Machine learning for comprehensive forecasting of Alzheimer's Disease progression

Most approaches to machine learning from electronic health data can only predict a single endpoint.The ability to simultaneously simulate dozens of patient characteristics is a crucial step towardspersonalized medicine for Alzheimer's Disease. Here, we use an unsupervised machine learning modelcalled a Conditional Restricted Boltzmann Machine (CRBM) to simulate detailed patient trajectories.We use data comprising 18-month trajectories of 44 clinical variables from 1909 patients with MildCognitive Impairment or Alzheimer's Disease to train a model for personalized forecasting of diseaseprogression. We simulate synthetic patient data including the evolution of each sub-component ofcognitive exams, laboratory tests, and their associations with baseline clinical characteristics. Syntheticpatient data generated by the CRBM accurately refect the means, standard deviations, and correlationsof each variable over time to the extent that synthetic data cannot be distinguished from actual databy a logistic regression. Moreover, our unsupervised model predicts changes in total ADAS-Cog scoreswith the same accuracy as specifcally trained supervised models, additionally capturing the correlationstructure in the components of ADAS-Cog, and identifes sub-components associated with word recallas predictive of progression.

Enter your email address to download paper.

Click the link to begin download.
Oops! Something went wrong while submitting the form.
Publications

Modeling Disease Progression in Mild Cognitive Impairment and Alzheimer's Disease with Digital Twins

Publications

Bayesian prognostic covariate adjustment

Publications

Using Digital Twins to Decrease Enrollment and Increase Statistical Power in Alzheimer's Disease Trials (CTAD 2020)

We showed that digital twins could reduce the number of control subjects required in the analysis to achieve equivalent results to an analysis of the actual subjects.
Our novel method - Bayesian prognostic covariate adjustment - is a Bayesian analysis that draws on the strengths of the prognostic model approach.
Here, we have demonstrated that a particular type of generative model (i.e., CRBMs) can be used to accurately model disease progression for patients with MCI or AD.