Objective       To establish a diagnostic model of Alzheimer’s disease and mild cognitive impairment with higher diagnosis accuracy.       Methods       Based on the researches of 33 clinical indices of 391 cases including healthy controls

Alzheimer’s disease patients and mild cognitive impairment patients

a stepwise Fisher discriminant model was carried out for diagnosis simulation

and the discriminant function with the highest accuracy was selected.       Results       Six indices were selected to establish the discriminant model of Alzheimer’s disease and mild cognitive impairment. After 100 times of random sampling for diagnosis simulation in the objects

including healthy controls

Alzheimer’s disease patients and mild cognitive impairment patients

the average diagnosis accuracy was 75.50%

and the highest accuracy reached 80.63%.       Conclusion       Our established stepwise Fisher discriminant model can be used to improve the diagnostic accuracy for Alzheimer’s disease and mild cognitive impairment

which can provide a new method for their discriminant for scientific research and clinical practice.