Background: and Purpose The prevalence of Alzheimer’s dementia (AD) is increasing as populations age, causing immense suffering for patients, families, and communities. Unfortunately, no treatments for this neurodegenerative disease have been established. Predicting AD is therefore becoming more important, because early diagnosis is the best way to prevent its onset and delay its progression. Methods: Mild cognitive impairment (MCI) is the stage between normal cognition and AD, with large variations in its progression. The disease can be effectively managed by accurately predicting the probability of MCI progressing to AD over several years. In this study we used the Alzheimer’s Disease Neuroimaging Initiative dataset to predict the progression of MCI to AD over a 3-year period from baseline. We developed and compared various recurrent neural network (RNN) models to determine the predictive effectiveness of four neuropsychological (NP) tests and magnetic resonance imaging (MRI) data at baseline. Results: The experimental results confirmed that the Preclinical Alzheimer’s Cognitive Composite score was the most effective of the four NP tests, and that the prediction performance of the NP tests improved over time. Moreover, the gated recurrent unit model exhibited the best performance among the prediction models, with an average area under the receiver operating characteristic curve of 0.916 Conclusions Timely prediction of progression from MCI to AD can be achieved using a series of NP test results and an RNN, both with and without using the baseline MRI data.

Background: and Purpose The prevalence of Alzheimer’s dementia (AD) is increasing as populations age, causing immense suffering for patients, families, and communities. Unfortunately, no treatments for this neurodegenerative disease have been established. Predicting AD is therefore becoming more important, because early diagnosis is the best way to prevent its onset and delay its progression. Methods: Mild cognitive impairment (MCI) is the stage between normal cognition and AD, with large variations in its progression. The disease can be effectively managed by accurately predicting the probability of MCI progressing to AD over several years. In this study we used the Alzheimer’s Disease Neuroimaging Initiative dataset to predict the progression of MCI to AD over a 3-year period from baseline. We developed and compared various recurrent neural network (RNN) models to determine the predictive effectiveness of four neuropsychological (NP) tests and magnetic resonance imaging (MRI) data at baseline. Results: The experimental results confirmed that the Preclinical Alzheimer’s Cognitive Composite score was the most effective of the four NP tests, and that the prediction performance of the NP tests improved over time. Moreover, the gated recurrent unit model exhibited the best performance among the prediction models, with an average area under the receiver operating characteristic curve of 0.916 Conclusions Timely prediction of progression from MCI to AD can be achieved using a series of NP test results and an RNN, both with and without using the baseline MRI data.

Background: and Purpose The prevalence of Alzheimer’s dementia (AD) is increasing as populations age, causing immense suffering for patients, families, and communities. Unfortunately, no treatments for this neurodegenerative disease have been established. Predicting AD is therefore becoming more important, because early diagnosis is the best way to prevent its onset and delay its progression. Methods: Mild cognitive impairment (MCI) is the stage between normal cognition and AD, with large variations in its progression. The disease can be effectively managed by accurately predicting the probability of MCI progressing to AD over several years. In this study we used the Alzheimer’s Disease Neuroimaging Initiative dataset to predict the progression of MCI to AD over a 3-year period from baseline. We developed and compared various recurrent neural network (RNN) models to determine the predictive effectiveness of four neuropsychological (NP) tests and magnetic resonance imaging (MRI) data at baseline. Results: The experimental results confirmed that the Preclinical Alzheimer’s Cognitive Composite score was the most effective of the four NP tests, and that the prediction performance of the NP tests improved over time. Moreover, the gated recurrent unit model exhibited the best performance among the prediction models, with an average area under the receiver operating characteristic curve of 0.916 Conclusions Timely prediction of progression from MCI to AD can be achieved using a series of NP test results and an RNN, both with and without using the baseline MRI data.

Background: and Purpose The prevalence of Alzheimer’s dementia (AD) is increasing as populations age, causing immense suffering for patients, families, and communities. Unfortunately, no treatments for this neurodegenerative disease have been established. Predicting AD is therefore becoming more important, because early diagnosis is the best way to prevent its onset and delay its progression. Methods: Mild cognitive impairment (MCI) is the stage between normal cognition and AD, with large variations in its progression. The disease can be effectively managed by accurately predicting the probability of MCI progressing to AD over several years. In this study we used the Alzheimer’s Disease Neuroimaging Initiative dataset to predict the progression of MCI to AD over a 3-year period from baseline. We developed and compared various recurrent neural network (RNN) models to determine the predictive effectiveness of four neuropsychological (NP) tests and magnetic resonance imaging (MRI) data at baseline. Results: The experimental results confirmed that the Preclinical Alzheimer’s Cognitive Composite score was the most effective of the four NP tests, and that the prediction performance of the NP tests improved over time. Moreover, the gated recurrent unit model exhibited the best performance among the prediction models, with an average area under the receiver operating characteristic curve of 0.916 Conclusions Timely prediction of progression from MCI to AD can be achieved using a series of NP test results and an RNN, both with and without using the baseline MRI data.

Striatal changes in the pathogenesis of Alzheimer’s disease (AD) is not fully understood yet. We compared structural and functional image differences in the striatum between patients with early onset AD (EOAD) and late onset AD (LOAD) to investigate whether EOAD harbors autosomal dominant AD like imaging findings. The clinical, neuropsychological and neuroimaging biomarkers of 77 probable AD patients and 107 elderly subjects with normal cognition (NC) from the Alzheimer’s Disease Neuroimaging Initiative (ADNI)-2 dataset were analyzed. Enrolled each subject completed a 3-Tesla MRI, baseline 18F-FDG-PET, and baseline 18F-AV-45 (Florbetapir) amyloid PET studies. AD patients were divided into two groups based on the onset age of clinical symptoms (EOAD <65 yrs; LOAD ≥65 yrs). A standardized uptake value ratio of the striatum and subcortical structures was obtained from both amyloid and FDG-PET scans. Structural MR imaging analysis was conducted using a parametric boundary description protocol, SPHARM-PDM. Of the 77 AD patients, 18 were EOAD and 59 were LOAD. Except for age of symptom onset, there were no statistically significant differences between the groups in demographics and detailed neuropsychological test results. 18F-AV-45 amyloid PET showed marked β-amyloid accumulation in the bilateral caudate nucleus and left pallidum in the EOAD group. Intriguingly, the caudate nucleus and putamen showed maintained glucose metabolism in the EOAD group compared to the LOAD group. Our image findings in the striatum of EOAD patients suggest that sporadic EOAD may share some pathophysiological changes noted in autosomal dominant AD.