Lay person-based screening for early detection of Alzheimer's disease: Development and validation of an instrument

Symptoms of cognitive impairment reported to telephone interviewers by care givers of 272 patients were analyzed with respect to research diagnoses of dementia. All patients received neuropsychological evaluation for establish ing the research diagnoses. A data mining program that used machine learnin g algorithms produced an optimized binary decision tl ee for differentiatin g patient groups according to all available information. The results of thi s analysis were used to help foul. dementia experts create a dementia scree ning instrument amenable to application and scoring by nonclinical personne l. The validity of the resulting instrument was then evaluated in an indepe ndent sample of 103 patients administered neuropsychological testing within the previous 60 days. The psychometric properties of the empirically deriv ed scale and its performance for discriminating control from probable or po ssible, Alzheimer's patients indicate strong potential for use as a dementi a screener for the general population.