The progression of Alzheimer’s Disease (AD) is characterized by the gradual deterioration of biomarkers and eventual loss of basic memory and decision-making functions (Figure 1). Using these biomarker values and other tests to estimate how far an individual has progressed in the disease is valuable in diagnosis as well as in assessing the efficacy of interventions. Additionally, prediction of how the individual will continue to progress is critical in decision making. While it is known that AD only gets worse over time, it is believed that patients with the disease progress at different rates and at different stages of their lives. There is no standard path of progression for people with the disease, which makes estimation of disease severity and future progression difficult. In addition to estimating these paths for an individual given their measurements, it is of clinical and biological significance to be able to understand the order in which certain biomarkers begin to deteriorate and what their distribution might look like for various stages of the disease.
[1]
A. Monsch,et al.
A Longitudinal Item Response Theory Model to Characterize Cognition Over Time in Elderly Subjects
,
2017,
CPT: pharmacometrics & systems pharmacology.
[2]
Maurizio Filippone,et al.
Disease Progression Modeling and Prediction through Random Effect Gaussian Processes and Time Transformation
,
2017,
1701.01668.
[3]
Aki Vehtari,et al.
Gaussian processes with monotonicity information
,
2010,
AISTATS.
[4]
J. Ramsay.
Monotone Regression Splines in Action
,
1988
.
[5]
Jerry L. Prince,et al.
A computational neurodegenerative disease progression score: Method and results with the Alzheimer's disease neuroimaging initiative cohort
,
2012,
NeuroImage.