Diagnosis of dementia from the History and Aetiology Schedule

Objective To provide a computerised method of diagnosing organic brain synd rome from history data without the use of mental state data. Methods Interview dataset from participants in a community study of the inc idence of dementia was used to form a training sample and validation sample . The algorithm was developed on the training sample and tested on the vali dation sample. Results Performance in the training and validation samples was very similar . The algorithm shows monotonically increasing probability of being diagnos ed with dementia as a function of the proposed level of diagnostic confiden ce. At the proposed cut point it has sensitivity 94% and specificity 84% fo r detecting concurrent psychiatrist's diagnosis of dementia. Conclusions The method provides a good agreement with psychiatrist's diagno sis, and the results in the validation sample show little shrinkage. The me thod will prove useful in studies where it has proved impossible to collect mental state information on all the study participants. Copyright (C) 2001 John Wiley & Sons, Ltd.