Related Experiment Video
Updated: Jun 2, 2026

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
Published on: January 11, 2020
[Multi-state Markov model in expressing the outcome of mild cognitive impairment among community-based elderly
Shan-shan Yang1, Li-ye Zhou, Rui-feng Liang
1Community Health Service Centers of Xuanwu Community, Beijing 100055, China.
Objective:
To introduce the Multi-state Markov model in studying the outcome prediction of mild cognitive impairment (MCI).
Methods:
Based on the intelligence quotient (IQ) changes that reflecting the trends in cognitive function in the patients under follow-up program, we constructed a four states model and used Multi-state Markov model to analyze the patients.
Results:
Among 600 MCI patients, there were 174 (29.0%) males and 426 (71.0%) females, with age range of 65-90 years-old (average 69.7 ± 6.6). For univariate analysis, gender, age, education level, marital status, smoking, household income, cerebral hemorrhage, hypertension, high cholesterol, diabetes, LDL-C, SBP and DBP were found to be associated with cognitive function. For multivariate analysis, female, older age, cerebral hemorrhage and higher SBP were shown to be the risk factors for transition from the state of cognitive stability to the state of severe deterioration, and their coefficients were 0.762, 0.366, 0.885, and 0.069, respectively. Age (0.038) could influence the transition from the state of cognitive stability to slight deterioration. Higher education level was shown to be the protective factor for these transitions (-0.219 and -0.297). Transition intensity from the state of cognitive stability to the state of slight and severe deterioration was 1.2 times that of transition to the state of improving. Transition intensity from state of slight deterioration to cognitive stability was 11.4 times that of transition to severe deterioration.
Conclusion:
Multi-state Markov model was an effective tool in dealing with longitudinal data.
Insights
The Multi-state Markov model effectively predicts mild cognitive impairment (MCI) outcomes using longitudinal data. Female gender, older age, and hypertension increase MCI progression risk, while education offers protection.
Area of Science:
- Neurology
- Biostatistics
- Gerontology
Background:
- Mild cognitive impairment (MCI) poses a significant challenge in predicting disease progression.
- Longitudinal studies are crucial for understanding the dynamic changes in cognitive function.
Purpose of the Study:
- To introduce and apply the Multi-state Markov model for predicting outcomes in patients with mild cognitive impairment (MCI).
- To identify risk and protective factors influencing cognitive status transitions.
Main Methods:
- A four-state model was constructed based on intelligence quotient (IQ) changes reflecting cognitive function trends.
- The Multi-state Markov model was employed to analyze longitudinal data from 600 MCI patients.
Main Results:
- Univariate analysis identified gender, age, education, hypertension, and other factors associated with cognitive function.
- Multivariate analysis revealed female gender, older age, cerebral hemorrhage, and higher systolic blood pressure (SBP) as risk factors for severe deterioration.
- Higher education level demonstrated a protective effect against cognitive decline.
Conclusions:
- The Multi-state Markov model is an effective tool for analyzing longitudinal data in cognitive impairment research.
- Understanding transition dynamics and identifying key risk/protective factors can inform clinical management strategies for MCI.
More Related Videos
Related Concept Videos
Alzheimer's Disease: Overview
The clinical diagnosis of AD hinges on the presence of memory and other cognitive impairments. Biomarkers, such as changes in Aβ and tau...
Alzheimer Disease l: Introduction
Dementia l: Introduction
Alzheimer Disease ll: Pathophysiology
Cognitive Development During Adulthood

