Explore the risk factors for predicting the progressess Lead Investigator: Ji Zhaohua Institution : Fourth Military Medical University E-Mail : hellojzh@msn.com Proposal ID : 965 Proposal Description: In China, Alzheimer's Disease is becoming a serious public problem because the the aging of population. But the long time follow-up corhort studies of Alzheimer's Disease were rare and the progression data based on the Chinese cohort is lacking. The patient's family wanted to know what the patient's cognition, composite scores and language would be after several years and be prepared for the situations. We assume that the patient's progress was related to the general characteristics of the patient and other disease history in the case of good care. The patient's general characteristics and other disease information, such as, Gender, age, education level, presence versus absence of hypertension, hypercholesterolemia, heart disease, stroke, and family dementia history, and so on. The progression included the MMSE, Composite scores and Test language, and so on. We would try some statistic model to predict the progression of Alzheimer's Disease. For example, predict the MMSE score of the patient five year later with the gender, age, education level, presence versus absence of hypertension, hypercholesterolemia, heart disease, stroke, and family dementia history with the BP and RBF Neural Network. So the baseline data of the patient (gender, age, education level, presence versus absence of hypertension, hypercholesterolemia, heart disease, stroke, and family dementia history, MMSE score) and the data of the first year, year 3, year 5, year 20 follow-up MMSE scores were preferred.