Data-driven disease progression models of Alzheimer{\textquoteright}s disease are important for clinical prediction model development, disease mechanism understanding and clinical trial design. Among them, dynamical models are particularly appealing because they are intrinsically interpretable. Most dynamical models proposed so far are consistent with a linear chain of events, inspired by the amyloid cascade hypothesis. However, it is now widely acknowledged that disease progression is not fully compatible with this conceptual model, at least in sporadic Alzheimer{\textquoteright}s disease, and more flexibility is needed to model the full spectrum of the disease. We propose a Bayesian model of the joint evolution of brain image-derived biomarkers based on explicitly modelling biomarkers{\textquoteright} velocities as a function of their current value and other subject characteristics. The model includes a system of ordinary differential equations to describe the biomarkers{\textquoteright} dynamics and sets a Gaussian process prior to the velocity field. We illustrate the model on amyloid PET SUVR and MRI-derived volumetric features from the ADNI study.
Bossa, M, Berenguer, AD & Sahli, H 2022, Non-parametric ODE-Based Disease Progression Model of Brain Biomarkers in Alzheimer’s Disease. in A Abdulkadir, DR Bathula, NC Dvornek, M Habes, SM Kia, V Kumar & T Wolfers (eds), International Workshop on Machine Learning in Clinical Neuroimaging: 5th International Workshop, MLCN 2022, Held in Conjunction with MICCAI 2022, Singapore, September 18, 2022, Proceedings. vol. 13596, Lecture Notes in Computer Science, vol. 13596, Springer Nature Switzerland AG, pp. 95-103. https://doi.org/10.1007/978-3-031-17899-3_10
Bossa, M., Berenguer, A. D., & Sahli, H. (2022). Non-parametric ODE-Based Disease Progression Model of Brain Biomarkers in Alzheimer’s Disease. In A. Abdulkadir, D. R. Bathula, N. C. Dvornek, M. Habes, S. M. Kia, V. Kumar, & T. Wolfers (Eds.), International Workshop on Machine Learning in Clinical Neuroimaging: 5th International Workshop, MLCN 2022, Held in Conjunction with MICCAI 2022, Singapore, September 18, 2022, Proceedings (Vol. 13596, pp. 95-103). (Lecture Notes in Computer Science; Vol. 13596). Springer Nature Switzerland AG. https://doi.org/10.1007/978-3-031-17899-3_10
@inbook{9671b3b30bc548ac8109c9a4e48e126f,
title = "Non-parametric ODE-Based Disease Progression Model of Brain Biomarkers in Alzheimer{\textquoteright}s Disease",
abstract = "Data-driven disease progression models of Alzheimer{\textquoteright}s disease are important for clinical prediction model development, disease mechanism understanding and clinical trial design. Among them, dynamical models are particularly appealing because they are intrinsically interpretable. Most dynamical models proposed so far are consistent with a linear chain of events, inspired by the amyloid cascade hypothesis. However, it is now widely acknowledged that disease progression is not fully compatible with this conceptual model, at least in sporadic Alzheimer{\textquoteright}s disease, and more flexibility is needed to model the full spectrum of the disease. We propose a Bayesian model of the joint evolution of brain image-derived biomarkers based on explicitly modelling biomarkers{\textquoteright} velocities as a function of their current value and other subject characteristics. The model includes a system of ordinary differential equations to describe the biomarkers{\textquoteright} dynamics and sets a Gaussian process prior to the velocity field. We illustrate the model on amyloid PET SUVR and MRI-derived volumetric features from the ADNI study.",
author = "Mat{\'i}as Bossa and Berenguer, {Abel D{\'i}az} and Hichem Sahli",
note = "Funding Information: The data used in preparation of this article was funded by the Alzheimer{\textquoteright}s Disease Neuroimaging Initiative (ADNI) (National Institutes of Health Grant U01 AG024904) and DOD ADNI (Department of Defense award number W81XWH-12-2-0012). Funding Information: Acknowledgements. This work was partially funded by INNOVIRIS (Brussels Capital Region, Belgium) under the project: {\textquoteright}DIMENTIA: Data governance in the development of machine learning algorithms to predict neurodegenerative disease evolution{\textquoteright} (BHG/2020-RDIR-2b). Publisher Copyright: {\textcopyright} 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG. Copyright: Copyright 2022 Elsevier B.V., All rights reserved.",
year = "2022",
month = oct,
day = "6",
doi = "10.1007/978-3-031-17899-3_10",
language = "English",
isbn = "978-3-031-17898-6",
volume = "13596",
series = "Lecture Notes in Computer Science",
publisher = " Springer Nature Switzerland AG",
pages = "95--103",
editor = "Ahmed Abdulkadir and Bathula, {Deepti R.} and Dvornek, {Nicha C.} and Mohamad Habes and Kia, {Seyed Mostafa} and Vinod Kumar and Thomas Wolfers",
booktitle = "International Workshop on Machine Learning in Clinical Neuroimaging",
}