Sequence Prediction Algorithm for the Diagnosis of Early Dementia Development

Abstract

Dementia is a combination of systematic symptoms of a long-term decline in human memory and thinking capabilities, typically caused by the aging process. The primary aim of this research is to employ a human activity prediction algorithm to distinguish between healthy subjects and dementia-affected patients, in order to provide diagnosis at the early stages of dementia. A new algorithm, viz. Sequence Prediction via All Discoverable Episodes (SPADE), is introduced in this research to find out distinct parameters that can be used to deliver successful diagnosis. Since dementia patients do not tend to have a recognisable activity pattern, this would make it difficult for the algorithm to function well. The experiment results establish a noticeable difference of 11% in the peak accuracy of sequence prediction performed between healthy adults and dementia-affected residents. SPADE has achieved an average accuracy of 80%, i.e. 12% improvement over M-SPEED in predicting future events. This is thus evidenced that the activity prediction algorithms possess the potentials to detect the early symptoms of dementia without using any expensive clinical procedures.