Longitudinal clinical score prediction in Alzheimer's disease with soft-split sparse regression based random forest
Public Deposited- Creator
-
Huang, Lei
- Affiliation: School of Medicine, Department of Radiology
-
Jin, Yan
- ORCID: 0000-0001-9392-5552
- Affiliation: School of Medicine, Department of Radiology
-
Gao, Yaozong
- Affiliation: School of Medicine, Department of Radiology
-
Thung, Kim-Han
- Affiliation: School of Medicine, Department of Radiology
-
Shen, Dinggang
- Affiliation: School of Medicine, Department of Radiology
- Other Affiliation: Department of Brain and Cognitive Engineering; Korea University
- Abstract
- Alzheimer’s disease (AD) is an irreversible neurodegenerative disease and affects a large population in the world. Cognitive scores at multiple time points can be reliably used to evaluate the progression of the disease clinically. In recent studies, machine learning techniques have shown promising results on the prediction of AD clinical scores. However, there are multiple limitations in the current models such as linearity assumption and missing data exclusion. Here, we present a nonlinear supervised sparse regression–based random forest (RF) framework to predict a variety of longitudinal AD clinical scores. Furthermore, we propose a soft-split technique to assign probabilistic paths to a test sample in RF for more accurate predictions. In order to benefit from the longitudinal scores in the study, unlike the previous studies that often removed the subjects with missing scores, we first estimate those missing scores with our proposed soft-split sparse regression–based RF and then utilize those estimated longitudinal scores at all the previous time points to predict the scores at the next time point. The experiment results demonstrate that our proposed method is superior to the traditional RF and outperforms other state-of-art regression models. Our method can also be extended to be a general regression framework to predict other disease scores.
- Date of publication
- 2016
- Keyword
- Male
- Diffusion Magnetic Resonance Imaging
- Female
- Regression Analysis
- Random forest
- Machine Learning
- Aged
- Longitudinal Studies
- Humans
- Alzheimer Disease
- Datasets as Topic
- Sparse representation
- Predictive Value of Tests
- Clinical scores
- Disease Progression
- Alzheimer's disease
- Brain
- Aged, 80 and over
- Longitudinal study
- Linear Models
- Soft-split
- Neuroimaging
- DOI
- Identifier
- Publisher DOI: https://doi.org/10.1016/j.neurobiolaging.2016.07.005
- Onescience id: e3d04c84913849679dd06328b49774c4583754e4
- PMID: 27500865
- PMCID: PMC5152677
- Resource type
- Article
- Rights statement
- In Copyright
- Journal title
- Neurobiology of Aging
- Journal volume
- 46
- Page start
- 180
- Page end
- 191
- Language
- English
- ISSN
- 0197-4580
- 1558-1497
Relations
- Parents:
- In Collection:
This work has no parents.
Items
| Thumbnail | Title | Date Uploaded | Visibility | Actions |
|---|---|---|---|---|
|
|
PubMedCentral-PMC5152677.pdf | 2016 | Public | Download |