5ANNs for Alzheimer's Disease Prognosis
5.1 Introduction
In this chapter we discuss how machine learning techniques can be exploited for solving otherwise formidable and sometimes intractable problems in life sciences. As a case study, we show how an ANN can be employed for prediction of Alzheimer's disease (AD) prognosis based on personalized biological information. We also present sample Python and Matlab script implementations of such an ANN, trained by field data for biomarkers collected from AD patients over time.
5.2 Alzheimer's Disease
Alzheimer's disease (AD) is an incurable progressive neurodegenerative disorder caused by destruction of neurons within the brain, with typical symptoms of cognitive decline, memory loss, behavioural changes and functional impairment of an individual. As the disease progresses, individuals with AD often experience worsening symptoms and a decline in overall health.
Everyone who develops Alzheimer's dementia first experiences mild cognitive impairment (MCI). Among those with MCI, about 15% develop dementia after two years and approximately one‐third within five years. However, some individuals with MCI do not have additional cognitive decline or revert to normal cognition. Among population‐based studies, a systematic review and meta‐analysis reported a reversion rate of 26% [52]. Therefore, it is vitally important to develop tools to predict whether a patient with MCI will decline (i.e. progressive MCI) or remain stable (i.e. stable MCI). ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access