, 1–15 (2014).
doi: 10.1186/1758-2946-6-10
Raschka, S. Model Evaluation, Model Selection, and Algorithm Selection in Machine Learning. (2018).
Kohavi, R. A study of cross-validation and bootstrap for accuracy estimation and model selection. Ijcai 14, 1137–1145 (1995).
Alonso, J. M., Castiello, C. & Mencar, C. A bibliometric analysis of the explainable artificial intelligence research field. In Information Processing and Management of Uncertainty in Knowledge-Based Systems-Theory and Foundations, CCIS853, 1–13 (Springer, 2018).
Cohen, W. Fast effective rule induction. In International Conference on Machine Learning (ICML) 115–123 (1995).
Alonso, J. M. & Bugar, A. ExpliClas: automatic generation of explanations in natural language for weka classifiers. In IEEE International Conference on Fuzzy Systems 1–6 (2019).
Landau, S. M. et al. Associations between cognitive, functional, and FDG-PET measures of decline in AD and MCI. Neurobiol. Aging 32, 1207–1218 (2011).
pubmed: 19660834
doi: 10.1016/j.neurobiolaging.2009.07.002
Chen, K. et al. Characterizing Alzheimer’s disease using a hypometabolic convergence index. Neuroimage 56, 52–60 (2011).
pubmed: 21276856
doi: 10.1016/j.neuroimage.2011.01.049
Cortizo, J. C. & Giraldez, I. Multi criteria wrapper improvements to Naive Bayes learning. In International Conference on Intelligent Data Engineering and Automated Learning 419–427 (Springer, Berlin, Heidelberg, 2006). https://doi.org/10.1007/11875581_51 .
Maldonado, S., Weber, R. & Famili, F. Feature selection for high-dimensional class-imbalanced data sets using support vector machines. Inf. Sci. (Ny) 286, 228–246 (2014).
doi: 10.1016/j.ins.2014.07.015
Rodin, A. S. et al. Use of wrapper algorithms coupled with a random forests classifier for variable selection in large-scale genomic association studies. J. Comput. Biol. 16, 1705–1718 (2010).
doi: 10.1089/cmb.2008.0037
Panthong, R. & Srivihok, A. Wrapper feature subset selection for dimension reduction based on ensemble learning algorithm. Procedia Comput. Sci. 72, 162–169 (2015).
doi: 10.1016/j.procs.2015.12.117
Li, Z., Xie, W. & Liu, T. Efficient feature selection and classification for microarray data. PLoS ONE 13, 1–21 (2018).
Granitto, P. M., Furlanello, C., Biasioli, F. & Gasperi, F. Recursive feature elimination with random forest for PTR-MS analysis of agroindustrial products. Chemom. Intell. Lab. Syst. 83, 83–90 (2006).
doi: 10.1016/j.chemolab.2006.01.007
Menze, B. H. et al. A comparison of random forest and its Gini importance with standard chemometric methods for the feature selection and classification of spectral data. BMC Bioinformatics 10, 1–16 (2009).
doi: 10.1186/1471-2105-10-213
Hall, P. On the Art and Science of Machine Learning Explanations. arXiv Prepr. arXiv 1810.02909 (2018).
Ando Saabas. Interpreting Random Forests, treeinterpreter. (2019).
Korobov, M. & Lopuhin, K. ELI5 Documentation. (2019).
Lundberg, S. & Lee, S.-I. A Unified approach to interpreting model predictions. In Advances in Neural Information Processing Systems 4765–4774 (2017).
Molnar, C. Interpretable Machine Learning A Guide for Making Black Box Models Explainable. (2020).
Štrumbelj, E. & Kononenko, I. Explaining prediction models and individual predictions with feature contributions. Knowl. Inf. Syst. 41, 647–665 (2014).
doi: 10.1007/s10115-013-0679-x