Using Machine Learning to Forecast Progression from Cognitively Normal to Alzheimer's Disease

Abstract

Alzheimer's Disease (AD) affects approximately 50 million individuals worldwide and is estimated to rise to 152 million by 2050. There is currently no treatment for AD that halts the progression from cognitively normal (CN) and/or mild cognitive impairment (MCI) to AD. The ability to predict disease progression will allow for early treatment. While Machine Learning (ML) has been successful in diagnosing the cognitive state, further improvement is necessary for predicting progression. In this study, Random Forest and Bagging Decision Tree Recursive Feature Elimination (RFE) was utilized to ascertain the cognitive state and forecast progression. Clinical diagnoses, demographics, and post-processed PET and MRI scans used in this study were obtained from the Open Access Series of Imaging Studies (OASIS). The findings suggest that aging and lower levels of education are associated with higher risk. The study found that ML using post-processed MRI and PET scans, particularly RFE ML, is effective in diagnosing cognitive states with 90% accuracy. It can predict progression from CN to MCI or AD with 85% accuracy, which is significantly higher than the average reported in literature. Patients with progression from CN to AD were distinguished by elevated amyloid deposition, hippocampus and amygdala atrophy, left accumbens atrophy, thinning of the left hemisphere temporal, and enlarged inferior lateral ventricles. The study demonstrated that RFE ML is effective in diagnosing and predicting the progression of AD. Future studies will concentrate on identifying the specific regions of amyloid plaque that have the most significant impact on cognitive state and progression.