Abstract
The paper proposes a novel approach of survival transformers and extreme gradient boosting models in predicting cognitive deterioration in individuals with mild cognitive impairment (MCI) using metabolomics data in the ADNI cohort. By leveraging advanced machine learning and transformer-based techniques applied in survival analysis, the proposed approach highlights the potential of these techniques for more accurate early detection and intervention in Alzheimer’s dementia disease. This research also underscores the importance of non-invasive biomarkers and innovative modelling tools in enhancing the accuracy of dementia risk assessments, offering new avenues for clinical practice and patient care. A comprehensive Monte Carlo simulation procedure consisting of 100 repetitions of a nested cross-validation in which models were trained and evaluated, indicates that the survival machine learning models based on Transformer and XGBoost achieved the highest mean C-index performances, namely 0.85 and 0.8, respectively, and that they are superior to the conventional survival analysis Cox Proportional Hazards model which achieved a mean C-Index of 0.77. Moreover, based on the standard deviations of the C-Index performances obtained in the Monte Carlo simulation, we established that both survival machine learning models above are more stable than the conventional statistical model.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Alzheimer’s Disease Neuroimaging Initiative. https://adni.loni.usc.edu/about/
Dementia Statistics Hub. https://dementiastatistics.org/
scikit-learn. https://scikit-learn.org/stable/
skrebate \(\cdot \) PyPI. https://pypi.org/project/skrebate/
Xgboost. https://xgboost.readthedocs.io
Barnwal, A., Cho, H., Hocking, T.: Survival regression with accelerated failure time model in XGBoost 31(4), 1292–1302 (2022). https://doi.org/10.1080/10618600.2022.2067548
Billichová, M., Coan, L.J., Czanner, S., Kováčová, M., Sharifian, F., Czanner, G.: Comparing the performance of statistical, machine learning, and deep learning algorithms to predict time-to-event: a simulation study for conversion to mild cognitive impairment 19(1) (2024). https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0297190
Collins, G.S., Reitsma, J.B., Altman, D.G., Moons, K.G.M.: Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): the TRIPOD statement 102(3), 148–158 (2015). https://doi.org/10.1002/bjs.9736
Davidson-Pilon, C.: Lifelines, survival analysis in Python (2024). https://lifelines.readthedocs.io/en/latest/
Ding, K., Zhou, M., Metaxas, D.N., Zhang, S.: Pathology-and-genomics multimodal transformer for survival outcome prediction (2023). http://arxiv.org/abs/2307.11952
Guo, Y., et al.: Plasma proteomic profiles predict future dementia in healthy adults 4(2), 247–260 (2024). https://www.nature.com/articles/s43587-023-00565-0
Hu, S., Fridgeirsson, E.A., van Wingen, G., Welling, M.: Transformer-based deep survival analysis (2021)
Huynh, K., Heart, B.: Lipidomic analysis of the ADNI1, 2 and GO cohorts
Alzheimer’s Disease International: World alzheimer report 2023: reducing dementia risk: never too early, never too late. https://www.alzint.org/resource/world-alzheimer-report-2023/
Machado-Fragua, M.D., et al.: Circulating serum metabolites as predictors of dementia: a machine learning approach in a 21-year follow-up of the whitehall II cohort study 20(1), 334 (2022). https://doi.org/10.1186/s12916-022-02519-6
Mirabnahrazam, G., et al.: Predicting time-to-conversion for dementia of Alzheimer’s type using multi-modal deep survival analysis 121, 139–156 (2023). https://www.sciencedirect.com/science/article/pii/S0197458022002196
Musto, H., Stamate, D., Logofatu, D., Ouarbya, L.: On a survival gradient boosting, neural network and cox PH based approach to predicting dementia diagnosis risk on ADNI, pp. 1–7. IEEE Computer Society (2023). https://doi.ieeecomputersociety.org/10.1109/BIBM58861.2023.10419115
Musto, H., Stamate, D., Pu, I., Stahl, D.: A machine learning approach for predicting deterioration in Alzheimer’s disease. In: 2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA), pp. 1443–1448. IEEE (2021). https://ieeexplore.ieee.org/document/9679955/
Musto, H., Stamate, D., Pu, I., Stahl, D.: Predicting Alzheimers disease diagnosis risk over time with survival machine learning on the ADNI cohort (2023). http://arxiv.org/abs/2306.10326
Qiang, Y.X., et al.: Plasma metabolic profiles predict future dementia and dementia subtypes: a prospective analysis of 274,160 participants 16(1), 16 (2024). https://doi.org/10.1186/s13195-023-01379-3
Sarica, A., Aracri, F., Bianco, M.G., Arcuri, F., Quattrone, A., Quattrone, A., for the Alzheimer’s Disease Neuroimaging Initiative: Explainability of random survival forests in predicting conversion risk from mild cognitive impairment to Alzheimer’s disease 10(1), 31 (2023). https://doi.org/10.1186/s40708-023-00211-w
Schmid, M., Wright, M.N., Ziegler, A.: On the use of Harrell’s C for clinical risk prediction via random survival forests 63, 450–459 (2016). https://www.sciencedirect.com/science/article/pii/S0957417416303633
Shahriari, B., Swersky, K., Wang, Z., Adams, R.P., de Freitas, N.: Taking the human out of the loop: a review of Bayesian optimization 104(1), 148–175 (2016). https://ieeexplore.ieee.org/document/7352306. Conference Name: Proceedings of the IEEE
Snoek, J., Larochelle, H., Adams, R.P.: Practical Bayesian optimization of machine learning algorithms (2012). http://arxiv.org/abs/1206.2944
Spooner, A., et al.: A comparison of machine learning methods for survival analysis of high-dimensional clinical data for dementia prediction 10(1), 20410 (2020). https://www.nature.com/articles/s41598-020-77220-w
Stamate, D., Lovestone, S., Legido-Quigley, C.: A metabolite-based machine learning approach to diagnose Alzheimer-type dementia in blood: results from the European medical information framework for Alzheimer disease biomarker discovery cohort 5(1), 933–938 (2019). https://onlinelibrary.wiley.com/doi/abs/10.1016/j.trci.2019.11.001
Stamate, D., Musto, H., Ajnakina, O., Stahl, D.: Predicting risk of dementia with survival machine learning and statistical methods: results on the English longitudinal study of ageing cohort (2023). https://ui.adsabs.harvard.edu/abs/2023arXiv230610330S
Steyerberg, E.W.: Clinical Prediction Models, 2nd edn. Springer, New York (2019). https://doi.org/10.1007/978-0-387-77244-8.
Teunissen, C.E., et al.: Blood-based biomarkers for Alzheimer’s disease: towards clinical implementation 21(1), 66–77 (2022). https://doi.org/10.1016/S1474-4422(21)00361-6
Urbanowicz, R.J., Olson, R.S., Schmitt, P., Meeker, M., Moore, J.H.: Benchmarking relief-based feature selection methods for bioinformatics data mining (2018). http://arxiv.org/abs/1711.08477
Vaswani, A., et al.: Attention is all you nee (2023). https://doi.org/10.48550/arXiv.1706.03762. http://arxiv.org/abs/1706.03762
Wang, Z., Sun, J.: SurvTRACE: transformers for survival analysis with competing events. In: Proceedings of the 13th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics, pp. 1–9 (2022). http://arxiv.org/abs/2110.00855
Wiegrebe, S., Kopper, P., Sonabend, R., Bischl, B., Bender, A.: Deep learning for survival analysis: a review 57(3), 65 (2024). http://arxiv.org/abs/2305.14961
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Musto, H., Stamate, D., Logofatu, D., Stahl, D. (2024). Predicting Deterioration in Mild Cognitive Impairment with Survival Transformers, Extreme Gradient Boosting and Cox Proportional Hazard Modelling. In: Wand, M., Malinovská, K., Schmidhuber, J., Tetko, I.V. (eds) Artificial Neural Networks and Machine Learning – ICANN 2024. ICANN 2024. Lecture Notes in Computer Science, vol 15023. Springer, Cham. https://doi.org/10.1007/978-3-031-72353-7_26
Download citation
DOI: https://doi.org/10.1007/978-3-031-72353-7_26
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-72352-0
Online ISBN: 978-3-031-72353-7
eBook Packages: Computer ScienceComputer Science (R0)