Explainability of CNN-based Alzheimer's disease detection from online handwriting.
1D-CNN
Alzheimer’s disease
Explainability
Online handwriting
Journal
Scientific reports
ISSN: 2045-2322
Titre abrégé: Sci Rep
Pays: England
ID NLM: 101563288
Informations de publication
Date de publication:
27 Sep 2024
27 Sep 2024
Historique:
received:
03
04
2024
accepted:
09
09
2024
medline:
28
9
2024
pubmed:
28
9
2024
entrez:
27
9
2024
Statut:
epublish
Résumé
With over 55 million people globally affected by dementia and nearly 10 million new cases reported annually, Alzheimer's disease is a prevalent and challenging neurodegenerative disorder. Despite significant advancements in machine learning techniques for Alzheimer's disease detection, the widespread adoption of deep learning models raises concerns about their explainability. The lack of explainability in deep learning models for online handwriting analysis is a critical gap in the literature in the context of Alzheimer's disease detection. This paper addresses this challenge by interpreting predictions from a Convolutional Neural Network applied to multivariate time series data, generated by online handwriting data associated with continuous loop series handwritten on a graphical tablet. Our explainability methods reveal distinct motor behavior characteristics for healthy individuals and those diagnosed with Alzheimer's. Healthy subjects exhibited consistent, smooth movements, while Alzheimer's patients demonstrated erratic patterns marked by abrupt stops and direction changes. This emphasizes the critical role of explainability in translating complex models into clinically relevant insights. Our research contributes to the enhancement of early diagnosis, providing significant and reliable insights to stakeholders involved in patient care and intervention strategies. Our work bridges the gap between machine learning predictions and clinical insights, fostering a more effective and understandable application of advanced models for Alzheimer's disease assessment.
Identifiants
pubmed: 39333681
doi: 10.1038/s41598-024-72650-2
pii: 10.1038/s41598-024-72650-2
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
22108Informations de copyright
© 2024. The Author(s).
Références
World Health Organization. Dementia Fact Sheet. https://www.who.int/news-room/fact-sheets/detail/dementia (2023).
Buchman, A. S. & Bennett, D. A. Loss of motor function in preclinical Alzheimer’s disease. Expert Rev. Neurother.11(5), 665–676 (2011).
doi: 10.1586/ern.11.57
pubmed: 21539487
pmcid: 3121966
Albert, M. S. et al. The diagnosis of mild cognitive impairment due to Alzheimer’s disease: Recommendations from the national institute on aging-Alzheimer’s association workgroups on diagnostic guidelines for Alzheimer’s disease. Alzheimer’s Dement.7(3), 270–279 (2011).
doi: 10.1016/j.jalz.2011.03.008
Hayashi, A. et al. Neural substrates for writing impairments in Japanese patients with mild Alzheimer’s disease: A SPECT study. Neuropsychologia. 49(7), 1962–1968. https://doi.org/10.1016/j.neuropsychologia.2011.03.024 (2011).
doi: 10.1016/j.neuropsychologia.2011.03.024
pubmed: 21439989
Yan, J. H., Rountree, S., Massman, P., Doody, R. S. & Li, H. Alzheimer’s disease and mild cognitive impairment deteriorate fine movement control. J. Psychiatr. Res.42(14), 1203–1212. https://doi.org/10.1016/j.jpsychires.2008.01.006 (2008).
doi: 10.1016/j.jpsychires.2008.01.006
pubmed: 18280503
Yu, N. Y. & Chang, S. H. Kinematic analyses of graphomotor functions in individuals with Alzheimer’s disease and amnestic mild cognitive impairment. J. Med. Biol. Eng.36(3), 334–343 (2016).
doi: 10.1007/s40846-016-0143-y
Dao, Q., El-Yacoubi, M. A. & Rigaud, A.-S. Detection of Alzheimer disease on online handwriting using 1d convolutional neural network. IEEE Access11, 2148–2155. https://doi.org/10.1109/ACCESS.2022.3232396 (2023).
doi: 10.1109/ACCESS.2022.3232396
Erdogmus, P. & Kabakus, A. T. The promise of convolutional neural networks for the early diagnosis of the Alzheimer’s disease. Eng. Appl. Artif. Intell.123, 106254. https://doi.org/10.1016/j.engappai.2023.106254 (2023).
doi: 10.1016/j.engappai.2023.106254
Mitra, U. & Rehman, S. U. Ml-powered handwriting analysis for early detection of Alzheimer’s disease. IEEE Access12, 69031–69050. https://doi.org/10.1109/ACCESS.2024.3401104 (2024).
doi: 10.1109/ACCESS.2024.3401104
Hakan, Ö. A novel approach to detection of Alzheimer’s disease from handwriting: Triple ensemble learning model. Gazi Univ. J. Sci. Part C Des. Technol. 1–1 (2024).
Lundberg, S. M. & Lee, S.-I. A unified approach to interpreting model predictions. In Advances in Neural Information Processing Systems (eds. Guyon, I., Luxburg, U.V., Bengio, S., Wallach, H., Fergus, R., Vishwanathan, S., Garnett, R.) vol. 30, 4765–4774. http://papers.nips.cc/paper/7062-a-unified-approach-to-interpreting-model-predictions.pdf (2017).
Ismail, A. A., Gunady, M., Bravo, H. C. & Feizi, S. Benchmarking deep learning interpretability in time series predictions. In Proceedings of the 34th International Conference on Neural Information Processing Systems. NIPS’20 (Curran Associates Inc., 2020).
. Ates, E., Aksar, B., Leung, V. J. & Coskun, A. K. Counterfactual explanations for multivariate time series. In 2021 International Conference on Applied Artificial Intelligence (ICAPAI). https://doi.org/10.1109/icapai49758.2021.9462056 . https://doi.org/10.11091109%2Ficapai49758.2021.9462056 (2021).
Werner, P., Rosenblum, S., Bar-On, G., Heinik, J. & Korczyn, A. Handwriting process variables discriminating mild Alzheimer’s disease and mild cognitive impairment. J. Gerontol. Psychol. Sci.61(4), 228–236 (2006).
doi: 10.1093/geronb/61.4.P228
Teulings, H.-L. & Stelmach, G. E. Control of stroke size, peak acceleration, and stroke duration in parkinsonian handwriting. Hum. Mov. Sci.10(2–3), 315–334 (1991).
doi: 10.1016/0167-9457(91)90010-U
Slavin, M. J., Phillips, J. G., Bradshaw, J. L., Hall, K. A. & Presnell, I. Consistency of handwriting movements in dementia of the Alzheimer’s type: A comparison with Huntington’s and Parkinson’s diseases. J. Int. Neuropsychol. Soc.5(1), 20–25. https://doi.org/10.1017/s135561779951103x (1999).
doi: 10.1017/s135561779951103x
pubmed: 9989020
El-Yacoubi, M. A., Garcia-Salicetti, S., Kahindo, C., Rigaud, A.-S. & Cristancho-Lacroix, V. From aging to early-stage Alzheimer’s: Uncovering handwriting multimodal behaviors by semi-supervised learning and sequential representation learning. Pattern Recognit.86, 112–133 (2019).
doi: 10.1016/j.patcog.2018.07.029
Mwamsojo, N. et al. Reservoir computing for early stage Alzheimer’s disease detection. IEEE Access10, 59821–59831. https://doi.org/10.1109/access.2022.3180045 (2022).
doi: 10.1109/access.2022.3180045
Impedovo, D. & Pirlo, G. Dynamic handwriting analysis for the assessment of neurodegenerative diseases: A pattern recognition perspective. IEEE Rev. Biomed. Eng.12, 209–220. https://doi.org/10.1109/RBME.2018.2840679 (2019).
doi: 10.1109/RBME.2018.2840679
pubmed: 29993722
Almendra Freitas, C.O., El Yacoubi, A., Bortolozzi, F. & Sabourin, R. Brazilian bank check handwritten legal amount recognition. In Proceedings 13th Brazilian Symposium on Computer Graphics and Image Processing (Cat. No.PR00878). SIBGRA-00. https://doi.org/10.1109/sibgra.2000.883901 (IEEE Comput. Soc).
El-Yacoubi, A., Sabourin, R., Gilloux, M. & Suen, C. Y. Off-line handwritten word recognition using hidden markovmodels. In Knowledge-based intelligent techniques in character recognition (eds. Jain L.C. & Lazzerini B.) 191–229 (CRC Press, 1999).
El-Yacoubi, A., Sabourin, R., Gilloux, M. & Suen, C.Y. Improved model architecture and training phase in an off-line hmm-based word recognition system. In Proceedings. Fourteenth International Conference on Pattern Recognition (Cat. No.98EX170) vol. 2, 1521–15252. https://doi.org/10.1109/ICPR.1998.711997 (1998).
Kahindo, C., El Yacoubi, M., Garcia-Salicetti, S., Rigaud, A.-S. & Cristancho-Lacroix, V. Characterizing early-stage Alzheimer through spatiotemporal dynamics of handwriting. IEEE Signal Process. Lett. https://doi.org/10.1109/LSP.2018.2794500 (2018).
doi: 10.1109/LSP.2018.2794500
Fawaz, H. I., Forestier, G., Weber, J., Idoumghar, L. & Muller, P.-A. Deep learning for time series classification: A review. Data Min. Knowl. Discov.33(4), 917–963. https://doi.org/10.1007/s10618-019-00619-1 (2019).
doi: 10.1007/s10618-019-00619-1
Tonekaboni, S., Joshi, S., McCradden, M. D. & Goldenberg, A. What clinicians want: Contextualizing explainable machine learning for clinical end use. arXiv:1905.05134 (2019).
Rojat, T. et al. Explainable artificial intelligence (XAI) on timeseries data: A survey (2021).
Höllig, J., Kulbach, C. & Thoma, S. TSInterpret: A unified framework for time series interpretability. https://doi.org/10.48550/arXiv.2208.05280 (2022).
American Psychiatric Association. DSM-5 Task Force: Diagnostic and Statistical Manual of Mental Disorders: DSM-5™ 5th edn. https://doi.org/10.1176/appi.books.9780890425596 (2013).
Wachter, S., Mittelstadt, B. & Russell, C. Counterfactual explanations without opening the black box: Automated decisions and the GDPR. Harv. J. Law Technol. https://doi.org/10.2139/ssrn.3063289 (2018).
doi: 10.2139/ssrn.3063289
Meng, H., Wagner, C. & Triguero, I. Explaining time series classifiers through meaningful perturbation and optimisation. Inf. Sci.645, 119334. https://doi.org/10.1016/j.ins.2023.119334 (2023).
doi: 10.1016/j.ins.2023.119334
Jin, W., Li, X., Fatehi, M. & Hamarneh, G. Generating post-hoc explanation from deep neural networks for multi-modal medical image analysis tasks. MethodsX10, 102009. https://doi.org/10.1016/j.mex.2023.102009 (2023).
doi: 10.1016/j.mex.2023.102009
pubmed: 36793676
pmcid: 9922805
Baehrens, D. et al. How to explain individual classification decisions. J. Mach. Learn. Res.11, 1803–1831 (2010).
Shrikumar, A., Greenside, P., Shcherbina, A. & Kundaje, A. Not just a black box: Learning important features through propagating activation differences (2017).
De Stefano, C., Fontanella, F., Impedovo, D., Pirlo, G. & Scotto di Freca, A. Handwriting analysis to support neurodegenerative diseases diagnosis: A review. Pattern Recognition Letters121, 37–45. https://doi.org/10.1016/j.patrec.2018.05.013 (2019) (Graphonomics for e-citizens: e-health, e-society, e-education).
doi: 10.1016/j.patrec.2018.05.013
Fernandes, C. P., Montalvo, G., Caligiuri, M., Pertsinakis, M. & Guimarães, J. Handwriting changes in Alzheimer’s disease: A systematic review. J. Alzheimers Dis.96(1), 1–11. https://doi.org/10.3233/JAD-230438 (2023).
doi: 10.3233/JAD-230438
pubmed: 37718808