Related Experiment Video
Updated: Jul 1, 2025
A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
Published on: January 11, 2020
Prediction of conversion from mild cognitive impairment to Alzheimer's disease and simultaneous feature selection and
Qi Zhang1, Ron Coury2, Wenlong Tang3
1Department of Mathematics and Statistics, University of New Hampshire, Durham, NH, 03824, USA. qi.zhang2@unh.edu.
Background:
Due to the heterogeneity among patients with Mild Cognitive Impairment (MCI), it is critical to predict their risk of converting to Alzheimer's disease (AD) early using routinely collected real-world data such as the electronic health record data or administrative claim data.
Methods:
The study used MarketScan Multi-State Medicaid data to construct a cohort of MCI patients. Logistic regression with tree-guided lasso regularization (TGL) was proposed to select important features and predict the risk of converting to AD. A subsampling-based technique was used to extract robust groups of predictive features. Predictive models including logistic regression, generalized random forest, and artificial neural network were trained using the extracted features.
Results:
The proposed TGL workflow selected feature groups that were robust, highly interpretable, and consistent with existing literature. The predictive models using TGL selected features demonstrated higher prediction accuracy than the models using all features or features selected using other methods.
Conclusions:
The identified feature groups provide insights into the progression from MCI to AD and can potentially improve risk prediction in clinical practice and trial recruitment.
Insights
Predicting Alzheimer's disease (AD) progression from Mild Cognitive Impairment (MCI) is crucial. Tree-guided lasso regularization effectively identified key features for accurate AD risk prediction using real-world data.
Area of Science:
- Neurology
- Data Science
- Biostatistics
Background:
- Mild Cognitive Impairment (MCI) patient heterogeneity necessitates early prediction of Alzheimer's disease (AD) conversion.
- Routinely collected real-world data, including electronic health records and administrative claims, are vital for risk prediction.
Purpose of the Study:
- To develop and validate a method for predicting the risk of conversion from MCI to AD.
- To identify robust and interpretable feature groups predictive of AD progression using real-world data.
Main Methods:
- Utilized MarketScan Multi-State Medicaid data to form an MCI patient cohort.
- Employed logistic regression with tree-guided lasso regularization (TGL) for feature selection and AD risk prediction.
- Applied a subsampling technique to extract robust predictive feature groups and trained various predictive models.
Main Results:
- The TGL workflow successfully identified feature groups that were robust, interpretable, and aligned with existing literature.
- Predictive models utilizing TGL-selected features achieved higher accuracy compared to models using all features or other selection methods.
Conclusions:
- The identified feature groups offer valuable insights into MCI to AD progression.
- This approach has the potential to enhance clinical practice and patient recruitment for AD trials.
More Related Videos
06:23The 4 Mountains Test: A Short Test of Spatial Memory with High Sensitivity for the Diagnosis of Pre-dementia Alzheimer's Disease
Published on: October 13, 2016
08:43Application of Granger Causality Analysis of the Directed Functional Connection in Alzheimer's Disease and Mild Cognitive Impairment
Published on: August 7, 2017
Related Concept Videos
01:26Alzheimer's Disease: Overview
The clinical diagnosis of AD hinges on the presence of memory and other cognitive impairments. Biomarkers, such as changes in Aβ...
01:22Alzheimer's Disease: Treatment
01:30Dementia
The progression of dementia is generally gradual....