Scientific article
Open access

Using normative modelling to detect disease progression in mild cognitive impairment and Alzheimer's disease in a cross-sectional multi-cohort study

Published inScientific reports, vol. 11, no. 1, 15746
Publication date2021-08-03
First online date2021-08-03

Normative modelling is an emerging method for quantifying how individuals deviate from the healthy populational pattern. Several machine learning models have been implemented to develop normative models to investigate brain disorders, including regression, support vector machines and Gaussian process models. With the advance of deep learning technology, the use of deep neural networks has also been proposed. In this study, we assessed normative models based on deep autoencoders using structural neuroimaging data from patients with Alzheimer's disease (n = 206) and mild cognitive impairment (n = 354). We first trained the autoencoder on an independent dataset (UK Biobank dataset) with 11,034 healthy controls. Then, we estimated how each patient deviated from this norm and established which brain regions were associated to this deviation. Finally, we compared the performance of our normative model against traditional classifiers. As expected, we found that patients exhibited deviations according to the severity of their clinical condition. The model identified medial temporal regions, including the hippocampus, and the ventricular system as critical regions for the calculation of the deviation score. Overall, the normative model had comparable cross-cohort generalizability to traditional classifiers. To promote open science, we are making all scripts and the trained models available to the wider research community.

  • Aged
  • Alzheimer Disease / diagnostic imaging
  • Alzheimer Disease / epidemiology
  • Alzheimer Disease / pathology
  • Brain / diagnostic imaging
  • Brain / pathology
  • Case-Control Studies
  • Cognitive Dysfunction / diagnostic imaging
  • Cognitive Dysfunction / epidemiology
  • Cognitive Dysfunction / pathology
  • Cohort Studies
  • Cross-Sectional Studies
  • Disease Progression
  • Female
  • Humans
  • Machine Learning
  • Male
  • Middle Aged
  • Models, Statistical
  • Neural Networks, Computer
  • Neuroimaging / methods
  • NIA NIH HHS - [P30 AG066444]
  • Medical Research Council - [MC_PC_17228]
  • NIA NIH HHS - [R01 AG021910]
  • NIA NIH HHS - [RF1 AG063153]
  • NCRR NIH HHS - [U24 RR021382]
  • Medical Research Council - [MC_QA137853]
  • NIA NIH HHS - [R01 AG073949]
  • NIA NIH HHS - [P01 AG003991]
  • NIA NIH HHS - [P50 AG005681]
  • NIMH NIH HHS - [P50 MH071616]
  • NIA NIH HHS - [P01 AG026276]
  • NIA NIH HHS - [U01 AG024904]
  • National Institutes of Health - [RF1AG063153]
  • Wellcome Trust - Using deep learning technology to make individualised inferences in brain-based disorders [208519]
  • Wellcome Trust - Programme for High Dimensional Translation in Neurology [213038]
Citation (ISO format)
PINAYA, Walter H L et al. Using normative modelling to detect disease progression in mild cognitive impairment and Alzheimer’s disease in a cross-sectional multi-cohort study. In: Scientific reports, 2021, vol. 11, n° 1, p. 15746. doi: 10.1038/s41598-021-95098-0
Main files (1)
Article (Published version)
Secondary files (1)
ISSN of the journal2045-2322

Technical informations

Creation11/16/2022 11:40:18 AM
First validation08/23/2023 2:48:02 PM
Update time08/23/2023 2:48:02 PM
Status update08/23/2023 2:48:02 PM
Last indexation02/01/2024 10:33:37 AM
All rights reserved by Archive ouverte UNIGE and the University of GenevaunigeBlack