Technical Name A novel blood based multi-biomarker modeling for predicting neurodegenerative disorders by machine learning
Project Operator National Taiwan University
Project Host 邱銘章
We constructed a model to differentiate different neurodegenerative diseases by using blood-based biomarkers. Linear Discriminant Analysis (LDA) was used to reduce dimensionsMICE (Multivariate Imputation by Chained Equations) was used for missing value treatmentchoose CART model to predict missing value imputation. This machine learning model would be used for early dectection of neurodegenerative diseases.
Scientific Breakthrough
Alzheimer's disease (AD)Parkinson's disease (PD) are the  most common neurodegenerative disorders. We developed a machine learning algorithmestablished a 3D model by reducing the multidimensional information from the blood levels of individual blood biomarkers. The developed 3D analytic model promptly differentiates the disease groups,also reflect the disease severity in either ADPD spectrum.
Industrial Applicability
Our developed machine learning algorithmestablished model could provide indispensable tools for intelligent data analysis incorporating multidimensional blood biomarkers to efficiently achieve the goal of early pre-clinical diagnosis of neurodegenerative disorders. This easily assessible blood-based markers combined with machine-learning platform could be applied for early detection of ADPD in the pre-clinical stage in the aging society.
Keyword Neurodegenerative disorders Alzheimer's disease Parkinson's disease Biomarker Model Machine learning Linear Discriminant Analysis Multiple imputation Feature extraction Supervised learning
  • Contact