Piecewise Constant Intensities Markov Model In Outcome Of Mild Cognitive Impairment To Alzheimer’s Disease

Objective The aim of this study was to introduce piecewise constant intensities Markov model in outcome prediction from mild cognitive impairment (MCI) to Alzheimer’s disease (AD) and to find out related factors in order to provide theory basis for AD prevention among various progressive stages. From the point of application, piecewise constant intensities Markov model in chronic diseases was discussed methodologically and suggested method for exploring influencing factors for various progressive stages of other chronic disease were provided.Methods Our data came from four waves of cohort study of600community dwelling older people in Taiyuan. MCI, moderate to severe cognitive impairment, and AD were defined as state1,2and3, respectively. Piecewise constant intensities Markov model was applied to explore factors for various progressive stages from MCI to AD.Results Based on hypothesis testing, the Markov assumption was satisfied (P=0.89) and the time-homogeneous assumption was not (P<0.001), so piecewise constant intensities Markov model was applied. For the first interval (0,12) months, multivariate analysis showed that gender, age, education, occupation and hypertension were statistically significant for transition from state1to state2; Age, education, occupation, hypertension and diabetes were statistically significant for transition from state1to state3; Gender, age, education, hypertension and diabetes were statistically significant for transition from state2to state3. For the second interval [12,18] months, multivariate analysis showed that gender, age, education, occupation, smoking and hypertension were statistically significant for transition from state1to state2; Education, occupation, smoking, hypertension and diabetes were statistically significant for transition from state1to state3; Age, education, occupation, smoking, hypertension and diabetes were statistically significant for transition from state2to state3. Therefore, women, older, smoking, hypertension and diabetes were risk factors for progression from MCI to AD; While high education and intellectual work were protecting factors for progression from MCI to AD. According to the fitted model, survival curves, transition intensities, and three years probabilities among each state were also estimated.Conclusion To delay the disease progression of AD, prevention measures phase by phase can be taken based on the main factors of each stage. Compared with homogeneous Markov model, the piecewise constant intensities Markov model was more all-around in the related factors analysis and variation pattern during disease progressive process. The appropriate model should be selected based on the collected data.