Personalized Explanations for Early Diagnosis of Alzheimer’s Disease Using Explainable Graph Neural Networks with Population Graphs
Abstract
:1. Introduction
- We demonstrate the effectiveness of using graph neural networks on population graphs for early AD diagnosis in cognitively unimpaired individuals;
- We provide explanations of graph neural network predictions, offering sample-level interpretations using demographic and neuroimaging features;
- We prioritized personalized risk factors for AD by explaining graph neural network predictions, thereby characterizing groups of individuals based on their risk factors in AD prognosis.
2. Materials and Methods
2.1. Dataset
2.2. Population Graph Construction
2.3. Graph Convolutional Networks
2.4. Interpretation with GNNExplainer
2.5. Performance Evaluation
3. Results
3.1. Experimental Setting
3.2. Performance of Prediction of A Positivity
3.3. Interpreting Predictions of Graph Neural Networks
4. Discussion
Supplementary Materials
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Acknowledgments
Conflicts of Interest
References
- Cullen, N.C.; Leuzy, A.; Janelidze, S.; Palmqvist, S.; Svenningsson, A.L.; Stomrud, E.; Dage, J.L.; Mattsson-Carlgren, N.; Hansson, O. Plasma biomarkers of Alzheimer’s disease improve prediction of cognitive decline in cognitively unimpaired elderly populations. Nat. Commun. 2021, 12, 3555. [Google Scholar] [CrossRef] [PubMed]
- Jeremic, D.; Jiménez-Díaz, L.; Navarro-López, J.D. Past, present and future of therapeutic strategies against amyloid-β peptides in Alzheimer’s disease: A systematic review. Ageing Res. Rev. 2021, 72, 101496. [Google Scholar] [CrossRef] [PubMed]
- Nakamura, A.; Kaneko, N.; Villemagne, V.L.; Kato, T.; Doecke, J.; Doré, V.; Fowler, C.; Li, Q.X.; Martins, R.; Rowe, C.; et al. High performance plasma amyloid-β biomarkers for Alzheimer’s disease. Nature 2018, 554, 249–254. [Google Scholar] [CrossRef] [PubMed]
- Selkoe, D.J.; Schenk, D. Alzheimer’s disease: Molecular understanding predicts amyloid-based therapeutics. Annu. Rev. Pharmacol. Toxicol. 2003, 43, 545–584. [Google Scholar] [CrossRef]
- Oddo, S.; Caccamo, A.; Kitazawa, M.; Tseng, B.P.; LaFerla, F.M. Amyloid deposition precedes tangle formation in a triple transgenic model of Alzheimer’s disease. Neurobiol. Aging 2003, 24, 1063–1070. [Google Scholar] [CrossRef]
- Shirbandi, K.; Khalafi, M.; Mirza-Aghazadeh-Attari, M.; Tahmasbi, M.; Shahvandi, H.K.; Javanmardi, P.; Rahim, F. Accuracy of deep learning model-assisted amyloid positron emission tomography scan in predicting Alzheimer’s disease: A systematic review and meta-analysis. Inform. Med. Unlocked 2021, 25, 100710. [Google Scholar] [CrossRef]
- Ezzati, A.; Harvey, D.J.; Habeck, C.; Golzar, A.; Qureshi, I.A.; Zammit, A.R.; Hyun, J.; Truelove-Hill, M.; Hall, C.B.; Davatzikos, C.; et al. Predicting amyloid-β levels in amnestic mild cognitive impairment using machine learning techniques. J. Alzheimer’s Dis. 2020, 73, 1211–1219. [Google Scholar] [CrossRef]
- Vergallo, A.; Mégret, L.; Lista, S.; Cavedo, E.; Zetterberg, H.; Blennow, K.; Vanmechelen, E.; De Vos, A.; Habert, M.O.; Potier, M.C.; et al. Plasma amyloid β 40/42 ratio predicts cerebral amyloidosis in cognitively normal individuals at risk for Alzheimer’s disease. Alzheimer’s Dement. 2019, 15, 764–775. [Google Scholar] [CrossRef]
- Kim, S.; Lee, P.; Oh, K.T.; Byun, M.S.; Yi, D.; Lee, J.H.; Kim, Y.K.; Ye, B.S.; Yun, M.J.; Lee, D.Y.; et al. Deep learning-based amyloid PET positivity classification model in the Alzheimer’s disease continuum by using 2-[18F] FDG PET. EJNMMI Res. 2021, 11, 56. [Google Scholar] [CrossRef]
- Chang, C.H.; Lin, C.H.; Lane, H.Y. Machine learning and novel biomarkers for the diagnosis of Alzheimer’s disease. Int. J. Mol. Sci. 2021, 22, 2761. [Google Scholar] [CrossRef]
- Basheera, S.; Ram, M.S.S. Deep learning based Alzheimer’s disease early diagnosis using T2w segmented gray matter MRI. Int. J. Imaging Syst. Technol. 2021, 31, 1692–1710. [Google Scholar] [CrossRef]
- Venugopalan, J.; Tong, L.; Hassanzadeh, H.R.; Wang, M.D. Multimodal deep learning models for early detection of Alzheimer’s disease stage. Sci. Rep. 2021, 11, 3254. [Google Scholar] [CrossRef] [PubMed]
- Houria, L.; Belkhamsa, N.; Cherfa, A.; Cherfa, Y. Multi-modality MRI for Alzheimer’s disease detection using deep learning. Phys. Eng. Sci. Med. 2022, 45, 1043–1053. [Google Scholar] [CrossRef]
- Ramzan, F.; Khan, M.U.G.; Rehmat, A.; Iqbal, S.; Saba, T.; Rehman, A.; Mehmood, Z. A deep learning approach for automated diagnosis and multi-class classification of Alzheimer’s disease stages using resting-state fMRI and residual neural networks. J. Med. Syst. 2020, 44, 37. [Google Scholar] [CrossRef]
- Zhang, T.; Liao, Q.; Zhang, D.; Zhang, C.; Yan, J.; Ngetich, R.; Zhang, J.; Jin, Z.; Li, L. Predicting MCI to AD conversation using integrated sMRI and rs-fMRI: Machine learning and graph theory approach. Front. Aging Neurosci. 2021, 13, 688926. [Google Scholar] [CrossRef] [PubMed]
- Grassi, M.; Rouleaux, N.; Caldirola, D.; Loewenstein, D.; Schruers, K.; Perna, G.; Dumontier, M.; Initiative, A.D.N. A novel ensemble-based machine learning algorithm to predict the conversion from mild cognitive impairment to Alzheimer’s disease using socio-demographic characteristics, clinical information, and neuropsychological measures. Front. Neurol. 2019, 10, 756. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Spasov, S.; Passamonti, L.; Duggento, A.; Lio, P.; Toschi, N.; Alzheimer’s Disease Neuroimaging Initiative. A parameter-efficient deep learning approach to predict conversion from mild cognitive impairment to Alzheimer’s disease. Neuroimage 2019, 189, 276–287. [Google Scholar] [CrossRef] [Green Version]
- Lee, G.; Nho, K.; Kang, B.; Sohn, K.A.; Kim, D. Predicting Alzheimer’s disease progression using multi-modal deep learning approach. Sci. Rep. 2019, 9, 1952. [Google Scholar] [CrossRef] [Green Version]
- Ocasio, E.; Duong, T.Q. Deep learning prediction of mild cognitive impairment conversion to Alzheimer’s disease at 3 years after diagnosis using longitudinal and whole-brain 3D MRI. PeerJ Comput. Sci. 2021, 7, e560. [Google Scholar] [CrossRef] [PubMed]
- Li, J.; Bur, A.M.; Villwock, M.R.; Shankar, S.; Palmer, G.; Sykes, K.J.; Villwock, J.A. Olfactory phenotypes differentiate cognitively unimpaired seniors from Alzheimer’s disease and mild cognitive impairment: A combined machine learning and traditional statistical approach. J. Alzheimer’s Dis. 2021, 81, 641–650. [Google Scholar] [CrossRef]
- Masters, C.L.; Selkoe, D.J. Biochemistry of amyloid β-protein and amyloid deposits in Alzheimer disease. Cold Spring Harb. Perspect. Med. 2012, 2, a006262. [Google Scholar] [CrossRef]
- Engler, H.; Forsberg, A.; Almkvist, O.; Blomquist, G.; Larsson, E.; Savitcheva, I.; Wall, A.; Ringheim, A.; Långström, B.; Nordberg, A. Two-year follow-up of amyloid deposition in patients with Alzheimer’s disease. Brain 2006, 129, 2856–2866. [Google Scholar] [CrossRef] [Green Version]
- Leffa, D.T.; Ferrari-Souza, J.P.; Bellaver, B.; Tissot, C.; Ferreira, P.C.; Brum, W.S.; Caye, A.; Lord, J.; Proitsi, P.; Martins-Silva, T.; et al. Genetic risk for attention-deficit/hyperactivity disorder predicts cognitive decline and development of Alzheimer’s disease pathophysiology in cognitively unimpaired older adults. Mol. Psychiatry 2023, 28, 1248–1255. [Google Scholar] [CrossRef]
- Gottesman, R.F.; Schneider, A.L.; Zhou, Y.; Chen, X.; Green, E.; Gupta, N.; Knopman, D.S.; Mintz, A.; Rahmim, A.; Sharrett, A.R.; et al. The ARIC-PET amyloid imaging study: Brain amyloid differences by age, race, sex, and APOE. Neurology 2016, 87, 473–480. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Wu, K.Y.; Hsiao, I.T.; Chen, C.S.; Chen, C.H.; Hsieh, C.J.; Wai, Y.Y.; Chang, C.J.; Tseng, H.J.; Yen, T.C.; Liu, C.Y.; et al. Increased brain amyloid deposition in patients with a lifetime history of major depression: Evidenced on 18 F-florbetapir (AV-45/Amyvid) positron emission tomography. Eur. J. Nucl. Med. Mol. Imaging 2014, 41, 714–722. [Google Scholar] [CrossRef]
- Genin, E.; Hannequin, D.; Wallon, D.; Sleegers, K.; Hiltunen, M.; Combarros, O.; Bullido, M.J.; Engelborghs, S.; De Deyn, P.; Berr, C.; et al. APOE and Alzheimer disease: A major gene with semi-dominant inheritance. Mol. Psychiatry 2011, 16, 903–907. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Meyer, M.R.; Tschanz, J.T.; Norton, M.C.; Welsh-Bohmer, K.A.; Steffens, D.C.; Wyse, B.W.; Breitner, J. APOE genotype predicts when—not whether—one is predisposed to develop Alzheimer disease. Nat. Genet. 1998, 19, 321–322. [Google Scholar] [CrossRef] [PubMed]
- Strittmatter, W.J.; Roses, A.D. Apolipoprotein E and Alzheimer disease. Proc. Natl. Acad. Sci. USA 1995, 92, 4725–4727. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Lerch, J.P.; Pruessner, J.C.; Zijdenbos, A.; Hampel, H.; Teipel, S.J.; Evans, A.C. Focal decline of cortical thickness in Alzheimer’s disease identified by computational neuroanatomy. Cereb. Cortex 2005, 15, 995–1001. [Google Scholar] [CrossRef]
- Lerch, J.P.; Pruessner, J.; Zijdenbos, A.P.; Collins, D.L.; Teipel, S.J.; Hampel, H.; Evans, A.C. Automated cortical thickness measurements from MRI can accurately separate Alzheimer’s patients from normal elderly controls. Neurobiol. Aging 2008, 29, 23–30. [Google Scholar] [CrossRef]
- Sun, Z.; Yin, H.; Chen, H.; Chen, T.; Cui, L.; Yang, F. Disease prediction via graph neural networks. IEEE J. Biomed. Health Inform. 2020, 25, 818–826. [Google Scholar] [CrossRef] [PubMed]
- Cui, H.; Dai, W.; Zhu, Y.; Li, X.; He, L.; Yang, C. Brainnnexplainer: An interpretable graph neural network framework for brain network based disease analysis. arXiv 2021, arXiv:2107.05097. [Google Scholar]
- Zhang, X.M.; Liang, L.; Liu, L.; Tang, M.J. Graph neural networks and their current applications in bioinformatics. Front. Genet. 2021, 12, 690049. [Google Scholar] [CrossRef]
- Bessadok, A.; Mahjoub, M.A.; Rekik, I. Graph neural networks in network neuroscience. IEEE Trans. Pattern Anal. Mach. Intell. 2022, 45, 5833–5848. [Google Scholar] [CrossRef]
- Shen, Z.A.; Luo, T.; Zhou, Y.K.; Yu, H.; Du, P.F. NPI-GNN: Predicting ncRNA—Protein interactions with deep graph neural networks. Briefings Bioinform. 2021, 22, bbab051. [Google Scholar] [CrossRef]
- Lv, G.; Hu, Z.; Bi, Y.; Zhang, S. Learning unknown from correlations: Graph neural network for inter-novel-protein interaction prediction. arXiv 2021, arXiv:2105.06709. [Google Scholar]
- Jha, K.; Saha, S.; Singh, H. Prediction of protein—Protein interaction using graph neural networks. Sci. Rep. 2022, 12, 8360. [Google Scholar] [CrossRef]
- Parisot, S.; Ktena, S.I.; Ferrante, E.; Lee, M.; Guerrero, R.; Glocker, B.; Rueckert, D. Disease prediction using graph convolutional networks: Application to autism spectrum disorder and Alzheimer’s disease. Med. Image Anal. 2018, 48, 117–130. [Google Scholar] [CrossRef] [Green Version]
- Gu, Y.; Yang, X.; Tian, L.; Yang, H.; Lv, J.; Yang, C.; Wang, J.; Xi, J.; Kong, G.; Zhang, W. Structure-aware siamese graph neural networks for encounter-level patient similarity learning. J. Biomed. Inform. 2022, 127, 104027. [Google Scholar] [CrossRef] [PubMed]
- Quan, Z.; Guo, Y.; Lin, X.; Wang, Z.J.; Zeng, X. Graphcpi: Graph neural representation learning for compound-protein interaction. In Proceedings of the 2019 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), San Diego, CA, USA, 18–21 November 2019; pp. 717–722. [Google Scholar]
- Zhang, Z.; Chen, L.; Zhong, F.; Wang, D.; Jiang, J.; Zhang, S.; Jiang, H.; Zheng, M.; Li, X. Graph neural network approaches for drug-target interactions. Curr. Opin. Struct. Biol. 2022, 73, 102327. [Google Scholar] [CrossRef]
- Qin, Z.; Liu, Z.; Zhu, P. Aiding Alzheimer’s Disease Diagnosis Using Graph Convolutional Networks Based on rs-fMRI Data. In Proceedings of the 2022 15th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI), Beijing, China, 5–7 November 2022; pp. 1–7. [Google Scholar]
- Kolahkaj, S.; Zare, H. A connectome-based deep learning approach for Early MCI and MCI detection using structural brain networks. Neurosci. Inform. 2023, 3, 100118. [Google Scholar] [CrossRef]
- Song, T.A.; Chowdhury, S.R.; Yang, F.; Jacobs, H.; El Fakhri, G.; Li, Q.; Johnson, K.; Dutta, J. Graph convolutional neural networks for Alzheimer’s disease classification. In Proceedings of the 2019 IEEE 16th international symposium on biomedical imaging (ISBI 2019), Venice, Italy, 8–11 April 2019; pp. 414–417. [Google Scholar]
- Kim, M.; Kim, J.; Qu, J.; Huang, H.; Long, Q.; Sohn, K.A.; Kim, D.; Shen, L. Interpretable temporal graph neural network for prognostic prediction of Alzheimer’s disease using longitudinal neuroimaging data. In Proceedings of the 2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), Virtual, 9–12 December 2021; pp. 1381–1384. [Google Scholar]
- Ma, J.; Zhu, X.; Yang, D.; Chen, J.; Wu, G. Attention-guided deep graph neural network for longitudinal Alzheimer’s disease analysis. In Proceedings of the Medical Image Computing and Computer Assisted Intervention—MICCAI 2020: 23rd International Conference, Lima, Peru, 4–8 October 2020; pp. 387–396. [Google Scholar]
- Kipf, T.N.; Welling, M. Semi-supervised classification with graph convolutional networks. arXiv 2016, arXiv:1609.02907. [Google Scholar]
- Selvaraju, R.R.; Cogswell, M.; Das, A.; Vedantam, R.; Parikh, D.; Batra, D. Grad-cam: Visual explanations from deep networks via gradient-based localization. In Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy, 22–29 October 2017; pp. 618–626. [Google Scholar]
- Pope, P.E.; Kolouri, S.; Rostami, M.; Martin, C.E.; Hoffmann, H. Explainability methods for graph convolutional neural networks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA, 15–20 June 2019; pp. 10772–10781. [Google Scholar]
- Luo, D.; Cheng, W.; Xu, D.; Yu, W.; Zong, B.; Chen, H.; Zhang, X. Parameterized explainer for graph neural network. Adv. Neural Inf. Process. Syst. 2020, 33, 19620–19631. [Google Scholar]
- Vu, M.; Thai, M.T. Pgm-explainer: Probabilistic graphical model explanations for graph neural networks. Adv. Neural Inf. Process. Syst. 2020, 33, 12225–12235. [Google Scholar]
- Yuan, H.; Tang, J.; Hu, X.; Ji, S. Xgnn: Towards model-level explanations of graph neural networks. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, Virtual, 23–27 August 2020; pp. 430–438. [Google Scholar]
- Ying, Z.; Bourgeois, D.; You, J.; Zitnik, M.; Leskovec, J. Gnnexplainer: Generating explanations for graph neural networks. Adv. Neural Inf. Process. Syst. 2019, 32, 9240–9251. [Google Scholar]
- Van der Velden, B.H.; Kuijf, H.J.; Gilhuijs, K.G.; Viergever, M.A. Explainable artificial intelligence (XAI) in deep learning-based medical image analysis. Med. Image Anal. 2022, 79, 102470. [Google Scholar] [CrossRef] [PubMed]
- Singh, A.; Sengupta, S.; Lakshminarayanan, V. Explainable deep learning models in medical image analysis. J. Imaging 2020, 6, 52. [Google Scholar] [CrossRef]
- Borys, K.; Schmitt, Y.A.; Nauta, M.; Seifert, C.; Krämer, N.; Friedrich, C.M.; Nensa, F. Explainable AI in Medical Imaging: An overview for clinical practitioners–Saliency-based XAI approaches. Eur. J. Radiol. 2023, 162, 110787. [Google Scholar] [CrossRef]
- Jiménez-Luna, J.; Grisoni, F.; Schneider, G. Drug discovery with explainable artificial intelligence. Nat. Mach. Intell. 2020, 2, 573–584. [Google Scholar] [CrossRef]
- Preuer, K.; Klambauer, G.; Rippmann, F.; Hochreiter, S.; Unterthiner, T. Interpretable deep learning in drug discovery. In Explainable AI: Interpreting, Explaining and Visualizing Deep Learning; Springer: Cham, Switzerland, 2019; pp. 331–345. [Google Scholar]
- Dey, S.; Luo, H.; Fokoue, A.; Hu, J.; Zhang, P. Predicting adverse drug reactions through interpretable deep learning framework. BMC Bioinform. 2018, 19, 476. [Google Scholar] [CrossRef] [Green Version]
- Karimi, M.; Wu, D.; Wang, Z.; Shen, Y. DeepAffinity: Interpretable deep learning of compound–protein affinity through unified recurrent and convolutional neural networks. Bioinformatics 2019, 35, 3329–3338. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Clark, C.M.; Schneider, J.A.; Bedell, B.J.; Beach, T.G.; Bilker, W.B.; Mintun, M.A.; Pontecorvo, M.J.; Hefti, F.; Carpenter, A.P.; Flitter, M.L.; et al. Use of florbetapir-PET for imaging β-amyloid pathology. JAMA 2011, 305, 275–283. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Joshi, A.D.; Pontecorvo, M.J.; Clark, C.M.; Carpenter, A.P.; Jennings, D.L.; Sadowsky, C.H.; Adler, L.P.; Kovnat, K.D.; Seibyl, J.P.; Arora, A.; et al. Performance characteristics of amyloid PET with florbetapir F 18 in patients with Alzheimer’s disease and cognitively normal subjects. J. Nucl. Med. 2012, 53, 378–384. [Google Scholar] [CrossRef] [PubMed] [Green Version]
CN (N = 214) | MCI (N = 292) | |
---|---|---|
Age | 74.18 ± 6.14 | 73.14 ± 7.48 |
Sex | 96 F/118 M | 173 F/119 M |
Education (years) | 16.7 ± 2.54 | 16.13 ± 2.64 |
APOE | 144 neg/70 pos | 173 neg/119 pos |
A positivity | 139 neg/75 pos | 152 neg/140 pos |
AUC (Mean ± 95% CI) | |||
---|---|---|---|
Model | CN | MCI | CN + MCI |
SVM (RBF) | 0.7515 ± 0.0131 | 0.7531 ± 0.0137 | 0.7537 ± 0.0129 |
RF | 0.7205 ± 0.0143 | 0.7226 ± 0.0140 | 0.7238 ± 0.0134 |
LR (ridge) | 0.7490 ± 0.0129 | 0.7480 ± 0.0112 | 0.7500 ± 0.0144 |
MLP | 0.7009 ± 0.0158 | 0.7013 ± 0.0137 | 0.7009 ± 0.0159 |
GCN-random | 0.8110 ± 0.0185 | 0.7768 ± 0.0153 | 0.7160 ± 0.0135 |
GCN-corr | 0.8851 ± 0.0154 | 0.8741 ± 0.0114 | 0.8632 ± 0.0115 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2023 by the author. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Kim, S.Y. Personalized Explanations for Early Diagnosis of Alzheimer’s Disease Using Explainable Graph Neural Networks with Population Graphs. Bioengineering 2023, 10, 701. https://doi.org/10.3390/bioengineering10060701
Kim SY. Personalized Explanations for Early Diagnosis of Alzheimer’s Disease Using Explainable Graph Neural Networks with Population Graphs. Bioengineering. 2023; 10(6):701. https://doi.org/10.3390/bioengineering10060701
Chicago/Turabian StyleKim, So Yeon. 2023. "Personalized Explanations for Early Diagnosis of Alzheimer’s Disease Using Explainable Graph Neural Networks with Population Graphs" Bioengineering 10, no. 6: 701. https://doi.org/10.3390/bioengineering10060701
APA StyleKim, S. Y. (2023). Personalized Explanations for Early Diagnosis of Alzheimer’s Disease Using Explainable Graph Neural Networks with Population Graphs. Bioengineering, 10(6), 701. https://doi.org/10.3390/bioengineering10060701