Research Data Supporting ‘A robust and interpretable machine learning approach using multimodal biological data to predict future pathological tau accumulation’
MetadataShow full item record
Giorgio, J., Jagust, W., Baker, S., Landau, S., Tino, P., & Kourtzi, Z. (2022). Research Data Supporting ‘A robust and interpretable machine learning approach using multimodal biological data to predict future pathological tau accumulation’ [Dataset]. https://doi.org/10.17863/CAM.80891
Multimodal predictor and outcome data used to train machine learning models to predict future tau accumulation. Predictor data includes measures of Aß (PET), medial temporal grey matter density (MRI) and APOE genotype. Outcome data include longitudinal categories of clinical decline and tau burden/rates of decline (PET). The data for each of the samples presented in the manuscript is found in the ‘master_data_file.xlsx. Also included are all source data used to generate the figures and tables presented in the manuscript ‘Source data.xlsx’. A detailed description of these data is given in the ‘description of uploaded files.doc’. The custom code developed to implement the machine learning approach is provided as a MATLAB package ‘Giorgio et al 2022 Custom code’. Within this folder are top level wrapper functions, the machine learning implementation, post hoc analysis functions and sample data to run the code. A full description of the attached code and data can be found in ‘Giorgio et al 2020 Custom code read me.doc’.
Custom Code: ‘Giorgio et al 2022 Custom code’, custom code in MATLAB developed in this work. This code implements the GMLVQ-Scalar Projection machine learning approach as described in ‘Supplementary Methods’ For detailed description on implementation and running refer to ‘Giorgio et al 2022 Custom code read me.docx’ attached in zipped Giorgio et al 2022 Custom code file.
Machine learning, prognostic modelling, Alzheimer's disease brain imaging, tau accumulation
This record's DOI: https://doi.org/10.17863/CAM.80891
Attribution 4.0 International (CC BY 4.0)
Licence URL: https://creativecommons.org/licenses/by/4.0/